An optimal measurement method for spatial distribution of radio frequency identification multi-tag based on image analysis and PSO. (August 2019)

• Record Type: Journal Article
• Authors: Yu, Xiaolei; Zhou, Yujun; Liu, Zhenlu; Zhao, Zhimin
• Is Part Of: Transactions of the Institute of Measurement and Control. Volume 41:Number 12(2019)
• Page Start: 3331
• Page End: 3339
• Publication Date: 2019-08
• Subjects: RFID -- multi-tag distribution -- image analysis -- PSO neural network -- optimal measurement; Automatic control -- Periodicals; Measuring instruments -- Periodicals; Commande automatique -- Périodiques; Mesure -- Instruments -- Périodiques; 681.2
• DOI: 10.1177/0142331218823864
• Languages: English
• ISSNs: 0142-3312

Abstract

In this paper, a multi-tag optimization method based on image analysis and particle swarm optimization (PSO) neural network is proposed to verify the effect of radio frequency identification (RFID) multi-tag distribution on the performance of the system. A RFID tag detection system is proposed with two charge coupled device (CCD). This system can automatically focus on the tag according to its position, so it can obtain the image information more accurately by template matching and edge detection method. Therefore, the spatial structure of multi-tag and the corresponding reading distance can be obtained for training. Because of its excellent performance in multi-objective optimization, the PSO neural network is used to train and predict multi-tag distribution at the maximum reading distance. Compared with other neural networks, PSO is more accurate and its uptime is shorter for RFID multi-tag analysis.