English  |  正體中文  |  简体中文  |  Items with full text/Total items : 73032/73032 (100%)
Visitors : 23248639      Online Users : 396
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version

    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/68991

    Title: 基於大數據的高速公路即時路況壅塞預測;Big Data Based Congestion Prediction for Real-time Highway Traffic
    Authors: 薛人豪;Hao,Hsueh Jen
    Contributors: 資訊工程學系
    Keywords: 大數據;模糊理論;即時串流資料;支援向量機
    Date: 2015-08-28
    Issue Date: 2015-09-23 14:52:28 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 隨著資訊科技的快速發展,數以萬計的資料在分秒中產生,如何應付這樣大量又迅速的資料即是大數據領域中研究的重點。在智慧型運輸系統中車輛提供了大量的資訊,若可以即時收集並分析車輛資訊並且避免掉塞車的路段便可以大大提升智慧型運輸系統的穩定性。本論文透過Apache Storm即時接收高速公路局提供的汽車偵測器資料進行即時運算,將路段時速、路段密度、路段車流量及目前路段的降雨量利用模糊理論進行評估,得出各個路段的用路等級。本論文也收集警察廣播電台的用路人及時回報資訊進行路段分析,透過用路人回報事件的位置對應高公局的車輛偵測器位置,取得事件發生時的道路資訊。另外採用支援向量機來進行下個時段的路段時速預測,透過支援向量機可以將過去的路段時速當作訓練資料輸入並且得到訓練模型,預測出下個時間點的行車時速。
    本文基於Apache Storm的架構下,提出即時收集來自高公局、氣象局及警察廣播電台開放資料的方法,將不同來源及格式的開放資料進行整合。並且利用模糊理論來分析出目前高速公路壅塞的程度,再利用SVM進行下個時間點的時速預測。本文所提出的SRHTCP(SVM based Real-time Highway Traffic Congestion Prediction)預測方法在MARE的比較下比WEMA(Weighted Exponential Moving Average)提升了25.6%的準確度。
    ;With the rapid development of information technology, tens of thousands of data generated in minutes and seconds, how to deal with such large amounts of data is the focus of research in big data. Vehicle provides a large of information in the Intelligent Transportation System. If all information can collect and analyze in real-time and find the traffic jam road section, the stability of the intelligent transportation system can greatly enhance. In this paper we use Apache Storm to collect and analyze traffic data provided by Taiwan Area National Freeway Bureau in real-time, and take road speed, road density, road traffic volume and rainfall value of road section as input of fuzzy theory, obtained with traffic level of the road section. This paper collect traffic event reported by road user in real-time from Police Broadcasting Service, and get the traffic data corresponding to the position of vehicle detector. In addition, this paper use support vector machine to predict road speed of next period, support vector machine use history road speed data to train and get training model, to predict traffic speed of the next period.
    This paper based on the Apache Storm architecture, propose real-time collection method to get different sources and formats data from Taiwan Area National Freeway Bureau, Police Broadcasting Service and Central Weather Bureau. Use fuzzy theory to analyze the current condition of highway, and use SVM to predict speed in next period. SRHTCP(SVM based Real-time Highway Traffic Congestion Prediction) mechanism proposed in this paper prediction method than WEMA (Weighted Exponential Moving Average) improved 25.6% accuracy.
    Appears in Collections:[資訊工程研究所] 博碩士論文

    Files in This Item:

    File Description SizeFormat

    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback  - 隱私權政策聲明