一种结合均值和互信息的线上AP选取新算法

A New AP Selection Algorithm Combined with Mean Value and Mutual Information

探讨了基于RSS（received signal strength）的WiFi室内定位技术的AP（access points）选取算法,并分析了两种现有AP选取算法对WiFi室内定位性能的影响。基于均值最大的AP选取算法存在无法顾及AP相互干扰的局限,而基于线上互信息最小的AP选取算法计算过程复杂,当AP个数较多时,其时耗较大,同时难以完全摒弃观测质量过差的AP。考虑到上述两种方法的局限,提出了一种线上AP选取新算法,首先利用均值最大选取算法对AP进行预处理,从而加快AP选取的速度,并剔除部分观测质量较差的AP,然后利用互信息进行AP的精确选取。实验分析表明,新算法能够有效地提高位置估计的速度,并且改进了位置估计精度。

This paper analyzes the performance influence of two different AP selection algorithms based on maximum mean and based on minimum mutual information on WiFi indoor positioning.To improve the limitations of the two methods,a new online AP selection algorithm is proposed.A pre-processing is applied to accelerate the speed of AP selection algorithm based on mutual information and remove some APs with too poor observation quality.Then the AP accurate selection is achieved by the selection algorithm based on mutual information.Experimental results show that the algorithm of our proposed can effectively improve the speed and the accuracy of position estimation.