基於高斯混合模型之室內定位系統設計與實作

近些年來，由於無線感測網路的發展，室内定位系統因而被廣泛地討論及研究。基於接收訊號強度的基礎上，有許多的研究在定位架構採單一高斯機率模型的建立，進而建立電波場域分佈資料，透過累積機率的運算來達到定位目的。然而，在實際的訊號強度的接收上，因為電波在空氣中傳遞過程中由於多路徑、電波反射、相互干擾等問題，使用單一高斯模型來描述一實際接收情況往往是不夠精確的，這也會造成在機率累積的過程中產生偌大誤差，進而造成最終產生定位估測錯誤。此篇論文採用混合高斯模型來描述實際複雜的訊號強度接收情況，此外，某些特殊領域的定位需求，例如：工地安全等，也搭配了雙頻定位器來輔助整個定位系統在必要的定位點具備99%的定位精度；最後，此篇論文亦搭載了平滑濾波器(Smoothing Filter)來調整目標移動的路徑記錄，以使在電腦畫面路徑的追溯上，達到更平滑的效果，此外，接收訊號強度濾波器(RSSI Filter)亦具改善定位精度的效果。此篇論文透過既有的RSSI參數，透過機率的演算及定位器的輔助，發展並實作了一套可被實現的定位系統。

關鍵字

主動式射頻電子標籤；室內定位系統

並列摘要

Indoor positioning systems are widely discussed in recent years since a wireless sensor network had been developed. Based on receiving of RSSI, much research proposed a structure of probability model to accomplish positioning system, and utilize single component of Gaussian model to structure radio map. But that is not enough if just using single component of Gaussian model to simulate a very complex environment since there exist some serious problems which may cause error estimation on distance such as reflection, interference, multi-path, etc. This thesis proposes multi-components of Gaussian model to get much close description for the received signal strength. Also, this thesis adopts Excitor to approach a 99% exactly positioning for some specific field application such as surveillance desired application. In addition, this thesis presents a smoothing filter to adjust the moving path therefore the movement path shown in computer graphical interface may looks fluently, in addition, RSSI filter also improve position accuracy. In this paper we developed and implemented a novel technology to accomplish positioning system by aiding of algorithmic and Excitor positioning.

並列關鍵字

Indoor positioning system ； Active RFID

參考文獻

[6] 陳大鈞, Measure Point selection Algorithms for Wireless Indoor Positioning Systems, 國立臺灣大學資訊管理研究所碩士論文, 2004年七月。

[7] 陳嶽東, 以訊號強度為基礎利用高斯混合模型之IEEE802.11無線區域網路定位演算法, 國立成功大學資訊工程研究所碩士論文, 2005年六月。

[10] P. Golle, D. Greene, and J. Staddon. “Detecting and correcting malicious data in vanets. ” In VANET, pp. 29-37, 2004.

[11] A.H. Sayed, A. Tarighat and N. Khajehnouri, “Network-based wireless location: challenges faced in developing techniques for accurate wireless location information, ” IEEE Signal Processing Magazine, vol. 22, Issue 4, pp.24-40, July, 2005.

[13] Y. Wu, J. Hu, and Z. Chen, “Radio Map Filter for Sensor Network Indoor Localization Systems.” 2007 5th IEEE International Conference, vol.1 23-27, pp.63-68, June 2007.

國際替代計量

基於高斯混合模型之室內定位系統設計與實作

未授權

主題瀏覽