关键词: 室内定位, 支持向量机, 核主成分分析, 粒子群优化算法

Abstract: Wi-Fi signal is unstable in complex indoor environment and localization precision of support vector machine is very low. In order to improve the localization precision of indoor nodes, a novel indoor localization algorithm is proposed based on improved support vector machine. The kernel principal component analysis is used to extract useful information and obtain the features which reduce the computing complexity, and then support vector machine is used to construct nonlinear mapping localization model between features and physical location, in which parameters are optimized by particle swarm optimization algorithm. The simulation experiments are used to test the performance. The results show that the proposed algorithm has improved localization precision and efficiency for indoor localization.

Key words: indoor localization, support vector machine, kernel principal component analysis, particle swarm optimization algorithm