簡易檢索 / 詳目顯示

回結果列表
研究生： 范雲瀚
Fan, Yun-Han
論文名稱： 以智慧車輛探測達成時空無縫隙之交通資料蒐集框架
A Spatiotemporal Seamless Traffic Information Collection Framework by Intelligent Vehicle Probing
指導教授： 李威勳
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： 2017
畢業學年度： 105
語文別： 中文
論文頁數： 105
中文關鍵詞： 智慧車輛探測 、車路聯網 、車載資通訊 、時空無縫隙的資料蒐集
外文關鍵詞： Intelligent Vehicle Probing, Spatiotemporal Seamless Data Collection, Intelligent Traffic Beacon
相關次數： 點閱：123  下載：11 
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

    • 交通資料的蒐集是個不斷在進化的技術，現今除了資訊的正確性還強調資訊的時空無縫隙，近年來有種使用無線通訊的交通蒐集技術，稱為智慧型車輛探測(Intelligent Vehicle Probing, IVP)，該技術具有時空無縫隙、低成本、雙向溝通等特性，是個具有潛力的資料源，但IVP在資料蒐集上會遇到一些問題，分別是一車多機、運具分類、車道判斷三個問題，本研究將解決此三個問題並研發新型的交通蒐集技術。

    本研究提出階層式的智慧型交通資訊蒐集框架，稱為IVP交通資訊框架(IVP-based Traffic Information Framework, ITIF)，此框架由行動裝置端、路側端及雲端組成，經由演算法串連各部分的資訊，並透過雙向溝通、分散式運算、正確率累積等概念達成時空無縫隙的交通資訊提供。ITIF包含開發新型的資料蒐集儀器，稱為智慧交通信標(Intelligent Traffic Beacon, ITB)，具有掃描和運算的功能，可在資料蒐集的階段透過演算法、佈設位置、ITB間的資料交換等做法，解決一車多機、運具分類、車道判斷的問題。

    本研究以實地測試的方式，蒐集藍芽和Wi-Fi的資料，再使用演算法解決三大問題，其結果顯示藍牙在主動回報的情況下具有良好的資料蒐集率，經由演算法運算可產生正確的結果，非主動回報的情況下則需要放寬演算法的限制才能達到較好的結果，而資料的正確性和ITB的數量呈現正相關，Wi-Fi則會面臨跳頻的問題而無法順利蒐集資料，殘缺的資料經由演算法運算無法得到較好的結果，以此實驗結果可推算藍牙技術較有機會達成時空無縫隙的資料蒐集。

    The idea of two-way communication or one-way sniffing by wireless communication scheme (e.g. Wi-Fi or Bluetooth) between road side units and mobile devices can be applied to traffic information collection. Similar to traditional GPS-based vehicle probing (GVP) or ETC-based vehicle probing (EVP), the proposed traffic data collection scheme is named as intelligent vehicle probing (IVP). IVP has some advantages like spatiotemporal seamless, low cost, high penetration rate, and two-way communication, however, there exists three issues to conquer, which are the multiple device in a vehicle problem (MDP), the transportation mode problem (TMP), and the location identification problem (LIP).
    In this research, an IVP-based traffic information framework (ITIF) is proposed and several algorithms are designed and implemented solve these issues. A new equipment named intelligent traffic beacon(ITB) is designed and implemented in the proposed ITIF, which can sniff or communicate with the mobile devices via Wi-Fi or Bluetooth communication scheme, and the designed algorithms are executed to analyze the communication raw data in ITB to solve the three problems.
    Two experiments are designed to evaluate the accuracy of the proposed IVP. The results show Bluetooth performs better than Wi-Fi communication scheme in all three issues. It may due to the hopping channel issue of Wi-Fi communication scheme. In future, ITB can combine with other data source to achieve the spatiotemporal seamless data collection.

    摘要 I 目錄 VIII 圖目錄 XI 表目錄 XII 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機 7 1.3 研究目的 10 1.4 研究流程 12 第二章 文獻回顧 14 2.1 智慧車輛探測(IVP) 14 2.1.1 相關技術 – 資訊傳遞 16 2.1.2 相關技術 – 定位 16 2.2 智慧車輛探測之相關研究 17 2.3 運具模式的分類 20 2.4 小結 21 第三章 智慧車輛探測之交通資訊框架 23 3.1 問題分析 23 3.1.1 一車多機 23 3.1.2 運具分類 25 3.1.3 車道判斷 27 3.2 系統架構 29 3.2.1 IVP APP 30 3.2.2 ITB 30 3.2.3 IVP cloud 33 3.2.4 框架的軟硬體配置 33 3.3 ITB交通資訊產生的Ontology 35 3.4 應用場域和研究假設 39 3.4.1 應用場域簡介 39 3.4.2 研究假設 40 3.4.3 ITB佈設方式 42 3.5 演算法說明 43 3.5.1 Notations 43 3.5.2 演算法一：車道分類 44 3.5.3 演算法二：資料分群 47 3.5.4 演算法三：未知裝置判斷 50 3.5.5 演算法四：速度計算 54 3.5.6 演算法五：車道存在機率計算 55 3.5.7 演算法六：分群比對 56 3.5.8 演算法七：最大速度判別和相似度辨識 57 3.5.9 小結 58 第四章 實驗設計和結果 60 4.1 實驗設計 60 4.1.1 應用場景、假設條件與實驗限制 61 4.1.2 實驗參數設置 63 4.2 實驗結果 66 4.2.1 實驗一 67 4.2.2 實驗二 69 4.3 實驗分析 – 運具速度 72 4.3.1 實驗一運具速度 72 4.3.2 實驗二運具速度 75 4.4 實驗分析 – 跳頻 77 4.5 實驗分析 – 藍牙主動回報和非主動回報的比較 77 4.6 小結 79 第五章 結論與未來研究 81 5.1 結論 81 5.2 未來研究 82 參考文獻 84 附錄一 實驗一之原始資料 87 附錄二 實驗二之原始資料 91 附錄三 本研究和其他研究的速度準確率比較 95 附錄四 口試委員的問題及回應 96

    1. Abedi, N., Bhaskar, A., Chung, E., & Miska, M. Assessment of antenna characteristic effects on pedestrian and cyclists travel-time estimation based on Bluetooth and Wi-Fi MAC addresses. Transportation Research Part C: Emerging Technologies, 60, 124-141, 2015.
    2. Abbott-Jard, M., Shah, H., & Bhaskar, A. Empirical evaluation of Bluetooth and Wi-Fi scanning for road transport. In Australasian Transport Research Forum (ATRF), 36th, 2013, Brisbane, Queensland, Australia (p. 14), 2013.
    3. Araghi, B. N., Hammershøj Olesen, J., Krishnan, R., Tørholm Christensen, L., & Lahrmann, H. Reliability of bluetooth technology for travel time estimation. Journal of Intelligent Transportation Systems, 19(3), 240-255, 2015.
    4. Araghi, B. N., Christensen, L. T., Krishnan, R., & Lahrmann, H. Application of Bluetooth technology for mode-specific travel time estimation on arterial roads: Potentials and challenges. In Proceedings from the Annual Transport Conference at Aalborg University.
    5. Ansari, S., Rajeev, S.G., Chandrashekar, H.S., Packet sniffing: a brief introduction. IEEE Potentials 21(5), 17-19, 2002.
    6. Bhaskar, A., Qu, M., Nantes, A., Miska, M., & Chung, E. Is bus overrepresented in Bluetooth MAC scanner data? Is MAC-ID really unique?. International Journal of Intelligent Transportation Systems Research, 13(2), 119-130, 2015.
    7. Díaz, J. J. V., González, A. B. R., & Wilby, M. R. Bluetooth Traffic Monitoring Systems for Travel Time Estimation on Freeways. IEEE Transactions on Intelligent Transportation Systems, 17(1), 123-132, 2016.
    8. Friesen, M., Jacob, R., Grestoni, P., Mailey, T., & McLeod, R. D. Vehicular traffic monitoring using Bluetooth. In Electrical and Computer Engineering (CCECE), 2013 26th Annual IEEE Canadian Conference on (pp. 1-6), 2013.
    9. Haghani, A., Hamedi, M., Sadabadi, K., Young, S., & Tarnoff, P. Data collection of freeway travel time ground truth with bluetooth sensors. Transportation Research Record: Journal of the Transportation Research Board, (2160), 60-68, 2010.
    10. Kieu, L.M., Bhaskar, A., Chung, E., Bus and car travel time on urban networks : integrating Bluetooth and bus vehicle identification data, 25th ARRB Conference : Shaping the future: Linking Policy, Research and Outcomes, Perth, WA, 2012.
    11. Laharotte, P. A., Billot, R., Come, E., Oukhellou, L., Nantes, A., & El Faouzi, N. E. Spatiotemporal analysis of bluetooth data: application to a large urban network. IEEE Transactions on Intelligent Transportation Systems, 16(3), 1439-1448, 2015.
    12. Lin, C.R., Gerla, M., Adaptive clustering for mobile wireless networks. IEEE Journal on Selected Areas in Communications 15(7), 1265-1275, 1997.
    13. Malinovskiy, Y., Wu, Y. J., Wang, Y., & Lee, U. K. Field experiments on bluetooth-based travel time data collection. In Transportation Research Board 89th Annual Meeting (No. 10-3134), 2010.
    14. Ryeng, E.O., Haugen, T., Grønlund, H., Overå, S.B. Evaluating Bluetooth and Wi-Fi Sensors as a Tool for Collecting Bicycle Speed at Varying Gradients. Transportation Research Procedia 14, 2289-2296, 2016
    15. Shafique, M. A., & Hato, E. Use of acceleration data for transportation mode prediction. Transportation, 42(1), 163-188, 2015.
    16. Salem, A., Nadeem, T., Cetin, M., & El-Tawab, S. Driveblue: Traffic incident prediction through single site bluetooth. In Intelligent Transportation Systems (ITSC), 2015 IEEE 18th International Conference on (pp. 725-730), 2015.
    17. Wang, H., Calabrese, F., Di Lorenzo, G., & Ratti, C. Transportation mode inference from anonymized and aggregated mobile phone call detail records. In Intelligent Transportation Systems (ITSC), 2010 13th International IEEE Conference on (pp. 318-323), 2010.
    18. Wasson, J. S., P.E., Sturdevant, J. R., P.E., & Bullock, D. M., P.E. Real-time travel time estimates using media access control address matching. Institute of Transportation Engineers.ITE Journal, 78(6), 20-23, 2008.
    19. Yassin, M., Rachid, E., Nasrallah, R. Performance comparison of positioning techniques in Wi-Fi networks. In: 2014 10th International Conference on Innovations in Information Technology (IIT), 75-79, 2014.

    下載圖示 校內：2022-09-01公開
    校外：2022-09-01公開
    QR CODE