Deep Learning for IoT Big Data and Streaming Analytics: A Survey

Institute of Electrical and Electronics Engineers (IEEE) - Tập 20 Số 4 - Trang 2923-2960 - 2018
Mehdi Mohammadi1, Ala Al‐Fuqaha1, Sameh Sorour2, Mohsen Guizani2
1Department of Computer Science, Western Michigan University, Kalamazoo, MI, USA
2Department of Electrical and Computer Engineering, University of Idaho, Moscow, ID, USA

Tóm tắt

Từ khóa


Tài liệu tham khảo

10.1016/j.jnca.2016.04.006

10.1109/INFOCOM.2017.8057098

10.1109/MWC.2017.1600304WC

canziani, 2016, An analysis of deep neural network models for practical applications, arXiv preprint arXive 1605 07678v4

2018, Global cell coverage maps - opensignal

bourguignat, 2014, Interpretable vs Powerful Predictive Models Why We Need Them Both

10.1007/978-3-319-46493-0_38

10.1145/3106237.3106290

chollet, 2018, Deep Learning with Python

10.1007/s10586-016-0667-5

10.1109/INDIN.2017.8104767

pascanu, 2013, How to construct deep recurrent neural networks, arXiv preprint arXiv 1312 6026

10.1109/5.58337

10.1017/atsip.2013.9

mikolov, 2014, Learning longer memory in recurrent neural networks, arXiv preprint arXiv 1412 7753

10.1162/neco.1997.9.8.1735

10.1109/CVPR.2016.90

krizhevsky, 2012, ImageNet classification with deep convolutional neural networks, Proc Adv Neural Inf Process Syst, 1097

chauvin, 1995, Backpropagation Theory Architectures and Applications

10.1038/323533a0

10.1007/978-3-7908-2604-3_16

10.1109/LPT.2017.2755663

ba, 2014, Do deep nets really need to be deep?, Proc Adv Neural Inf Process Syst, 2654

10.1145/3007787.3001163

han, 2015, Learning both weights and connections for efficient neural network, Proc Adv Neural Inf Process Syst, 1135

lecun, 1989, Optimal brain damage, Proc NIPS, 2, 598

denil, 2013, Predicting parameters in deep learning, Proc Adv Neural Inf Process Syst, 2148

10.1109/WACV.2016.7477614

10.1145/2627369.2627613

courbariaux, 2016, Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or ?1, arXiv preprint arXiv 1602 02830v3 [cs LG]

chen, 2015, Compressing neural networks with the hashing trick, Proceedings of the 32nd Intl Conf on Machine Learning, 37, 2285

hinton, 2012, Improving neural networks by preventing co-adaptation of feature detectors, arXiv preprint arXiv 1207 0580

glorot, 2011, Deep sparse rectifier neural networks, Proc 14th Int Conf Artificial Intell, 315

10.5244/C.28.6

sutskever, 2013, On the importance of initialization and momentum in deep learning, Proc Int Conf Mach Learn, 1139

hu, 2014, Toward scalable systems for big data analytics: A technology tutorial, IEEE Access, 2, 652, 10.1109/ACCESS.2014.2332453

10.1038/nature07634

10.1109/CTS.2013.6567203

10.1126/science.1127647

10.1007/978-3-319-09177-8_11

10.1016/j.neunet.2014.09.003

10.1016/S0169-7439(97)00061-0

rasmus, 2015, Semi-supervised learning with ladder networks, Proc Adv Neural Inf Process Syst, 3546

lecun, 2018, The MNIST Database of Handwritten Digits

10.1007/978-3-319-51811-4_49

steinberg, 2015, Changing the Game The Rise of Sports Analytics Forbes

shah, 2016, Applying deep learning to basketball trajectories, arXiv preprint arXiv 1608 03793 [cs NE], 1

wang, 2016, Classifying NBA offensive plays using neural networks, MIT Sloan Sports Anal Conf, 1

10.1016/j.procs.2016.07.144

10.1145/3004725.3004729

10.1109/TETC.2017.2699169

10.1016/j.knosys.2016.12.012

10.1016/j.jmsy.2017.02.007

10.1109/TSM.2016.2628865

yan, 2015, On accurate and reliable anomaly detection for gas turbine combustors: A deep learning approach, Proc Annu Conf Prognostics Health Manag Soc, 8

10.1109/CVPR.2016.91

10.1109/TETC.2016.2593643

10.1109/ICCV.2015.169

10.1109/TPAMI.2016.2577031

10.1109/WF-IoT.2014.6803130

10.1016/j.neucom.2015.05.120

10.1109/TNN.2006.880583

krizhevsky, 2009, Learning multiple layers of features from tiny images

hermans, 2013, Training and analysing deep recurrent neural networks, Proc Adv Neural Inf Process Syst, 190

10.1109/MCOM.2013.6525600

10.1109/TETCI.2017.2772792

10.3390/s17091967

10.1007/s11227-017-2017-7

10.1109/CVPR.2016.216

10.1109/MCE.2016.2614422

10.1109/ICCV.2015.382

10.1109/ITNEC.2016.7560389

panetta, 2016, Top 10 Strategic Technology Trends for 2017

10.1126/science.aap8062

chen, 2014, Big Data Related Technologies Challenges and Future Prospects, 10.1007/978-3-319-06245-7

10.1109/MCOM.2018.1700298

zaharia, 2012, Fast and interactive analytics over Hadoop data with spark, USENIX login, 37, 45

10.1145/2766959

10.1109/ACCESS.2014.2325029

10.1016/B978-0-12-802806-3.00008-7

10.1007/s10618-017-0495-0

10.1145/2213836.2213934

10.1109/CVPR.2016.217

10.1109/ICCV.2017.323

goodfellow, 2014, Generative adversarial nets, Proc Adv Neural Inf Process Syst, 2672

10.1561/2200000006

metz, 2018, How an A I ‘Cat-and-Mouse Game’ Generates Believable Fake Photos

baldi, 2012, Autoencoders, unsupervised learning, and deep architectures, Proc ICML Workshop Unsupervised Transf Learn, 27, 37

chung, 2014, Empirical evaluation of gated recurrent neural networks on sequence modeling, arXiv preprint arXiv 1412 3555v1 [cs NE]

kingma, 2014, Semi-supervised learning with deep generative models, Proc Adv Neural Inf Process Syst, 3581

doersch, 2016, Tutorial on variational autoencoders, arXiv preprint arXiv 1606 05908v2 [stat ML]

10.1145/2647868.2654889

raschka, 2017, Machine Learning in Python

bastien, 2012, Theano: New features and speed improvements, arXiv preprint arXiv 1211 5590v1 [cs SC]

collobert, 2011, Torch7: A MATLAB-like environment for machine learning, NIPS Workshop BigLearn, 1

10.1109/CCBD.2016.029

10.1109/ACCESS.2017.2668840

10.5244/C.29.41

10.1109/CVPR.2015.7298594

10.1109/BigData.2016.7841045

10.1371/journal.pone.0119044

mnih, 2013, Playing Atari with deep reinforcement learning, arXiv preprint arXiv 1312 5602v1 [cs LG]

bengio, 2012, Deep learning of representations for unsupervised and transfer learning, Proc ICML Workshop Unsupervised Transfer Learn, 27, 17

10.1109/JIOT.2017.2712560

10.1109/ICASSP.2014.6854517

10.1145/2502081.2502112

jaini, 2016, Online algorithms for sum-product networks with continuous variables, Proc 8th Int Conf Probabilistic Graph Models, 228

10.1007/978-3-319-46227-1_48

bahrampour, 2016, Comparative study of deep learning software frameworks, arXiv preprint arXiv 1511 06435v3 [cs LG]

candel, 2015, Deep learning with h2o

abadi, 2016, Tensorflow: Large-scale machine learning on heterogeneous distributed systems, arXiv preprint arXiv 1603 04467

10.1109/ASPDAC.2016.7428029

10.1038/nphys551

10.1109/MSPEC.2017.7880447

10.1109/IPSN.2016.7460664

bang, 2017, 14.7 A $288~\mu $ w programmable deep-learning processor with 270KB on-chip weight storage using non-uniform memory hierarchy for mobile intelligence, Proc IEEE Int Solid-State Circuits Conf (ISSCC), 250

netzer, 2018, The Street View House Numbers (SVHN) Dataset

xu, 2017, ApproxDBN: Approximate computing for discriminative deep belief networks, arXiv preprint arXiv 1704 03993v3 [cs NE]

10.1109/TMM.2016.2636750

10.1016/j.neucom.2016.02.055

10.1145/2627369.2627625

10.1016/j.neucom.2015.04.011

10.1109/JSSC.2016.2616357

wang, 2015, DeepFi: Deep learning for indoor fingerprinting using channel state information, Proc IEEE Wireless Commun Netw Conf (WCNC), 1666

chen, 2014, DianNao: A small-footprint high-throughput accelerator for ubiquitous machine-learning, ACM SIGPLAN Notices, 49, 269, 10.1145/2644865.2541967

10.1109/ISSCC.2017.7870352

larry, 2017, Voice Control Everywhere Low-Power Special-Purpose Chip Could Make Speech Recognition Ubiquitous in Electronics

10.1109/CVPR.2014.214

10.1109/ISM.2016.0050

becker, 2017, Indoor positioning solely based on user’s sight, Proc Int Conf Inf Sci Appl, 76

10.1007/s12652-017-0483-7

10.1109/TSC.2017.2662008

10.1145/2971648.2971731

liu, 2016, Application of deep convolutional neural networks for detecting extreme weather in climate datasets, arXiv preprint arXiv 1605 01156 [CS cv]

10.1155/2016/3289801

10.1145/2820975.2820980

gantz, 2012, The digital universe in 2020: Big data, bigger digital shadows, and biggest growth in the far east, IDC IView IDC Analyze the Future, 2007, 1

tokui, 2015, Chainer: A next-generation open source framework for deep learning, Proc Workshop Mach Learn Syst (LearningSys) 29th Annu Conf Neural Inf Process Syst (NIPS), 1

hada-muranushi, 2016, A deep-learning approach for operation of an automated realtime flare forecast, arXiv preprint arXiv 1606 01587v1 [astro-ph SR]

10.1145/2991561.2991575

10.1145/2996890.2996907

10.1109/VLSIC.2016.7573525

10.1109/JIOT.2016.2561962

10.3390/s16010115

daniel, 0, Lessons learned from deploying deep learning at scale

nguyen-thanh, 2016, Cognitive computation and communication: A complement solution to cloud for IoT, Proc Int Conf Adv Technol Commun (ATC), 222

10.1109/TII.2017.2679740

howard, 2017, MobileNets: Efficient convolutional neural networks for mobile vision applications, arXiv preprint arXiv 1704 04861v1 [cs CV]

10.1109/JBHI.2016.2633287

chilimbi, 2014, Project ADAM: Building an efficient and scalable deep learning training system, Proc USENIX Symp Oper Syst Design Implementation, 14, 571

10.1145/3079856.3080246

10.1109/MCOM.2015.7263375

coates, 2013, Deep learning with COTS HPC systems, Proc 30th Int Conf Mach Learn, 28, 1337

simmhan, 2016, Big data analytics platforms for real-time applications in IoT, Big Data Analytics, 115

hemsoth, 2015, GPU Platforms Set to Lengthen Deep Learning Reach

10.1007/978-3-319-62404-4_16

10.1109/SEC.2016.38

2017, List of Datasets for Machine Learning Research

mcdaniel, 2016, The limitations of deep learning in adversarial settings, Proc IEEE Eur Symp Secur Privacy (EuroS P), 372

10.1186/s40537-014-0007-7

lavalle, 2011, Big data, analytics and the path from insights to value, Mit Sloan Manag Rev, 52, 21

10.1109/CVPR.2015.7298640

10.1109/CIEL.2014.7015739

10.1109/MNET.2016.7474340

2017, Cyber-Physical Systems (CPS)—Program Solicitation (NSF 17-529)

10.1109/JIOT.2017.2724938

10.1109/IROS.2016.7759589

tai, 2016, Deep-learning in mobile robotics-from perception to control systems: A survey on why and why not, arXiv preprint arXiv 1612 07139v3 [cs RO]

sutanto, 2017, 3D integral imaging based augmented reality with deep learning implemented by faster R-CNN, Proc Int Conf Mobile Wireless Technol, 241

10.1109/SITIS.2016.17

10.1109/IROS.2016.7759428

10.1109/IRC.2017.77

10.1109/COMST.2017.2727878

ackerman, 2017, Deep-learning first: Drive.ai’s path to autonomous driving, IEEE Spectr

10.1371/journal.pone.0173317

10.1016/j.neunet.2012.02.023

10.1109/SmartCity.2015.63

10.1007/978-3-319-50478-0_19

10.1007/978-3-319-39601-9_4

10.1109/MCOM.2017.1600425CM

lipton, 2016, Learning to diagnose with LSTM recurrent neural networks, Proc ICLR, 1

10.1109/JBHI.2016.2636665

10.1109/TMI.2017.2655486

10.1109/ICDSP.2014.6900806

10.1109/IGARSS.2015.7325900

10.1109/LGRS.2017.2681128

10.3390/jimaging2010006

10.1109/LGRS.2017.2657778

10.3390/s16081222

10.1016/j.compedu.2013.09.004

10.1186/s40561-015-0009-8

10.1145/2783258.2783273

10.1109/JSTSP.2017.2700227

manyika, 2013, Disruptive Technologies Advances That Will Transform Life Business and the Global Economy, 180

piech, 2015, Deep knowledge tracing, Proc Adv Neural Inf Process Syst, 505

10.1109/COMST.2015.2444095

10.1109/CVPRW.2014.95

10.1145/2740070.2631434

10.1371/journal.pone.0155781

10.1109/TSG.2017.2703842

10.1109/ACCESS.2016.2557846

10.1007/s12193-015-0195-2

10.1109/ICCV.2015.494

10.1007/s11263-016-0957-7

10.1145/2994551.2994569

10.1145/2976749.2978318

hazen, 2016, Microsoft and Liebherr Collaborating on New Generation of Smart Refrigerators

shokri, 2015, Privacy-preserving deep learning, Proc 22nd ACM SIGSAC Conf Comput Commun Security, 1310, 10.1145/2810103.2813687

10.1038/nature14539

10.1109/SURV.2013.103013.00206

10.1109/SURV.2013.042313.00197

10.1109/COMST.2014.2320099

10.1109/COMST.2017.2707140

10.1186/s13634-016-0355-x

10.1109/ACCESS.2017.2697839

10.1007/s11356-016-7812-9

10.14778/2809974.2809979

10.1109/ICDE.2016.7498348

10.1111/dpr.12142

10.1145/2481244.2481246

10.1016/j.eswa.2016.10.055

yoshida, 2016, The Internet of Things That Matter Integrating Smart Cities With Smart Agriculture Digitalist Magazine

10.1109/MIE.2016.2615575

song, 2016, Deeptransport: Prediction and simulation of human mobility and transportation mode at a citywide level, Proc IJCAI, 2618

2016, Toshiba and Dell Technologies’ Deep Learning Testbed for IoT Is First Approved by Industrial Internet Consortium

10.1109/WF-IoT.2016.7845408

10.1109/SMC.2016.7844820

10.1016/j.segan.2016.02.005

10.1109/SMC.2016.7844673