Nội dung được dịch bởi AI, chỉ mang tính chất tham khảo
Một phương pháp tiềm năng để nhận diện tương tác giữa người với người từ dữ liệu kênh Wi-Fi sử dụng mạng nơ-ron tích cực hai chiều có sự chú ý và triển khai ứng dụng GUI
Multimedia Tools and Applications - Trang 1-44 - 2024
Tóm tắt
Nghiên cứu Nhận diện Hoạt động của Con người (HAR) đã đạt được động lực đáng kể nhờ vào những tiến bộ công nghệ gần đây, các thuật toán trí tuệ nhân tạo, nhu cầu cho các thành phố thông minh và sự chuyển đổi kinh tế xã hội. Tuy nhiên, các giải pháp HAR hiện tại dựa trên tầm nhìn máy tính và cảm biến có những hạn chế như vấn đề riêng tư, tiêu thụ bộ nhớ và năng lượng, cũng như sự không thoải mái khi đeo cảm biến, điều này khiến cho các nhà nghiên cứu đang quan sát một sự chuyển mình trong nghiên cứu HAR. Để đáp ứng, HAR dựa trên Wi-Fi đang trở nên phổ biến nhờ vào sự sẵn có của Thông tin Trạng thái Kênh thô hơn. Tuy nhiên, các phương pháp HAR hiện tại dựa trên Wi-Fi còn hạn chế trong việc phân loại các hoạt động độc lập và không đồng thời của con người diễn ra trong khoảng thời gian bằng nhau. Nghiên cứu gần đây thường sử dụng liên kết truyền thông Đầu vào Đầu ra Đơn với tín hiệu Wi-Fi tần số kênh 5 GHz, sử dụng hai bộ định tuyến Wi-Fi hoặc hai NIC Intel 5300 làm thiết bị phát-đón. Nghiên cứu của chúng tôi, mặt khác, sử dụng một liên kết vô tuyến Đầu vào Đầu ra Đa giữa một bộ định tuyến Wi-Fi và một NIC Intel 5300, với thông tin trạng thái kênh Wi-Fi theo chuỗi thời gian dựa trên tần số kênh 2.4 GHz cho việc nhận diện tương tác đồng thời giữa người với người. Mô hình học sâu Mạng nơ-ron Tích cực Hai chiều hướng dẫn Bằng sự chú ý (Attention-BiGRU) được đề xuất có thể phân loại 13 tương tác lẫn nhau với độ chính xác tối đa chuẩn 94% cho một cặp đối tượng đơn. Điều này đã được mở rộng cho mười cặp đối tượng, đạt được độ chính xác chuẩn 88% với sự cải thiện trong phân loại quanh vùng chuyển tiếp tương tác. Một phần mềm giao diện người dùng đồ họa (GUI) có thể thực thi cũng đã được phát triển trong nghiên cứu này bằng cách sử dụng module PyQt5 của python để phân loại, lưu trữ và hiển thị tổng thể các tương tác đồng thời của con người diễn ra trong một khoảng thời gian nhất định. Cuối cùng, bài viết này kết luận với một cuộc thảo luận về các giải pháp khả thi cho những hạn chế đã quan sát và xác định các lĩnh vực cần nghiên cứu thêm. Việc phân tích mẫu nhiễu kênh Wi-Fi được cho là một phương pháp hiệu quả, kinh tế và thân thiện với sự riêng tư, có thể được sử dụng cho việc nhận diện tương tác giữa người với người trong giám sát hoạt động trong nhà, hệ thống giám sát, hệ thống giám sát sức khỏe thông minh, và sống độc lập hỗ trợ.
Từ khóa
#Nhận diện Hoạt động của Con người #HAR #Wi-Fi #Mạng nơ-ron #Thông tin Trạng thái Kênh #Giao diện người dùng đồ họa #Tương tác giữa người với ngườiTài liệu tham khảo
Gowda SG, Shetty SM, Darshini MS et al (2023) Analysis of human activity detection using machine learning approaches. SN Comput Sci 4(2). https://doi.org/10.1007/s42979-022-01550-x
Saleem G, Bajwa UI, Raza RH (2022) Toward human activity recognition: a survey. Neural Comput & Applic 35(5):4145–4182. https://doi.org/10.1007/s00521-022-07937-4
Kulsoom F, Narejo S, Mehmood Z et al (2022) A review of machine learning-based human activity recognition for diverse applications. Neural Comput & Applic 34(21):18289–18324. https://doi.org/10.1007/s00521-022-07665-9
Gupta N, Gupta SK, Pathak RK et al (2022) Human activity recognition in artificial intelligence framework: a narrative review. Artif Intell Rev 55(6):4755–4808. https://doi.org/10.1007/s10462-021-10116-x
Islam MM, Nooruddin S, Karray F et al (2022) Human activity recognition using tools of convolutional neural networks: a state of the art review, data sets, challenges, and future prospects. Comput Biol Med 149:106060. https://doi.org/10.1016/j.compbiomed.2022.106060
Beddiar DR, Nini B, Sabokrou M et al (2020) Vision-based human activity recognition: a survey. Multimed Tools Appl 79(41–42):30509–30555. https://doi.org/10.1007/s11042-020-09004-3
Zhang S, Wei Z, Nie J et al (2017) A review on human activity recognition using vision-based method. J Healthc Eng 2017:1–31. https://doi.org/10.1155/2017/3090343
Ranasinghe S, Al Machot F, Mayr HC (2016) A review on applications of activity recognition systems with regard to performance and evaluation. Int J Distrib Sens Netw 12(8). https://doi.org/10.1177/1550147716665520
Golestani N, Moghaddam M (2020) Human activity recognition using magnetic induction-based motion signals and deep recurrent neural networks. Nat Commun 11(1). https://doi.org/10.1038/s41467-020-15086-2
Li J, Li Z, Tyson G et al (2020) Your privilege gives your privacy away: an analysis of a home security camera service. In: IEEE INFOCOM 2020 - IEEE conference on computer communications, pp 387–396. https://doi.org/10.1109/INFOCOM41043.2020.9155516
Li H, He Y, Sun L et al (2016) Side-channel information leakage of encrypted video stream in video surveillance systems. In: IEEE INFOCOM 2016 - The 35th annual IEEE international conference on computer communications, pp 1–9. https://doi.org/10.1109/INFOCOM.2016.7524621
Xu K, Wang J, Zhang L et al (2023) Dual-stream contrastive learning for channel state information based human activity recognition. IEEE J Biomed Health Inform 27:329–338. https://doi.org/10.1109/JBHI.2022.3219640
McCaldin D, Wang K, Schreier G et al (2016) Unintended consequences of wearable sensor use in healthcare. Yearb Med Inform 25(01):73–86. https://doi.org/10.15265/iy-2016-025
Ding W, Guo X, Wang G (2021) Radar-based human activity recognition using hybrid neural network model with multidomain fusion. IEEE Trans Aerosp Electron Syst 57(5):2889–2898. https://doi.org/10.1109/TAES.2021.3068436
Noori FM, Uddin MZ, Torresen J (2021) Ultra-wideband radar-based activity recognition using deep learning. IEEE Access 9:138132–138143. https://doi.org/10.1109/ACCESS.2021.3117667
Ghosh A, Sanyal A, Chakraborty A et al (2017) On automatizing recognition of multiple human activities using ultrasonic sensor grid. In: 2017 9th International conference on communication systems and networks (COMSNETS), pp 488–491. https://doi.org/10.1109/COMSNETS.2017.7945440
Damodaran N, Schäfer J (2019) Device free human activity recognition using wifi channel state information. In: 2019 IEEE SmartWorld, ubiquitous intelligence computing, advanced trusted computing, scalable computing communications, cloud big data computing, internet of people and smart city innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), pp 1069–1074. https://doi.org/10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00205
Yang J, Xu Y, Cao H et al (2022) Deep learning and transfer learning for device-free human activity recognition: a survey. J Autom Intell 1(1):100007. https://doi.org/10.1016/j.jai.2022.100007
Liu R, Ramli AA, Zhang H et al (2022) An overview of human activity recognition using wearable sensors: healthcare and artificial intelligence. Internet of Things - ICIOT 2021:1–14. https://doi.org/10.1007/978-3-030-96068-1_1
Ye Q, Zhong H, Qu C et al (2020) Human interaction recognition based on whole-individual detection. Sensors 20(8). https://doi.org/10.3390/s20082346. https://www.mdpi.com/1424-8220/20/8/2346
Ahmed MU, Kim YH, Kim JW et al (2019) Two person interaction recognition based on effective hybrid learning. KSII Trans Internet Inf Syst 13(2). https://doi.org/10.3837/tiis.2019.02.015
Stergiou A, Poppe R (2019) Analyzing human-human interactions: a survey. Comput Vis Image Underst 188. https://doi.org/10.1016/j.cviu.2019.102799. https://www.sciencedirect.com/science/article/pii/S1077314219301158’
Liu H, Yang R, Yang Y et al (2020) Human-human interaction recognition based on ultra-wideband radar. SIViP 14(6):1181–1188. https://doi.org/10.1007/s11760-020-01658-8
Finkelhor D, Ormrod R (2001) Crimes against children by babysitters. Juvenile justice bulletin NCJ198102:1-7. https://doi.org/10.1037/e317992004-001. https://scholars.unh.edu/ccrc/9/
Gerard A, McGrath A, Colvin E et al (2018) ‘I’m not getting out of bed!’ the criminalisation of young people in residential care. Aust N Z J Criminol 52(1):76–93. https://doi.org/10.1177/0004865818778739
Hemphill SA, Smith R, Toumbourou JW et al (2009) Modifiable determinants of youth violence in australia and the united states: a longitudinal study. Aust N Z J Criminol 42(3):289–309. https://doi.org/10.1375/acri.42.3.289
Cristóbal S, Boettcher ML (2018) Critical perspectives on hazing in colleges and universities: a guide to disrupting hazing culture, 1st edn. Routledge. https://doi.org/10.4324/9781315177311
Allan EJ, Madden M (2012) The nature and extent of college student hazing. Int J Adolesc Med Health 24(1). https://doi.org/10.1515/ijamh.2012.012
Campo S, Poulos G, Sipple JW (2005) Prevalence and profiling: hazing among college students and points of intervention. Am J Health Behav 29(2):137–149. https://doi.org/10.5993/ajhb.29.2.5
Kozicki M, Hoenig S, Robinson P (1991) Personnel and contamination, Springer, pp 211–251. https://doi.org/10.1007/978-94-011-7950-8_11
Alavi-Moghadam S, Sarvari M, Goodarzi P et al (2020) The importance of cleanroom facility in manufacturing biomedical products. Springer, pp 69–79. https://doi.org/10.1007/978-3-030-35626-2_7
Alazrai R, Awad A, Alsaify B et al (2020) A dataset for wi-fi-based human-to-human interaction recognition. Data Br 31:105668. https://doi.org/10.1016/j.dib.2020.105668
Willman J (2020) Overview of pyqt5. Modern PyQt p 1-42. https://doi.org/10.1007/978-1-4842-6603-8_1
Thariq Ahmed HF, Ahmad H, Aravind CV (2020) Device free human gesture recognition using wi-fi csi: a survey. Eng Appl Artif Intell 87:103281. https://doi.org/10.1016/j.engappai.2019.103281
Ashleibta AM, Taha A, Khan MA et al (2021) 5g-enabled contactless multi-user presence and activity detection for independent assisted living. Sci Rep 11(1). https://doi.org/10.1038/s41598-021-96689-7
Wang Z, Huang Z, Zhang C et al (2021) Csi-based human sensing using model-based approaches: a survey. J Comput Des Eng 8(2):510–523. https://doi.org/10.1093/jcde/qwab003
Wang F, Gong W, Liu J (2019) On spatial diversity in wifi-based human activity recognition: a deep learning-based approach. IEEE Internet Things J 6(2):2035–2047. https://doi.org/10.1109/JIOT.2018.2871445
Wang F, Gong W, Liu J et al (2020) Channel selective activity recognition with wifi: a deep learning approach exploring wideband information. IEEE Trans Netw Sci Eng 7(1):181–192. https://doi.org/10.1109/TNSE.2018.2825144
Damodaran N, Haruni E, Kokhkharova M et al (2020) Device free human activity and fall recognition using wifi channel state information (csi). CCF Trans Pervasive Comput Interact 2(1):1–17. https://doi.org/10.1007/s42486-020-00027-1
Halperin D, Hu W, Sheth A et al (2011) Tool release: gathering 802.11n traces with channel state information. ACM SIGCOMM Comput Commun Rev 41(1):53–53. https://doi.org/10.1145/1925861.1925870
Ettus M, Braun M (2015) The universal software radio peripheral (usrp) family of low-cost sdrs. Opportunistic Spectrum Sharing and White Space Access, pp 3–23. https://doi.org/10.1002/9781119057246.ch1
Serkin F, Vazhenin N (2013) Usrp platform for communication systems research. In: 2013 15th International conference on transparent optical networks (ICTON), pp 1–4. https://doi.org/10.1109/ICTON.2013.6602738
Shalaby E, ElShennawy N, Sarhan A (2022) Utilizing deep learning models in csi-based human activity recognition. Neural Comput & Applic 34(8):5993–6010. https://doi.org/10.1007/s00521-021-06787-w
Yang J, Chen X, Zou H et al (2022) Autofi: towards automatic wifi human sensing via geometric self-supervised learning. IEEE Internet Things 1–1. https://doi.org/10.1109/JIOT.2022.3228820
Bocus MJ, Lau HS, McConville R et al (2022) Self-supervised wifi-based activity recognition. IEEE 552–557. https://doi.org/10.1109/GCWkshps56602.2022.10008537
Al-qaness MAA (2019) Device-free human micro-activity recognition method using wifi signals. Geo Spat Inf Sci 22:128–137. https://doi.org/10.1080/10095020.2019.1612600
Li C, He Y, Li X et al (2019) Bigru network for human activity recognition in high resolution range profile. In: 2019 International radar conference (RADAR), pp 1–5. https://doi.org/10.1109/RADAR41533.2019.171259
Liu X, You J, Wu Y et al (2020) Attention-based bidirectional gru networks for efficient https traffic classification. Inf Sci 541:297–315. https://doi.org/10.1016/j.ins.2020.05.035. https://www.sciencedirect.com/science/article/pii/S002002552030445X’
Chen JX, Jiang DM, Zhang YN (2019) A hierarchical bidirectional gru model with attention for eeg-based emotion classification. IEEE Access 7:118530–118540. https://doi.org/10.1109/ACCESS.2019.2936817
Sheng L (2020) Application of attention-based gru combined with cnn classification on p300 signals. In: 2020 5th International conference on smart grid and electrical automation (ICSGEA), pp 182–185. https://doi.org/10.1109/ICSGEA51094.2020.00046
Paul T, Ogunfunmi T (2008) Wireless lan comes of age: understanding the ieee 802.11n amendment. IEEE Circ Syst Mag 8(1):28–54. https://doi.org/10.1109/mcas.2008.915504
Rappaport TS (2002) Wireless Communications: principles and practice. Prentice Hall PTR, Chap 3(4):69–192
Wong KD (2012) Fundamentals of wireless communication engineering technologies. John Wiley & Sons, chap 5: Propagation, pp 125-154
Stein JC (1998) Indoor radio wlan performance part ii : range performance in a dense office environment. In: Intersil corporation, 2401 Palm Bay, Florida 32905
Shankar PM (2017) Fading and shadowing in wireless systems, 2nd edn., Springer International Publishing AG, chap 3.8 Orthogonal frequency division multiplexing, 4.3.1 Rayleigh Fading, 4.3.2 Rician Fading, pp 263303–267312
Weisstein WE (2021) Modified bessel function of the first kind. https://mathworld.wolfram.com/ModifiedBesselFunctionoftheFirstKind.html
Abramowitz M, Stegun IA (1972) Handbook of mathematical functions with formulas, graphs, and mathematical tables, 9th edn., Dover Publications, chap Section-9.6: Modified bessel functions, pp 374–377
Andjamba TS, Zodi GAL, Jat DS (2016) Interference analysis of ieee 802.11 wireless networks: a case study of namibia university of science and technology. In: 2016 International conference on ICT in business industry government (ICTBIG), pp 1–5. https://doi.org/10.1109/ICTBIG.2016.7892726
Liu J, Aoki T, Li Z et al (2020) Throughput analysis of ieee 802.11 wlans with inter-network interference. Appl Sci 10(6). https://doi.org/10.3390/app10062192. https://www.mdpi.com/2076-3417/10/6/2192
Wan Y, Sanada K, Komuro N et al (2016) Throughput analysis of wlans in saturation and non-saturation heterogeneous conditions with airtime concept. IEICE Trans Commun E99.B(11):2289–2296. https://doi.org/10.1587/transcom.2016NEP0010
Chandaliya P, Dhakate N, Lokhande U et al (2012) Interference analysis of ieee 802.11n. In: 2012 International Conference on Communication, Information Computing Technology (ICCICT), pp 1–6. https://doi.org/10.1109/ICCICT.2012.6398169
Natarajan R, Zand P, Nabi M (2016) Analysis of coexistence between ieee 802.15. 4, ble and ieee 802.11 in the 2.4 ghz ism band. In: IECON 2016 - 42nd Annual conference of the IEEE industrial lectronics Society, 24-27 October 2016, Firenze, Italy. Institute of Electrical and Electronics Engineers, United States, pp 6025–6032. https://doi.org/10.1109/IECON.2016.7793984. http://www.iecon2016.org/?jjj=1483537444731, http://www.iecon2016.org/, 42nd Annual Conference of the IEEE Industrial Electronics Society (IECON 2016), IECON 2016 ; Conference date: 24-10-2016 Through 27-10-2016
Sarkar NI, Mussa O, Gul S (2021) Impact of people’s movement on wi-fi link throughput in indoor propagation environments: an empirical study. Electronics 10(7):856. https://doi.org/10.3390/electronics10070856
Wu RH, Lee YH, Tseng HW et al (2008) Study of characteristics of rssi signal. In: 2008 IEEE International conference on industrial technology, pp 1–3. https://doi.org/10.1109/ICIT.2008.4608603
Byrne D, Kozlowski M, Santos-Rodriguez R et al (2018) Residential wearable rssi and accelerometer measurements with detailed location annotations. Sci Data 5(1). https://doi.org/10.1038/sdata.2018.168
Rosu I (2015) Automatic gain control (agc) in receivers. https://www.qsl.net/va3iul/Files/Automatic_Gain_Control.pdf
Li Y, Yang L, Yu L et al (2020) Digital agc circuit design based on fpga. J Phys Conf Ser 1654(1):012030. https://doi.org/10.1088/1742-6596/1654/1/012030
Kang H, No JS (2017) Automatic gain control in high adjacent channel interference for ofdm systems. In: 2017 23rd Asia-pacific conference on communications (APCC), pp 1–4. https://doi.org/10.23919/APCC.2017.8303964
Sure P, Bhuma CM (2017) A survey on ofdm channel estimation techniques based on denoising strategies. Eng Sci Technol Int J 20(2):629–636. https://doi.org/10.1016/j.jestch.2016.09.011
Kaur H, Khosla M, Sarin R (2018) Channel estimation in mimo-ofdm system: a review. In: 2018 Second international conference on electronics, communication and aerospace technology (ICECA), pp 974–980. https://doi.org/10.1109/ICECA.2018.8474747
Iserte AP, Ángel Lagunas Hernández Miguel, Ana IPN (2005) Channel state information and joint transmitter-receiver design in multi-antenna systems. PhD thesis, Universitat Politècnica de Catalunya
Gao J, Ozdural O, Ardalan S et al (2006) Performance modeling of mimo ofdm systems via channel analysis. IEEE Trans Wirel Commun 5(9):2358–2362. https://doi.org/10.1109/TWC.2006.1687758
Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830
CyberZHG (2020) Cyberzhg/keras-pos-embd: position embedding layers in keras. https://github.com/CyberZHG/keras-pos-embd
Cho K, van Merrienboer B, Bahdanau D et al (2014) On the properties of neural machine translation: Encoder-decoder approaches. arXiv:1409.1259
Shen G, Tan Q, Zhang H et al (2018) Deep learning with gated recurrent unit networks for financial sequence predictions. Procedia Comput Sci 131:895–903. https://doi.org/10.1016/j.procs.2018.04.298
Schuster M, Paliwal K (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45(11):2673–2681. https://doi.org/10.1109/78.650093
Vaswani A, Shazeer N, Parmar N, et al (2017) Attention is all you need. In: Guyon I, Luxburg UV, Bengio S, et al (eds) Advances in neural information processing systems, vol 30. Curran Associates, Inc., https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
Hassan E, Shams MY, Hikal NA et al (2022) The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study. Multimed Tools Appl. https://doi.org/10.1007/s11042-022-13820-0
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. https://doi.org/10.48550/ARXIV.1412.6980. arXiv:1412.6980
Ajagekar A (2021) Adam optimizer. https://optimization.cbe.cornell.edu/index.php?title=Adam
Ben-David S, Blitzer J, Crammer K et al (2009) A theory of learning from different domains. Mach Learn 79(1–2):151–175. https://doi.org/10.1007/s10994-009-5152-4
Habrard A, Younès B, Morvant E et al (2019) Advances in domain adaptation theory, 1st edn. Elsevier, chap 1-9, pp 1–208
Redko I, Morvant E, Habrard A et al (2020) A survey on domain adaptation theory: learning bounds and theoretical guarantees. arXiv:2004.11829
Xie Y, Li Z, Li M (2015) Precise power delay profiling with commodity wifi. ACM, pp 53–64. https://doi.org/10.1145/2789168.2790124
Kaveh M, Mesgari MS (2022) Application of meta-heuristic algorithms for training neural networks and deep learning architectures: a comprehensive review. Neural Process Lett. https://doi.org/10.1007/s11063-022-11055-6
Abd Elaziz M, Dahou A, Abualigah L et al (2021) Advanced metaheuristic optimization techniques in applications of deep neural networks: a review. Neural Comput & Applic 33(21):14079–14099. https://doi.org/10.1007/s00521-021-05960-5
Khan MS, Jabeen F, Ghouzali S et al (2021) Metaheuristic algorithms in optimizing deep neural network model for software effort estimation. IEEE Access 9:60309–60327. https://doi.org/10.1109/access.2021.3072380
Movassagh AA, Alzubi JA, Gheisari M et al (2021) Artificial neural networks training algorithm integrating invasive weed optimization with differential evolutionary model. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02623-6
Xu S, Panwar SS, Kodialam M et al (2020) Deep neural network approximated dynamic programming for combinatorial optimization. Proc AAAI Conf Artif Intell 34(02):1684–1691. https://doi.org/10.1609/aaai.v34i02.5531
Wu N, Wang H (2018) Deep learning adaptive dynamic programming for real time energy management and control strategy of micro-grid. J Clean Prod 204:1169–1177. https://doi.org/10.1016/j.jclepro.2018.09.052
Alzubi OA, Alzubi JA, Alweshah M et al (2020) An optimal pruning algorithm of classifier ensembles: Dynamic programming approach. Neural Comput & Applic 32(20):16091–16107. https://doi.org/10.1007/s00521-020-04761-6
Gheisari M, Najafabadi HE, Alzubi JA et al (2021) Obpp: an ontology-based framework for privacy-preserving in iot-based smart city. Futur Gener Comput Syst 123:1–13. https://doi.org/10.1016/j.future.2021.01.028
Hanzo L, Akhtman YJ, Wang L (2011) MIMO-OFDM for LTE, Wi-Fi and WiMAX: coherent versus non-coherent and cooperative turbotransceivers, Wiley, chap Chapter-1: Introduction to OFDM and MIMOOFDM, Section-7.8: Channel Estimation for MIMO-OFDM, pp 1233–33244