Abstract: In order to improve location accuracy and reduce environmental impact on indoor wireless location, this paper presents a novel indoor location method based on particle swarm optimization algorithm and support vector machine. Firstly, the indoor reference nodes are selected and the learning samples of indoor wireless location are obtained, and then support vector machine is used to establish the nonlinear model which can describe the relationship between input and output while and the parameters of support vector machine is optimized by particle swarm optimization algorithm, finally, the simulation is carried out to test the performance. The experimental results show that the proposed method has improved location accuracy and can control location error in effective range, and can meet the real-time requirement of indoor wireless location.

Key words: Support Vector Machine（SVM）, Particle Swarm Optimization（PSO） algorithm, indoor location, wireless network

摘要： 为了提高室内的定位精度，减少环境因素的不利影响，提出了一种基于粒子群优化支持向量机的室内无线定位方法。选择参考点，构建室内无线定位的学习样本，采用支持向量机建立输入与输出之间的非线性关系模型，并用粒子群算法优化支持向量机参数；进行仿真实验测试其性能。实验结果表明，相对当前经典室内定位方法，该方法提高了提高室内的定位精度，将定位误差控制在实际应用的有效围，而且较好地满足了室内定位的实时性要求。

关键词: 支持向量机, 粒子群优化算法, 室内定位, 无线网络