- 學位論文
混合人工免疫系統與粒子群最佳化為基之支持向量機於RFID定位系統之研究
Hybrid of Artificial Immune System and Particle Swarm Optimization-based Support Vector Machine for RFID-based Positioning System
摘要
RFID具有非接觸、可重複讀取、耐用、資訊儲存量大及可同時讀取多個標籤等特性，非常適合用在貨物追蹤與資訊的收集。除了上述應用外，還可用於室內定位系統。RFID為較新的無線通訊技術之一，其一些物理上的特徵，像是接收訊號強度及訊號從傳輸端至接收端所經過時間等資訊，可利用定位技術來計算出物品位置。 本研究將混合人工免疫系統與粒子群最佳化於最佳化支持向量機之參數。為了驗證該方法之效能，會先以Australian、Heart disease、Iris、Ionosphere、Sonar與Vowel六組基準資料集作為驗證對象。結果顯示所提出HIP-SVM有較好的結果。在確認效能後在應用至RFID的接收訊號值上，以進行室內定位。在實證分析中，使用HIP-SVM來做為分類模型，其準確率最高可達到99.6%，顯示RFID除了用在存取資料外，在不增加成本的情況下，可利用標籤接收訊號值做為定位的依據。
並列摘要
RFID has the characteristics of contactless, to be reused, durable, the mass storage capacity and multi-read and is suitable to be used in cargo tracking and the information collection. In addition to the applications mentioned above, RFID may also be applied in the indoor positioning system. RFID is one of the recent wireless communication technologies. Due to some physic characteristics, like received signal strength index (RSSI) and the arrival time of radio frequency (RF) between the interrogator and tag, it can be utilized to locate the goods position. Thus, this study intends to propose a hybrid of artificial immune system and particle swarm optimization in optimizing parameters of support vector machine (HIP-SVM) for RFID-based positioning system. In order to evaluate HIP-SVM, Australian, Heart disease, Iris, Ionosphere, Sonar and Vowel benchmark data sets are first employed. The computational results showed that HIP-SVM has the best performance. Then, HIP-SVM is applied to classify RSSI for indoor positioning. The experiment results also indicated that HIP-SVM can achieve accuracy of 99.6%. It demonstrated that RFID can be not only used in storing information but also in indoor positioning without additional cost.