Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66562
Title: | 都會範圍Wi-Fi定位準確度分析與改進之研究 Accuracy Analyses and Improvements on Metropolitan-Scale Wi-Fi Localization |
Authors: | Wen (Arvin) Tsui 崔文 |
Advisor: | 朱浩華 |
Keyword: | Wi-Fi定位技術,訊號特徵定位法,都會區定位技術,訊號地圖,駕車收訊,步行收訊,行人定位技術, Wi-Fi localization,Fingerprint-based localization,metropolitan localization,radio maps,war driving,war walking,pedestrian localization, |
Publication Year : | 2012 |
Degree: | 博士 |
Abstract: | Wi-Fi訊號特徵定位法(fingerprint localization)之準確度與訊號地圖(radio map)的品質息息相關。本論文分析了多個都會區訊號地圖可能影響定位準確度的因素。在我們的研究中分別以步行與駕車的方式大規模地收集了都會範圍的訊號地圖,其中包括了數十萬個Wi-Fi基地台以及數以百萬計的訊號樣本。藉由對步行與駕車收集的訊號地圖所進行的深入分析與比較,我們找到了許多影響定位準確度的關鍵因素,在得知這些因素的影響程度後,根據這些分析結果設計了有效的改善方法。此外,硬體裝置的差異也是影響Wi-Fi定位的重要因素,雖然可以藉由手動調整來改善,但因為裝置不斷推陳出新而無法大量實做,我們提出了非人力介入 (unsu-pervised) 的自動演算法來解決這個問題,實驗結果顯示,自動演算學習的過程只需不到100秒即可收斂。我們更進一步根據定位信心度指標設計了混和型的行人定位系統,使得定位準確度的中位數可以達到十公尺以內,對GPS在都市叢林中準度下降的情形 (urban canyon problem) 提供了良好的輔助效果。這是藉由整合Wi-Fi定位系統以及手機上的加速感應器與電子羅盤所達成,這個系統的最終準確度達到中位數8.6公尺的水準。 The accuracy of a Wi-Fi-fingerprint localization system critically depends on the quality of its radio map. This thesis explores various properties of a metropolitan radio map that may affect the accuracy of Wi-Fi-fingerprint localization systems. In our study, metro-politan-scale radio maps are obtained using war walking and war driving. These maps contain hundreds of thousands of access points and signal samples. A detailed comparison analysis of selected radio map properties reveals how different map properties affect the difference between the positional accuracies of the driving and walking radio maps in Wi-Fi fingerprint-based localization. Hardware variance can significantly degrade the positional accuracy of RSS-based Wi-Fi localization systems. Although manual adjust-ment can reduce positional error, this solution is not scalable as the number of new Wi-Fi devices increases. We propose an unsupervised learning method to automatically solve the hardware variance problem in Wi-Fi localization. Experimental results demonstrate that the proposed learning method improves positional accuracy within 100 seconds of learning time. To further optimize the metropolitan Wi-Fi localization algorithm, we propose a confidence-based pedestrian localization system that can achieve <10 meters average positional accuracy on a mobile phone in the outdoor environments of cities where GPS may perform poorly under urban canyon. Our pedestrian localization system works by combining an outdoor Wi-Fi-based localization method and a relative localization method based on accelerometers/digital compass signals. Experimental results show that our hybrid pedestrian localization system achieved a median positional accuracy of 8.6 meters. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66562 |
Fulltext Rights: | 有償授權 |
Appears in Collections: | 資訊網路與多媒體研究所 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-101-1.pdf Restricted Access | 4.84 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.