簡易檢索 / 詳目顯示

研究生: 王偲帆
Ssu-Fan Wang
論文名稱: 基於天氣之車速預測系統─使用大數據分析
Weather-Based Traffic Prediction System with Big Data Analysis
指導教授: 賴源正
Yuan-Cheng Lai
口試委員: 林伯慎
Bor-Shen Lin
羅乃維
Nai-Wei Lo
學位類別: 碩士
Master
系所名稱: 管理學院 - 資訊管理系
Department of Information Management
論文出版年: 2016
畢業學年度: 104
語文別: 英文
論文頁數: 29
中文關鍵詞: Hadoop大數據MapReduce決策樹交通預測
外文關鍵詞: MapReduce, Hadoop, Big Data, Decision Tree, Traffic Prediction
相關次數: 點閱:766下載:2
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
  • 提供駕駛人正確、有效率的交通預測資訊以便規劃行車路徑及減少交通壅塞是非常重要的,而隨著道路監視設備的廣泛佈建,許多的交通資料如車速、車流量的取得更加容易,並被使用來做交通預測。

    現存的交通預測方法主要使用歷史交通資料來做預測,然而這些方法有兩個缺點:(1)現存方法並未注重資料量及運算時間;(2)現存方法僅考慮到使用交通資料來做預測,然而天氣是一大影響交通狀況的因素,若未考慮天氣因素可能會產出不盡理想的預測結果。

    本論文提出一套基於天氣之車速預測系統(Weather-Based Traffic Prediction System,WTPS),其使用歷史交通資料及天氣資料來做預測,透過實驗發現,WTPS的預測準確度比沒考慮天氣因素的預測準確度還要好,另外因WTPS是基於大數據分析的技術所設計的,故其延展性也較佳。


    Providing drivers accurate and efficient traffic prediction is very important for their planning routes and reducing traffic congestion. For providing traffic prediction, monitors are deployed in roads to collect such traffic data as vehicle speed or the number of passing vehicles.

    Existing traffic prediction methods mainly use collected historical traffic data to make prediction. However, they have two drawbacks: (1) they did not pay much attention to data volume and computation time; (2) they considered only the traffic data to make prediction. However, weather is a significant factor that affects the traffic condition. Without considering weather, existing methods might produce unsatisfactory prediction results.

    In this thesis, we propose a weather-based traffic prediction system (WTPS) which uses historical traffic data and weather data both to make prediction. Experiments demonstrate the prediction accuracy of WTPS is superior to that without considering weather. WTPS is also scalable for handling huge traffic volume because it is designed based on the technique of big data analysis.

    摘要 I Abstract II Acknowledgment III Contents IV List of Tables V List of Figures VI Chapter 1. Introduction 1 Chapter 2. Related Work 3 2.1. Big Data 3 2.2. Traffic Prediction 5 Chapter 3. Weather-Based Traffic Prediction System 8 3.1. Model Constructing Phase 8 3.2. Traffic Prediction Phase 9 Chapter 4. System Module Implementation 11 4.1. Training Features 11 4.2. C4.5 Based on MapReduce Architecture 13 4.3. JSON Format of Decision Tree 18 4.4. Road Mapping Mechanism 19 Chapter 5. Experimental Results 20 Chapter 6. Conclusions 25 References 26

    [1] S. Boyles, D. Fajardo, and S. T. Waller, “A Naïve Bayesian Classifier for Incident Duration Prediction,” In 86th Annual Meeting of the Transportation Research Board, Washington, DC, 2007.
    [2] M. Bernaś, B. Płaczek, P. Porwik, and T. Pamuła, “Segmentation of Vehicle Detector Data for Improved k-Nearest Neighbours-Based Traffic Flow Prediction,” IET Intelligent Transport Systems, vol. 9, no. 3, pp. 264-274, 2014.
    [3] Y. -S. Jeong, Y. -J. Byon, M. M. Castro-Neto, and S. M. Easa, “Supervised Weighting-Online Learning Algorithm for Short-Term Traffic Flow Prediction,” IEEE Transactions on Intelligent Transportation Systems, vol. 14, no. 4, pp. 1700-1707, 2013.
    [4] Y. Lv, Y. Duan, W. Kang, Z. Li, and F. -Y. Wang, “Traffic Flow Prediction With Big Data: A Deep Learning Approach,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 2, pp. 865-873, 2015.
    [5] B. Pan, U. Demiryurek, and C. Shahabi, “Utilizing Real-World Transportation Data for Accurate Traffic Prediction,” 2012 IEEE 12th International Conference on Data Mining (ICDM), pp. 595-604, 2012.
    [6] H. -C. Chang, “Exploiting Traffic Patterns for Real-time Traffic Prediction and Vehicle Routing,” Unpublished Master Dissertation, The Department of Computer Science of The National Tsing-Hua University, 2013.
    [7] Autoregressive integrated moving average. [Online]. Available: http://en.wikipedia.org/wiki/Autoregressive_integrated_moving_average
    [8] S. Jeon, B. Hong, and B. Kim, “Big Data Processing for Prediction of Traffic Time Based on Vertical Data Arrangement,” 2014 IEEE 6th International Conference on Cloud Computing Technology and Science, pp. 326-333, 2014.
    [9] B. Pan, U. Demiryurek, C. Shahabi, and C. Gupta, “Forecasting Spatiotemporal Impact of Traffic Incidents on Road Networks,” 2013 IEEE 13th International Conference on Data Mining (ICDM), pp. 587-596, 2013.
    [10] T. L. Pan, A. Sumalee, R. X. Zhong, and N. Indra-Payoong, “Short-Term Traffic State Prediction Based on Temporal–Spatial Correlation,” IEEE Transactions on Intelligent Transportation Systems, vol. 14, no. 3, pp. 1242-1254, 2013.
    [11] J. Xu, D. Deng, U. Demiryurek, C. Shahabi, and M. v. d. Schaar, “Mining the Situation: Spatiotemporal Traffic Prediction With Big Data,” IEEE Journal of Selected Topics in Signal Processing, vol. 9, no. 4, pp. 702-715, 2015
    [12] Y. Xu, Q. -J. Kong, R. Klette, and Y. Liu, “Accurate and Interpretable Bayesian MARS for Traffic Flow Prediction,” IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 6, pp. 2457-2469, 2014.
    [13] J. R. Quinlan, “C4.5: Programs for Machine Learning,” California: Morgan Kaufmann, 2014.
    [14] J. R. Quinlan, “Improved Use of Continuous Attributes in C4.5,” Journal of Artificial Intelligence Research, pp. 77-90, 1996.
    [15] W. Dai, and W. Ji, “A MapReduce Implementation of C4.5 Decision Tree Algorithm,” International Journal of Database Theory and Application, vol. 7, no. 1, pp. 49-60, 2014.
    [16] J. Dean, and S. Ghemawat, “MapReduce: Simplified Data Processing on Large Clusters,” Communications of the ACM, vol. 51, no. 1, pp. 107-113, 2008.
    [17] S. Sagiroglu, and D. Sinanc, “Big Data: A Review,” 2013 International Conference on Collaboration Technologies and Systems (CTS), pp. 42-47, 2013.
    [18] A. Katal, M. Wazid, and R H Goudar, “Big Data Issues, Challenges, Tools and Good Practices,” 2013 Sixth International Conference on Contemporary Computing (IC3), pp. 404-409, 2013.
    [19] S. Sharma, and V. Mangat, “Technology and Trends to Handle Big Data: Survey,” 2015 Fifth International Conference on Advanced Computing & Communication Technologies (ACCT), pp. 266-271, 2015.
    [20] Big data. [Online]. Available: https://en.wikipedia.org/wiki/Big_data
    [21] H. Hu, Y. Wen, T. -S. Chua, and X. Li, “Toward Scalable Systems for Big Data Analytics: A Technology Tutorial,” IEEE Access, vol. 2, pp. 652-687, 2014.
    [22] S. Sagiroglu, and D. Sinanc, “Big Data: A Review,” 2013 International Conference on Collaboration Technologies and Systems (CTS), pp. 42-47, 2013.
    [23] A. Katal, M. Wazid, and R H Goudar, “Big Data Issues, Challenges, Tools and Good Practices,” 2013 Sixth International Conference on Contemporary Computing (IC3), pp. 404-409, 2013.
    [24] Welcome to Apache Hadoop. [Online]. Available: https://hadoop.apache.org/
    [25] Hadoop. [Online]. Available: http://www.inside.com.tw/2015/03/12/big-data-4-hadoop
    [26] Apache Hadoop. [Online]. Available: https://zh.wikipedia.org/wiki/Apache_Hadoop
    [27] Rainfall Classification. [Online]. Available: http://www.cwb.gov.tw/V7/knowledge/faq/rainfaq.htm
    [28] Taipei City ATIS Web. [Online]. Available: http://its.taipei.gov.tw/atis_index/mapviewer.aspx?Lang=ENG
    [29] Taipei City Traffic Engineering Office Traffic Control Center. [Online]. Available: http://tms.bote.taipei.gov.tw/ttc2/main.jsp?lang=en

    無法下載圖示 全文公開日期 2021/01/18 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)
    全文公開日期 本全文未授權公開 (國家圖書館:臺灣博碩士論文系統)
    QR CODE