计算机工程与应用 ›› 2014, Vol. 50 ›› Issue (17): 191-194.

• 信号处理 • 上一篇    下一篇

基于权重参数实时更新的室内定位算法

周  雄,陈国彬   

  1. 重庆工商大学 融智学院,重庆 400033
  • 出版日期:2014-09-01 发布日期:2014-09-12

Indoor localization algorithm based on weight parameter real-time updating

ZHOU Xiong, CHEN Guobin   

  1. College of Rongzhi, Chongqing Technology and Business University, Chongqing 400033, China
  • Online:2014-09-01 Published:2014-09-12

摘要: 为了提高室内节点的定位精度,提出一种基于权值参数实时更新的室内定位算法。选择3个最能反映待定位点信息的访问接入点,实时获取测距模型的参数,并采用最小二乘支持向量机对测距进行补偿,得到距离权重,三边定位算法根据权重对节点进行定位,并对计算中的距离进行加权处理,采用卡尔曼滤波法对定位误差的进行校正。实验结果表明,该算法可以较好地降低环境变化和测量误差对定位的不利影响,提高了室内节点的定位精度。

关键词: 室内定位, 线网络, 最小二乘支持向量机, 卡尔曼滤波

Abstract: In order to improve the localization precision, a novel indoor localization algorithm based on weight parameter real-time updating is proposed in this paper. Three APs which can best explain the information of object are selected, and then the parameters of range model are updated in a real-time way, and the least square support vector machine is used to correct the range error to obtain the distance weights, the localization is obtained by using triangle-based localization algorithm based on distance weights and the localization error is corrected by Kalman filter method. The experimental results show that the proposed algorithm can reduce the error caused by surroundings and signal strength, and it has improved the higher localization precision.

Key words: indoor location, wireless network, least square support vector machine, Kalman filter