Three-dimensional localization algorithm of mobile nodes based on received signal strength indicator-angle of arrival and least-squares support-vector regression. (July 2022)

• Record Type: Journal Article
• Authors: Zhang, Lieping; Peng, Huihao; He, Jiajie; Zhang, Shenglan; Zhang, Zuqiong
• Is Part Of: International journal of distributed sensor networks. Volume 18:Number 7(2022)
• Publication Date: 2022-07
• Subjects: Wireless sensor network -- received signal strength indicator -- angle of arrival -- least-squares support-vector regression -- 3D localization; Sensor networks -- Periodicals; Intelligent agents (Computer software) -- Periodicals; Multisensor data fusion -- Periodicals; 681.2
• DOI: 10.1177/15501329221111961
• Languages: English
• ISSNs: 1550-1329

Abstract

Node localization is one of the key technologies in the wireless sensor network research field, which is crucial to the high-accuracy localization of mobile nodes, but the positioning error of traditional algorithms such as received signal strength indicator and angle of arrival is more than 4 m, which has almost no practical value. For example, the localization accuracy of the localization algorithm based on received signal strength indicator will be reduced sharply when affected by signal reflection, multipath propagation, and other interference factors. To solve the problem, a three-dimensional localization algorithm of mobile nodes was proposed in this article based on received signal strength indicator–angle of arrival and least-squares support-vector regression, which fused the ranging information of received signal strength indicator algorithm and the angle of arrival algorithm and optimized the estimated distance of unknown nodes. Next, the mobile node model and least-squares support-vector regression modeling mechanism were built according to the hop count of the shortest distance between nodes. Finally, the unknown mobile nodes were localized based on least-squares support-vector regression modeling. The experimental results showed that compared with the localization algorithms without optimized ranging information or least-squares support-vector regression modeling, the algorithm proposed in this study exhibited significantly improved stability, a reduced mean localization error by more than 50%, and increased localization accuracy.