本篇論文主要利用WiFi AP的訊號強度來進行室內定位，首先透過擷取無線接取點(Wi-Fi Access Point) 內的接收訊號強度(Received Signal Strength Indicator, RSSI)來建構出離線地圖，接下來於線上定位階段正確地取得各個無線接取點(Wi-Fi Access Point)內信標框(beacon frame)的相關資訊，並將接收到的訊號強度轉換成位置資訊；利用各種適用於定位系統的演算法(K個最近鄰居演算法、K分群演算法、粒子群優化演算法)進行室內定位，透過比較這些演算法我們可以發現，本篇論文所使用的粒子群優化演算法（Particle Swarm Optimization，PSO）應用於定位系統上可以達到較高的定位精準度與收斂速度。 根據模擬實驗的結果，本文所提出的粒子群演算法，在平均定位誤差優於其它演算法，平均定位誤差在1M內，最大定位誤差在1.5M內，非常符合智慧型手持式裝置在室內定位服務上的需求。 ;This thesis is mainly to use the Wi-Fi access points signal strength for indoor positioning. i.e. Received Signal Strength Indicator measurements from multiple Wi-Fi access points. During an offline phase, fingerprints are collected at known positions in the building. This database of locations and the associated fingerprints are called the radio map. During an online phase, the current Wi-Fi fingerprint Particle Swarm optimization are compared with those of the radio map. This paper compared different algorithm, such as K Nearest Neighbor algorithm, K-means clustering algorithms, Particle Swarm Optimization, we can find the Particle Swarm Optimization algorithm on the indoor positioning system can achieve high positioning accuracy and convergence speed. This simulation results showed the proposed Particle Swarm Optimization algorithm, the average location error better than others, the median error of 1m, the maximum positioning error in 1.5M, it means Particle Swarm Optimization algorithm more suitable for indoor positioning and smart handheld devices.
