Fast fingerprint localisation based on product quantisation and convolution neural network in a massive MIMO system. (26th August 2022)

• Record Type: Journal Article
• Authors: Ren, Yijie; Wang, Xiaojun; Liu, Lin; Chen, Xiaoshu
• Is Part Of: International journal of sensor networks. Volume 40:Number 1(2022)
• Page Start: 67
• Page End: 75
• Publication Date: 2022-08-26
• Subjects: fingerprint localisation -- massive multiple-in-multiple-out -- MIMO -- product quantisation -- convolution neural network -- CNN; Sensor networks -- Periodicals; 681.2
• Languages: English
• ISSNs: 1748-1279

Abstract

Location-based service (LBS) has recently been popular, such as auto-driving, navigation, and tracking. Fingerprint localisation is one of the most effective localisation schemes for both indoor and outdoor localisation. In this paper, fingerprint localisation algorithms are researched based on a massive multiple-in-multiple-out (MIMO) system. Firstly, the extraction of angle-delay channel power matrix (ADCPM) fingerprints and the channel model are introduced. Then, two new fast fingerprint localisation algorithms based on product quantisation (PQ) and convolution neural network (CNN) are proposed, respectively. PQ and CNN are applied to process the data in the online matching phase. Compared with other previously known positioning techniques, the test results show that the proposed algorithms achieve high accuracy, reduce delay, and greatly reduce computational complexity.