WLAN Indoor Positioning Based on D-LDA Feature Extraction Algorithm
This paper introduces the Direct Linear Discriminant Analysis (D-LDA) algorithm into wireless LAN (WLAN) indoor positioning system as a feature extraction method to reduce noise and redundant location information of the access points (APs) signals produced by the complex radio propagation environment. Feature database is obtained by application of D-LDA algorithm to extract the effective positioning feature of the original WLAN Signal database and adjusting the threshold parameter for retained eigenvalues of between-class scatter matrix as well. During the online time, three typical localization algorithms including weighted knearest neighbor (WKNN), nearest-neighbor (NN) and maximum likelihood (ML) are applied to real-time positioning based on feature database and the results are compared. DLDA feature extraction algorithm obtains the higher accuracy than traditional localization algorithms while reducing the storage and computation cost significantly.
D-LDA feature extraction WLAN positioning accuracy feature database
Yubin Xu Haoyuan Zhang Zhian Deng
School of Electronics and Information Engineering, Harbin Institute of TechnologyHarbin, China School of Electronics and Information Engineering, Harbin Institute of Technology Harbin, China
国际会议
哈尔滨
英文
218-222
2011-01-18（万方平台首次上网日期，不代表论文的发表时间）