Optimization Analysis of Wireless Sensor Coverage Indoor Positioning Based on KWAP-KNN Algorithm

In complex indoor environments, due to factors such as multipath effects, attenuation, and occlusion of signals, indoor positioning results often have significant errors. This study proposes for the first time to optimize the traditional KNN algorithm by introducing the KWAP-KNN (Kernel Weighted Average Precision k-Nearest Neighbors) algorithm, aiming to reduce indoor positioning errors caused by factors such as signal attenuation and multipath effects. Firstly, by introducing the kernel weight method, the nearest neighbor selection in traditional KNN is improved. Then, using the improved weight allocation mechanism, combined with nearest neighbor prediction, the accuracy and stability of localization are improved. Finally, through actual indoor positioning experiments, the effectiveness of KWAP-KNN algorithm in improving environmental adaptability and reducing the influence of outliers and noise data is verified. The experimental results show that the positioning accuracy of KWAP-KNN algorithm is superior to traditional KNN and weighted KNN algorithms in obstacle free, dynamic obstacle free, and highdensity obstacle environments, with an average error of only 0.5 meters in high-density obstacle environments. The research results further validate the application value of KWAP-KNN algorithm in the field of indoor positioning, and provide technical support for optimizing real-time positioning systems, demonstrating its broad application prospects in future smart devices and IoT technology.