Issue No. 05 - May (2008 vol. 20)
We present a novel approach to the indoor localization in wireless environments. The main contribution of this paper is four folds: (a) we show that, by projecting the measured signal into a decorrelated signal space, the accuracy is improved since the cross-correlation between each AP is reduced. (b) We demonstrate that this novel approach achieves a more efficient information compaction and provides a better scheme to reduce the online computation. The drawback of AP selection techniques is overcomed since we reduce the dimensionality by combing features. Each component in the decorrelated space is the linear combination of all APs. Therefore a more efficient mechanism is provided to utilize information of all APs while reducing the computational complexity. (c) Experimental results show that the size of training samples can be greatly reduced. That is, fewer human efforts are required for developing the system. (d) We carry out comparisons between RSS and three decorrelated spaces including Discrete Cosine Transform, principal component analysis (PCA), and independent component analysis in this paper. Two AP selection criteria proposed in literature, MaxMean and InfoGain are also compared. Testing on a realistic WLAN environment, we find that PCA achieves the best performance on the location fingerprinting task.
Wireless, Mobile environments
P. Lin, S. Fang and T. Lin, "Location Fingerprinting In A Decorrelated Space," in IEEE Transactions on Knowledge & Data Engineering, vol. 20, no. , pp. 685-691, 2007.