Notice of RetractionPost-processing of fingerprint-based vehicle positioning using improved particle filter

Notice of Retraction

After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.

We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.

In this paper, a novel algorithm called Receding Horizon Kalman Particle Filter (RHKPF) has been proposed and is applied to our improved fingerprint-based WLAN vehicle positioning system. The RHKPF is a particle filter that the optimal importance density is approximated by incorporating the most current measurement through a Receding Horizon Kalman Filter (RHKF), for that the RHKF is believed to be robust against temporary modeling uncertainties since it utilizes only finite measurements on the most recent horizon. In this paper, the RHKPF and the Kalman Particle Filter (KPF) are both applied to the WLAN-based vehicle positioning system with temporary measurement modeling uncertainty. Through simulations we find that, although the KPF has the property of robustness compared with the RHKPF when there is temporary modeling uncertainty, whereas the RHKPF has the property of fast convergence after temporary modeling uncertainty disappears compared with the KPF. So we propose a scheme called KPF-RHKPF that both of the RHKPF and the KPF are used to estimate the position of the vehicle, that is, when there is a modeling uncertainty, the estimation results of the KPF are used as the estimation of the vehicle, and when the modeling uncertainty disappears, the estimation results of the RHKPF is used as the vehicle estimation. Simulation results show us the robustness and the fast convergence properties of the KPF-RHKPF.