簡易檢索 / 詳目顯示

回結果列表
研究生： 梁騰駿
Liang, Teng-Jyun
論文名稱： 以機器學習進行無線嗅探技術之交通資料分析
Applying Machine Learning to Analyze Vehicular Traffic Information Collected by Wireless Sniffing Technique
指導教授： 李威勲
Lee, Wei-Hsun
學位類別： 碩士
Master
系所名稱： 管理學院 - 交通管理科學系
Department of Transportation and Communication Management Science
論文出版年： 2019
畢業學年度： 107
語文別： 英文
論文頁數： 76
中文關鍵詞： 無線嗅探技術 、車路聯網 、機器學習 、車流 、車道 、交通模式
外文關鍵詞： wireless sniff, machine learning, transportation modes, traffic flow, V2R
相關次數： 點閱：83  下載：1 
分享至:
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

    • 在交通資料的蒐集上，現有之常見的方式和來源多為使用車輛偵測器、自
    動車輛辨識系統、GPS 定位資訊……等，然，各種交通資料源無論在蒐集或是應用上皆有其缺點，因此，開發多元的交通資料蒐集方式成了不可或缺的一步。而隨著時代及科技的發展，近年由於行動裝置及車機等智慧裝置的普及，人們使用Wi-Fi 上網及藍牙資料傳輸的機會亦大幅增加，特別是當行駛車輛內之手機或車載機發出Wi-Fi 或藍牙(Bluetooth, BT)等無線訊號時，因為訊號的時空變化而產生出隱含的交通訊息，值得做更進一步的探討。
    於范雲瀚(2017)的「以智慧車輛探測達成時空無縫隙之交通資料蒐集框架」研究中，其提出使用上述無線訊號作為交通資料源會遇到的三大問題，分別為車道判斷、運具分類及一車多機，該研究在高速公路長隧道的應用場域下，提出七個啟發式演算法以解決上述三大問題。本研究基於前述之研究，以支援向量機(Support Vector Machine, SVM)、最近鄰近法(K Nearst Neighbor, KNN)及近鄰傳播演算法(Affinity Propagation, AP)等機器學習演算法，搭配不同的偵測器佈設型態(X 形/長方形/菱形)，在一般路段的應用場域下，對三大問題做更進一步的延伸，包含在車道判斷增加變換車道之情形、運具分類上增加車種、車流
    量在複雜場域下之估算等，並改良及擴大實驗規模，對三大問題有更深入的探討並解決之。
    關於本研究之結果，在車道判斷上，藍牙資料的表現優於Wi-Fi 資料，而在ITB 布設上，X 形與長方形之結果相近，菱形的結果較不定，在固定車道的判斷下大致有80%準確度；運具分類的部分，X 形與長方形佈設在藍牙資料的表現下皆優於Wi-Fi，皆達到98%準確度，菱形則為Wi-Fi 資料較優，三個佈設型態分別配上兩資料源皆達到92%以上之準確度；在一車多機問題上，兩車在一前一後的行駛關係下，藍牙資料搭配X 形佈設之表現較佳也最為穩定。

    In the collection of traffic data, the most common techniques are the use of vehicle detectors, automatic vehicle identification systems, GPS positioning information, etc. However, each technique has their own disadvantages. Therefore,the development of techniques for collecting traffic data has become indispensable.Due to the popularity of mobile devices such as smartphones in recent years, the use of Wi-Fi Internet and Bluetooth (BT) transmission has increased significantly,especially when smartphones or in-vehicle devices broadcast Wi-Fi or BT signals.It’s worth discussing since the variations of signals with time and space produce some implied traffic information.
    In Fan (2017), the three major problems, the lane identification problem (LIP),the transportation mode problem (TMP) and the multiple devices problem (MDP) are
    proposed and solved preliminary by seven heuristic algorithms in the scenario of freeway tunnels. In this study, with different ITB topologies (type X, type Rectangle and Type Diamond) in the scenario of road sections and collecting data via two communication technologies (BT and Wi-Fi), the classification and clustering accuracy of three problems predicted by three machine learning models, SVM, KNN and Affinity Propagation, will be presented respectively. For the results in this study, in LIP, the performance of BT is better than that of Wi-Fi ; In terms of the topologies, the performances of type X and type Rectangle are similar, and that of type Diamond is irregular. In TMP, type X and type Rectangle with BT data perform the best, and the accuracies of three topologies with BT and Wi-Fi are above 92%. In MDP, the scenario of two cars in tandem with type X and BT performs the best.

    ABSTRACT I 摘要 II ACKNOWLEDGEMENTS III LIST of FIGURES VII LIST of TABLES IX Chapter1 Introduction 1 1.1 Background 1 1.1.1 Common ways to collect traffic information 1 1.1.2 Wireless sniffing technique 2 1.1.3 Artificial intelligence and machine learning 4 1.1.4 The previous research 5 1.2 Motivation 7 1.3 Goal 8 1.4 Study Process 10 Chapter2 Literature Review 12 2.1 Human Flow Detection 12 2.2 Traffic Flow Detection 14 2.3 Conclusion 17 Chapter3 Traffic Information Collected by Wireless Sniffing Technique 20 3.1 Lane Identification Problem (LIP) 20 3.1.1 Description of LIP 20 3.1.2 The Solution of LIP 20 3.1.3 SVM 23 3.1.4 K-fold Cross Validation 25 3.2 Transportation Mode Problem (TMP) 26 3.2.1 Description of TMP 26 3.2.2 The Solution of TMP 26 3.2.3 KNN 29 3.3 Multiple Devices Problem (MDP) 30 3.3.1 Description of MDP 30 3.3.2 The Solution of MDP 30 3.3.3 Affinity Propagation 31 3.4 Research Scenario and Assumptions 32 3.4.1 Introduction of the research scenario 32 3.4.2 Research Assumptions 33 3.4.3 Topologies of ITB 34 3.5 System 35 3.5.1 Framework 35 3.5.2 Hardware of ITB 37 3.5.3 Software 38 Chapter4 Experiments and Discussions 39 4.1 LIP 39 4.1.1 Experiments 39 4.1.2 Results 43 4.1.3 Discussion 55 4.2 TMP 57 4.2.1 Experiments 57 4.2.2 Results 59 4.2.3 Discussion 65 4.3 MDP 66 4.3.1 Experiments 66 4.3.2 Results 67 4.3.3 Discussion 69 Chapter5 Conclusion and Future Works 72 5.1 Conclusion 72 5.2 Future Works and Suggestions 74 Reference 75

    1. 范雲瀚 (2017). 以智慧車輛探測達成時空無隙縫之交通資料蒐集框架.國立成功大學交通管理科學研究所學位論文, p.1-p.86.
    2. Alessandrini, A., Gioia, C., Sermi, F., Sofos, I., Tarchi, D., & Vespe, M. (2017, May). WiFi positioning and Big Data to monitor flows of people on a wide scale. In Navigation Conference (ENC), 2017 European(pp. 322-328). IEEE.
    3. Aliari, Y., & Haghani, A. (2012). BT sensor data and ground truth testing of reported travel times. Transportation Research Record: Journal of the Transportation Research Board, 2308, 167–172. doi:10.3141/2308-18.
    4. Carvalho, E., Ferreira, B. V., Ferreira, J., de Souza, C., Carvalho, H. V., Suhara, Y., ... & Pessin, G. (2017, May). Exploiting the use of recurrent neural networks for driver behavior profiling. In Neural Networks (IJCNN), 2017 International Joint Conference on (pp. 3016-3021). IEEE.
    5. Cortés, C. E., Gibson, J., Gschwender, A., Munizaga, M., & Zúñiga, M. (2011). Commercial bus speed diagnosis based on GPS-monitored data. Transportation Research Part C: Emerging Technologies, 19(4), 695-707.
    6. Dabiri, S., & Heaslip, K. (2018). Inferring transportation modes from GPS trajectories using a convolutional neural network. Transportation research part C: emerging technologies, 86, 360-371.
    7. Ding, F., Chen, X., He, S., Shou, G., Zhang, Z., & Zhou, Y. (2019). Evaluation of a Wi-Fi signal based system for freeway traffic states monitoring: an exploratory field test. Sensors, 19(2), 409.
    8. Du, Y., Yue, J., Ji, Y., & Sun, L. (2017). Exploration of optimal Wi-Fi probes layout and estimation model of real-time pedestrian volume detection. International Journal of Distributed Sensor Networks, 13(11), 1550147717741857.
    9. Dunlap, M., Li, Z., Henrickson, K., & Wang, Y. (2016). Estimation of origin and destination information from BT and Wi-Fi sensing for transit. Transportation Research Record: Journal of the Transportation Research Board, (2595), 11-17.
    10. El-Tawab, S., Oram, R., Garcia, M., Johns, C., & Park, B. B. (2017, March). Data analysis of transit systems using low-cost IoT technology. In Pervasive Computing and Communications Workshops (PERCOM Workshops), 2017 IEEE International Conference on (pp. 497-502). IEEE.
    11. Fang, S. H., Liao, H. H., Fei, Y. X., Chen, K. H., Huang, J. W., Lu, Y. D., & Tsao, Y. (2016). Transportation modes classification using sensors on smartphones. Sensors, 16(8), 1324.
    12. Friesen, M., Jacob, R., Grestoni, P., Mailey, T., & McLeod, R. D. (2013, May). Vehicular traffic monitoring using BT. In Electrical and Computer Engineering (CCECE), 2013 26th Annual IEEE Canadian Conference on (pp. 1-6). IEEE.
    13. Goodall, N. J. (2016). Fundamental characteristics of Wi Fi and wireless local area network re-identification for transportation. IET Intelligent Transport Systems, 11(1), 37-43.
    14. Jahangiri, A., & Rakha, H. A. (2015). Applying Machine Learning Techniques to Transportation Mode Recognition Using Mobile Phone Sensor Data. IEEE Trans. Intelligent Transportation Systems, 16(5), 2406-2417.
    15. Jiang, M., Fan, X., Zhang, F., Xu, C., Mao, H., & Liu, R. (2016, November). Characterizing On-Bus WiFi Passenger Behaviors by Approximate Search and Cluster Analysis. In 2016 7th International Conference on Cloud Computing and Big Data (CCBD) (pp. 31-36). IEEE.
    16. Kim, Z. (2008). Robust lane detection and tracking in challenging scenarios.
    17. Kurkcu, A., & Ozbay, K. (2017). Estimating Pedestrian Densities, Wait Times, and Flows with Wi-Fi and BT Sensors. Transportation Research Record: Journal of the Transportation Research Board, (2644), 72-82.
    18. Li, J., Mei, X., Prokhorov, D., & Tao, D. (2017). Deep neural network for structural prediction and lane detection in traffic scene. IEEE transactions on neural networks and learning systems, 28(3), 690-703.
    19. Mikkelsen, L., Buchakchiev, R., Madsen, T., & Schwefel, H. P. (2016, September). Public transport occupancy estimation using WLAN probing. In Resilient Networks Design and Modeling (RNDM), 2016 8th International Workshop on (pp. 302-308). IEEE.
    20. Oransirikul, T., Nishide, R., Piumarta, I., & Takada, H. (2016, March). Feasibility of analyzing Wi-Fi activity to estimate transit passenger population. In Advanced Information Networking and Applications (AINA), 2016 IEEE 30th International Conference on(pp. 362-369). IEEE.
    21. Simoncini, Matteo, et al. "Vehicle classification from low-frequency GPS data with recurrent neural networks." Transportation Research Part C: Emerging Technologies 91 (2018): 176-191.
    22. Won, M., Zhang, S., & Son, S. H. (2017, July). WiTraffic: low-cost and non-intrusive traffic monitoring system using WiFi. In Computer Communication and Networks (ICCCN), 2017 26th International Conference on (pp. 1-9). IEEE.
    23. Yang, C., & Shao, H. R. (2015). WiFi-based indoor positioning. IEEE Communications Magazine, 53(3), 150-157.
    24. Yang, S., & Wu, Y. J. (2018). Travel mode identification using BT technology. Journal of Intelligent Transportation Systems, 22(5), 407-421.

    無法下載圖示 校內：2024-08-27公開
    校外：不公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE