基于核直接判别分析和支持向量回归的WLAN室内定位算法

WLAN Indoor Positioning Algorithm Based on KDDA and SVR

该文针对RSS信号的时变性降低WLAN室内定位精度的问题,提出了一种新的基于核直接判别分析和支持向量回归的定位算法。该算法利用核直接判别分析对原始RSS信号进行定位信息重组,去除冗余定位特征和噪声,提取最具判别力的定位特征,然后采用支持向量回归算法建立定位特征与物理位置的映射关系。实验结果表明,提出算法的定位精度明显高于传统定位算法,且大大降低了离线阶段数据采集的工作量。

The time-varying Received Signal Strength（RSS） drastically degrades the indoor positioning accuracy in Wireless Local Area Network（WLAN）.A new positioning algorithm based on Kernel Direct Discriminant Analysis（KDDA） and Support Vector Regression（SVR） is proposed to resolve the problem in this paper.The proposed algorithm employs KDDA to reconstruct the localization information contained in the RSS signal.The most discriminative localization features are then extracted while the redundant localization features and noise are discarded by KDDA.The extracted localization features are taken as inputs to SVR learning machine and the mapping between localization features and physical locations is established.The experimental results show that the proposed algorithm obtains significant accuracy improvement while requiring a much smaller set of RSS training data than previous methods.