[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"_public_publisher_byId_700ecf87-6a49-485b-80ad-d0d5ba813f72":3,"_public_publication_all{\"sortAscending\":false,\"sortField\":\"updateTime\",\"page\":0,\"size\":10,\"facet\":true,\"searchKey\":\"publisherId:700ecf87-6a49-485b-80ad-d0d5ba813f72,\"}":175},{"code":4,"data":5,"meta":20},"SUCCESS",{"id":6,"createTime":7,"updateTime":8,"relativeEntities":9,"slug":10,"properties":11,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":22,"manageAffiliations":47,"indexDatabases":63,"url":20,"thumbnailPath":20,"statistic":101,"gsStatistic":20,"type":20,"analyzePriority":20},"700ecf87-6a49-485b-80ad-d0d5ba813f72","2024-04-16T01:27:42.185+00:00","2025-11-21T10:04:08.965+00:00",[],"Springer-Science-and-Business-Media-LLC",{"issn":12,"title":14,"eissn":16},{"VOID":13},"0926-8782",{"EN":15},"Springer Science and Business Media LLC",{"VOID":17},"1573-7578","PUBLISHER","PENDING",null,0,[23,29,35,41],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":25,"label":26,"description":28,"parentId":20,"standard":20,"scholarHubFieldId":20},"c41bb0c4-b86d-4bd6-ac06-d1efed5edcce",[],{"EN":27},"Information Systems",{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":31,"label":32,"description":34,"parentId":20,"standard":20,"scholarHubFieldId":20},"aae089e7-8b62-4df4-ab86-aada3693b3f8",[],{"EN":33},"Software",{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":37,"label":38,"description":40,"parentId":20,"standard":20,"scholarHubFieldId":20},"e408ae20-6803-4097-9614-89dd11b88962",[],{"EN":39},"Information Systems and Management",{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":43,"label":44,"description":46,"parentId":20,"standard":20,"scholarHubFieldId":20},"6dbce0ad-8fe9-432e-b415-2441d8c2f0bd",[],{"EN":45},"Hardware and Architecture",{},[48,55],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":50,"slug":20,"properties":51,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":54,"statistic":20},"26a19206-5cad-4456-bb2f-49abd254fbc6",[],{"title":52},{"EN":53},"SPRINGER",[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":57,"slug":20,"properties":58,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":61,"statistic":20},"b2bfac93-563a-4fa4-bd81-e546a66bf9bd",[],{"title":59},{"EN":60},"Springer Netherlands",[62],"9a7c7208-b28a-42c2-a634-5a7f90eee3ab",[64,81],{"id":65,"indexDatabase":66,"url":78,"indexYears":20,"academicFieldIds":79,"indexDatabaseRanking":20},"09606007-5193-497f-bd4b-8207103004c0",{"id":67,"createTime":20,"updateTime":20,"relativeEntities":68,"label":69,"description":71,"key":74,"publicationTags":75,"standard":20},"a4921856-b128-4d9f-8f1f-e80813d3bbd4",[],{"EN":70,"VI":70},"ISI\u002FSCIE - Science Citation Index Expanded",{"EN":72,"VI":73},"SCIE database","Cơ sở dữ liệu SCIE","scie",[76,77],"SCIE","ISI","https:\u002F\u002Fmjl.clarivate.com\u002Fsearch-results?issn=0926-8782",[80],"874c55e0-262a-4246-b3d1-85e02c3c09db",{"id":82,"indexDatabase":83,"url":93,"indexYears":94,"academicFieldIds":95,"indexDatabaseRanking":100},"d0fb5daa-54ef-4b53-aeee-06b37770f0d1",{"id":84,"createTime":20,"updateTime":20,"relativeEntities":85,"label":86,"description":88,"key":90,"publicationTags":91,"standard":20},"3c7051d4-eb7d-4c57-a56b-36fc74c5d1e9",[],{"EN":87,"VI":87},"Scopus - Elsevier",{"EN":87,"VI":89},"Cơ sở dữ liệu Scopus thuộc Elsevier","scopus",[92],"SCOPUS","https:\u002F\u002Fwww.scopus.com\u002Fsourceid\u002F13130","1993-2025",[96,97,98,99],"499fd762-4414-45c1-b2b3-cc8d2abe204b","d5abd5bd-04fc-4adb-ad3e-286daf3b4967","f8ab36fc-bc72-48f2-a425-9f3e042f2272","b9d39d61-9a3d-4dc5-9ca6-68f27e2cfc9f","SCOPUS__Q2",{"impactFactor":21,"impactFactorByYear":102,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":118,"totalCitation":137,"totalCitationByYear":138,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":155,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},0.07,0.68,0.48,0.26,0.42,0.53,0.44,0.45,0.06,0.27,0.35,0.36,23,3,431,{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},8,12,5,9,15,16,13,7,17,18,20,10,21,28,24,31,14,1,776,{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},55,2,85,32,84,6,77,71,29,57,27,80,4,38,37,1.8,{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},6.88,0.17,7.08,2.12,0.92,2.46,1.11,0.86,4.53,10.14,2.23,2.85,2.7,0.1,0.32,0.31,1.58,1.19,0.54,{"meta":176,"data":178},{"total":177},"431",[179,371,694,796,929,1031,1160,1288,1396,1530],{"id":180,"createTime":181,"updateTime":182,"relativeEntities":183,"slug":184,"properties":185,"entityType":196,"verifyStatus":197,"verifyTime":198,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":200,"fullTextUrl":20,"authors":201,"publicationType":300,"publisherRelationship":301,"citationCount":361,"citationInfo":362,"publishDate":366,"publishYear":363,"citationAnalyzeStatus":367,"lastCitationAnalyze":368,"indexDatabases":369,"openAccess":20,"references":20,"isForceReanalyzing":370},"b30e2a1a-38e8-463c-80e1-edbdc1a565f0","2024-01-27T04:05:30.049+00:00","2026-08-15T09:40:50.054+00:00",[],"DataSynapse-A-Social-Data-Curation-Foundry",{"abstract":186,"title":188,"gsPaper":190,"references":192,"doi":194},{"EN":187},"Social data analytics have become a vital asset for organizations and governments. For example, over the last few years, governments started to extract knowledge and derive insights from vastly growing open data to personalize the advertisements in elections, improve government services, predict intelligence activities, as well as to improve national security and public health. A key challenge in analyzing social data is to transform the raw data generated by social actors into curated data, i.e., contextualized data and knowledge that is maintained and made available for use by end-users and applications. To address this challenge, we present the notion of knowledge lake, i.e., a contextualized Data Lake, to provide the foundation for big data analytics by automatically curating the raw social data and to prepare them for deriving insights. We present a social data curation foundry, namely DataSynapse, to enable analysts engage with social data to uncover hidden patterns and generate insight. In DataSynapse, we present a scalable algorithm to transform social items (e.g., a Tweet in Twitter) into semantic items, i.e., contextualized and curated items. This algorithm offers customizable feature extraction to harness desired features from diverse data sources. To link contextualized information items to the domain knowledge, we present a scalable technique which leverages cross document coreference resolution assisting analysts to derive targeted insights. DataSynapse is offered as an extensible and scalable microservice-based architecture that are publicly available on GitHub supporting networks such as Twitter, Facebook, GooglePlus and LinkedIn. We adopt a typical scenario for analyzing urban social issues from Twitter as it relates to the government budget, to highlight how DataSynapse significantly improves the quality of extracted knowledge compared to the classical curation pipeline (in the absence of feature extraction, enrichment and domain-linking contextualization).",{"EN":189},"DataSynapse: A Social Data Curation Foundry",{"VOID":191},"[\"5968122109289193248\"]",{"VOID":193},"Aggarwal, C.C.: An Introduction to Social Network Data Analytics, pp. 1–15. Springer, Berlin (2011)\nAnderson, M.R., Antenucci, D., Bittorf, V., Burgess, M., Cafarella, M.J., Kumar, A., Niu, F. et al.: Brainwash: a data system for feature engineering. In: CIDR (2013)\nBeheshti, S.-M.-R., Nezhad, H.R.M., Benatallah, B.: Temporal provenance model (TPM): model and query language. CoRR, abs\u002F1211.5009 (2012)\nBeheshti, S.-M.-R. et al.: Galaxy: a platform for explorative analysis of open data sources. In: Proceedings of the 19th International Conference on Extending Database Technology, (EDBT), pp. 640–643 (2016). https:\u002F\u002Fdblp.org\u002Frec\u002Fbibtex\u002Fconf\u002Fedbt\u002FBeheshtiBM16\nBeheshti, S.-M.-R., Benatallah, B., Motahari-Nezhad, H.R.: Scalable graph-based OLAP analytics over process execution data. Distrib. Parallel Databases 34(3), 379–423 (2016)\nBeheshti, S.-M.-R., Benatallah, B., Sakr, S., Grigori, D., Motahari-Nezhad, H.R., Barukh, M.C., Gater, A., Ryu, S.H.: Process Analytics—Concepts and Techniques for Querying and Analyzing Process Data. Springer, Berlin (2016)\nArocena, P.C., Glavic, B., Mecca, G., Miller, R.J., Papotti, P., Santoro, D.: Benchmarking data curation systems. IEEE Data Eng. Bull. 39(2), 47–62 (2016)\nBeheshti, S.-M.-R., Tabebordbar, A., Benatallah, B., Nouri, R.: On automating basic data curation tasks. In: Proceedings of the 26th International Conference on World Wide Web Companion, Perth, Australia, April 3–7, 2017, pp. 165–169 (2017)\nBeheshti, S.-M.-R., Benatallah, B., Venugopal, S., Ryu, S.H., Motahari-Nezhad, H.R., Wang, Wei: A systematic review and comparative analysis of cross-document coreference resolution methods and tools. Computing 99(4), 313–349 (2017)\nBeheshti, A., Benatallah, B., Nouri, R., Chhieng, Van M., Xiong, H., Zhao, X.: Coredb: a data lake service. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017, Singapore, November 06–10, 2017, pp. 2451–2454 (2017)\nBeheshti, A., Benatallah, B., Nouri, R., Tabebordbar, A.: Corekg: a knowledge lake service. PVLDB 11(12), 1942–1945 (2018). https:\u002F\u002Fdblp.org\u002Frec\u002Fbibtex\u002Fjournals\u002Fpvldb\u002FBeheshtiBNT18\nBeheshti, A., Schiliro, F., Ghodratnama, S., Amouzgar, F., Benatallah, B., Yang, J., Sheng, Q.Z., Casati, F., Motahari-Nezhad, H.R.: iprocess: Enabling iot platforms in data-driven knowledge-intensive processes. In: Business Process Management Forum - BPM Forum 2018 (2018)\nBeheshti, A., Vaghani, K., Benatallah, B., Tabebordbar, A.: Crowdcorrect: A curation pipeline for social data cleansing and curation. In: Information Systems in the Big Data Era—CAiSE Forum 2018, Tallinn, Estonia, June 11–15, 2018, Proceedings, pp. 24–38 (2018)\nChai, X., Deshpande, O., Garera, N., Gattani, A., Lam, W., Lamba, D.S., Liu, L., Tiwari, M., Tourn, M., Vacheri, Z., Prasad, S.T.S., Subramaniam, S., Harinarayan, V., Rajaraman, A., Ardalan, A., Das, S., Suganthan, G.C.P., Doan, A.: Social media analytics: the kosmix story. IEEE Data Eng. Bull. 36(3), 4–12 (2013)\nChen, H., Chiang, R.H.L., Storey, V.C.: Business intelligence and analytics: from big data to big impact. MIS Q. 36(4), 1165–1188 (2012)\nChiticariu, L., Krishnamurthy, R., Li, Y., Raghavan, S., Reiss, F., Vaithyanathan, S.: Systemt: an algebraic approach to declarative information extraction. In: ACL 2010, Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, July 11–16, 2010, Uppsala, pp. 128–137 (2010)\nDean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. Commun. ACM. 51(1), 107 (2008)\nDeshpande, M., Ray, D., Dixit, S., Agasti, A.: Shareinsights: an unified approach to full-stack data processing. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Victoria, Australia, May 31–June 4, 2015, pp. 1925–1940 (2015)\nDoan, A., Domingos, P.M., Halevy, A.Y.: Reconciling schemas of disparate data sources: a machine-learning approach. In: Proceedings of the 2001 ACM SIGMOD international conference on Management of data, Santa Barbara, CA, USA, May 21–24, 2001, pp. 509–520 (2001)\nFerrucci, D.A.: Introduction to ’this is watson’. IBM J. Res. Dev. 56(3.4), 4:1–4:11 (2012)\nFreitas, A., Curry, E.: Big data curation. In: Cavanillas, J.M., (ed.), New Horizons for a Data-Driven Economy, pp. 87–118. Springer, Berlin (2016)\nTerrizzano, I. et al.: Data wrangling: the challenging journey from the wild to the lake. In: CIDR (2015)\nKim, N.W., Jung, J., Ko, E.-Y., Han, S., Lee, C.W., Kim, J., Kim, J.: Budgetmap: engaging taxpayers in the issue-driven classification of a government budget. In: Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social Computing, CSCW 2016, San Francisco, CA, USA, February 27–March 2, 2016, pp. 1026–1037 (2016)\nLee, K., Agrawal, A., Choudhary, A.: Real-time disease surveillance using twitter data: demonstration on flu and cancer. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’13, pages 1474–1477, New York, NY, USA (2013). ACM\nLohr, S.: The age of big data. New York Times, 11 (2012)\nNakov, P., Ritter, A., Rosenthal, S., Sebastiani, F., Stoyanov, V.: Semeval-2016 task 4: sentiment analysis in twitter. In: Proceedings of the 10th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT 2016, San Diego, CA, USA, June 16–17, 2016, pp. 1–18 (2016)\nPandey, N., Natarajan, S.: How social media can contribute during disaster events? case study of chennai floods 2015. In: 2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016, Jaipur, India, September 21–24, 2016, pp. 1352–1356 (2016)\nPaul Suganthan, G.C., Sun, C., Krishna Gayatri, K., Zhang, H., Yang, F., Rampalli, N., Prasad, S., Arcaute, E., Krishnan, G., Deep, R., Raghavendra, V., Doan, A.: Why big data industrial systems need rules and what we can do about it. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Victoria, Australia, May 31–June 4, 2015, pp. 265–276 (2015)\nPu, X., Jin, R., Wu, G., Han, D., Xue, G.-R.: Topic modeling in semantic space with keywords. In: Proceedings of the 24th ACM International Conference on Information and Knowledge Management, CIKM 2015, Melbourne, VIC, Australia, October 19–23, 2015, pp. 1141–1150 (2015)\nRitter, A., Clark, S., Mausam, E., Oren: named entity recognition in tweets: an experimental study. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, EMNLP 2011, 27–31 July 2011, John McIntyre Conference Centre, Edinburgh, UK, A meeting of SIGDAT, a Special Interest Group of the ACL, pp. 1524–1534 (2011)\nRuder, T.D., Hatch, G.M., Ampanozi, G., Thali, M.J., Fischer, N.: Suicide announcement on facebook. Crisis (2011)\nRussom, P., et al.: Big data analytics. TDWI best practices report, fourth quarter 19, 40 (2011)\nSellam, T., Müller, E., Kersten, M.L.: Semi-automated exploration of data warehouses. In: Proceedings of the 24th ACM International Conference on Information and Knowledge Management, CIKM 2015, Melbourne, VIC, Australia, October 19–23, 2015, pp. 1321–1330 (2015)\nStonebraker, M. et al.: Data curation at scale: the data tamer system. In: CIDR (2013)\nFabian, M.: Suchanek and Gerhard Weikum. Knowledge bases in the age of big data analytics. Proc. VLDB Endow. 7(13), 1713–1714 (2014)\nTabebordbar, A., Beheshti, A.: Adaptive rule monitoring system. In: 40th International Conference on Software Engineering (ICSE), International Workshop on Software Engineering for Cognitive Services (SE4COG) (2018)\nTene, O., Polonetsky, J.: Big data for all: Privacy and user control in the age of analytics. N. J. Tech. Intell. Prop. 11, xxvii (2012)\nTroncy, R.: Linking entities for enriching and structuring social media content. In: WWW, pp. 597–597 (2016)\nKarlgren, J., Bohman, M., Ekgren, A., Isheden, G., Kullmann, E., Nilsson, D.: Semantic topology. In: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, CIKM 2014, Shanghai, China, November 3–7, 2014, pp. 1939–1942 (2014)\nWang, S., Tang, J., Aggarwal, C.C., Liu, H.: Linked document embedding for classification. In: Proceedings of the 25th ACM International Conference on Information and Knowledge Management, CIKM 2016, Indianapolis, IN, USA, October 24–28, 2016, pp. 115–124 (2016)\nZarras, A.V., Vassiliadis, P., Dinos, I.: Keep calm and wait for the spike! insights on the evolution of amazon services. In: Advanced Information Systems Engineering - 28th International Conference, CAiSE 2016, Ljubljana, Slovenia, June 13-17, 2016. Proceedings, pp. 444–458 (2016)",{"VOID":195},"10.1007\u002Fs10619-018-7245-1","PUBLICATION","VERIFIED","2024-05-16T21:22:08.375+00:00","Auto Verify","https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10619-018-7245-1",[202,220,237,252,274,287],{"id":203,"sortIndex":21,"researcher":20,"roles":204,"affiliations":206,"properties":215},"264e9c8a-600b-4f79-a5a7-1e058c14f4df",[205],"AUTHOR",[207],{"id":208,"sortIndex":21,"affiliation":209,"properties":20},"4a5f6d10-6e79-441b-96bf-c44148f359ab",{"id":208,"createTime":20,"updateTime":20,"relativeEntities":210,"slug":20,"properties":211,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":214,"statistic":20},[],{"title":212},{"VI":213},"Macquarie University, Sydney, Australia",[],{"title":216,"gsAuthor":218},{"VI":217},"Amin Beheshti",{"VOID":219},"[\"Uw1OLAgAAAAJ\"]",{"id":221,"sortIndex":136,"researcher":20,"roles":222,"affiliations":223,"properties":232},"37a2c41a-5f06-47bf-9532-4358cf946a35",[205],[224],{"id":225,"sortIndex":21,"affiliation":226,"properties":20},"0ab0ab20-40dd-4a7c-a6d1-8028237cad4f",{"id":225,"createTime":20,"updateTime":20,"relativeEntities":227,"slug":20,"properties":228,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":231,"statistic":20},[],{"title":229},{"VI":230},"University of New South Wales, Sydney, Australia",[],{"title":233,"gsAuthor":235},{"VI":234},"Boualem Benatallah",{"VOID":236},"[\"WYmChp0AAAAJ\"]",{"id":238,"sortIndex":140,"researcher":20,"roles":239,"affiliations":240,"properties":247},"14a3ddf8-e1c4-4e66-94dc-ae355c311750",[205],[241],{"id":225,"sortIndex":21,"affiliation":242,"properties":20},{"id":225,"createTime":20,"updateTime":20,"relativeEntities":243,"slug":20,"properties":244,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":246,"statistic":20},[],{"title":245},{"VI":230},[],{"title":248,"gsAuthor":250},{"VI":249},"Alireza Tabebordbar",{"VOID":251},"[\"zux2V6EAAAAJ\"]",{"id":253,"sortIndex":116,"researcher":20,"roles":254,"affiliations":255,"properties":271},"5d849fcf-01b3-41f1-b9ab-ee8194fd28ec",[205],[256,262],{"id":225,"sortIndex":21,"affiliation":257,"properties":20},{"id":225,"createTime":20,"updateTime":20,"relativeEntities":258,"slug":20,"properties":259,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":261,"statistic":20},[],{"title":260},{"VI":230},[],{"id":263,"sortIndex":136,"affiliation":264,"properties":270},"1a789022-f2f8-4be3-a0e2-cf774d71d90b",{"id":263,"createTime":20,"updateTime":20,"relativeEntities":265,"slug":20,"properties":266,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":269,"statistic":20},[],{"title":267},{"VI":268},"EY AI Lab, Palo Alto, USA",[],{},{"title":272},{"VI":273},"Hamid Reza Motahari-Nezhad",{"id":275,"sortIndex":151,"researcher":20,"roles":276,"affiliations":277,"properties":284},"b6e98c0f-a0c7-4772-91d3-53bbafc7635c",[205],[278],{"id":225,"sortIndex":21,"affiliation":279,"properties":20},{"id":225,"createTime":20,"updateTime":20,"relativeEntities":280,"slug":20,"properties":281,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":283,"statistic":20},[],{"title":282},{"VI":230},[],{"title":285},{"VI":286},"Moshe Chai Barukh",{"id":288,"sortIndex":121,"researcher":20,"roles":289,"affiliations":290,"properties":297},"49127e2b-c5b1-4528-8f3a-477a569edc5f",[205],[291],{"id":225,"sortIndex":21,"affiliation":292,"properties":20},{"id":225,"createTime":20,"updateTime":20,"relativeEntities":293,"slug":20,"properties":294,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":296,"statistic":20},[],{"title":295},{"VI":230},[],{"title":298},{"VI":299},"Reza Nouri","ARTICLE",{"url":200,"publisher":302,"properties":356},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":303,"slug":10,"properties":304,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":308,"manageAffiliations":325,"indexDatabases":336,"url":20,"thumbnailPath":20,"statistic":351,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":305,"title":306,"eissn":307},{"VOID":13},{"EN":15},{"VOID":17},[309,313,317,321],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":310,"label":311,"description":312,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":314,"label":315,"description":316,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":318,"label":319,"description":320,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":322,"label":323,"description":324,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[326,331],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":327,"slug":20,"properties":328,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":330,"statistic":20},[],{"title":329},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":332,"slug":20,"properties":333,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":335,"statistic":20},[],{"title":334},{"EN":60},[62],[337,344],{"id":65,"indexDatabase":338,"url":78,"indexYears":20,"academicFieldIds":343,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":339,"label":340,"description":341,"key":74,"publicationTags":342,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":345,"url":93,"indexYears":94,"academicFieldIds":350,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":346,"label":347,"description":348,"key":90,"publicationTags":349,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":352,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":353,"totalCitation":137,"totalCitationByYear":354,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":355,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"pages":357,"volume":359},{"VOID":358},"351-384",{"VOID":360},"37",81,{"total":361,"publishYear":363,"statisticByYear":364},2018,{"2019":121,"2020":365,"2021":365,"2022":125,"2023":130,"2024":119,"2025":144},19,"2018-08-23","ERROR_IN_ANALYZE_CITATION","2026-08-15T09:40:50.053+00:00",[100,76],false,{"id":372,"createTime":373,"updateTime":374,"relativeEntities":375,"slug":376,"properties":377,"entityType":196,"verifyStatus":197,"verifyTime":386,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":387,"fullTextUrl":20,"authors":388,"publicationType":300,"publisherRelationship":472,"citationCount":21,"citationInfo":532,"publishDate":535,"publishYear":533,"citationAnalyzeStatus":367,"lastCitationAnalyze":536,"indexDatabases":537,"openAccess":20,"references":538,"isForceReanalyzing":370},"758f60dc-ad09-4c6f-8036-76cfdf2767a0","2024-01-25T15:09:35.297+00:00","2026-08-14T07:20:20.570+00:00",[],"Stratified-random-sampling-from-streaming-and-stored-data",{"abstract":378,"title":380,"gsPaper":382,"doi":384},{"EN":379},"Stratified random sampling (SRS) is a widely used sampling technique for approximate query processing. We consider SRS on continuously arriving data streams and statically stored data sets. We present a tight lower bound showing that any streaming algorithm for SRS over the entire stream must have, in the worst case, a variance that is \n                \n                  \n                \n                $$\\varOmega (r)$$\n                \n               factor away from the optimal, where r is the number of strata. We present S-VOILA, a practical streaming algorithm for SRS over the entire stream that is locally variance-optimal. We prove that any sliding window-based streaming SRS needs a workspace of \n                \n                  \n                \n                $$\\varOmega (rM\\log W)$$\n                \n               in the worst case, to maintain a variance-optimal SRS of size M, where W is the number of elements in the sliding window. Due to the inherent high workspace needs for sliding window-based SRS, we present SW-VOILA, a multi-layer practical sampling algorithm that uses only O(M) workspace but can maintain an SRS of size close to M in practice over a sliding window. Experiments show that both S-VOILA and SW-VOILA result in a variance that is typically close to their optimal offline counterparts, which was given the entire input beforehand. We also present VOILA, a variance-optimal offline algorithm for stratified random sampling. VOILA is a strict generalization of the well-known Neyman allocation, which is optimal only under the assumption that each stratum is abundant. Experiments show that VOILA can have significantly smaller variance (1.4x to 50x) than Neyman allocation on real-world data.",{"EN":381},"Stratified random sampling from streaming and stored data",{"VOID":383},"[\"9286789239621017106\"]",{"VOID":385},"10.1007\u002Fs10619-020-07315-w","2024-05-02T11:49:08.356+00:00","https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10619-020-07315-w",[389,408,425,442,457],{"id":390,"sortIndex":21,"researcher":20,"roles":391,"affiliations":392,"properties":403},"fd6809d2-4e08-4068-b879-ae14283622d8",[205],[393],{"id":394,"sortIndex":21,"affiliation":395,"properties":401},"a2b75297-5f39-497a-ad6d-d4090441889e",{"id":394,"createTime":20,"updateTime":20,"relativeEntities":396,"slug":20,"properties":397,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":400,"statistic":20},[],{"title":398},{"EN":399},"Iowa State University, Ames, USA",[],{"title":402},{"VI":399},{"title":404,"gsAuthor":406},{"VI":405},"Trong Duc Nguyen",{"VOID":407},"[\"wClXFsEAAAAJ\"]",{"id":409,"sortIndex":136,"researcher":20,"roles":410,"affiliations":411,"properties":420},"0f2993bf-759e-4e62-8869-17eeffbed645",[205],[412],{"id":394,"sortIndex":21,"affiliation":413,"properties":418},{"id":394,"createTime":20,"updateTime":20,"relativeEntities":414,"slug":20,"properties":415,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":417,"statistic":20},[],{"title":416},{"EN":399},[],{"title":419},{"VI":399},{"title":421,"gsAuthor":423},{"VI":422},"Ming-Hung Shih",{"VOID":424},"[\"D5XbiwcAAAAJ\"]",{"id":426,"sortIndex":140,"researcher":20,"roles":427,"affiliations":428,"properties":437},"3e7cd3cf-9bd9-4e33-acd6-c8ec3df0a73d",[205],[429],{"id":430,"sortIndex":21,"affiliation":431,"properties":20},"ab7d2e79-bc9d-4de3-b283-24f5c9275ed3",{"id":430,"createTime":20,"updateTime":20,"relativeEntities":432,"slug":20,"properties":433,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":436,"statistic":20},[],{"title":434},{"VI":435},"AT&T - Research, Austin, USA",[],{"title":438,"gsAuthor":440},{"VI":439},"Divesh Srivastava",{"VOID":441},"[\"kGKlHp0AAAAJ\"]",{"id":443,"sortIndex":116,"researcher":20,"roles":444,"affiliations":445,"properties":454},"3416d31d-b66a-41e4-b381-3d681747222f",[205],[446],{"id":394,"sortIndex":21,"affiliation":447,"properties":452},{"id":394,"createTime":20,"updateTime":20,"relativeEntities":448,"slug":20,"properties":449,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":451,"statistic":20},[],{"title":450},{"EN":399},[],{"title":453},{"VI":399},{"title":455},{"VI":456},"Srikanta Tirthapura",{"id":458,"sortIndex":151,"researcher":20,"roles":459,"affiliations":460,"properties":469},"007b79b3-6fa4-416b-aeb0-4ebb823b04ee",[205],[461],{"id":462,"sortIndex":21,"affiliation":463,"properties":20},"ba38e34d-f36a-4025-a660-961618498dac",{"id":462,"createTime":20,"updateTime":20,"relativeEntities":464,"slug":20,"properties":465,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":468,"statistic":20},[],{"title":466},{"VI":467},"Eastern Washington University, Cheney, USA",[],{"title":470},{"VI":471},"Bojian Xu",{"url":387,"publisher":473,"properties":527},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":474,"slug":10,"properties":475,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":479,"manageAffiliations":496,"indexDatabases":507,"url":20,"thumbnailPath":20,"statistic":522,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":476,"title":477,"eissn":478},{"VOID":13},{"EN":15},{"VOID":17},[480,484,488,492],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":481,"label":482,"description":483,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":485,"label":486,"description":487,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":489,"label":490,"description":491,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":493,"label":494,"description":495,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[497,502],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":498,"slug":20,"properties":499,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":501,"statistic":20},[],{"title":500},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":503,"slug":20,"properties":504,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":506,"statistic":20},[],{"title":505},{"EN":60},[62],[508,515],{"id":65,"indexDatabase":509,"url":78,"indexYears":20,"academicFieldIds":514,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":510,"label":511,"description":512,"key":74,"publicationTags":513,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":516,"url":93,"indexYears":94,"academicFieldIds":521,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":517,"label":518,"description":519,"key":90,"publicationTags":520,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":523,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":524,"totalCitation":137,"totalCitationByYear":525,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":526,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"pages":528,"volume":530},{"VOID":529},"665-710",{"VOID":531},"39",{"total":21,"publishYear":533,"statisticByYear":534},2020,{},"2020-10-23","2026-08-14T07:20:20.569+00:00",[100,76],[539,545,548,551,554,561,564,567,570,573,579,582,585,588,591,594,597,600,603,606,609,612,615,618,621,624,627,630,633,636,642,645,648,651,654,657,660,663,666,673,676,679,682,685,688,691],{"id":540,"text":541,"url":542,"identifiers":543},"4c68646b-0035-4279-8000-0006b275d4fa","Nguyen, T.D., Shih, M., Srivastava, D., Tirthapura, S., Xu, B.: Stratified random sampling over streaming and stored data. In: EDBT, pp. 25–36 (2019)","https:\u002F\u002Flink.springer.com\u002F10.1007\u002Fs10440-022-00541-7",{"doi":544},"10.1007\u002Fs10440-022-00541-7",{"id":540,"text":546,"url":542,"identifiers":547},"Acharya, S., Gibbons, P.B., Poosala, V., Ramaswamy, S.: The aqua approximate query answering system. In: Proceedings in SIGMOD, pp. 574–576 (1999)",{"doi":544},{"id":540,"text":549,"url":542,"identifiers":550},"Agarwal, S., Mozafari, B., Panda, A., Milner, H., Madden, S., Stoica, I.: BlinkDB: Queries with bounded errors and bounded response times on very large data. In: Proceedings in EuroSys, pp. 29–42 (2013)",{"doi":544},{"id":20,"text":552,"url":20,"identifiers":553},"Kandula, S., Shanbhag, A., Vitorovic, A., Olma, M., Grandl, R., Chaudhuri, S., Ding, B.: Quickr: lazily approximating complex adhoc queries in bigdata clusters. In: SIGMOD, pp. 631–646 (2016)",{},{"id":20,"text":555,"url":556,"identifiers":557},"Chaudhuri, S., Das, G., Narasayya, V.: Optimized stratified sampling for approximate query processing. ACM TODS (2007). https:\u002F\u002Fdoi.org\u002F10.1145\u002F1242524.1242526","https:\u002F\u002Fdoi.org\u002F10.1145\u002F1242524.1242526",{"mag":558,"openalex":559,"doi":560},"2152029707","W2152029707","10.1145\u002F1242524.1242526",{"id":540,"text":562,"url":542,"identifiers":563},"Johnson, T., Shkapenyuk, V.: Data stream warehousing in tidalrace. In: Proceeding in CIDR (2015)",{"doi":544},{"id":20,"text":565,"url":20,"identifiers":566},"Zaharia, M., Das, T., Li, H., Hunter, T., Shenker, S., Stoica, I.: Discretized streams: fault-tolerant streaming computation at scale. In: SOSP, pp. 423–438 (2013)",{},{"id":540,"text":568,"url":542,"identifiers":569},"Neyman, J.: On the two different aspects of the representative method: the method of stratified sampling and the method of purposive selection. J. R. Stat. Soc. 97(4), 558–625 (1934)",{"doi":544},{"id":540,"text":571,"url":542,"identifiers":572},"Al-Kateb, M., Lee, B.S.: Adaptive stratified reservoir sampling over heterogeneous data streams. Inf. Syst. 39, 199–216 (2014)",{"doi":544},{"id":574,"text":575,"url":576,"identifiers":577},"b7594790-82a9-4b05-aec8-e89a6e12641d","Efraimidis, P.S., Spirakis, P.G.: Weighted random sampling with a reservoir. Inf. Process. Lett. 97(5), 181–185 (2006)","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS002001900500298X",{"doi":578},"10.1016\u002Fj.ipl.2005.11.003",{"id":540,"text":580,"url":542,"identifiers":581},"Meng, X.: Scalable simple random sampling and stratified sampling. In: Proceedings in ICML, pp. 531–539 (2013)",{"doi":544},{"id":540,"text":583,"url":542,"identifiers":584},"Al-Kateb, M., Lee, B.S.: Stratified reservoir sampling over heterogeneous data streams. In: Proceedings of SSDBM, pp. 621–639 (2010)",{"doi":544},{"id":540,"text":586,"url":542,"identifiers":587},"Al-Kateb, M., Lee, B.S., Wang, X.S.: Adaptive-size reservoir sampling over data streams. In: Proceedings in SSDBM, p. 22 (2007)",{"doi":544},{"id":540,"text":589,"url":542,"identifiers":590},"Bankier, M.D.: Power allocations: determining sample sizes for subnational areas. Am. Stat. 42(3), 174–177 (1988)",{"doi":544},{"id":540,"text":592,"url":542,"identifiers":593},"Vitter, J.S.: Random sampling with a reservoir. ACM Trans. Math. Softw. 11(1), 37–57 (1985)",{"doi":544},{"id":540,"text":595,"url":542,"identifiers":596},"Lang, K., Liberty, E., Shmakov, K.: Stratified sampling meets machine learning. In: Proceedings in ICML, pp. 2320–2329 (2016)",{"doi":544},{"id":540,"text":598,"url":542,"identifiers":599},"Acharya, S., Gibbons, P., Poosala, V.: Congressional samples for approximate answering of group-by queries. In: Proceedings in SIGMOD, pp. 487–498 (2000)",{"doi":544},{"id":540,"text":601,"url":542,"identifiers":602},"Babcock, B., Chaudhuri, S., Das, G.: Dynamic sample selection for approximate query processing. In: Proceedings in SIGMOD, pp. 539–550 (2003)",{"doi":544},{"id":540,"text":604,"url":542,"identifiers":605},"Joshi, S., Jermaine, C.: Robust stratified sampling plans for low selectivity queries. In: Proceedings in ICDE, pp. 199–208 (2008)",{"doi":544},{"id":20,"text":607,"url":20,"identifiers":608},"Ding, B., Huang, S., Chaudhuri, S., Chakrabarti, K., Wang, C.: Sample + seek: approximating aggregates with distribution precision guarantee. In: SIGMOD, pp. 679–694 (2016)",{},{"id":540,"text":610,"url":542,"identifiers":611},"Babcock, B., Babu, S., Datar, M., Motwani, R., Widom, J.: Models and issues in data stream systems. In: Proceeding in PODS, pp. 1–16 (2002)",{"doi":544},{"id":20,"text":613,"url":20,"identifiers":614},"Cochran, W.G.: Sampling Techniques, 3rd edn. Wiley, New York (1977)",{},{"id":20,"text":616,"url":20,"identifiers":617},"Haas, P.J.: Data-stream sampling: basic techniques and results. Data Stream Management, pp. 13–44. Springer, Berlin (2016)",{},{"id":20,"text":619,"url":20,"identifiers":620},"Lohr, S.L.: Sampling: Design and Analysis, 2nd edn. Duxbury Press, London (2009)",{},{"id":20,"text":622,"url":20,"identifiers":623},"Thompson, S.K.: Sampling, 3rd edn. Wiley, New York (2012)",{},{"id":20,"text":625,"url":20,"identifiers":626},"Tillé, Y.: Sampling Algorithms, 1st edn. Springer, Berlin (2006)",{},{"id":540,"text":628,"url":542,"identifiers":629},"Mcleod, I., Bellhouse, D.: A convenient algorithm for drawing a simple random sample. J. R. Stat. Soc. Ser. C 32, 182–184 (1983)",{"doi":544},{"id":540,"text":631,"url":542,"identifiers":632},"Vitter, J.S.: Optimum algorithms for two random sampling problems. In: Proceeding in FOCS, pp. 65–75 (1983)",{"doi":544},{"id":540,"text":634,"url":542,"identifiers":635},"Braverman, V., Ostrovsky, R., Vorsanger, G.: Weighted sampling without replacement from data streams. Inf. Process. Lett. 115(12), 923–926 (2015)",{"doi":544},{"id":637,"text":638,"url":639,"identifiers":640},"6a73dee6-555e-4c60-a8d7-5a9e81a2610b","Gemulla, R., Lehner, W., Haas, P.J.: Maintaining bounded-size sample synopses of evolving datasets. VLDB J. 17(2), 173–201 (2008)","https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs00778-007-0065-y",{"doi":641},"10.1007\u002Fs00778-007-0065-y",{"id":540,"text":643,"url":542,"identifiers":644},"Gibbons, P.B., Tirthapura, S.: Estimating simple functions on the union of data streams. In: Proceedings in SPAA, pp. 281–291 (2001)",{"doi":544},{"id":540,"text":646,"url":542,"identifiers":647},"Babcock, B., Datar, M., Motwani, R.: Sampling from a moving window over streaming data. In: SODA (2002)",{"doi":544},{"id":540,"text":649,"url":542,"identifiers":650},"Braverman, V., Ostrovsky, R., Zaniolo, C.: Optimal sampling from sliding windows. In: Proceedings in PODS, pp. 147–156 (2009)",{"doi":544},{"id":540,"text":652,"url":542,"identifiers":653},"Gemulla, R., Lehner, W.: Sampling time-based sliding windows in bounded space. In: SIGMOD (2008)",{"doi":544},{"id":540,"text":655,"url":542,"identifiers":656},"Cormode, G., Shkapenyuk, V., Srivastava, D., Xu, B.: Forward decay: a practical time decay model for streaming systems. In: Proceedings in ICDE, pp. 138–149 (2009)",{"doi":544},{"id":540,"text":658,"url":542,"identifiers":659},"Cormode, G., Tirthapura, S., Xu, B.: Time-decaying sketches for robust aggregation of sensor data. SIAM J. Comput. 39(4), 1309–1339 (2009)",{"doi":544},{"id":540,"text":661,"url":542,"identifiers":662},"Chung, Y., Tirthapura, S.: Distinct random sampling from a distributed stream. In: IPDPS, pp. 532–541 (2015)",{"doi":544},{"id":540,"text":664,"url":542,"identifiers":665},"Chung, Y., Tirthapura, S., Woodruff, D.: A simple message-optimal algorithm for random sampling from a distributed stream. IEEE TKDE 28(6), 1356–1368 (2016)",{"doi":544},{"id":20,"text":667,"url":668,"identifiers":669},"Cormode, G., Muthukrishnan, S., Yi, K., Zhang, Q.: Continuous sampling from distributed streams. JACM (2012). https:\u002F\u002Fdoi.org\u002F10.1145\u002F0000000.0000000","https:\u002F\u002Fdoi.org\u002F10.1145\u002F2160158.2160163",{"mag":670,"openalex":671,"doi":672},"2139076222","W2139076222","10.1145\u002F2160158.2160163",{"id":540,"text":674,"url":542,"identifiers":675},"Tirthapura, S., Woodruff, D.P.: Optimal random sampling from distributed streams revisited. In: DISC, pp. 283–297 (2011)",{"doi":544},{"id":540,"text":677,"url":542,"identifiers":678},"Datar, M., Gionis, A., Indyk, P., Motwani, R.: Maintaining stream statistics over sliding windows. SIAM J. Comput. 31(6), 1794–1813 (2002)",{"doi":544},{"id":540,"text":680,"url":542,"identifiers":681},"Gibbons, P.B., Tirthapura, S.: Distributed streams algorithms for sliding windows. In: SPAA, pp. 63–72 (2002)",{"doi":544},{"id":540,"text":683,"url":542,"identifiers":684},"Babcock, B., Datar, M., Motwani, R., O’Callaghan, L.: Maintaining variance and k-medians over data stream windows. In: Proceedings of 22nd ACM Symposium on Principles of Database Systems (PODS), pp. 234–243, June (2003)",{"doi":544},{"id":540,"text":686,"url":542,"identifiers":687},"Zhang, L., Guan, Y.: Variance estimation over sliding windows. In: PODS, pp. 225–232 (2007)",{"doi":544},{"id":20,"text":689,"url":689,"identifiers":690},"http:\u002F\u002Fopenaq.org",{},{"id":20,"text":692,"url":692,"identifiers":693},"https:\u002F\u002Fwww.divvybikes.com\u002Fsystem-data",{},{"id":695,"createTime":696,"updateTime":697,"relativeEntities":698,"slug":699,"properties":700,"entityType":196,"verifyStatus":197,"verifyTime":711,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":712,"fullTextUrl":20,"authors":713,"publicationType":300,"publisherRelationship":729,"citationCount":136,"citationInfo":789,"publishDate":792,"publishYear":790,"citationAnalyzeStatus":793,"lastCitationAnalyze":794,"indexDatabases":795,"openAccess":20,"references":20,"isForceReanalyzing":370},"df3f08fd-0d72-4ccb-8108-8c6990fffbd1","2024-01-25T17:01:11.422+00:00","2026-07-24T20:17:24.644+00:00",[],"A-New-Algorithm-for-the-Decentralized-Aggregation-Problem",{"abstract":701,"title":703,"gsPaper":705,"references":707,"doi":709},{"EN":702},"This paper describes a new algorithm for solving the distributed aggregation problem in which individual values from N nodes have to be aggregated in an associative and commutative manner, and the final result must be either computed at all sites or communicated to them. Our algorithm has a message-delay product of Θ(dN(N\n                  \n                    \n                  \n                  \n$$\\Theta (dN(N^{\\frac{1}{d}} ))$$\n\n                )) where N is the number of nodes, and d is a parameter that corresponds to the number of dimensions of the hypercube into which the nodes are logically organized. This reflects an improvement upon existing algorithms by a factor of d. The algorithm can be initiated by any node, and works by creating multiple parallel streams that collect partial aggregates and finally converge at a node to compute the final result.",{"EN":704},"A New Algorithm for the Decentralized Aggregation Problem",{"VOID":706},"[\"7485465028461760977\"]",{"VOID":708},"A. Albert and R. Sandler, An Introduction to Finite Projective Planes, Holt, Rinehart and Winston, 1968.\nD. Barbara and H. Garcia-Molina, “The Demarcation protocol: A technique for maintaining arithmetic constraints in distributed database systems,” EDBT Conference, Vienna, 1992.\nF. Chung, “Diameters of communications networks,” in AMS Short Course on Mathematics of Information Processing, American Mathematical Society, 1984.\nD. Dolev, et al., “An O(n log n) unidirectional distributed algorithm for extrema finding in a circle,” J. Algorithms, vol. 3, pp. 245-260, 1982.\nC. Hsieh, “Decentralized evaluation of associative and commutative functions,” IEEE International conference on Distributed Computing, Newport Beach, CA, 1989.\nA. Kumar and M. Stonebraker, “Semantics based transaction management techniques for replicated data,” ACM SIGMOD Conference, Chicago, IL, June 1988.\nT.V. Lakshman and A.K. Agrawala, “Efficient decentralized consensus protocols,” IEEE Transactions on Software Engineering, vol. SE-12,no. 5, pp. 600-607, May 1986.\nT.V. Lakshman and V. Wei, “Distributed computing on regular networks with anonymous nodes,” IEEE Transactions on Computers, vol. 43,no. 2, pp. 211-218, February 1994.\nM. Maekawa, “A \\(\\sqrt N \\) Algorithm for Mutual Exclusion in Decentralized Systems,” ACM Transactions on Computer Systems, vol. 3,no. 2, pp. 145-159, May 1985.\nG. Peterson, “An O(n log n) unidirectional algorithm for the circular extrema finding problems,” ACM TOPLAS, vol. 4,no. 4, pp. 758-762, 1982.\nD. Skeen, “Non Blocking Commit Protocols,” ACM SIGMOD Conference, 1981, pp. 133-142.\nD. Skeen and M. Stonebraker, “A Formal Model for Crash Recovery in a Distributed System,” IEEE Transactions on Software Engineering, vol. SE-9, pp. 219-228, May 1983.",{"VOID":710},"10.1023\u002FA:1026483919295","2024-05-16T18:48:45.020+00:00","https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1023\u002FA:1026483919295",[714],{"id":715,"sortIndex":21,"researcher":20,"roles":716,"affiliations":717,"properties":726},"4860a714-b907-4df0-9210-34d826a278a3",[205],[718],{"id":719,"sortIndex":21,"affiliation":720,"properties":20},"e8b6c33f-60ce-4672-9736-b8faf28708da",{"id":719,"createTime":20,"updateTime":20,"relativeEntities":721,"slug":20,"properties":722,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":725,"statistic":20},[],{"title":723},{"VI":724},"College of Business, Boulder",[],{"title":727},{"VI":728},"Akhil Kumar",{"url":712,"publisher":730,"properties":784},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":731,"slug":10,"properties":732,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":736,"manageAffiliations":753,"indexDatabases":764,"url":20,"thumbnailPath":20,"statistic":779,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":733,"title":734,"eissn":735},{"VOID":13},{"EN":15},{"VOID":17},[737,741,745,749],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":738,"label":739,"description":740,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":742,"label":743,"description":744,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":746,"label":747,"description":748,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":750,"label":751,"description":752,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[754,759],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":755,"slug":20,"properties":756,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":758,"statistic":20},[],{"title":757},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":760,"slug":20,"properties":761,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":763,"statistic":20},[],{"title":762},{"EN":60},[62],[765,772],{"id":65,"indexDatabase":766,"url":78,"indexYears":20,"academicFieldIds":771,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":767,"label":768,"description":769,"key":74,"publicationTags":770,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":773,"url":93,"indexYears":94,"academicFieldIds":778,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":774,"label":775,"description":776,"key":90,"publicationTags":777,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":780,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":781,"totalCitation":137,"totalCitationByYear":782,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":783,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"pages":785,"volume":787},{"VOID":786},"415-427",{"VOID":788},"7",{"total":136,"publishYear":790,"statisticByYear":791},1999,{"2016":136},"1999-10-01","DONE_ANALYZE_CITATION","2026-07-24T20:17:24.643+00:00",[100,76],{"id":797,"createTime":798,"updateTime":799,"relativeEntities":800,"slug":801,"properties":802,"entityType":196,"verifyStatus":197,"verifyTime":813,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":814,"fullTextUrl":20,"authors":815,"publicationType":300,"publisherRelationship":863,"citationCount":21,"citationInfo":923,"publishDate":926,"publishYear":924,"citationAnalyzeStatus":19,"lastCitationAnalyze":927,"indexDatabases":928,"openAccess":20,"references":20,"isForceReanalyzing":370},"e7bee323-9795-41f9-8122-369f06648242","2024-01-09T22:30:25.919+00:00","2026-07-21T04:59:41.941+00:00",[],"Specification-and-Management-of-Interdependent-Data-in-Operational-Systems-and-Data-Warehouses",{"abstract":803,"title":805,"gsPaper":807,"references":809,"doi":811},{"EN":804},"\n(Inter)Dependent objectsinclude data replicated or cached in multiple database systems, datacollected and summarized in data warehouses for analysis, planning,and decision support, as well as any other category of objects whosestates are related and they are maintained in different informationsystems. In this paper we discuss dependencies between objects in anenvironment consisting of operational systems and a data warehouse,and describe their specification and enforcement. To specify objectdependencies we introduce Object∖ Dependency∖ Descriptors(ObjectDDs). These describe the relationships between dependent objects, and define howmuch inconsistency between original objects and theirreplicas\u002Fcollections\u002Fsummaries can be tolerated before it isnecessary to restore their consistency. Object dependencies areenforced by extended∖ transactions designed specifically forevaluating if dependent objects satisfy their specifiedrelationships, evaluating whether possible inconsistencies can betolerated, and (if not) restoring consistency. To describe thetransactional behavior of such consistency∖ evaluation and restoration transactions we useTransaction∖ Dependency∖ Descriptors(TransactionDDs). TransactionDDsdefine the transactional relationships between consistency evaluation andrestoration (asynchronous) transactions, as well as the relationshipsbetween such asynchronous transactions and regular (synchronous)transactions executed directly by applications. To automaticallymaintain the consistency of dependent objects, we propose the conceptof a Dependency∖ Management∖ System(DMS). A DMS monitors dependent objects, evaluates object consistency, and schedules andcontrols consistency restoration transactions to keep dependentobjects within acceptable consistency levels. We describe keycomponents in the DMS architecture, and a relatively simpleimplementation involving straightforward extensions in a relationalDBMS.",{"EN":806},"Specification and Management of Interdependent Data in Operational Systems and Data Warehouses",{"VOID":808},"[\"16287620594569156679\"]",{"VOID":810},"R. Alonso, D. Barbara, and H. Garcia-Molina, “Data caching issues in an information retrieval system,” ACM-TODS, vol. 15, no. 3, Sept. 1990.\nB.R. Badrinath and K. Ramamritham, “Semantics-based concurrency control: Beyond commutativity,” in Proceedings of 3rd International Conference on Data Engineering, 1987.\nP. Bernstein, J. Rothnie, N. Goodman, and C. Papadimitriou, “The concurrency control mechanism of SDD-1: A system for distributed databases (The fully redundant case),” IEEE Trans. on Software Engineering, vol. 4, no. 3, May 1978.\nP.A. Bernstein, V. Hadzilacos, and N. Goodman, Concurrency Control and Recovery in Database Systems, Addison-Wesley, 1987.\nY. Breitbart, D. Georgakopoulos, M. Rusinkiewicz, and A. Silberschatz, “On rigorous transaction scheduling,” IEEE Trans. on Software Engineering, vol. 17, no. 9, Sept. 1991.\nA. Buchmann, M. Ozsu, M. Hornick, D. Georgakopoulos, and F. Manola, “A transaction model for active distributed object systems,” Database Transaction Models for Advanced Applications, A. Elmagarmid (Ed.), Morgan-Kaufmann, 1992.\nS. Chakravarthy, B. Blaustein et al., “HiPAC: A research project in active, time-constrained database management,” Tech. Report, XEROX (XAIT), Cambridge, MA, July 1989.\nU. Dayal, M. Hsu, and R. Ladin, “Organizing long-running activities with triggers and transactions,” in Proceedings of the ACM SIGMOD Conf. on Management of Data, 1990.\nU. Dayal, M. Hsu, and R. Ladin, “A transactional model for long-running activities,” in Proceedings of the 17th International Conference on VLDB, 1991.\nW. Du and A. Elmagarmid, “QSR: A correctness criterion for global concurrency control in interbase,” in Proceedings of the 15th International Conference on VLDB, 1989.\nA. Elmagarmid (Ed.), Database Transaction Models for Advanced Applications, Morgan-Kaufmann, 1992.\nA. Elmagarmid, Y. Leu, W. Litwin, and M. Rusinkiewicz, “A multidatabase transaction model for interbase,” in Proceedings of the 16th Int. Conf. on VLDB, 1990.\nA. Farrag and T. Ozsu, “Using semantic knowledge of transactions to increase concurrency,” ACM Transactions on Database Systems, vol. 14, no. 4, Dec. 1989.\nH. Garcia-Molina, “Using semantic knowledge for transaction processing in a distributed database,” ACM Trans. on Database Systems, vol. 8, no. 2, June 1983.\nH. Garcia-Molina and K. Salem, “SAGAS,” in Proceedings of ACMSIGMOD Conf. on Management of Data, 1987.\nS. Gatziu and K. Dittrich, “Events in an active object-oriented database system,” Technical Report 93.11, Institut fur Informatik der Universitat Zurich, Zurich, Switzerland, 1993.\nN. Gehani, H. Jagadish, and O. Shmueli, “Event specification in an active object-oriented database,” in Proceedings of ACM SIGMOD Conference, June 1992.\nD. Georgakopoulos and M. Hornick, “An environment for the specification and management of extended transactions and workflows in DOMS,” Tech. Report, TR-0218-09-92-165, GTE Laboratories Incorporated, Oct. 1992.\nD. Georgakopoulos and M. Hornick, “A framework for enforceable specification of extended transaction models and transactional workflows,” International Journal of Intelligent and Cooperative Information Systems, World Scientific, Sept. 1994.\nD. Georgakopoulos, M. Hornick, Piotr Krychniak, and Frank Manola, “Specification and management of extended transactions in a programmable transaction environment,” in Proceedings of the 10th Int. Conf. on Data Engineering, Houston, TX, Feb. 1994.\nD. Georgakopoulos, M. Rusinkiewicz, and A. Sheth, “Using ticket-based methods to enforce the serializability of multidatabase transactions,” IEEE Trans. on Data and Knowledge Engineering, Feb. 1994.\nD. Georgakopoulos, M. Hornick, and Frank Manola, “Customizing transaction models and mechanisms in a programmable environment supporting reliable workflow automation,” IEEE Transactions on Knowledge and Data Engineering, vol. 8, no. 4, Aug. 1996.\nM. Herlihy, “Apologizing versus asking permission: Optimistic concurrency control for abstract data types,” ACM Transactions on Database Systems, vol. 15, no. 1, 1990.\nM. Hornick and D. Georgakopoulos, “Extending heterogeneous transaction systems to support application-specific requirements,” Tech. Report, TR-0241-12-93-165, GTE Laboratories Incorporated, Dec. 1993.\nM. Hsu, R. Ladin, and D. McCarthy, “An execution model for active data base management systems,” in Proceedings of the 3rd International Conference on Data and Knowledge Bases, June 1988.\nW. Inmon, “Data warehouse defined,” Computerworld, March 1995. Special Advertising Supplement.\nG. Karabatis, Management of Interdependent Data in a Multidatabase Environment: A Polytransaction Approach, Ph.D. thesis, University of Houston, May 1995.\nN. Lynch, “Multilevel atomicity: A new correctness criterion for database concurrency control,” ACM Trans. on Database Systems, vol. 8, no. 4, Dec. 1983.\nE. Moss, Nested Transactions, MIT Press: Cambridge, Mass., 1985.\nA. Radding, “Support decision makers with a data warehouse,” Datamation, March 1995.\nD. Rinaldi, “Metadata management separates prism from data warehouse pack,” Client\u002FServer Computing, Mar. 1995.\nM. Rusinkiewicz, A. Sheth, and G. Karabatis, “Specifying interdatabase dependencies in a multidatabase environment,” IEEE Computer, vol. 24, no. 12, Dec. 1991.\nU. Schreier, H. Pirahesh, R. Agrawal, and C. Mohan, “Alert: An architecture for transforming a passive DBMS into an active DBMS,” in Proceedings of the 17th VLDB Conference, Sept. 1991.\nA. Sheth and P. Krishnamurthy, “Redundant data management in bellcore and BCC databases,” Tech. Report TM-STS-015011, Bellcore, Dec. 1989.\nA. Sheth, Y. Leu, and A. Elmagarmid, “Maintaining consistency of interdependent data in multidatabase systems,” Technical Report CSD-TR-91-016, Computer Sciences Department, Purdue University, March 1991.\nE. Simon and P. Valduriez, “Integrity control in distributed database systems,” in Proceedings of the 20th Hawaii International Conference on System Sciences, 1986.\nE. Simon, J. Kiernan, and C. de Maindreville, “Implementing high level active rules on top of a relational DBMS,” in Proceedings of the 18th VLDB Conference, 1992.\nH. Wachter and A. Reuter, “Contracts: A means for extending control beyond transaction boundaries,” Database Transaction Models for Advanced Applications, A. Elmagarmid (Ed.), Morgan-Kaufmann, 1992.\nW. Weihl, “Commutativity-based concurrency control for abstract data types,” IEEE Transactions on Computers, vol. 37, no. 12, Dec. 1988.\nW. Weihl, “Local atomicity properties: Modular concurrency control for abstract data types,” ACM Transactions on Programming Languages and Systems, vol. 11, no. 2, 1989.\nG. Wiederhold and X. Qian, “Modeling asynchrony in distributed databases,” in Proceedings of the IEEE International Conference on Data Engineering, Feb. 1987.\nG. Wiederhold and X. Qian, “Consistency control of replicated data in federated databases,” in Proceedings of the Workshop on the Management of Replicated Data, Houston, TX, Nov.1990.",{"VOID":812},"10.1023\u002FA:1008692007657","2024-05-28T21:59:03.502+00:00","https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1023\u002FA:1008692007657",[816,833,848],{"id":817,"sortIndex":21,"researcher":20,"roles":818,"affiliations":819,"properties":828},"02ab4e5f-555d-44a9-a736-120313838b6c",[205],[820],{"id":821,"sortIndex":21,"affiliation":822,"properties":20},"5a8dbe39-e16d-44a3-b043-8fea1c857353",{"id":821,"createTime":20,"updateTime":20,"relativeEntities":823,"slug":20,"properties":824,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":827,"statistic":20},[],{"title":825},{"VI":826},"GTE Laboratories, Incorporated, Waltham",[],{"title":829,"gsAuthor":831},{"VI":830},"Dimitrios Georgakopoulos",{"VOID":832},"[\"HEFGlx8AAAAJ\"]",{"id":834,"sortIndex":136,"researcher":20,"roles":835,"affiliations":836,"properties":845},"142a6c23-9b16-428a-9a7a-29744c34014a",[205],[837],{"id":838,"sortIndex":21,"affiliation":839,"properties":20},"01ae0cee-0263-4828-ab9f-25efb8d4fee1",{"id":838,"createTime":20,"updateTime":20,"relativeEntities":840,"slug":20,"properties":841,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":844,"statistic":20},[],{"title":842},{"VI":843},"Bellcore, Morristown",[],{"title":846},{"VI":847},"George Karabatis",{"id":849,"sortIndex":140,"researcher":20,"roles":850,"affiliations":851,"properties":860},"2ce5de39-dc9e-4a37-9c5f-bb00548308bb",[205],[852],{"id":853,"sortIndex":21,"affiliation":854,"properties":20},"6063ca0b-87a6-4a3b-ad8a-8ad0c74de20d",{"id":853,"createTime":20,"updateTime":20,"relativeEntities":855,"slug":20,"properties":856,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":859,"statistic":20},[],{"title":857},{"VI":858},"Sybase Incorporated, Emeryville",[],{"title":861},{"VI":862},"Sridhar Gantimahapatruni",{"url":814,"publisher":864,"properties":918},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":865,"slug":10,"properties":866,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":870,"manageAffiliations":887,"indexDatabases":898,"url":20,"thumbnailPath":20,"statistic":913,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":867,"title":868,"eissn":869},{"VOID":13},{"EN":15},{"VOID":17},[871,875,879,883],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":872,"label":873,"description":874,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":876,"label":877,"description":878,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":880,"label":881,"description":882,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":884,"label":885,"description":886,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[888,893],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":889,"slug":20,"properties":890,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":892,"statistic":20},[],{"title":891},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":894,"slug":20,"properties":895,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":897,"statistic":20},[],{"title":896},{"EN":60},[62],[899,906],{"id":65,"indexDatabase":900,"url":78,"indexYears":20,"academicFieldIds":905,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":901,"label":902,"description":903,"key":74,"publicationTags":904,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":907,"url":93,"indexYears":94,"academicFieldIds":912,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":908,"label":909,"description":910,"key":90,"publicationTags":911,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":914,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":915,"totalCitation":137,"totalCitationByYear":916,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":917,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"pages":919,"volume":921},{"VOID":920},"121-166",{"VOID":922},"5",{"total":21,"publishYear":924,"statisticByYear":925},1997,{},"1997-04-01","2026-07-21T04:59:41.940+00:00",[100,76],{"id":930,"createTime":931,"updateTime":932,"relativeEntities":933,"slug":934,"properties":935,"entityType":196,"verifyStatus":197,"verifyTime":946,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":947,"fullTextUrl":20,"authors":948,"publicationType":300,"publisherRelationship":966,"citationCount":116,"citationInfo":1026,"publishDate":1028,"publishYear":533,"citationAnalyzeStatus":793,"lastCitationAnalyze":1029,"indexDatabases":1030,"openAccess":20,"references":20,"isForceReanalyzing":370},"254adda0-4d9f-43d8-8097-466d647a34ba","2024-01-25T11:40:15.294+00:00","2026-07-13T09:48:10.070+00:00",[],"Speeding-up-AutoTuning-of-the-Memory-Management-Options-in-Data-Analytics",{"abstract":936,"title":938,"gsPaper":940,"references":942,"doi":944},{"EN":937},"Many solutions used towards building autonomous (or, self-driving) data processing systems today are trying to leverage the “black box” algorithm of Bayesian Optimization (BO) both due to its wider applicability and the theoretical guarantees provided on the quality of results produced. The black-box approach, however, could be time and labor-intensive; or otherwise get stuck in a local minima. We study an important problem of auto-tuning the memory allocation for applications running on modern distributed data processing systems. A simple “white-box” model is developed which can quickly separate good configurations from bad ones. To combine the benefits of the two approaches to tuning, we build a framework called Guided Bayesian Optimization (GBO) that uses the white-box model as a guide during the Bayesian Optimization exploration process. An evaluation carried out on Apache Spark using industry-standard benchmark applications shows that GBO consistently provides performance speedups across the application workload with the magnitude of savings being close to 2x.",{"EN":939},"Speeding up AutoTuning of the Memory Management Options in Data Analytics",{"VOID":941},"[\"12965339777031573327\"]",{"VOID":943},"Agrawal, S., Chaudhuri, S., Narasayya, V.R.: Automated selection of materialized views and indexes in SQL databases. In: Proceedings of the 26th International Conference on Very Large Data Bases (VLDB ’00), pp. 496–505. Morgan Kaufmann Publishers, San Francisco (2000). ISBN 1-55860-715-3. http:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=645926.671701\nAken, D.V., Pavlo, A., Gordon, G.J., Zhang, B.: Automatic database management system tuning through large-scale machine learning. In: Salihoglu, S., Zhou, W., Chirkova, R., Yang, J., Suciu, D. (eds.) Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD Conference 2017, Chicago, IL, USA, 14–19 May 2017, pp. 1009–1024. ACM, New York (2017). ISBN 978-1-4503-4197-4. https:\u002F\u002Fdoi.org\u002F10.1145\u002F3035918.3064029\nAlipourfard, O., Liu, H.H., Chen, J., Venkataraman, S., Yu, M., Zhang, M.: Cherrypick: Adaptively unearthing the best cloud configurations for big data analytics. In: 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17), pp. 469–482, Boston, MA. USENIX Association, Berkeley (2017). ISBN 978-1-931971-37-9. https:\u002F\u002Fwww.usenix.org\u002Fconference\u002Fnsdi17\u002Ftechnical-sessions\u002Fpresentation\u002Falipourfard\nArvanitis, A., Babu, S., Chu, E., Popescu, A., Simitsis, A., Wilkinson, K.: Automated performance management for the big data stack. In: CIDR 2019, 9th Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA, 13–16 January 2019, Online Proceedings (2019). www.cidrdb.org, http:\u002F\u002Fcidrdb.org\u002Fcidr2019\u002Fpapers\u002Fp150-arvanitis-cidr19.pdf\nBao, L., Liu, X., Chen, W.: Learning-based automatic parameter tuning for big data analytics frameworks. CoRR (2018). arXiv:1808.06008\nBreiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001). https:\u002F\u002Fdoi.org\u002F10.1023\u002FA:1010933404324\nByrd, R.H., Lu, P., Nocedal, J.: A limited-memory algorithm for bound constrained optimization. SIAM J. Sci. Comput. 16, 1190–1208 (1994)\nCao, Z., Tarasov, V., Tiwari, S., Zadok, E.: Towards better understanding of black-box auto-tuning: A comparative analysis for storage systems. In: Proceedings of the 2018 USENIX Conference on Usenix Annual Technical Conference. USENIX ATC ’18, pp. 893–907. USENIX Association, Berkeley (2018). ISBN 978-1-931971-44-7. URL http:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3277355.3277441\nChaudhuri, S., Narasayya, V.: Self-tuning database systems: a decade of progress. In: Proceedings of the 33rd International Conference on Very Large Data Bases (VLDB ’07), pp. 3–14. VLDB Endowment, 2007. ISBN 978-1-59593-649-3. http:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=1325851.1325856\nChaudhuri, S., Narasayya, V.R.: An efficient cost-driven index selection tool for microsoft sql server. In: Proceedings of the 23rd International Conference on Very Large Data Bases (VLDB ’97), pp. 146–155. Morgan Kaufmann Publishers, San Francisco (1997). ISBN 1-55860-470-7. http:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=645923.673646\nDalibard, V., Schaarschmidt, M., Yoneki, E.: BOAT: Building auto-tuners with structured bayesian optimization. In: Proceedings of the 26th International Conference on World Wide Web (WWW ’17), Republic and Canton of Geneva, Switzerland, pp. 479–488. International World Wide Web Conferences Steering Committee (2017). ISBN 978-1-4503-4913-0. https:\u002F\u002Fdoi.org\u002F10.1145\u002F3038912.3052662\nDias, K., Ramacher, M., Shaft, U., Venkataramani, V., Wood, G.: Automatic performance diagnosis and tuning in oracle. In: CIDR 2005, Second Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA, 4–7 January 2005, Online Proceedings. pp. 84–94 (2005). www.cidrdb.org, http:\u002F\u002Fcidrdb.org\u002Fcidr2005\u002Fpapers\u002FP07.pdf\nDraper, N., Smith, H.: Applied Regression Analysis. Wiley Series in Probability and Statistics: Texts and References Section, vol. 1. Wiley, New York (1998). ISBN 9780471170822. URL https:\u002F\u002Fbooks.google.co.in\u002Fbooks?id=8n8pAQAAMAAJ\nDuan, S., Thummala, V., Babu, S.: Tuning database configuration parameters with ituned. PVLDB 2(1), 1246–1257 (2009). https:\u002F\u002Fdoi.org\u002F10.14778\u002F1687627.1687767\nGounaris, A., Torres, J.: A methodology for spark parameter tuning. Big Data Res. 11, 22–32 (2018)\nHerodotou, H., Dong, F., Babu, S.: No One (Cluster) Size Fits All: Automatic Cluster Sizing for Data-Intensive Analytics (SOCC ’11), pp. 18:1–18:14. ACM, New York (2011). ISBN 978-1-4503-0976-9. https:\u002F\u002Fdoi.org\u002F10.1145\u002F2038916.2038934\nHerodotou, H., Lim, H., Luo, G., Borisov, N., Dong, L., Cetin, F.B., Babu, S.: Starfish: A self-tuning system for big data analytics. In: CIDR, Asilomar, pp. 261–272 (2011)\nHsu, C., Nair, V., Freeh, V.W., Menzies, T.: Arrow: low-level augmented Bayesian optimization for finding the best cloud VM. In: 38th IEEE International Conference on Distributed Computing Systems (ICDCS 2018), Vienna, Austria, 2–6 July 2018, pp. 660–670. IEEE Computer Society (2018). ISBN 978-1-5386-6871-9. https:\u002F\u002Fdoi.org\u002F10.1109\u002FICDCS.2018.00070\nHuang, S., Huang, J., Dai, J., Xie, T., Huang, B.: The hibench benchmark suite: Characterization of the mapreduce-based data analysis. In: 2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW 2010), pp. 41–51, March 2010.https:\u002F\u002Fdoi.org\u002F10.1109\u002FICDEW.2010.5452747\nHutter, F., Hoos, H.H., Leyton-Brown, K.: Sequential model-based optimization for general algorithm configuration. In: International Conference on Learning and Intelligent Optimization, pp. 507–523. Springer, Heidelberg (2011)\nIreland, C.: Fundamental concepts in the design of experiments. Technometrics 7(4), 652–653 (1965). https:\u002F\u002Fdoi.org\u002F10.1080\u002F00401706.1965.10490308\nJamshidi, P., Casale, G.: An uncertainty-aware approach to optimal configuration of stream processing systems. In: 24th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS 2016), London, UK, 19–21 September 2016, pp. 39–48. IEEE Computer Society (2016). ISBN 978-1-5090-3432-1. https:\u002F\u002Fdoi.org\u002F10.1109\u002FMASCOTS.2016.17\nKunjir, M., Babu, S.: Thoth in action: memory management in modern data analytics. Proc. VLDB Endow. 10(12), 1917–1920 (2017). https:\u002F\u002Fdoi.org\u002F10.14778\u002F3137765.3137808\nKwan, E., Lightstone, S., Schiefer, K.B., Storm, A.J., Wu, L.: Automatic database configuration for DB2 universal database: Compressing years of performance expertise into seconds of execution. In: Weikum, G., Schöning, H., Rahm, E. (eds.) BTW 2003, Datenbanksysteme für Business, Technologie und Web, Tagungsband der 10. BTW-Konferenz, 26–28 Februar 2003, Leipzig, LNI, vol. 26, pp. 620–629. GI (2003). ISBN 3-88579-355-5. http:\u002F\u002Fsubs.emis.de\u002FLNI\u002FProceedings\u002FProceedings26\u002Farticle665.html\nLeskovec, J., Krevl, A.: SNAP Datasets: Stanford large network dataset collection (2014). http:\u002F\u002Fsnap.stanford.edu\u002Fdata\nLi, G., Zhou, X., Li, S., Gao, B.: Qtune: A query-aware database tuning system with deep reinforcement learning. Proc. VLDB Endow. 12(12), 2118–2130 (2019). https:\u002F\u002Fdoi.org\u002F10.14778\u002F3352063.3352129\nLi, M., Zeng, L., Meng, S., Tan, J., Zhang, L., Butt, A.R., Fuller, N.: Mronline: Mapreduce online performance tuning. In: Proceedings of the 23rd International Symposium on High-Performance Parallel and Distributed Computing, pp. 165–176. ACM, New York (2014)\nMao, H., Alizadeh, M., Menache, I., Kandula, S.: Resource management with deep reinforcement learning. In: Proceedings of the 15th ACM Workshop on Hot Topics in Networks (HotNets ’16), pp. 50–56. ACM, New York (2016). ISBN 978-1-4503-4661-0. https:\u002F\u002Fdoi.org\u002F10.1145\u002F3005745.3005750\nMarcus, R., Negi, P., Mao, H., Zhang, C., Alizadeh, M., Kraska, T., Papaemmanouil, O., Tatbul, N.: Neo: A learned query optimizer. Proc. VLDB Endow. 12(11), 1705–1718 (2019). https:\u002F\u002Fdoi.org\u002F10.14778\u002F3342263.3342644\nMockus, J.: Bayesian Approach to Global Optimization: Theory and Applications. Mathematics and Its Applications . Soviet Series. Kluwer, Dordrecht (1989). ISBN 9780792301158\nOnline: Java garbage collection basics (2019). https:\u002F\u002Fbit.ly\u002F2N8JyOp. Accessed 10 July 2019\nOnline: Java management extensions (jmx) (2019). https:\u002F\u002Fbit.ly\u002F2KIvbNn. Accessed 10 July 2019\nOnline: Intel’s performance analysis tool (2019). https:\u002F\u002Fgithub.com\u002Fintel-hadoop\u002FPAT. Accessed 10 July 2019\nOnline: RelM Technical Report (2019). https:\u002F\u002Fwww.dropbox.com\u002Fs\u002F2wwmdmw7a77qz03\u002Fmain.pdf?dl=0. Accessed 10 July 2019\nOnline: Amazon EMR documentation (2019). https:\u002F\u002Famzn.to\u002F2zrpNtt. Accessed 10 July 2019\nPedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)\nRao, J., Zhang, C., Megiddo, N., Lohman, G.: Automating physical database design in a parallel database. In: Proceedings of the 2002 ACM SIGMOD International Conference on Management of Data (SIGMOD ’02), pp. 558–569. ACM, New York (2002). ISBN 1-58113-497-5.https:\u002F\u002Fdoi.org\u002F10.1145\u002F564691.564757\nRasmussen, C.E.: Gaussian Processes for Machine Learning. MIT, Cambridge (2006)\nShahriari, B., Swersky, K., Wang, Z., Adams, R.P., de Freitas, N.: Taking the human out of the loop: a review of bayesian optimization. Proc. IEEE 104, 148–175 (2016)\nShi, J., Zou, J., Lu, J., Cao, Z., Li, S., Wang, C.: Mrtuner: a toolkit to enable holistic optimization for mapreduce jobs. Proc. VLDB Endow. 7(13), 1319–1330 (2014). https:\u002F\u002Fdoi.org\u002F10.14778\u002F2733004.2733005\nStorm, A.J., Garcia-Arellano, C., Lightstone, S.S., Diao, Y., Surendra, M.: Adaptive self-tuning memory in DB2. In: Proceedings of the 32nd International Conference on Very Large Data Bases (VLDB ’06), pp. 1081–1092. VLDB Endowment (2006). http:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=1182635.1164220\nTan, Z., Babu, S.: Tempo: Robust and self-tuning resource management in multi-tenant parallel databases. Proc. VLDB Endow. 9(10), 720–731 (2016). https:\u002F\u002Fdoi.org\u002F10.14778\u002F2977797.2977799\nTibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B 58(1), 267–288 (1996)\nVenkataraman, S., Yang, Z., Franklin, M., Recht, B., Stoica, I.: Ernest: Efficient performance prediction for large-scale advanced analytics. In: 13th USENIX Symposium on Networked Systems Design and Implementation (NSDI 16), pp. 363–378, Santa Clara, CA. USENIX Association, Berkeley (2016). ISBN 978-1-931971-29-4. https:\u002F\u002Fwww.usenix.org\u002Fconference\u002Fnsdi16\u002Ftechnical-sessions\u002Fpresentation\u002Fvenkataraman\nWang, G., Xu, J., He, B.: A novel method for tuning configuration parameters of spark based on machine learning. In: 2016 IEEE 18th International Conference on High Performance Computing and Communications, pp. 586–593. IEEE, Piscataway (2016). https:\u002F\u002Fdoi.org\u002F10.1109\u002FHPCC-SmartCity-DSS.2016.0088\nWang, M., Au, K., Ailamaki, A., Brockwell, A., Faloutsos, C., Ganger, G.R.: Storage device performance prediction with cart models. In: Proceedings of the IEEE Computer Society’s 12th Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, 2004 (MASCOTS 2004), pp. 588–595. IEEE, Washington DC (2004)\nWeikum, G., Moenkeberg, A., Hasse, C., Zabback, P.: Self-tuning database technology and information services: from wishful thinking to viable engineering. In: Proceedings of the 28th International Conference on Very Large Data Bases (VLDB ’02), pp. 20–31. VLDB Endowment (2002). http:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=1287369.1287373\nWikipedia Contributors: Pearson correlation coefficient—Wikipedia, the free encyclopedia (2019). https:\u002F\u002Fen.wikipedia.org\u002Fw\u002Findex.php?title=Pearson_correlation_coefficient&oldid=905965350. Accessed 10 July 2019\nXi, B., Liu, Z., Raghavachari, M., Xia, C.H., Zhang, L.: A smart hill-climbing algorithm for application server configuration. In: Proceedings of the 13th International Conference on World Wide Web, WWW ’04, pp. 287–296, New York, NY, USA, 2004. ACM. ISBN 1-58113-844-X. https:\u002F\u002Fdoi.org\u002F10.1145\u002F988672.988711\nYadwadkar, N.J., Hariharan, B., Gonzalez, J.E., Smith, B., Katz, R.H.: Selecting the best vm across multiple public clouds: A data-driven performance modeling approach. In: Proceedings of the 2017 Symposium on Cloud Computing, SoCC ’17, pp. 452–465, New York, NY, USA, 2017. ACM. ISBN 978-1-4503-5028-0. https:\u002F\u002Fdoi.org\u002F10.1145\u002F3127479.3131614\nYe, T., Kalyanaraman, S.: A recursive random search algorithm for large-scale network parameter configuration. SIGMETRICS Perform. Eval. Rev. 31(1), 196–205 (2003). https:\u002F\u002Fdoi.org\u002F10.1145\u002F885651.781052\nZhang, J., Liu, Y., Zhou, K., Li, G., Xiao, Z., Cheng, B., Xing, J., Wang, Y., Cheng, T., Liu, L., Ran, M., Li, Z.: An end-to-end automatic cloud database tuning system using deep reinforcement learning. In: Proceedings of the 2019 International Conference on Management of Data (SIGMOD ’19), pp. 415–432. ACM, New York (2019). ISBN 978-1-4503-5643-5. https:\u002F\u002Fdoi.org\u002F10.1145\u002F3299869.3300085\nZhu, Y., Liu, J., Guo, M., Bao, Y., Ma, W., Liu, Z., Song, K., Yang, Y.: Bestconfig: tapping the performance potential of systems via automatic configuration tuning. In: Proceedings of the 2017 Symposium on Cloud Computing, pp. 338–350. ACM, New York (2017)",{"VOID":945},"10.1007\u002Fs10619-019-07281-y","2024-05-09T09:09:04.320+00:00","https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10619-019-07281-y",[949],{"id":950,"sortIndex":21,"researcher":20,"roles":951,"affiliations":952,"properties":961},"0c96ec96-1dce-4744-84c0-f6452f9720c5",[205],[953],{"id":954,"sortIndex":21,"affiliation":955,"properties":20},"23a62ea6-fc32-4d17-9914-219961e5614f",{"id":954,"createTime":20,"updateTime":20,"relativeEntities":956,"slug":20,"properties":957,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":960,"statistic":20},[],{"title":958},{"EN":959},"Duke University, Durham, USA",[],{"title":962,"gsAuthor":964},{"VI":963},"Mayuresh Kunjir",{"VOID":965},"[\"-FfCq38AAAAJ\"]",{"url":947,"publisher":967,"properties":1021},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":968,"slug":10,"properties":969,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":973,"manageAffiliations":990,"indexDatabases":1001,"url":20,"thumbnailPath":20,"statistic":1016,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":970,"title":971,"eissn":972},{"VOID":13},{"EN":15},{"VOID":17},[974,978,982,986],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":975,"label":976,"description":977,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":979,"label":980,"description":981,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":983,"label":984,"description":985,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":987,"label":988,"description":989,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[991,996],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":992,"slug":20,"properties":993,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":995,"statistic":20},[],{"title":994},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":997,"slug":20,"properties":998,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1000,"statistic":20},[],{"title":999},{"EN":60},[62],[1002,1009],{"id":65,"indexDatabase":1003,"url":78,"indexYears":20,"academicFieldIds":1008,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":1004,"label":1005,"description":1006,"key":74,"publicationTags":1007,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":1010,"url":93,"indexYears":94,"academicFieldIds":1015,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":1011,"label":1012,"description":1013,"key":90,"publicationTags":1014,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":1017,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":1018,"totalCitation":137,"totalCitationByYear":1019,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":1020,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"pages":1022,"volume":1024},{"VOID":1023},"841-863",{"VOID":1025},"38",{"total":116,"publishYear":533,"statisticByYear":1027},{"2024":140,"2025":136},"2020-01-03","2026-07-13T09:48:10.069+00:00",[100,76],{"id":1032,"createTime":1033,"updateTime":1034,"relativeEntities":1035,"slug":1036,"properties":1037,"entityType":196,"verifyStatus":197,"verifyTime":1050,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":1051,"fullTextUrl":20,"authors":1052,"publicationType":300,"publisherRelationship":1100,"citationCount":124,"citationInfo":1155,"publishDate":1158,"publishYear":1156,"citationAnalyzeStatus":19,"lastCitationAnalyze":1034,"indexDatabases":1159,"openAccess":20,"references":20,"isForceReanalyzing":370},"bf41adc7-88fa-4b49-8010-543398efa75a","2024-04-05T14:48:23.666+00:00","2026-05-07T10:04:37.229+00:00",[],"Partitioning-methods-for-multi-version-XML-data-warehouses",{"abstract":1038,"title":1040,"gsPaper":1042,"keywords":1044,"references":1046,"doi":1048},{"EN":1039},"Due to an explosive increase of XML documents, it is imperative to manage XML data in an XML data warehouse. XML warehousing imposes challenges, which are not found in the relational data warehouses. In this paper, we firstly present a framework to build an XML data warehouse schema. For the purpose of scalability due to the increase of data volume, we propose a number of partitioning techniques for multi-version XML data warehouses, including document based partitioning, schema based partitioning, and cascaded (mixed) partitioning model. Finally, we formulate cost models to evaluate various types of queries for an XML data warehouse.",{"EN":1041},"Partitioning methods for multi-version XML data warehouses",{"VOID":1043},"5441085193499887639",{"EN":1045},"",{"VOID":1047},"Abadi, D., Marcus, A., Madden, S.R., Hollenbach, K.: Scalable semantic web data management using vertical partitioning. In: Proceedings of the International Conference on Very Large Data Bases (VLDB’2007), pp. 411–422 (2007)\nBellatreche, L., Karlapalem, K., Mohania, M.: OLAP query processing for partitioned data warehouses. In: Proceedings of the International Symposium on Database Applications in Non-Traditional Environments, pp. 35–42 (1999)\nBellatreche, L., Karlapalem, K., Mohania, M., Schneider, M.: What can partitioning do for your data warehouses and data marts? In: Proceedings of International Symposium on Database Engineering and Applications, pp. 437–445 (2000)\nBellatreche, L., Boukhalfa, L.: An evolutionary approach to schema partitioning selection in a data warehouse. In: Proceedings of the International Conference on Data Warehousing and Knowledge Discovery (DaWaK’2005). Lecture Notes in Computer Science, vol. 3589, pp. 115–125. Springer, Berlin (2005)\nChien, S.Y., Tzotras, V.J., Zaniolo, C., Zhang, D.: Storing and querying multiversion XML documents using durable node numbers. In: Proceedings of the International Conference on Web Information Systems Engineering (WISE’2001), pp. 232–241 (2001)\nCobena, G., Abiteboul, S., Marian, A.: Detecting changes in XML documents. In: Proceedings of the 18th International Conference on Data Engineering (ICDE 2002), pp. 41–52 (2002)\nDehne, F., Eavis, T., Rau-Chaplin, A.: RCUBE: parallel multi-dimensional ROLAP indexing. Int. J. Data Warehous. Min. IGI Glob. 4(3), 1–14 (2008)\nFurtado, P.: Workload-based placement and join processing in node-partitioned data warehouses. In: Proceedings of the International Conference on Data Warehousing and Knowledge Discovery (DaWaK’2004). Lecture Notes in Computer Science, vol. 3181, pp. 38–47. Springer, Berlin (2004)\nGorla, N., Pang, B.: Vertical fragmentation in databases using data-mining technique. Int. J. Data Warehous. Min. IGI Glob. 4(3), 33–53 (2008)\nMarian, A., Abiteboul, S., Cobena, G., Mignet, L.: 2001, Change-centric management of versions in an XML warehouse. In: Proceedings of the International Conference on Very Large Data Bases (VLDB’2001), pp. 581–590 (2001)\nPardede, E., Rahayu, J.W., Taniar, D.: Object-relational complex structures for XML storage. Inf. Softw. Technol. 48(6), 370–384 (2006)\nRusu, L.I., Rahayu, W., Taniar, D.: On data cleaning in building XML data warehouses. In: Proceedings of the 6th International Conference on Information Integration and Web-based Applications & Services (iiWAS’2004), pp. 797–807 (2004)\nRusu, L.I., Rahayu, W., Taniar, D.: A methodology for building XML data warehouses. Int. J. Data Warehous. Min. 1(2), 67–92 (2005)\nRusu, L.I., Rahayu, W., Taniar, D.: Maintaining versions of dynamic XML documents. In: Proceedings of the 6th International Conference on Web Information Systems Engineering (WISE’2005). Lecture Notes in Computer Science Lecture Notes in Computer Science, vol. 3806, pp. 536–543. Springer, Berlin (2005)\nRusu, L.I., Rahayu, W., Taniar, D.: Warehousing dynamic XML documents. In: Proceedings of the International Conference on Data Warehousing and Knowledge Discovery (DaWaK’2006). Lecture Notes in Computer Science, vol. 4081, pp. 175–184. Springer, Berlin (2006)\nRusu, L.I., Rahayu, W., Taniar, D.: Storage techniques for multi-versioned XML documents. In: Proceedings of the 13th International Conference on Database Systems for Advanced Applications (DASFAA’2008). Lecture Notes in Computer Science, vol. 4947, pp. 538–545. Springer, Berlin (2008)\nTaniar, D., Rahayu, J.W.: Parallel sort-merge object-oriented collection join algorithms. Int. J. Comput. Syst. Sci. Eng. 17(3), 145–158 (2002)\nTaniar, D., Rahayu, J.W.: Parallel group-by query processing in a cluster architecture. Int. J. Comput. Syst. Sci. Eng. 17(1), 23–39 (2002)\nTaniar, D., Leung, C.H.C.: Query execution scheduling in parallel object-oriented databases. Inf. Softw. Technol. 41(3), 163–178 (1999)\nTaniar, D., Leung, C.H.C.: The impact of load balancing to object-oriented query execution scheduling in parallel machine environment. Inf. Sci. 157, 33–71 (2003)\nWang, F., Zaniolo, C.: Temporal queries in XML document archives and web warehouses. In: Proceedings of the 10th International Symposium on Temporal Representation and Reasoning\u002F4th International Conference on Temporal Logic (TIME-ICTL 2003), pp. 47–55 (2003)\nXyleme, L.: A dynamic warehouse for XML data of the web. IEEE Data Eng. Bull. 24(2), 40–47 (2001)\nMahboubi, H., Darmont, J.: Data mining-based fragmentation of XML data warehouses. In: Proceedings of DOLAP 2008, pp. 9–16. ACM, New York (2008)",{"VOID":1049},"10.1007\u002Fs10619-009-7034-y","2024-04-29T10:40:04.315+00:00","https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10619-009-7034-y",[1053,1068,1083],{"id":1054,"sortIndex":21,"researcher":20,"roles":1055,"affiliations":1056,"properties":1065},"307f57e7-f8db-4faa-aaff-345d4f14a041",[205],[1057],{"id":1058,"sortIndex":21,"affiliation":1059,"properties":20},"513c3a29-ea66-43f9-b270-70483db40d74",{"id":1058,"createTime":20,"updateTime":20,"relativeEntities":1060,"slug":20,"properties":1061,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1064,"statistic":20},[],{"title":1062},{"VI":1063},"Department of Computer Science and Computer Engineering, La Trobe University, Bundoora, Australia",[],{"title":1066},{"VI":1067},"Laura Irina Rusu",{"id":1069,"sortIndex":136,"researcher":20,"roles":1070,"affiliations":1071,"properties":1078},"a62ea2dd-8417-4e00-b9fd-b5edfe75380a",[205],[1072],{"id":1058,"sortIndex":21,"affiliation":1073,"properties":20},{"id":1058,"createTime":20,"updateTime":20,"relativeEntities":1074,"slug":20,"properties":1075,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1077,"statistic":20},[],{"title":1076},{"VI":1063},[],{"title":1079,"gsAuthor":1081},{"VI":1080},"Wenny Rahayu",{"VOID":1082},"_t98_OAAAAAJ",{"id":1084,"sortIndex":140,"researcher":20,"roles":1085,"affiliations":1086,"properties":1095},"eddcd3f9-fd64-492a-8606-5a76f55a2c42",[205],[1087],{"id":1088,"sortIndex":21,"affiliation":1089,"properties":20},"91481c43-9936-4640-98e9-d81185b157c3",{"id":1088,"createTime":20,"updateTime":20,"relativeEntities":1090,"slug":20,"properties":1091,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1094,"statistic":20},[],{"title":1092},{"VI":1093},"Clayton School of Information Technology, Monash University, Clayton, Australia",[],{"title":1096,"gsAuthor":1098},{"VI":1097},"David Taniar",{"VOID":1099},"M1acg20AAAAJ",{"url":20,"publisher":1101,"properties":20},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":1102,"slug":10,"properties":1103,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":1107,"manageAffiliations":1124,"indexDatabases":1135,"url":20,"thumbnailPath":20,"statistic":1150,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":1104,"title":1105,"eissn":1106},{"VOID":13},{"EN":15},{"VOID":17},[1108,1112,1116,1120],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":1109,"label":1110,"description":1111,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":1113,"label":1114,"description":1115,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":1117,"label":1118,"description":1119,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":1121,"label":1122,"description":1123,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[1125,1130],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":1126,"slug":20,"properties":1127,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1129,"statistic":20},[],{"title":1128},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":1131,"slug":20,"properties":1132,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1134,"statistic":20},[],{"title":1133},{"EN":60},[62],[1136,1143],{"id":65,"indexDatabase":1137,"url":78,"indexYears":20,"academicFieldIds":1142,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":1138,"label":1139,"description":1140,"key":74,"publicationTags":1141,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":1144,"url":93,"indexYears":94,"academicFieldIds":1149,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":1145,"label":1146,"description":1147,"key":90,"publicationTags":1148,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":1151,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":1152,"totalCitation":137,"totalCitationByYear":1153,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":1154,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"total":124,"publishYear":1156,"statisticByYear":1157},2009,{"2009":136,"2011":140,"2012":121,"2013":151,"2014":116,"2017":136},"2009-02-20",[100,76],{"id":1161,"createTime":1162,"updateTime":1163,"relativeEntities":1164,"slug":1165,"properties":1166,"entityType":196,"verifyStatus":197,"verifyTime":1177,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":1178,"fullTextUrl":20,"authors":1179,"publicationType":300,"publisherRelationship":1223,"citationCount":20,"citationInfo":20,"publishDate":1283,"publishYear":1284,"citationAnalyzeStatus":1285,"lastCitationAnalyze":1286,"indexDatabases":1287,"openAccess":20,"references":20,"isForceReanalyzing":370},"b5df71d6-c27b-4178-80cd-3e17825fe1ce","2023-12-01T03:08:39.067+00:00","2026-03-06T23:34:08.544+00:00",[],"Disk-Allocation-for-Fast-Range-and-Nearest-Neighbor-Queries",{"abstract":1167,"title":1169,"gsPaper":1171,"references":1173,"doi":1175},{"EN":1168},"As databases increasingly integrate non-textual multimedia information it is becoming necessary to support efficient similarity searching in addition to range searching. Range and nearest-neighbor (similarity) queries are the most important class of queries for multimedia and multi-dimensional databases. Due to the large sizes of the datasets involved, I\u002FO is a critical factor limiting performance. The use of parallel I\u002FO through declustering of the data is a promising approach to improve performance. Consequently several research efforts have addressed the problem of declustering multidimensional data for optimizing range and partial match queries. Very limited work has been done for similarity queries, and the problem of declustering for combined range and similarity queries has not been addressed in the literature. Consider a dataset of images where the following metadata for each image is also stored: date on which the picture was taken, longitudeand latitude of the site of the picture. An example of a combined query is: Given a target image, find the 5 most similar images taken within 3 months of the target image and located within 2 degrees of longitude and latitude of the target image. In order to answer this query, it is necessary to conduct a range search on the date, longitude and latitude values and a similarity search on the image content. In this paper, we develop new declustering schemes that provide good declustering for similarity searching. In addition, we show that the new schemes have very good performance for range queries as well as combination queries. The new schemes are based upon the Cyclic declustering schemes which were developed for range and partial match queries. The Cyclic schemes not only provide superior performance to earlier schemes, but are also very robust and consistent with respect to query types and variations in system parameters.",{"EN":1170},"Disk Allocation for Fast Range and Nearest-Neighbor Queries",{"VOID":1172},"[]",{"VOID":1174},"K.A.S. Abdel-Ghaffar and A. El Abbadi, “Optimal disk allocation for partial match queries,” Transactions of Database Systems, vol. 18, no. 1, pp. 132–156, 1993.\nK.A.S. Abdel-Ghaffar and A. El Abbadi, “Optimal allocation of two-dimensional data,” in Int. Conf. on Database Theory, Delphi, Greece, Jan. 1997, pp. 409–418.\nR. Agrawal, C. Faloutsos, and A. Swami, “Efficient similarity search in sequence databases,” in 4th Int. Conference on Foundations of Data Organization and Algorithms, 1993, pp. 69–84.\nN. Beckmann, H. Kriegel, R. Schneider, and B. Seeger, “The R*-tree: An efficient and robust access method for points and rectangles,” in Proc.ACMSIGMOD Int. Conf. on Management of Data, May 23–25 1990, pp. 322–331.\nS. Berchtold, C. Bohm, B. Braunmuller, D.A. Keim, and H.-P. Kriegel, “Fast parallel similarity search in multimedia databases,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, Arizona, USA, 1997, pp. 1–12.\nS. Berchtold, D.A. Keim, and H.P. Kreigel, “The X-tree: An index structure for high-dimensional data,” in 22nd Conference on Very Large Databases, Bombay, India, 1996, pp. 28–39.\nR. Bhatia, R.K. Sinha, and C.-M. Chen, “Declutering using golden ratio sequences,” in Proc. of Int'l. Conference on Data Engineering (ICDE), San Diego, California, March 2000.\nT. Brinkhoff, H. Horn, H.P. Kriegel, and R. Schneider, “A storage and access architecture for efficient query processing in spatial database systems,” Lecture Notes in Computer Science, vol. 692, pp. 357–376, 1993.\nB. Chor, C.E. Leiserson, R.L. Rivest, and J.B. Shearer, “An application of number theory to the organization of raster-graphics memory,” Journal of the Association for Computing Machinery, vol. 33, no. 1, pp. 86–104, 1986.\nH.C. Du and J.S. Sobolewski, “Disk allocation for cartesian product files on multiple-disk systems,” ACM Transactions of Database Systems, vol. 7, no. 1, pp. 82–101, 1982.\nC. Faloutsos and P. Bhagwat, “Declustering using fractals,” in Proc. of the 2nd Int. Conf. on Parallel and Distributed Information Systems, San Diego, CA, Jan. 1993, pp. 18–25.\nC. Faloutsos and D. Metaxas, “Declustering using error correcting codes,” in Proc. ACMSymp. on Principles of Database Systems, 1989, pp. 253–258.\nS. Ghandeharizadeh and D.J. DeWitt, “Amultiuser performance analysis of alternative declustering strategies,” in Proceedings of the International Conference on Data Engineering (ICDE), Los Angeles, California, Feb. 1990, pp. 466–475.\nS. Ghandeharizadeh and D.J. DeWitt, “A performance analysis of alternative multi-attribute declustering strategies,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, San Diego, 1992, pp. 29–38.\nO. Gunther, “The design of the cell tree: An object-oriented index structure for geometric databases,” in Proceedings of the International Conference on Data Engineering (ICDE), 1989, pp. 598–605.\nA. Guttman, “R-trees: A dynamic index structure for spatial searching,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, 1984, pp. 47–57.\nJ. Hellerstein, J. Naughton, and A. Pfeffer, “Generalized search trees for database systems,” in Proceedings of the Int. Conf. on Very Large Data Bases, Sept. 1995, pp. 562–573.\nH.V. Jagdish, “A retrieval technique for similar shapes,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, 1991, pp. 208–217.\nM.H. Kim and S. Pramanik, “Optimal file distribution for partial match retrieval,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, Chicago, 1988, pp. 173–182.\nC. Kolovson and M. Stonebraker, “Segment indexes: Dynamic indexing techniques for multidimensional interval data,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, 1991, pp. 138–147.\nJ. Li, J. Srivastava, and D. Rotem, “CMD: A multidimensional declustering method for parallel database systems,” in Proceedings of the Int. Conf. on Very Large Data Bases, Vancouver, Canada, Aug. 1992, pp. 3–14.\nD.B. Lomet and B. Salzberg, “The hB-tree: A multi-attribute indexing method with good guaranteed performance,” Transactions of Database Systems, vol. 15, no. 4, pp. 625–658, 1990.\nB.S. Manjunath and W.Y. Ma, “Texture features for browsing and retrieval of image data,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 8, pp. 837–842, 1996.\nS. Prabhakar, K. Abdel-Ghaffar, D. Agrawal, and A. El Abbadi, “Cyclic allocation of two-dimensional data,” in Proc. of the International Conference on Data Engineering (ICDE'98), Orlando, Florida, Feb. 1998, pp. 94–101.\nS. Prabhakar, D. Agrawal, and A. El Abbadi, “Data declustering for efficient range and similarity searching,” in Proc. Multimedia Storage and Archiving Systems III (SPIE Symposium on Voice, Video, and Data Communications), Boston, Massachusetts, Nov. 1998.\nS. Prabhakar, D. Agrawal, and A. El Abbadi, “Efficient disk allocation for fast similarity searching,” in Proc. of the 10th Int. Sym. on Parallel Algorithms and Architectures (SPAA'98), Puerto Vallarta, Mexico, June 1998, pp. 78–87.\nS. Prabhakar, D. Agrawal, and A. El Abbadi, “Efficient retrieval of multidimensional datasets through parallel I\u002FO,” in Proc. of the 5th International Conference on High Performance Computing (HiPC'98), Chennai, India, Dec. 1998.\nJ.T. Robinson, “The kdb-tree: A search structure for large multi-dimensional dynamic indexes,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, 1981, pp. 10–18.\nA.S. Slazay, P.Z. Kunst, A. Thakar, J. Gray, D. Slutz, and R.J. Brunner, “Designing and mining multi-terabyte astronomy archives: The sloan digital sky survey,” in Proc. ACM SIGMOD Int. Conf. on Management of Data, Dallas, Texas, May 2000, pp. 451–462.\nD. White and R. Jain, “Similarity indexing with the SS-tree,” in Proceedings of the International Conference on Data Engineering (ICDE), 1996, pp. 516–523.",{"VOID":1176},"10.1023\u002FA:1024895525526","2024-05-11T10:17:33.342+00:00","http:\u002F\u002Flink.springer.com\u002F10.1023\u002FA:1024895525526",[1180,1195,1210],{"id":1181,"sortIndex":21,"researcher":20,"roles":1182,"affiliations":1183,"properties":1192},"e935808b-4d0a-451b-8a14-327f47445248",[205],[1184],{"id":1185,"sortIndex":21,"affiliation":1186,"properties":20},"21c8469f-fe86-4cd3-a596-e3dafe46a327",{"id":1185,"createTime":20,"updateTime":20,"relativeEntities":1187,"slug":20,"properties":1188,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1191,"statistic":20},[],{"title":1189},{"VI":1190},"Department of Computer Sciences, Purdue University, West Lafayette , USA",[],{"title":1193},{"VI":1194},"Sunil Prabhakar",{"id":1196,"sortIndex":136,"researcher":20,"roles":1197,"affiliations":1198,"properties":1207},"d709aea5-469d-4fa3-926a-7ed7acfe560f",[205],[1199],{"id":1200,"sortIndex":21,"affiliation":1201,"properties":20},"09a25f16-32a1-41a7-9825-b5003a71dd73",{"id":1200,"createTime":20,"updateTime":20,"relativeEntities":1202,"slug":20,"properties":1203,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1206,"statistic":20},[],{"title":1204},{"VI":1205},"Department of Computer Science, University of California, Santa Barbara, USA",[],{"title":1208},{"VI":1209},"Divyakant Agrawal",{"id":1211,"sortIndex":140,"researcher":20,"roles":1212,"affiliations":1213,"properties":1220},"8b7dcd5f-62eb-4e31-a9e8-c062e36bd479",[205],[1214],{"id":1200,"sortIndex":21,"affiliation":1215,"properties":20},{"id":1200,"createTime":20,"updateTime":20,"relativeEntities":1216,"slug":20,"properties":1217,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1219,"statistic":20},[],{"title":1218},{"VI":1205},[],{"title":1221},{"VI":1222},"Amr El Abbadi",{"url":1178,"publisher":1224,"properties":1278},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":1225,"slug":10,"properties":1226,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":1230,"manageAffiliations":1247,"indexDatabases":1258,"url":20,"thumbnailPath":20,"statistic":1273,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":1227,"title":1228,"eissn":1229},{"VOID":13},{"EN":15},{"VOID":17},[1231,1235,1239,1243],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":1232,"label":1233,"description":1234,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":1236,"label":1237,"description":1238,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":1240,"label":1241,"description":1242,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":1244,"label":1245,"description":1246,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[1248,1253],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":1249,"slug":20,"properties":1250,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1252,"statistic":20},[],{"title":1251},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":1254,"slug":20,"properties":1255,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1257,"statistic":20},[],{"title":1256},{"EN":60},[62],[1259,1266],{"id":65,"indexDatabase":1260,"url":78,"indexYears":20,"academicFieldIds":1265,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":1261,"label":1262,"description":1263,"key":74,"publicationTags":1264,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":1267,"url":93,"indexYears":94,"academicFieldIds":1272,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":1268,"label":1269,"description":1270,"key":90,"publicationTags":1271,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":1274,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":1275,"totalCitation":137,"totalCitationByYear":1276,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":1277,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"pages":1279,"volume":1281},{"VOID":1280},"107-135",{"VOID":1282},"14","2003-09-01",2003,"ERROR_IN_GET_PLATFORM_ID","2026-03-06T23:34:08.543+00:00",[100,76],{"id":1289,"createTime":1290,"updateTime":1291,"relativeEntities":1292,"slug":1293,"properties":1294,"entityType":196,"verifyStatus":197,"verifyTime":1291,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":1303,"fullTextUrl":20,"authors":1304,"publicationType":300,"publisherRelationship":1333,"citationCount":20,"citationInfo":20,"publishDate":1393,"publishYear":1394,"citationAnalyzeStatus":19,"lastCitationAnalyze":20,"indexDatabases":1395,"openAccess":20,"references":20,"isForceReanalyzing":370},"561fe388-8f32-4911-b536-be68772f5b47","2023-12-31T07:11:09.641+00:00","2025-02-26T21:01:38.597+00:00",[],"On-compressing-data-in-wireless-sensor-networks-for-energy-efficiency-and-real-time-delivery",{"abstract":1295,"title":1297,"references":1299,"doi":1301},{"EN":1296},"Wireless sensor networks possess significant limitations in storage, bandwidth, processing, and energy. Additionally, real-time sensor network applications such as monitoring poisonous gas leaks cannot tolerate high latency. While some good data compression algorithms exist specific to sensor networks, in this paper we present TinyPack, a suite of energy-efficient methods with high-compression ratios that reduce latency, storage, and bandwidth usage further in comparison with some other recently proposed algorithms. Our Huffman style compression schemes exploit temporal locality and delta compression to provide better bandwidth utilization important in the wireless sensor network, thus reducing latency for real time sensor-based monitoring applications. Our performance evaluations over many different real data sets using a simulation platform as well as a hardware implementation show comparable compression ratios and energy savings with a significant decrease in latency compared to some other existing approaches. We have also discussed robust error correction and recovery methods to address packet loss and corruption common in sensor network environments.",{"EN":1298},"On compressing data in wireless sensor networks for energy efficiency and real time delivery",{"VOID":1300},"Huffman, D.A.: A method for the construction of minimum-redundancy codes. In: Proceedings of the I.R.E. (1952)\nVitter, J.S.: Design and analysis of dynamic Huffman codes. J. ACM 34(4), 825–845 (1987)\nZiv, J., Lempel, A.: A universal algorithm for sequential data compression. IEEE Trans. Inf. Theory 23(3), 337–343 (1977)\nArici, T., Gedik, B., Altunbasak, Y., Liu, L.: PINCO: a pipelined in-network compression scheme for data collection in wireless sensor networks. In: Proceedings of 12th International Conference on Computer Communications and Networks, October 2003\nPetrovic, D., Shah, R.C., Ramchandran, K., Rabaey, J.: Data funneling: routing with aggregation and compression for wireless sensor networks. In: Proceedings of First IEEE International Workshop on Sensor Network Protocols and Applications, May 2003\nSadler, C., Martonosi, M.: Data compression algorithms for energy-constrained devices in delay tolerant networks. In: Proceedings of the ACM Conference on Embedded Networked Sensor Systems (SenSys) (2006)\nMarcelloni, F., Vecchio, M.: An efficient lossless compression algorithm for tiny nodes of monitoring wireless sensor networks. Comput. J. 52(8), 969–987 (2009)\nGandhi, S., Nath, S., Suri, S., Liu, J.: GAMPS: compressing multi sensor data by grouping and amplitude scaling. In: Proceedings of the 35th SIGMOD international Conference on Management of Data, New York, NY, pp. 771–784 (2009)\nMainwaring, A., Culler, D., Polastre, J., Szewczyk, R., Anderson, J.: Wireless sensor networks for habitat monitoring. In: WSNA’02: Proceedings of the 1st ACM International Workshop on Wireless Sensor Networks and Applications, pp. 88–97. ACM, New York (2002)\nBodik, P., Hong, W., Guestrin, C., Madden, S., Paskin, M., Thibaux, R.: Intel Berkley Labs. (2004)\nZhang, P., Sadler, C.M., Lyon, S.A., Martonosi, M.: Hardware design experiences in ZebraNet. In: Proc. of the ACM Conf. on Embedded Networked Sensor Systems (SenSys) (2004)\nMetzler, J.M., Linderman, M.H., Seversky, L.M.: N-CET: network-centric exploitation and tracking. In: MILCOM 2009—2009 IEEE Military Communications Conference, October. IEEE, New York (2009)\nZhao, X., Qian, T., Mei, G., Kwan, C., Zane, R., Walsh, C., Paing, T., Popovic, Z.: Active health monitoring of an aircraft wing with an embedded piezoelectric sensor\u002Factuator network: II. Wireless approaches. Smart Mater. Struct. 16(4), 1218–1225 (2007)\nCrossbow Technology, Inc.: Mica2 and MicaZ Datasheets. http:\u002F\u002Fwww.xbow.com\u002F (2010)\nShannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27, 379–423, 623–656 (1948)\nMadden, S., Franklin, M., Hellerstein, J., Hong, W.: TAG: a tiny aggregation service for ad-hoc sensor networks. In: Proceedings of the Fifth Symposium on Operating Systems Design and Implementation (OSDI’02) (2002)\nSharaf, A., Beaver, J., Labrinidis, A., Chrysanthis, K.: Balancing energy efficiency and quality of aggregate data in sensor networks. VLDB J. 13(4), 384–403 (2004)\nDeligiannakis, A., Kotidis, Y., Roussopoulos, N.: Hierarchical in-network data aggregation with quality guarantees. In: Proceedings of EDBT Conference (2004)\nLevis, P., Lee, N., Welsh, M., Culler, D.: TOSSIM: accurate and scalable simulation of entire TinyOS applications. In: Proceedings of the First ACM Conference on Embedded Networked Sensor Systems (SenSys) (2003)\nShnayder, V., Hempstead, M., Chen, B., Allen, G.W., Welsh, M.: Simulating the power consumption of large-scale sensor network applications. In: Proceedings of the ACM Conference on Embedded Networked Sensor Systems (SenSys) (2004)\nChaimanonart, N., Suster, M., Ko, W., Young, D.: Two-channel data telemetry with remote RF powering for high-performance wireless MEMS strain sensing applications. In: 4th IEEE Conference on Sensors (2005)",{"VOID":1302},"10.1007\u002Fs10619-012-7111-5","https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10619-012-7111-5",[1305,1320],{"id":1306,"sortIndex":21,"researcher":20,"roles":1307,"affiliations":1308,"properties":1317},"ca1e7540-4420-4691-aaa5-d4fa49fbcc87",[205],[1309],{"id":1310,"sortIndex":21,"affiliation":1311,"properties":20},"a8e2f2a4-2742-4f44-a89d-7c5ce554e432",{"id":1310,"createTime":20,"updateTime":20,"relativeEntities":1312,"slug":20,"properties":1313,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1316,"statistic":20},[],{"title":1314},{"VI":1315},"Department of Computer Science, Missouri S&T, Rolla, USA",[],{"title":1318},{"VI":1319},"Tommy Szalapski",{"id":1321,"sortIndex":136,"researcher":20,"roles":1322,"affiliations":1323,"properties":1330},"692bb416-dfe2-4ced-94c1-5ef3747eaced",[205],[1324],{"id":1310,"sortIndex":21,"affiliation":1325,"properties":20},{"id":1310,"createTime":20,"updateTime":20,"relativeEntities":1326,"slug":20,"properties":1327,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1329,"statistic":20},[],{"title":1328},{"VI":1315},[],{"title":1331},{"VI":1332},"Sanjay Madria",{"url":1303,"publisher":1334,"properties":1388},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":1335,"slug":10,"properties":1336,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":1340,"manageAffiliations":1357,"indexDatabases":1368,"url":20,"thumbnailPath":20,"statistic":1383,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":1337,"title":1338,"eissn":1339},{"VOID":13},{"EN":15},{"VOID":17},[1341,1345,1349,1353],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":1342,"label":1343,"description":1344,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":1346,"label":1347,"description":1348,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":1350,"label":1351,"description":1352,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":1354,"label":1355,"description":1356,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[1358,1363],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":1359,"slug":20,"properties":1360,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1362,"statistic":20},[],{"title":1361},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":1364,"slug":20,"properties":1365,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1367,"statistic":20},[],{"title":1366},{"EN":60},[62],[1369,1376],{"id":65,"indexDatabase":1370,"url":78,"indexYears":20,"academicFieldIds":1375,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":1371,"label":1372,"description":1373,"key":74,"publicationTags":1374,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":1377,"url":93,"indexYears":94,"academicFieldIds":1382,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":1378,"label":1379,"description":1380,"key":90,"publicationTags":1381,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":1384,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":1385,"totalCitation":137,"totalCitationByYear":1386,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":1387,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"pages":1389,"volume":1391},{"VOID":1390},"151-182",{"VOID":1392},"31","2012-09-21",2012,[100,76],{"id":1397,"createTime":1398,"updateTime":1399,"relativeEntities":1400,"slug":1401,"properties":1402,"entityType":196,"verifyStatus":197,"verifyTime":1399,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":1411,"fullTextUrl":20,"authors":1412,"publicationType":300,"publisherRelationship":1467,"citationCount":20,"citationInfo":20,"publishDate":1527,"publishYear":1528,"citationAnalyzeStatus":19,"lastCitationAnalyze":20,"indexDatabases":1529,"openAccess":20,"references":20,"isForceReanalyzing":370},"acd6c185-46a9-4079-b522-982a9fffb62a","2023-12-08T08:27:56.227+00:00","2025-02-26T19:06:31.167+00:00",[],"On-resolving-schematic-heterogeneity-in-multidatabase-systems",{"abstract":1403,"title":1405,"references":1407,"doi":1409},{"EN":1404},"The objective of a multidatabase system is to provide a single uniform interface to accessing multiple independent databases being managed by multiple independent, and possibly heterogeneous, database systems. One crucial element in the design of a multidatabase system is the design of a data definition language for specifying a schema that represents the integration of the schemas of multiple independent databases. The design of such a language in turn requires a comprehensive classification of the conflicts (i.e., discrepancies) among the schemas of the independent databases and development of techniques for resolving (i.e., homogenizing) all of the conflicts in the classification. An earlier paper provided a comprehensive classification of schematic conflicts that may arise when integrating multiple independent relational database (RDB) schemas into a single multidatabase (MDB) schema. In this paper, we provide a comprehensive classification of techniques for resolving the schematic conflicts that may arise when integrating multiple RDB schemas, or RDB schemas and object-oriented database (OODB) schemas, or multiple OODB schemas. The classification of conflict resolution techniques includes not only those necessary for resolving schematic conflicts identified in the earlier paper, but also additional conflicts that arise when OODBs become part of the databases to be integrated. Most of the conflict resolution techniques discussed in the paper have already been incorporated into SQL\u002FM, a multidatabase language implemented in UniSQL\u002FM, a commercially available multidatabase system from UniSQL, Inc. which integrated SQL-based relational database systems and the UniSQL\u002FX unified relational and object-oriented database system.",{"EN":1406},"On resolving schematic heterogeneity in multidatabase systems",{"VOID":1408},"American National Standards Institute:Database Language SQL, Document ANSI X3. 135-1986. (Addendum 1: Document ANSI X3. 135. 1-1989.)\n“Special issue on Heterogeneous Databases,”ACM Comput. Surveys, vol. 22, no. 3, 1990.\nC. Batini, M. Lenzerini, and S.B. Navathe, “A comparative analysis of methodologies for database schema integration,”ACM Comput. Surveys, vol. 18, pp. 323–364, 1986.\nY. Breitbart, P.L. Olson, and G.R. Thompson, “Database integration in a distributed heterogeneous database system,”Proc. 2nd IEEE Conf. Data Engineering, Los Angeles, 1986.\nD. Brill and M. Templeton, “Distributed query processing strategies in MERMAID: a front-end to a data management system,”Proc. IEEE Conf. Data Engineering, Los Angeles, 1984.\nT. Connors and P. Lyngbaek, “Providing uniform access to heterogeneous information bases,” inAdvances in Object-Oriented Database Systems (K.R. Dittrich, ed.), Lecture Notes in Computer Science, vol. 334, Springer-Verlag, 1988.\nU. Dayal and H. Hwang, “View definition and generalization for database integration of a multidatabase system,”IEEE Trans. Software Eng., vol. SE-10(11), pp. 628–644, 1984.\nW. Effelsberg and M. Mannino, “Attribute equivalence in global schema design for heterogeneous distributed databases,”Inform. Systems, vol. 9, no. 3\u002F4, 1984.\nW. Kim,Introduction to Object-Oriented Databases, MIT Press, 1990.\nW. Kim and J. Seo, “Classifying schematic and data heterogeneity in multidatabase systems,”IEEE Comput., Dec. 1991.\nT.A. Landers, and R.L. Rosenberg, “An overview of multibase — a heterogeneous database system,”Proc. Second Symp. Distributed Databases (H-J. Schneider, ed.), North-Holland, 1982.\nJ. Larson, S. Navathe, and R. Elmasri, “A theory of attribute equivalence in databases with applications to schema integration,”IEEE Trans. Soft. Eng., vol. 15, no. 4, 1989.\nW. Litwin, A. Abdellatif, B. Nicolas, P. Vigier, and A. Zeroual, “MSQL: a multidatabase language,”Inform. Sci., June 1987.\nW. Litwin, L. Mark, and N. Roussopoulos, “Interoperability of multiple autonomous databases,”ACM Comput. Surveys, vol. 22, no. 3, 1990.\nA. Motro, “Superviews: virtual integration of multiple database,”IEEE Trans. Software Eng., vol. SE-13(7), pp. 785–798, 1987.\nA.P. Sheth and S.K. Gala, “Attribute relationships: an impediment in automating schema integration,”Proc. NSF Workshop Heterogeneous Database Systems, Chicago, 1989.\nS. Spaccapietra, C. Parent, and Y. Dupont, “Automating heterogeneous schema integration,” Technical Report, Ecole Polytechnique Federale, Lausanne, Switzerland, 1991.",{"VOID":1410},"10.1007\u002FBF01263333","http:\u002F\u002Flink.springer.com\u002F10.1007\u002FBF01263333",[1413,1428,1441,1454],{"id":1414,"sortIndex":21,"researcher":20,"roles":1415,"affiliations":1416,"properties":1425},"5a911ced-39d8-4a70-a427-0cf2c58b6d5a",[205],[1417],{"id":1418,"sortIndex":21,"affiliation":1419,"properties":20},"c9c3fbb7-518d-4cb8-ad3b-08554ca3d64e",{"id":1418,"createTime":20,"updateTime":20,"relativeEntities":1420,"slug":20,"properties":1421,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1424,"statistic":20},[],{"title":1422},{"VI":1423},"UniSQL, Inc., Austin",[],{"title":1426},{"VI":1427},"Won Kim",{"id":1429,"sortIndex":136,"researcher":20,"roles":1430,"affiliations":1431,"properties":1438},"96de2f91-4ce9-41ab-8881-741842e43481",[205],[1432],{"id":1418,"sortIndex":21,"affiliation":1433,"properties":20},{"id":1418,"createTime":20,"updateTime":20,"relativeEntities":1434,"slug":20,"properties":1435,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1437,"statistic":20},[],{"title":1436},{"VI":1423},[],{"title":1439},{"VI":1440},"Injun Choi",{"id":1442,"sortIndex":140,"researcher":20,"roles":1443,"affiliations":1444,"properties":1451},"ad03ad68-1c60-4136-b464-67be1f1c35fd",[205],[1445],{"id":1418,"sortIndex":21,"affiliation":1446,"properties":20},{"id":1418,"createTime":20,"updateTime":20,"relativeEntities":1447,"slug":20,"properties":1448,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1450,"statistic":20},[],{"title":1449},{"VI":1423},[],{"title":1452},{"VI":1453},"Sunit Gala",{"id":1455,"sortIndex":116,"researcher":20,"roles":1456,"affiliations":1457,"properties":1464},"f87530c8-88b2-4d54-8d34-0bec98cc1409",[205],[1458],{"id":1418,"sortIndex":21,"affiliation":1459,"properties":20},{"id":1418,"createTime":20,"updateTime":20,"relativeEntities":1460,"slug":20,"properties":1461,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1463,"statistic":20},[],{"title":1462},{"VI":1423},[],{"title":1465},{"VI":1466},"Mark Scheevel",{"url":1411,"publisher":1468,"properties":1522},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":1469,"slug":10,"properties":1470,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":1474,"manageAffiliations":1491,"indexDatabases":1502,"url":20,"thumbnailPath":20,"statistic":1517,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":1471,"title":1472,"eissn":1473},{"VOID":13},{"EN":15},{"VOID":17},[1475,1479,1483,1487],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":1476,"label":1477,"description":1478,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":1480,"label":1481,"description":1482,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":1484,"label":1485,"description":1486,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":1488,"label":1489,"description":1490,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[1492,1497],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":1493,"slug":20,"properties":1494,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1496,"statistic":20},[],{"title":1495},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":1498,"slug":20,"properties":1499,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1501,"statistic":20},[],{"title":1500},{"EN":60},[62],[1503,1510],{"id":65,"indexDatabase":1504,"url":78,"indexYears":20,"academicFieldIds":1509,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":1505,"label":1506,"description":1507,"key":74,"publicationTags":1508,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":1511,"url":93,"indexYears":94,"academicFieldIds":1516,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":1512,"label":1513,"description":1514,"key":90,"publicationTags":1515,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":1518,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":1519,"totalCitation":137,"totalCitationByYear":1520,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":1521,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"pages":1523,"volume":1525},{"VOID":1524},"251-279",{"VOID":1526},"1","1993-07-01",1993,[100,76],{"id":1531,"createTime":1532,"updateTime":1533,"relativeEntities":1534,"slug":1535,"properties":1536,"entityType":196,"verifyStatus":197,"verifyTime":1533,"verifyNote":199,"languages":20,"translateLanguages":20,"viewCount":21,"primaryUrl":1545,"fullTextUrl":20,"authors":1546,"publicationType":300,"publisherRelationship":1575,"citationCount":20,"citationInfo":20,"publishDate":1635,"publishYear":1636,"citationAnalyzeStatus":19,"lastCitationAnalyze":20,"indexDatabases":1637,"openAccess":20,"references":20,"isForceReanalyzing":370},"93bf1913-5870-4fba-b4ff-7ca82219bcf9","2024-01-16T00:47:16.893+00:00","2025-02-26T14:26:12.054+00:00",[],"Set-similarity-join-on-massive-probabilistic-data-using-MapReduce",{"abstract":1537,"title":1539,"references":1541,"doi":1543},{"EN":1538},"In this paper, we focus on set similarity join on massive probabilistic data using MapReduce, there is no effective approach that can process this problem efficiently. MapReduce is a popular paradigm that can process large volume data more efficiently, in this paper, we proposed two approaches using MapReduce to deal with this task: Hadoop Join by Map Side Pruning and Hadoop Join by Reduce Side Pruning. Hadoop Join by Map Side Pruning uses the sum of the existence probability to filter out the probabilistic sets directly at the Map task side which have no any chance to be similar with any other probabilistic set. Hadoop Join by Reduce Side Pruning uses probability sum based pruning principle and probability upper bound based pruning principle to reduce the candidate pairs at Reduce task side, it can save the comparison cost. Based on the above approaches, we proposed a hybrid solution that employs both Map-side and Reduce-side pruning methods. Finally we implemented the above approaches on Hadoop-0.20.2 and performed comprehensive experiments to their performance, we also test the speedup ratio compared with the naive method: Block Nested Loop Join. The experiment results show that our approaches have much better performance than that of Block Nested Loop Join and also have good scalability. To the best of our knowledge, this is the first work to try to deal with set similarity join on massive probabilistic data problem using MapReduce paradigm, and the approaches proposed in this paper provide a new way to process the massive probabilistic data.",{"EN":1540},"Set similarity join on massive probabilistic data using MapReduce",{"VOID":1542},"Afrati, F.N., Sarma, A.D., Menestrina, D., Parameswaran, A.G., Ullman, J.D.: Fuzzy joins using MapReduce. In: ICDE’12, pp. 498–509 (2012)\nAfrati, F.N., Ullman, J.D.: Optimizing joins in a map-reduce environment. In: EDBT’10, pp. 99–110 (2010)\nArasu, A., Ganti, V., Kaushik, R.: Efficient exact set-similarity joins. In: VLDB’06, pp. 918–929 (2006)\nArasu, A., Ganti, V., Kaushik, R.: Efficient exact set-similarity joins. In: VLDB’06, pp. 918–929 (2006)\nBaraglia, R., Morales, G.D.F., Lucchese, C.: Document similarity self-join with MapReduce. In: ICDM’10, pp. 731–736 (2010)\nBayardo, R.J., Ma, Y., Srikant, R.: Scaling up all pairs similarity search. In: WWW’07, pp. 131–140 (2007)\nBroder, Glassman, S.C., Manasse, M.S., Zweig, G.: Syntactic clustering of the web. Comput. Netw. (1997). doi:10.1016\u002FS0169-7552(97)00031-7\nChaudhuri, S., Ganti, V., Kaushik, R.: A primitive operator for similarity joins in data cleaning. In: ICDE’06 (2006)\nCheng, R., Singh, S., Prabhakar, S., Shah, R., Vitter, J.S., Xia, Y.: Efficient join processing over uncertain data. In: CIKM’06, pp. 738–747 (2006)\nDean, J., Ghemawat, S.: Mapreduce: Simplified data processing on large clusters. In: OSDI’04, pp. 137–150 (2004)\nDong, X.L., Halevy, A.Y., Yu, C.: Data integration with uncertainty. VLDB J. (2009) doi:10.1007\u002Fs00778-008-0119-9\nElsayed, T., Lin, J.J., Oard, D.W.: Pairwise document similarity in large collections with MapReduce. In: ACL (Short Papers)’08, pp. 265–268 (2008)\nGhemawat, S., Gobioff, H., Leung, S.T.: The Google file system. In: SOSP’03, pp. 29–43 (2003)\nHenzinger, M.R.: Finding near-duplicate web pages: a large-scale evaluation of algorithms. In: SIGIR’06, pp. 284–291 (2006)\nJestes, J., Li, F., Yan, Z., Yi, K.: Probabilistic string similarity joins. In: SIGMOD Conference’10, pp. 327–338 (2010)\nKim, Y., Shim, K.: Parallel top-k similarity join algorithms using MapReduce. In: ICDE, pp. 510–521 (2012)\nKimura, H., Madden, S., Zdonik, S.B.: Upi: a primary index for uncertain databases. In: PVLDB, pp. 630–637 (2010)\nKriegel, H.P., Kunath, P., Pfeifle, M., Renz, M.: Probabilistic similarity join on uncertain data. In: DASFAA’06, pp. 295–309 (2006)\nLian, X., Chen, L.: Set similarity join on probabilistic data. In: PVLDB, pp. 650–659 (2010)\nLuo, W., Tan, H., Mao, H., Ni, L.: Efficient similarity joins on massive high-dimensional datasets using MapReduce. In: MDM’12, p. TBA (2012)\nOkcan, A., Riedewald, M.: Processing theta-joins using MapReduce. In: SIGMOD Conference’11, pp. 949–960 (2011)\nVernica, R., Carey, M.J., Li, C.: Efficient parallel set-similarity joins using MapReduce. In: SIGMOD Conference’10, pp. 495–506 (2010)\nXiao, C., Wang, W., Lin, X., Yu, J.X., Wang, G.: Efficient similarity joins for near-duplicate detection. ACM Trans. Database Syst. (2011). doi:10.1145\u002F2000824.2000825\nYang, H.-c., Dasdan, A., Hsiao, R.-L., Stott Parker, D.: Map-reduce-merge: simplified relational data processing on large clusters. In: SIGMOD Conference’07, pp. 1029–1040 (2007)",{"VOID":1544},"10.1007\u002Fs10619-013-7137-3","https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs10619-013-7137-3",[1547,1562],{"id":1548,"sortIndex":21,"researcher":20,"roles":1549,"affiliations":1550,"properties":1559},"d005641d-1d80-4ea0-b05c-b571c7bca9ad",[205],[1551],{"id":1552,"sortIndex":21,"affiliation":1553,"properties":20},"b1d1a68b-a4a1-4d8b-ab15-6c36f39da9a1",{"id":1552,"createTime":20,"updateTime":20,"relativeEntities":1554,"slug":20,"properties":1555,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1558,"statistic":20},[],{"title":1556},{"VI":1557},"School of Information, Renmin University of China, Beijing, China",[],{"title":1560},{"VI":1561},"Youzhong Ma",{"id":1563,"sortIndex":136,"researcher":20,"roles":1564,"affiliations":1565,"properties":1572},"4e462cb7-b5ea-4d4f-8769-144dff42d341",[205],[1566],{"id":1552,"sortIndex":21,"affiliation":1567,"properties":20},{"id":1552,"createTime":20,"updateTime":20,"relativeEntities":1568,"slug":20,"properties":1569,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1571,"statistic":20},[],{"title":1570},{"VI":1557},[],{"title":1573},{"VI":1574},"Xiaofeng Meng",{"url":1545,"publisher":1576,"properties":1630},{"id":6,"createTime":7,"updateTime":8,"relativeEntities":1577,"slug":10,"properties":1578,"entityType":18,"verifyStatus":19,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":21,"subjectFields":1582,"manageAffiliations":1599,"indexDatabases":1610,"url":20,"thumbnailPath":20,"statistic":1625,"gsStatistic":20,"type":20,"analyzePriority":20},[],{"issn":1579,"title":1580,"eissn":1581},{"VOID":13},{"EN":15},{"VOID":17},[1583,1587,1591,1595],{"id":24,"createTime":20,"updateTime":20,"relativeEntities":1584,"label":1585,"description":1586,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":27},{},{"id":30,"createTime":20,"updateTime":20,"relativeEntities":1588,"label":1589,"description":1590,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":33},{},{"id":36,"createTime":20,"updateTime":20,"relativeEntities":1592,"label":1593,"description":1594,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":39},{},{"id":42,"createTime":20,"updateTime":20,"relativeEntities":1596,"label":1597,"description":1598,"parentId":20,"standard":20,"scholarHubFieldId":20},[],{"EN":45},{},[1600,1605],{"id":49,"createTime":20,"updateTime":20,"relativeEntities":1601,"slug":20,"properties":1602,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1604,"statistic":20},[],{"title":1603},{"EN":53},[],{"id":56,"createTime":20,"updateTime":20,"relativeEntities":1606,"slug":20,"properties":1607,"entityType":20,"verifyStatus":20,"verifyTime":20,"verifyNote":20,"languages":20,"translateLanguages":20,"viewCount":20,"url":20,"parentIds":1609,"statistic":20},[],{"title":1608},{"EN":60},[62],[1611,1618],{"id":65,"indexDatabase":1612,"url":78,"indexYears":20,"academicFieldIds":1617,"indexDatabaseRanking":20},{"id":67,"createTime":20,"updateTime":20,"relativeEntities":1613,"label":1614,"description":1615,"key":74,"publicationTags":1616,"standard":20},[],{"EN":70,"VI":70},{"EN":72,"VI":73},[76,77],[80],{"id":82,"indexDatabase":1619,"url":93,"indexYears":94,"academicFieldIds":1624,"indexDatabaseRanking":100},{"id":84,"createTime":20,"updateTime":20,"relativeEntities":1620,"label":1621,"description":1622,"key":90,"publicationTags":1623,"standard":20},[],{"EN":87,"VI":87},{"EN":87,"VI":89},[92],[96,97,98,99],{"impactFactor":21,"impactFactorByYear":1626,"i10Index":115,"i10IndexLast5Year":116,"totalPublication":117,"totalPublicationByYear":1627,"totalCitation":137,"totalCitationByYear":1628,"totalCitationPerPublication":154,"totalCitationPerPublicationByYear":1629,"hindexLast5Year":124,"hindex":124},{"2011":103,"2012":104,"2013":105,"2014":106,"2015":107,"2016":108,"2017":109,"2018":110,"2019":111,"2020":103,"2021":112,"2022":113,"2023":114},{"1993":119,"1994":120,"1995":120,"1996":119,"1997":121,"1998":119,"1999":120,"2000":122,"2001":123,"2002":124,"2003":123,"2004":125,"2005":125,"2006":120,"2007":122,"2008":126,"2009":127,"2010":120,"2011":126,"2012":128,"2013":125,"2014":129,"2015":130,"2016":119,"2017":131,"2018":132,"2019":125,"2020":133,"2021":134,"2022":125,"2023":135,"2024":136},{"1993":139,"1994":140,"1995":141,"1996":127,"2004":120,"2005":142,"2006":143,"2007":130,"2008":144,"2009":145,"2010":120,"2011":146,"2012":128,"2013":147,"2014":148,"2015":149,"2016":150,"2017":140,"2018":122,"2019":151,"2020":152,"2021":153,"2022":126,"2024":136},{"1993":156,"1994":157,"1995":158,"1996":159,"2004":160,"2005":161,"2006":126,"2007":162,"2008":163,"2009":164,"2010":136,"2011":165,"2012":136,"2013":166,"2014":167,"2015":168,"2016":130,"2017":169,"2018":170,"2019":171,"2020":172,"2021":173,"2022":174,"2024":136},{"pages":1631,"volume":1633},{"VOID":1632},"447-464",{"VOID":1634},"32","2013-12-03",2013,[100,76]]