An Indoor Positioning Algorithm with Kernel Direct Discriminant Analysis

Location estimation based on received signal strength (RSS) in WLAN environment is an attractive method for indoor positioning system. Unfortunately, due to the explicit nonlinearity and uncertainty of RSS signal, the traditional approaches always fail to deliver good location accuracy. This paper presents a novel positioning algorithm with kernel direct discriminant analysis (KDDA). We deploy the KDDA to map the original RSS vectors into a kernel feature space for feature extraction. The experimental results show that the proposed algorithm leads to higher location accuracy over the traditional algorithms including weighted k-nearest neighbor, maximum likelihood and kernel method. The performance improvement can be attributed to that the nonlinear discriminative location information can be efficiently extracted, while the redundant location information is considered as noise and discarded adaptively.