A Multi-classifier-Based Multi-agent Model for Wi-Fi Positioning System

Abstract

Fingerprint-based Wi-Fi localization systems have become attractive for researchers in indoor location-based services. Due to the fluctuant characteristics of received signal strength (RSS) and the lack of the research on environmental factors affecting the signal propagation, the accuracy of the previous systems heavily relies on environmental conditions. In this chapter, we propose a novel multi-agent fusion algorithm which combines multiple classifiers. Unlike previous multi-classifier combination rule, the proposed approach considers the relativity among classifiers according to co-decision matrix. Experimental results show that the multi-classifier approach outperforms single classifier in the test environment with the average accuracy and standard deviations greatly improved in the test environment.

Weight-RSS: A Calibration-Free and Robust Method for WLAN-Based Indoor Positioning

“…For example, Villarubia et al [19] proposed a novel approach which uses multiple classifiers and RSS intensity maps for indoor positioning. Similarly, Zhu et al [20] proposed a multiagent fusion algorithm which combines multiple classifiers for indoor positioning. In addition, hybrid indoor localization systems [21, 22] which combine information from various sensors are also proposed for solving this problem.…”