ANN indoor position determination based on area correlation in WLAN environment

Indoor position determination based on artificial neural network (ANN) with area correlation is proposed in this paper. For any pattern matching based algorithm in WLAN environment, the characteristics of received signal strength (RSS) or signal to noise ratio (SNR) to multiple access points (APs) are utilized to establish radio map in the off-line phase, and in the online phase, the actual two or three dimensional coordinates of mobile terminals (MTs) are estimated based on the comparison between the new recorded RSS or SNR and fingerprints stored in radio map. Although the feed-forward ANN with three layers is sufficient to approximate any continuous function to a desired accuracy and describe any mapping relationship between input and output values, the optimal types of input vectors for different actual complex indoor environments is difficult to be determined. So in this paper, the correlation between SNR from different APs and physical area is analyzed for the purpose of establishing multiple ANN subsystems for separate sub areas. Feasibility and effectiveness of this method is verified according to the experimental comparison with K-nearest neighbor (KNN), probability and ANN methods without area division.