ANFIS Indoor Positioning System Based on Improved-GA in WLAN Environment

This paper proposes an ANFIS indoor positioning system based on improved genetic algorithm (GA). In the offline phase, fuzzy rules are abstracted by means of subtractive clustering algorithm with training data, generating the structure of each ANFIS positioning subsystem in X and Y directions. Then each positioning subsystem is trained with improved-GA. In this training algorithm, BP algorithm acts as an operator of GA, thus fully integrating the global search ability of GA and the local search ability of BP. On the other hand, advanced methods such as migration and adaptive mutation probability are also adopted, thus greatly accelerating the convergence of error and achieving the purpose of fast global optimization. Experimental results indicate that this algorithm can achieve a positioning error within 3m with an average positioning error of 1.2965m, meeting the needs in most practical applications. Moreover, it outperforms other positioning algorithms such as BP-ANN and BP-ANFIS positioning systems.