無線網路已遍佈於日常生活中的每個角落，行動裝置也廣泛為大眾使用。裝置所產生的無線訊號，讓使用者在操作過程中留下了相當可觀的資料量，包含時間與地點等訊息。無線訊號可以被採集成為無線指紋，以此開啟了探索人類行為的新方向。不僅如此，無線訊號如Wi-Fi及BLE等的無限訊號強度已發展成為鄰近服務中相當可靠的解決方案。因此，從無線指紋中提取關鍵訊息讓我們能逐步學習人與人之間的鄰近關係。此篇論文中，我們提出名為WiTrack的無線感測系統，該系統藉由分析使用者各自無線指紋的相關性，以追蹤人類移動行為之間的相互關係。進一步來說，透過將感測器部屬於不同的地點採集一段時間的行動裝置訊號強度變化，系統以此來評估使用者之間的移動行為相似度。當獲得越高的相似度，代表裝置使用者間的移動軌跡的相似程度也越高。為了實現目標，我們在大學校園中建築物的長廊中建立了檢測環境，把無線感測系統部屬於其中，以多種現實情況下的走路情境來進行方法驗證。對攜帶行動裝置不同使用者之間的移動相似度進行比對後，我們的系統不僅成功辨識預先規範好移動行為的測試角色，也揭示了更多檢視現實環境中人類移動間的相關性中可供深入觀察的切入方式。我們相信這項成就將能持續精進以解決更多具有挑戰性的實際環境，也能揭開更多研究現實互動的嶄新觀點。

Wireless networks have surrounded our societies nowadays. With the widespread adoption of mobile devices, users produce a massive amount of wireless signals with time and location information. Those signals can be processed as wireless fingerprints, providing great potential to discover human behaviors. Besides, the wireless signal strength measurement of Wi-Fi and BLE signals have emerged as assuring solutions for developing proximity services. Therefore, the critical details derived from wireless fingerprints grant access to learn the person-to-person proximity. In the thesis, we proposed a wireless sensing system, WiTrack, for tracking human mobility relationships in indoor environments based on the correlation between wireless fingerprints of users. Specifically, the system evaluated mobility similarity with signal strength features obtained by a set of scanners deployed at different locations over time. A higher similarity indicates more similar mobility patterns among device users. To implement our concepts, We set up a testbed at a corridor in a university campus building, where we deployed the system to verify several scripted walking scenarios close to the real world. By comparing similarity values among individuals carrying different mobile devices, the system not only managed to identify predefined roles in the testing group but also give insight into the real-life human mobility relationships from multiple aspects. We believe that our achievements can be further enhanced to adapt to more challenging environments and to reveal more brand new visions from real-world interaction.

[1] F. J.Wu and H. B. Lim, “UrbanMobilitySense: A User-Centric Participatory Sensing System for Transportation Activity Surveys,” IEEE Sensors Journal, vol. 14,
no. 12, pp. 4165–4174, 2014.
[2] G. Solmaz and D. Turgut, “Theme park mobility in disaster scenarios,” in 2013 IEEE Global Communications Conference (GLOBECOM), 2013, pp. 377–382.
[3] ——, “Pedestrian mobility in theme park disasters,” IEEE Communications Magazine, vol. 53, no. 7, pp. 172–177, Jul. 2015.
[4] C. Pahla, H. N. Muyingi, and F. B. Shava, “Analysis of group mobility for opportunistic campus network,” in 2017 IEEE Region 10 Symposium (TENSYMP),
Jul. 2017, pp. 1–6.
[5] R. Wang, F. Chen, Z. Chen, T. Li, G. Harari, S. Tignor, X. Zhou, D. Ben-Zeev, and A. T. Campbell, “StudentLife: Assessing Mental Health, Academic Performance and Behavioral Trends of College Students Using Smartphones,” in
Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, ser. UbiComp ’14. New York, NY, USA: ACM, 2014, pp. 3–14. [Online]. Available: http://doi.acm.org/10.1145/2632048.2632054
[6] C. A. Ronao and S. B. Cho, “Human activity recognition using smartphone sensors with two-stage continuous hidden Markov models,” in 2014 10th International Conference on Natural Computation (ICNC), 2014, pp. 681–686.
[7] D. Anguita, A. Ghio, L. Oneto, X. Parra, and J. L. Reyes-Ortiz, “A Public Domain Dataset for Human Activity Recognition using Smartphones,” in ESANN, 2013. 48
[8] Y. Fu, P. Chen, S. Yang, and J. Tang, “An Indoor Localization Algorithm Based on Continuous Feature Scaling and Outlier Deleting,” IEEE Internet of Things Journal, vol. PP, no. 99, pp. 1–1, 2018.
[9] N. M. Oliver, B. Rosario, and A. P. Pentland, “A Bayesian computer vision system for modeling human interactions,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 831–843, Aug. 2000.
[10] J. Yun and S.-S. Lee, “Human Movement Detection and Identification Using Pyroelectric Infrared Sensors,” Sensors (Basel, Switzerland), vol. 14, pp. 8057–81, 2014.
[11] X. Yang and Y. Tian, “Super Normal Vector for Human Activity Recognition with Depth Cameras,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 5, pp. 1028–1039, May 2017.
[12] C. Comito, D. Falcone, and D. Talia, “Mining human mobility patterns from social geo-tagged data,” Pervasive and Mobile Computing, vol. 33, pp. 91 – 107, 2016. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S1574119216300700
[13] C. Fan, Y. Liu, J. Huang, Z. Rong, and T. Zhou, “Correlation between social proximity and mobility similarity,” Scientific Reports, vol. 7, no. 1, p. 11975, Sep. 2017. [Online]. Available: https://doi.org/10.1038/s41598-017-12274-x
[14] S. Sou, W. Lin, K. Lan, and C. Lin, “Indoor Location Learning Over Wireless Fingerprinting System With Particle Markov Chain Model,” IEEE Access, vol. 7, pp. 8713–8725, 2019.
[15] T. H. Chen, S. I. Sou. and Y. Lee, “Witrack: Human-to-human mobility relationship tracking in indoor environments based on spatio-temporal wireless signal
strength,” in The 17th IEEE International Conference on Pervasive Intelligence and Computing (PICom 2019), Fukuoka, Japan, 2019.
[16] C. Cattuto, W. Van den Broeck, A. Barrat, V. Colizza, J.-F. Pinton, and A. Vespignani, “Dynamics of Person-to-Person Interactions from Distributed 49 RFID Sensor Networks,” PLOS ONE, vol. 5, no. 7, pp. 1–9, 2010. [Online]. Available: https://doi.org/10.1371/journal.pone.0011596
[17] M. Andersson, J. Gudmundsson, P. Laube, and T. Wolle, “Reporting Leaders and Followers among Trajectories of Moving Point Objects,” GeoInformatica, vol. 12, no. 4, pp. 497–528, Dec. 2008. [Online]. Available: https://doi.org/10.1007/s10707-007-0037-9
[18] M. B. Kjærgaard, H. Blunck, M. Wüstenberg, K. Grønbask, M. Wirz, D. Roggen, and G. Tröster, “Time-lag method for detecting following and leadership behavior of pedestrians from mobile sensing data,” in 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom), Mar. 2013, pp. 56–64.
[19] H. Hong, C. Luo, and M. C. Chan, “SocialProbe: Understanding Social Interaction Through Passive WiFi Monitoring,” in Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing,
Networking and Services, ser. MOBIQUITOUS 2016. New York, NY, USA: ACM, 2016, pp. 94–103, event-place: Hiroshima, Japan. [Online]. Available: http://doi.acm.org/10.1145/2994374.2994387
[20] J. Baker and C. Efstratiou, “Next2me: Capturing Social Interactions through Smartphone Devices using WiFi and Audio signals,” in EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous 2017). ACM, Nov. 2017, pp. 412–421. [Online]. Available: https://kar.kent.ac.uk/63969/
[21] H. Du, Z. Yu, F. Yi, Z. Wang, Q. Han, and B. Guo, “Recognition of Group Mobility Level and Group Structure with Mobile Devices,” IEEE Transactions on Mobile Computing, vol. 17, no. 4, pp. 884–897, Apr. 2018.
[22] F. J. Wu and G. Solmaz, “We hear your activities through Wi-Fi signals,” in 2016 IEEE 3rd World Forum on Internet of Things (WF-IoT), 2016, pp. 251–256.
[23] Raspberry pi 3 model b+. [Online]. Available: https://www.raspberrypi.org/products/raspberry-pi-3-model-b-plus/50
[24] Raspbian for raspberry pi. [Online]. Available: https://www.raspberrypi.org/downloads/raspbian/
[25] Welcome to python.org. [Online]. Available: https://www.python.org/
[26] I. Harvey, “Python interface to bluetooth LE on linux. contribute to IanHarvey/bluepy development by creating an account on GitHub,” original-date: 2013-10-19T08:35:00Z. [Online]. Available: https://github.com/IanHarvey/bluepy
[27] Scapy: the python-based interactive packet manipulation program & library. supports python 2 & python 3.: secdev/scapy. Original-date: 2015-10-01T17:06:46Z. [Online]. Available: https://github.com/secdev/scapy
[28] Logging - logging facility for python - python 3.6.8 documentation. [Online]. Available: https://docs.python.org/3.6/library/logging.html
[29] N. Harris, “A simple command line tool for monitoring and logging 802.11 probe frames: nikharris0/probemon,” original-date: 2015-01-09T09:22:18Z. [Online].
Available: https://github.com/nikharris0/probemon
[30] Ubuntu 16.04.5 LTS (xenial xerus). [Online]. Available: http://releases.ubuntu.com/16.04/
[31] C. Y. Yeoh and A. A. A. Rahman, “Implementing 802.11 probe request scanner using WARP platform,” in 2014 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Dec. 2014, pp. 307–311.
[32] A. F. H. III, V. Khanna, G. Tuncay, R. Want, and R. Kravets, “Bluetooth Low Energy in Dense IoT Environments,” IEEE Communications Magazine, vol. 54, no. 12, pp. 30–36, Dec. 2016.
[33] A. Awang and S. Agarwal, “Data aggregation using dynamic selection of aggregation points based on rssi for wireless sensor networks,” Wireless Personal Com-
munications, vol. 80, 01 2014.
[34] R. Anggrainingsih, G. R. Aprianto, and S. W. Sihwi, “Time series forecasting using exponential smoothing to predict the number of website visitor of Sebelas Maret 51 University,” in 2015 2nd International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), Oct. 2015, pp. 14–19.
[35] F. Wu and G. Solmaz, “Are you in the line? RSSI-based queue detection in crowds,” in 2017 IEEE International Conference on Communications (ICC), 2017,
pp. 1–7.
[36] “statsmodels.tsa.api.SimpleExpSmoothing documentation.” [Online]. Available: https://www.statsmodels.org/dev/generated/statsmodels.tsa.holtwinters. SimpleExpSmoothing.html#statsmodels.tsa.holtwinters.SimpleExpSmoothing
[37] “Moving average and exponential smoothing models.” [Online]. Available: http://people.duke.edu/~rnau/411avg.htm
[38] R. W. Schafer, “What Is a Savitzky-Golay Filter? [Lecture Notes],” IEEE Signal Processing Magazine, vol. 28, no. 4, pp. 111–117, Jul. 2011.
[39] Mi global home. [Online]. Available: https://www.mi.com/global/miband2/
[40] Wristband beacon. [Online]. Available: https://blog.aprbrother.com/product/wristband-beacon
[41] WiFi monitor - analyzer of wi-fi networks. [Online]. Available: https://play.google.com/store/apps/details?id=com.signalmonitoring.wifimonitoring
[42] Bluetooth LE tool. [Online]. Available: https://play.google.com/store/apps/details?id=com.michalpolewczak.bluetoothletool