Visible light positioning system based on an improved weighted k-nearest neighbor algorithm

作者：Ye Tian, Lei Jing, Zhengrong Tong, Peng Li, Xue Wang, Hao Wang, Zhonghan Wang, Yongsheng Jiang · 年份：2025 · DOI：10.1117/12.3054323 · 被引用次数：2 · 研究领域：Optical Wireless Communication Technologies、Advanced Measurement and Detection Methods、Impact of Light on Environment and Health

Traditional K-Nearest Neighbors (KNN) and Weighted K-Nearest Neighbors (WKNN) algorithms face challenges due to the fixed selection of the K value. To address this issue, we propose a new algorithm that combines Genetic Algorithm (GA) with WKNN, referred to as GA-WKNN. The GA algorithm optimizes and adjusts the K value, thereby reducing errors in the visible light positioning system. Experimental results show that the GA-optimized WKNN significantly improves localization accuracy compared to traditional methods with a fixed K value. This optimization strategy allows the positioning system to more accurately determine the actual position.