成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	陳盈君 Chen, Ying-Jun
論文名稱：	以智慧型手機感測資料偵測設備間移動關係 Detecting Device-to-Device Mobility Relationship by Smartphone Sensor Data
指導教授：	蘇淑茵 Sou, Sok-Ian
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電腦與通信工程研究所 Institute of Computer & Communication Engineering
論文出版年：	2019
畢業學年度：	107
語文別：	英文
論文頁數：	89
中文關鍵詞：	設備間移動關係、指紋分析定位、無線網路圖型(Wireless Network Pattern) 、運動頻率分布
外文關鍵詞：	D2D mobility relationship, smartphone sensor data, wireless network pattern, proximity detection, fingerprinting, movement frequency distribution
相關次數：	點閱：89 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

本篇論文利用智慧型手機收集Wi-Fi無線訊號以及加速度，透過Wi-Fi無線訊號追蹤巨觀上的移動，加速度訊號分析微觀上的運動，以兩種不同面向分析設備間移動關係。有別於以往利用Wi-Fi無線訊號製作指紋分析定位資料(Fingerprinting)，本篇論文則是用於紀錄移動軌跡，偵測設備與周遭網路橋接器(Access Point)鄰近程度及相對關係，建立無線網路圖型(Wireless Network Pattern)，以降低如指紋分析定位技術需大量資料庫的問題。另一方面，本論文將加速度訊號由時域轉至頻域分析，觀察設備的運動頻率分布，更進一步探討設備是否由同一運動載體所乘載——簡言之，是否由同一個人所攜帶？為了驗證提出的想法，我們設計多種移動策略、配戴位置、實驗場域，在現實生活中進行實驗及分析數據。一般而言，無線網路圖型足以判斷設備間的移動關係，判斷其是否一起行動。而想要更進一步判斷是否為同一人攜帶時，則需要同時考慮設備的運動頻率分布。我們也針對在兩人一起行動的情況下，能否判斷裝置為同一人攜帶的情境進行效能評估，在重複32次實驗後，本篇論文提出的演算法在收集70秒後的資料分析，其準確性、靈敏性及明確性皆高達90%，顯現出偵測設備移動關係的可行性。

Smartphones are pervasively used in all aspects of our daily lives. With ambient sensors in smartphones and massive amount of transmitted wireless signals in our surrounding, detecting device-to-device (D2D) mobility relationship is possible. Accordingly, we propose a novel system, CarryOn, exploiting the smartphone sensor data, to
detect the D2D mobility relationship in the thesis. We employ wireless signals to create the wireless network pattern, tracking the human trajectory by proximity detection rather than fingerprinting. In addition, we extract the accelerations, converting into frequency domain to observe the movement frequency distribution. By the observation of smartphone sensor data, we aim to infer whether the devices are carried by the same person. To evaluate the feasibility of our proposed system, we conduct various experiments in real world and analyze the experimental records offline. In general, comparing the wireless network pattern is sufficient to detect the D2D mobility relationship. However, in the scenario when persons walk forwards together, we need to consider the movement frequency distribution additionally. We also evaluate the system performance in such difficult scenario. By repeating 32 times of the experiment, the accuracy, sensitivity, and specificity can reach around 90% after 70 seconds. It implies that our system is feasible to detect D2D mobility relationship.

Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ix
Introduction 1
Related Work 4
1 Passive Sensing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2 Active Sensing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
3 Crowdsensing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
System Design 6
1 Wireless Signals . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.1 Collecting Phase . . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.2 Processing Phase . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2 Accelerations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.1 Collecting Phase . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.2 Processing Phase . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3 D2D Mobility Relationship Detection Algorithm . . . . . . . . . . . . . 11
Experimental Study - Two Devices 15
1 Basic Experiment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
1.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . 15
1.2 Scripted Experiment . . . . . . . . . . . . . . . . . . . . . . . . 18
1.3 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . 24
2 Effect of Altering Device . . . . . . . . . . . . . . . . . . . . . . . . . . 37
2.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . 37
2.2 Experimental Result . . . . . . . . . . . . . . . . . . . . . . . . 37
3 Effect of Walking Route . . . . . . . . . . . . . . . . . . . . . . . . . . 49
3.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . 49
3.2 Experimental Result . . . . . . . . . . . . . . . . . . . . . . . . 50
4 Effect of Similarity Measurement . . . . . . . . . . . . . . . . . . . . . 61
4.1 Jaccard Index . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61
4.2 Euclidean Distance . . . . . . . . . . . . . . . . . . . . . . . . . 61
4.3 Similarity Measurement Comparison . . . . . . . . . . . . . . . 62
Experimental Study - 4 Devices 73
1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 73
2 Scripted Experiment . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75
3 Experimental Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77
3.1 Network Pattern Similarity . . . . . . . . . . . . . . . . . . . . 77
3.2 Power Spectral Density . . . . . . . . . . . . . . . . . . . . . . . 79
Performance Evaluation 82
Conclusion and Discussion 85
Bibliography 85

                                    

[1] “Gsma intelligence global data,” https://www.gsmaintelligence.com/, accessed:
2019-03-05.
[2] “Current world population,” http://www.worldometers.info/world-population/,
accessed: 2019-03-05.
[3] H. Alemdar and C. Ersoy, “Wireless sensor networks for healthcare: A survey,”
Computer networks, vol. 54, no. 15, pp. 2688–2710, 2010.
[4] M. Hadian, T. Altuwaiyan, X. Liang, B. Sheng, and K. Zhang, “Smarteye: Mobile device proximity monitoring via wireless signal analysis,” in 2019 International Conference on Computing, Networking and Communications (ICNC). IEEE, 2019, pp. 365–369.
[5] K. Wankhede, B. Wukkadada, and V. Nadar, “Just walk-out technology and its challenges: A case of amazon go,” in 2018 International Conference on Inventive Research in Computing Applications (ICIRCA). IEEE, 2018, pp. 254–257.
[6] F. Xu, P. Zhang, and Y. Li, “Context-aware real-time population estimation for metropolis,” in Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. ACM, 2016, pp. 1064–1075.
[7] 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.
[8] S.-I. Sou, W.-H. Lin, K.-C. Lan, and C.-S. Lin, “Indoor location learning over wireless fingerprinting system with particle markov chain model,” IEEE Access,
2019.
[9] G. Solmaz and F.-J. Wu, “Together or alone: Detecting group mobility with wireless fingerprints,” in 2017 IEEE International Conference on Communications (ICC). IEEE, 2017, pp. 1–7.
[10] S. He and K. G. Shin, “Crowd-flow graph construction and identification with spatio-temporal signal feature fusion,” in IEEE INFOCOM 2019-IEEE Conference on Computer Communications. IEEE, 2019, pp. 757–765.
[11] F. Li, C. Zhao, G. Ding, J. Gong, C. Liu, and F. Zhao, “A reliable and accurate indoor localization method using phone inertial sensors,” in Proceedings of the 2012 ACM conference on ubiquitous computing. ACM, 2012, pp. 421–430.
[12] F.-J. Wu, F.-I. Chu, and Y.-C. Tseng, “Cyber-physical handshake,” in ACM SIGCOMM Computer Communication Review, vol. 41, no. 4. ACM, 2011, pp. 472–473.
[13] F.-J. Wu and G. Solmaz, “Are you in the line? rssi-based queue detection in crowds,” in 2017 IEEE International Conference on Communications (ICC).
IEEE, 2017, pp. 1–7.
[14] 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. ACM, 2016, pp. 94–103.
[15] K. Chen and J.-K. Kämäräinen, “Pedestrian density analysis in public scenes with spatiotemporal tensor features,” IEEE Transactions on Intelligent Transportation
Systems, vol. 17, no. 7, pp. 1968–1977, 2016.
[16] 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, 2016.
[17] X. Hu, J. Shang, F. Gu, and Q. Han, “Improving wi-fi indoor positioning via ap sets similarity and semi-supervised affinity propagation clustering,” International
Journal of Distributed Sensor Networks, vol. 11, no. 1, p. 109642, 2015.
[18] P. Sapiezynski, A. Stopczynski, D. K. Wind, J. Leskovec, and S. Lehmann, “Inferring person-to-person proximity using wifi signals,” Proceedings of the ACM on
Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 1, no. 2, p. 24, 2017.
[19] J. Jun, Y. Gu, L. Cheng, B. Lu, J. Sun, T. Zhu, and J. Niu, “Social-loc: Improving indoor localization with social sensing,” in Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems. ACM, 2013, p. 14.
[20] Y. Shu, Z. Li, B. Karlsson, Y. Lin, T. Moscibroda, and K. Shin, “Incrementally-deployable indoor navigation with automatic trace generation,” https://www.microsoft.com/en-us/research/publication/
incrementally-deployable-indoor-navigation-with-automatic-trace-generation/,
April 2019.
[21] R. Sen, Y. Lee, K. Jayarajah, A. Misra, and R. K. Balan, “Grumon: Fast and accurate group monitoring for heterogeneous urban spaces,” in Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems. ACM, 2014, pp. 46–60.
[22] H. Du, Z. Yu, F. Yi, Z. Wang, Q. Han, and B. Guo, “Group mobility classification and structure recognition using mobile devices,” in 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE, 2016, pp. 1–9.
[23] 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, 2018.
[24] J. Fernández, L. Calavia, C. Baladrón, J. Aguiar, B. Carro, A. Sánchez-Esguevillas, J. Alonso-López, and Z. Smilansky, “An intelligent surveillance platform for large metropolitan areas with dense sensor deployment,” Sensors, vol. 13, no. 6, pp. 7414–7442, 2013.
[25] M. Shimosaka, K. Maeda, T. Tsukiji, and K. Tsubouchi, “Forecasting urban dynamics with mobility logs by bilinear poisson regression,” in Proceedings of the 2015 ACM international joint conference on pervasive and ubiquitous computing.
ACM, 2015, pp. 535–546.
[26] “Android open source project - scanresult.java,” https://android.googlesource.
com/platform/frameworks/base/+/refs/heads/master/wifi/java/android/net/
wifi/ScanResult.java, accessed: 2018.
[27] “Android open source project - wifimanager.java,” https://android.googlesource.
com/platform/frameworks/base/+/refs/heads/master/wifi/java/android/net/
wifi/WifiManager.java, accessed: 2018.
[28] R. E. Ziemer and W. H. Tranter, Principles of communications. John Wiley & Sons, 2014.
[29] J. Larsen, “Correlation functions and power spectra,” Section for Cognitive Systems, Informatics and Mathematical Modelling, 2009.
[30] W.-z. Wang, Y.-w. Guo, B.-y. Huang, G.-r. Zhao, B.-q. Liu, and L. Wang, “Analysis of filtering methods for 3d acceleration signals in body sensor network,” in
International Symposium on Bioelectronics and Bioinformations 2011. IEEE, 2011, pp. 263–266.
[31] J. S. Zhang, M. Gartrell, R. Han, Q. Lv, and S. Mishra, “Gevr: An event venue recommendation system for groups of mobile users,” Proceedings of the ACM on
Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 3, no. 1, p. 34, 2019.
[32] T. Segaran, Programming collective intelligence: building smart web 2.0 applications. " O’Reilly Media, Inc.", 2007.

校內：2024-06-18公開
校外：2024-06-18公開

簡易檢索 / 詳目顯示

相關論文