Abstract: Aiming at the problem that the positioning accuracy is affected by the dynamic indoor environment and time-varying received signal strength (RSS) values, a Wi-Fi based indoor positioning method using kernel principal component Analysis (KPCA) and echo state networks (ESN) is proposed. The KPCA method is used to preprocess the RSS fingerprints effectively and extract the nonlinear principal components of the inputs of the model. On the basis of KPCA, the extracted principal components are taken as the inputs to the ESN network, the nonlinear mapping between corresponding positioning features and physical locations is then established by the ESN. The proposed KPCA-ESN method is then applied to Wi-Fi based indoor positioning instances by simulation and physical environment experiments. Compared with the other positioning methods under the same condition, experimental results confirm that the proposed method has higher positioning accuracy, and can also automatically timely adapt to environmental dynamics.

Key words: echo state networks, kernel principal component analysis, Wi-Fi, indoor positioning, received signal strength