Multivariable fuzzy inference system for fingerprinting indoor localization

The emergence of wireless sensor network has raised the need for cheap wireless indoor localization technique. This paper considers the problem of fingerprinting indoor localization based on signal strength measurements RSS. A new approach based on Fuzzy logic has been put forward. The proposal makes use of k-nearest neighbor classification in signal space. The localization of target node is then determined as a weighted combination of nearest fingerprints. The weights are determined using Takagi-Sugeno fuzzy controller with two inputs. A new enhancement to the kNN is proposed to enhance the accuracy of location estimation; this enhancement allows the kNN to outlier some miss elected neighbors based on triangular area measurements. The performance of the developed estimation algorithm has been evaluated using both Monte Carlo simulations and real testbed scenarios while compared to other alternative approaches.