Signal perturbation based support vector regression for Wi-Fi positioning


Location estimation using received signal strength (RSS) in pervasively available Wi-Fi infrastructures has been considered as a popular indoor positioning solution. However, accuracy deterioration due to uncertainty of RSS and offline manual calibration cost limit the deployment of Wi-Fi positioning systems. This paper proposes a signal perturbation technique to enhance existing support vector regression (SVR) based Wi-Fi positioning. By signal perturbation, more RSS training samples are generated, thus enhancing the generalization ability of SVR. In addition, access point (AP) selection method is applied to reduce the input dimension by discarding the redundant APs. The proposed method is compared with previous classical methods in a real wireless indoor environment. Experimental results show that the proposed method improves accuracy while reducing calibration cost.

DOI: 10.1109/WCNC.2012.6214342

6 Figures and Tables

Cite this paper

@article{Xu2012SignalPB, title={Signal perturbation based support vector regression for Wi-Fi positioning}, author={Yubin Xu and Zhian Deng and Siwei Ma and Weixiao Meng and Cheng Li}, journal={2012 IEEE Wireless Communications and Networking Conference (WCNC)}, year={2012}, pages={3123-3127} }