近年來，人類行為分析一直是相當熱門的研究領域，而基於視覺的研究佔了該領域的大多數篇幅。隨著智慧型手機的普及和物聯網技術的蓬勃發展，行動裝置發送的大量無線訊號（如 Wi-Fi，藍牙和電信）為人類行為分析的研究提供了另一種可行的選擇。 同時，與基於視覺的方法相比，基於無線訊號的計算成本更低。 本文提出了一種可以利用無線訊號強度（RSSI）序列檢測人與人之間運動距離的方法。我們在大學校園的走廊上進行了多次實驗，以驗證該方法的可行性。

In recent years, human behavior analysis has been a research hotspot, and vision-based research is majority in this field. Through the spread of smart mobile devices and the vigorous development of Internet of Things technology, a large number of wireless signals such as Wi-Fi, Bluetooth and telecommunications sent by mobile devices provide another kind of analyzable choice for human behavior analysis. At the same time, compared with the vision-based method, the computing costs based on the wireless signal is lower. This thesis proposes a method that can use wireless signal strength (RSSI) sequence to detect the proximity of movement between people. We conducted several experiments on the corridor of the university campus to test the feasibility of this method.

[1]G. Di Lorenzo, M. Sbodio, F. Calabrese, M. Berlingerio, F. Pinelli, and R. Nair,“Allaboard: Visual exploration of cellphone mobility data to optimise public trans-port,”IEEE transactions on visualization and computer graphics, vol. 22, no. 2,pp. 1036–1050, 2015.
[2]H. A. Naji, C. Wu, H. Zhang, and L. Li, “Towards understanding the impactof human mobility patterns on taxi drivers’ income based on gps data: A casestudy in wuhan—china,” in2017 4th International Conference on TransportationInformation and Safety (ICTIS). IEEE, 2017, pp. 1152–1160.
[3]C. Meurisch, T. A. B. Nguyen, M. Kromm, A. Ortiz, R. Mogk, and M. Muhlhauser,“Disvis 2.0: Decision support for rescue missions using predictive disaster simu-lations with human-centric models,” in2017 26th International Conference onComputer Communication and Networks (ICCCN). IEEE, 2017, pp. 1–2.
[4]X. Andrade, F. Layedra, C. Vaca, and E. Cruz, “Risc: Quantifying change afternatural disasters to estimate infrastructure damage with mobile phone data,” in2018 IEEE International Conference on Big Data (Big Data). IEEE, 2018, pp.3383–3391.
[5]B. Tang, C. Jiang, H. He, and Y. Guo, “Human mobility modeling for robot-assisted evacuation in complex indoor environments,”IEEE Transactions onHuman-Machine Systems, vol. 46, no. 5, pp. 694–707, 2016.
[6]R. Papa, C. Gargiulo, and L. Russo, “The evolution of smart mobility strategiesand behaviors to build the smart city,” in2017 5th IEEE International Conferenceon Models and Technologies for Intelligent Transportation Systems (MT-ITS).IEEE, 2017, pp. 409–414.36.
[7]W. Zeng, C.-W. Fu, S. M. Arisona, S. Schubiger, R. Burkhard, and K.-L. Ma,“Visualizing the relationship between human mobility and points of interest,”IEEE Transactions on Intelligent Transportation Systems, vol. 18, no. 8, pp. 2271–2284, 2017.
[8]V. Bhatia and V. Hasija, “Targeted advertising using behavioural data and socialdata mining,” in2016 Eighth International Conference on Ubiquitous and FutureNetworks (ICUFN). IEEE, 2016, pp. 937–942.
[9]S. Chernbumroong, A. Lotfi, and C. Langensiepen, “Prediction of mobility entropyin an ambient intelligent environment,” in2014 IEEE Symposium on IntelligentAgents (IA). IEEE, 2014, pp. 65–72.
[10]E. Union, “General data protection regulation (gdpr),” https://gdpr-info.eu/.
[11]F.-J. Wu and G. Solmaz, “We hear your activities through wi-fi signals,” in2016IEEE 3rd World Forum on Internet of Things (WF-IoT). IEEE, 2016, pp. 251–256.
[12]S.-I. Sou, W.-H. Lin, K.-C. Lan, and C.-S. Lin, “Indoor location learning overwireless fingerprinting system with particle markov chain model,”IEEE Access,vol. 7, pp. 8713–8725, 2019.
[13]V. Daiya, J. Ebenezer, S. S. Murty, and B. Raj, “Experimental analysis of rssifor distance and position estimation,” in2011 International Conference on Recenttrends in information technology (ICRTIT). IEEE, 2011, pp. 1093–1098.
[14]M. Ros, J. Boom, G. de Hosson, and M. D’Souza, “Indoor localisation using acontext-aware dynamic position tracking model,”International Journal of Navi-gation and Observation, vol. 2012, 2012.
[15]W. Ge, R. T. Collins, and R. B. Ruback, “Vision-based analysis of small groupsin pedestrian crowds,”IEEE transactions on pattern analysis and machine intel-ligence, vol. 34, no. 5, pp. 1003–1016, 2012.
[16]J. Shen, J. Cao, X. Liu, and S. Tang, “Snow: Detecting shopping groups usingwifi,”IEEE Internet of Things Journal, vol. 5, no. 5, pp. 3908–3917, 2018.37.
[17]M. B. Kjærgaard, H. Blunck, M. Wüstenberg, K. Grønbask, M. Wirz, D. Roggen,and G. Tröster, “Time-lag method for detecting following and leadership behaviorof pedestrians from mobile sensing data,” in2013 IEEE International Conferenceon Pervasive Computing and Communications (PerCom). IEEE, 2013, pp. 56–64.
[18]T.-H. Chen, S.-I. Sou, and Y. Lee, “Witrack: Human-to-human mobility rela-tionship tracking in indoor environments based on spatio-temporal wireless signalstrength,” in2019 IEEE Intl Conf on Dependable, Autonomic and Secure Com-puting, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloudand Big Data Computing, Intl Conf on Cyber Science and Technology Congress(DASC/PiCom/CBDCom/CyberSciTech). IEEE, 2019, pp. 788–795.
[19]H. Du, Z. Yu, F. Yi, Z. Wang, Q. Han, and B. Guo, “Recognition of groupmobility level and group structure with mobile devices,”IEEE Transactions onMobile Computing, vol. 17, no. 4, pp. 884–897, 2017.
[20]G. Solmaz, J. Fürst, S. Aytaç, and F.-J. Wu, “Group-in: Group inference fromwireless traces of mobile devices,” in2020 19th ACM/IEEE International Con-ference on Information Processing in Sensor Networks (IPSN). IEEE, 2020, pp.157–168.
[21]GoIndoor, “What is the difference between proximity detection and indoor loca-tion?” https://www.goindoor.co/proximity-detection-vs-indoor-location/, 2016.