中大機構典藏-NCU Institutional Repository-提供博碩士論文、考古題、期刊論文、研究計畫等下載:Item 987654321/54374
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 80990/80990 (100%)
Visitors : 42573177      Online Users : 1708
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/987654321/54374


    Title: 利用時間延遲分類器應用於免攜帶式定位之研究;A Device-free Localization System with Tapped Delay Line classifiers
    Authors: 李奕承;LEE,YIH-CHERNG
    Contributors: 通訊工程研究所
    Keywords: 免(非)攜帶式定位;時間延遲器(等化器);支持向量機;Device free localization;support vector machine;tapped delay line
    Date: 2012-07-25
    Issue Date: 2012-09-11 18:49:30 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 在廣泛的佈建無線設備下,藉由日漸普及手機或感測器促進了許多關於定位系統上的成功。本篇論文的核心是在802.11無線區域網路下,針對非攜帶式定位提出了一個特別的系統。關於非攜帶式系統主要是在強調如何去偵測人或物體的位置即使是身上沒有攜帶任何無線裝置[1]。提出的系統是藉由觀察從無線網路基地台(AP)發送訊號強度源(RSS)的定位研究。RSS訊號強度源將會被收集以及用於定位被追蹤物體的位置。為了判斷物體的位置,我們引用了整合性分類器,包含著名SVM和機率Bayesian分類器。除此之外,我們也提出了時間延遲器架構,來降低誤差跟錯誤藉此提高正確率。並且在平均約1.3 公尺距離內和10延遲預測步,我們利用四台AP提出的系統可以達到非常高的準確率:90.6%,而且當我們再拉高到20延遲預測步,分類準確率更進一次的達到94.3%。本篇提出的論文達到了令人訝異的成果: 高成功率、快速,便宜,可操作性應用在實際的無線區域網路環境中。而且在不需要額外的硬體設施也指出我們的系統能夠更有效率的利用於在現有廣大的設備之中。Wireless networks are ubiquitous now. It promotes the subject of location technology by the cell-phone or sensor. This paper proposes a special system for device-free localization over IEEE 802.11 wireless local area network (WLAN).This area of research emphasizes that a person does not need to carry a wireless device to be detected and located.Our system is to analyze the received signal strength (RSS) transmitted from access points (APs). RSS signals will be collected and used for locating the tracked subject. To identify the location of the subject, this work adopts an ensemble of classifiers, which contains the support vector machine (SVM) and the Bayesian classifier. Moreover, this work incorporates the classifiers with the tapped delay line (TDL) architecture to verify the decision made by the classifiers at different time unit. Within 1.3 meters distance error and 10 taps, the proposed framework achieves a high precision rate of 90.6% using four access points. The precision rate further increases of 94.3% by considering 20 taps.The characteristics of the proposed system are highly successful, fast, cheap, and can be applied to any established WLAN environment now. Therefore, by inexpensive equipment, it also indicates our system can be widely used for many real applications.
    Appears in Collections:[Graduate Institute of Communication Engineering] Electronic Thesis & Dissertation

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML606View/Open


    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 ©   - 隱私權政策聲明