Abstract—Indoor localization system has been continuously developed. However, there is still an error in the positioning due to the variance of the signal. This paper proposed method to reduce variance of received signal strength indicator (RSSI) using frequency analysis and applied Genetic Algorithm to search the optimal weights for weighted distant fingerprint algorithm (WDF). Experiments are conducted in indoor environment using android mobile received signal strength from access point and the proposed algorithm can be compared with K-Nearest Neighbor (KNN) algorithm and conventional weighted distant fingerprint (WDF) algorithm. Results demonstrate that the proposed algorithm can improve an accuracy increase to 89.75% for identifying correctly 0.5 m × 0.5 m area of target node.
Index Terms—Indoor localization, frequency analysis, fingerprint, genetic algorithm.
Piyapan Suwannawach is with the Electrical Engineering Department, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand (e-mail: 56601019@kmitl.ac.th, piyapan.s@rmutp.ac.th).
Sorawat Chivapreecha is with the Telecommunication Engineering Department, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand (e-mail: sorawat@telecom.kmitl.ac.th).
[PDF]
Cite: Piyapan Suwannawach and Sorawat Chivapreecha, "Reduce RSSI Variance for Indoor Localization System Using Frequency Analysis," International Journal of Future Computer and Communication vol. 8, no. 2, pp. 34-38, 2019.
