A WiFi Indoor Location Tracking Algorithm Based on Improved Weighted K Nearest Neighbors and Kalman Filter

The Weighted K Nearest Neighbor (WKNN) algorithm is a widely adopted lightweight methodology for indoor WiFi positioning based on location fingerprinting. Nonetheless, it suffers from the disadvantage of fixed value and susceptibility to incorrect reference point matching. To address this issue, we present novel in paper, referred as Static Continuous Statistical Characteristics-Soft Range Limited-Self-Adaptive WKNN (SCSC-SRL-SAWKNN). Our not only takes into account tracking motion state but also exploits continuous statistical features extended periods inactivity enhance localization. In state, initially employ adaptive (SAWKNN) determine optimal value, followed by employment Soft Limited KNN (SR-KNN) identify correct ultimately estimate position. When prolonged stationary detected, first utilize moving window method obtain more stable position fingerprint (SCSC), then proceed with process same state. Ultimately, use Kalman filter generate trajectory. experimental findings demonstrate that proposed SCSC-SRL-SAWKNN outperforms traditional WKNN, SAWKNN, SRL-KNN techniques terms localization accuracy Specifically, our 56.7% 36.6% higher than static overall situation, respectively.