Research on Indoor Fingerprint Localization Method Based on Improved K-Means Clustering
Due to the complexity and variability of indoor environments,traditional fingerprint positioning techniques often struggle to achieve high-precision indoor positioning.This article proposes a fingerprint indoor positioning method based on improved K-means clustering.By introducing the elbow method to determine the K value,the offline position fingerprint database is clustered and divided,improving the effectiveness of K-means clustering.Outliers are detected and corrected during both clustering and positioning processes,further improving positioning accuracy.After comparing and analyzing the experimental results,the method proposed in this paper reduces the positioning error from 3.7 m to 1.8 m compared to before clustering correction,effectively improving the positioning accuracy.
万方数据
维普
