Behavioral Biometrics Based on Human-Computer Interaction Devices
The purpose of this chapter is to describe a new approach to recognize the identity of a person through analyzing the behavioral biometrics in Wi-Fi signals and their potential application prospects. A solid understanding of processing Wi-Fi signals helps to interpret solid information and problem statement on identity recognition through Wi-Fi signals. The ubiquitous and temporal features of Wi-Fi signals are the basis of recognition and localization. We introduce a new paradigm on how to use Wi-Fi signals to identify the human in the open environment. We proposed Wide, a Wi-Fi signal-based human identity recognition system. First, we describe the components of Wide and how it works in detail. Through collecting CSI (channel state information) profiles, Wide is able to recognize the human identity through sampling and extracting features of the received Wi-Fi signals. Then, to reduce the storage overhead while guaranteeing high recognizing accuracy, principal component analysis (PCA) technique is used. Finally, test-bed experiments are conducted to show the performance of Wide, indicating that Wide can quickly recognize people in a high accuracy.
The chapter starts with the definition of Wi-Fi signals and CSI (channel state information) and behavioral biometrics-related applications. Particular emphasis is placed on the characteristic of the CSI, which indicates that CSI can be used for recognizing the identity of people. Then we highlight our objective and demonstrate our design in detail. At last, experiments are conducted through collecting, analyzing, and processing Wi-Fi signals to recognize the identity of people, revealing that the proposed scheme can recognize people with promising accuracy in a short time.
This chapter is structured as follows. Section 1 focuses on research background in behavioral biometrics and illustrations on characteristics of key technologies. Section 2 gives a brief overview on related achievement in this research field. Section 3 looks at the essence of related theory and behavioral biometric recognition methods. Section 4 deals with experimental installations and configurations. Section 5 analyzes the experimental results and discusses the potential features of our scheme. Section 6 concludes this chapter and outlines future research trends in Wi-Fi signal topics.
- 1.S. Sigg, S. Shi, F. Buesching, Y. Ji, L Wolf, Leveraging Rf-channel fluctuation for activity recognition: Active and passive systems, continuous and RSSI-based signal features, in Proceedings of International Conference on Advances in Mobile Computing & Multimedia, (ACM, 2013), page 43Google Scholar
- 5.S. Sen, J. Lee, K.-H. Kim, P. Congdon, Avoiding multipath to revive in building WiFi localization. in Proceeding of ACM MobiSys, (2013), pp. 249–262Google Scholar
- 6.K. Ali, A.X. Liu, W. Wang, M. Shahzad, Keystroke recognition using WiFi signals, in Proceedings of ACM MobiCom, (2015), pp. 90–102Google Scholar
- 8.Q. Pu, S. Gupta, S. Gollakota, Shwetak Patel, Whole-home gesture recognition using wireless signals, in Proceedings of the 19th annual international conference on Mobile computing & networking, (ACM, 2013), pp. 27–38Google Scholar
- 9.F. Adib, Z. Kabelac, D. Katabi, R. Miller. 3d tracking via body radio reflections, in Usenix NSDI, vol. 14, (2013)Google Scholar
- 10.Y. Wang, J. Liu, Y. Chen, M. Gruteser, J. Yang, H. Liu. E-eyes: In-home device-free activity identification using fine-grained WiFi signatures, in Proceedings of ACM MobiCom, (2014)Google Scholar
- 11.K. Ali, A.X. Liu, W. Wang, M. Shahzad, Keystroke recognition using WiFi signals, (ACM MobiCom, 2015), pp. 90–102Google Scholar
- 16.K. Wu, J. Xiao, Y. Yi, et al., Fila: fine-grained indoor localization[C], in INFOCOM, 2012 Proceedings IEEE, (IEEE, 2012), pp. 2210–2218Google Scholar
- 17.X. Liu, J. Cao, S. Tang, et al., Wi-Sleep: contactless sleep monitoring via WiFi signals[C], in Real-Time Systems Symposium (RTSS), 2014 IEEE, (IEEE, 2014), pp. 346–355Google Scholar
- 18.X. Wang, L. Gao, S. Mao, et al., DeepFi: deep learning for indoor fingerprinting using channel state information[C], in Wireless Communications and Networking Conference (WCNC), 2015 IEEE, (IEEE, 2015), pp. 1666–1671Google Scholar
- 19.W. Wang, A.X. Liu, M. Shahzad, et al., Understanding and modeling of wifi signal based human activity recognition[C], in Proceedings of the 21st Annual International Conference on Mobile Computing and Networking, (ACM, 2015), pp. 65–76Google Scholar
- 22.K. Ali, A.X. Liu, W. Wang, et al., Keystroke recognition using wifi signals[C], in Proceedings of the 21st Annual International Conference on Mobile Computing and Networking, (ACM, 2015), pp. 90–102Google Scholar
- 23.Y. Wen, X. Tian, X. Wang, et al., Fundamental limits of RSS fingerprinting based indoor localization[C], in Computer Communications (INFOCOM), 2015 I.E. Conference on. IEEE, (2015), pp. 2479–2487Google Scholar
- 24.Z. Zhou, Z. Yang, C. Wu, et al., Lifi: line-of-sight identification with wifi[C], in INFOCOM, 2014 Proceedings IEEE, (IEEE, 2014), pp. 2688–2696Google Scholar
- 25.B. Wei, W. Hu, M. Yang, et al., Radio-based device-free activity recognition with radio frequency interference[C], in Proceedings of the 14th International Conference on Information Processing in Sensor Networks, (ACM, 2015), pp. 154–165Google Scholar
- 27.X. Wang, L. Gao, S. Mao, et al., CSI-based fingerprinting for indoor localization: a deep learning approach[J]. IEEE Trans. Veh. Technol. 66(1), 763–776 (2017)Google Scholar
- 29.Xu H, Yang Z, Zhou Z, et al. Enhancing wifi-based localization with visual clues[C]. in Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. (ACM 2015), pp. 963–974Google Scholar