Channel State Information Auto-Labeling System (CALS) for Large-Scale Deep-Learning-Based Wi-Fi Sensing
Keywords:
Wi-Fi sensing, Channel state information, Auto-labeling, Computer vision, Deep learningAbstract
Wi-Fi sensing involves using Wi-Fi technology to sense the surrounding environments, and it has strong potential in a variety of sensing applications. Recently, several advanced deep-learning-based solutions using channel state information (CSI) data have shown great performance, but it is still difficult to use in practice without explicit data collection, which requires expensive adaptation efforts for model retraining. In this study, we propose a Channel State Information Automatic Labeling System (CALS) that automatically collects and labels training CSI data for deep-learning-based Wi-Fi sensing systems. The proposed system enhanced the efficiency of collecting labeled CSI data for supervised learning through computer vision technologies like object detection algorithms. We built a prototype of CALS to demonstrate its efficiency and collected data to train deep learning models for detecting the presence of a person in an indoor environment. Our results indicate an accuracy of over 90% using the auto labeled datasets generated by CALS.
References
Wang J, Zhao Y, Fan X, et al., 2018, Device-Free Identification Using Intrinsic CSI Features. IEEE Transactions on Vehicular Technology, 67(9): 8571–8581, https://www.doi.org/10.1109/TVT.2018.2853185
Mo H, Kim S, 2021, A Deep Learning-Based Human Identification System with Wi-Fi CSI Data Augmentation. IEEE Access, 9: 91913 91920, 2021. https://www.doi.org/ 10.1109/ACCESS.2021.3092435
Wang W, Liu AX, Shahzad M, et al., 2017, Device-Free Human Activity Recognition Using Commercial WiFi Devices. IEEE Journal on Selected Areas in Communications, 35(5): 1118–1131. https://www.doi.org/10.1109/JSAC.2017.2679658
Chen Z, Zhang L, Jiang C, Z, et al., 2018, WiFi CSI Based Passive Human Activity Recognition Using Attention Based BLSTM. IEEE Transactions on Mobile Computing, 18(11): 2714–2724. https://www.doi.org/10.1109/TMC.2018.2878233
Wang D, Yang J, Cui W, et al., 2021, Multimodal CSI-Based Human Activity Recognition Using GANs. IEEE Internet of Things Journal, 8(24): 17345–17355. https://www.doi.org/10.1109/JIOT.2021.3080401
Palipana S, Agrawal P, Pesch D, 2016, Channel State Information Based Human Presence Detection Using Non- Linear Techniques. Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments, 177–186. https://www.doi.org/10.1145/2993422.2993579
Zhou R, Lu X, Zhao P, et al., 2017, Device Free Presence Detection and Localization with SVM and CSI Fingerprinting. IEEE Sensors Journal, 17(23): 7990–7999. https://www.doi.org/10.1109/JSEN.2017.2762428
Wu K, Xiao J, Yi Y, et al., 2012, CSI-Based Indoor Localization. IEEE Transactions on Parallel and Distributed Systems, 24(7): 1300–1309. https://www.doi.org/10.1109/TPDS.2012.214
Wang X, Gao L, Mao S, et al., 2016, CSI-Based Fingerprinting for Indoor Localization: A Deep Learning Approach, IEEE Transactions on Vehicular Technology, 66(1): 763–776. https://www.doi.org/10.1109/TVT.2016.2545523
Li Q, Liao X, Liu M, et al., 2021, Indoor Localization Based on CSI Fingerprint by Siamese Convolution Neural Network. IEEE Transactions on Vehicular Technology, 70(11): 12168–12173. https://www.doi.org/10.1109/TVT.2021.3107936
Zheng Y, Zhang Y, Qian K, et al., 2019, Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi. Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services, 313–325. https://www.doi.org/10.1145/3307334.3326081
Zhang J, Tang Z, Li M, et al., 2018, CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing. Proceedings of the 24th Annual International Conference on Mobile Computing and Networking, 305–320. https://www.doi.org/10.1145/3241539.3241570
Zhang Y, Sun P, Jiang Y, et al., 2021, Bytetrack: Multi-Object Tracking by Associating Every Detection Box, arXiv.
Gringoli F, Schulz M, Link J, et al., 2019, Free your CSI: A Channel State Information Extraction Platform for Modern Wi-Fi Chipsets. Proceedings of the 13th International Workshop on Wireless Network Testbeds, Experimental Evaluation & Characterization, 21–28. https://www.doi.org/10.1145/3349623.3355477
Ma Y, Zhou G, Wang S, 2019, Wi-Fi Sensing with Channel State Information: A Survey. ACM Computing Surveys (CSUR), 52(3): 1–36. https://www.doi.org/10.1145/3310194
