Enhanced WKNN Indoor Positioning Algorithm with Dynamic AP Selection Strategy

Indoor positioning systems (IPS) have become indispensable in modern smart environments, where Global Positioning Systems (GPS) fail due to signal obstruction. This study introduces an enhanced Weighted K-Nearest Neighbor (WKNN) algorithm incorporating a Dynamic Access Point Selection (DAPS) strategy to improve accuracy and reliability in indoor settings. By intelligently filtering access points (APs) based on signal quality and spatial relevance, the proposed method mitigates the effects of noisy signals and optimizes AP utilization. Experimental evaluations in real-world environments demonstrate that the DAPS-enhanced WKNN achieves up to 30% higher positioning accuracy compared to traditional WKNN methods, reducing average positioning errors to 1–2 meters. The findings highlight the algorithm’s potential in diverse applications such as healthcare, retail, and smart buildings. This research paves the way for scalable and cost-effective IPS solutions, emphasizing adaptability to varying environmental complexities.