Journal of Systems Engineering and Electronics ›› 2022, Vol. 33 ›› Issue (2): 305-311.doi: 10.23919/JSEE.2022.000031

• ELECTRONICS TECHNOLOGY • Previous Articles     Next Articles

Improved adaptive genetic algorithm based RFID positioning

Yu LI(), Honglan WU(), Youchao SUN*()   

  1. 1 Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211100, China
  • Received:2021-03-15 Online:2022-05-06 Published:2022-05-06
  • Contact: Youchao SUN E-mail:893792696@qq.com;wuhonglan@126.com;sunyc@nuaa.deu.cn
  • About author:|LI Yu was born in 1997. He received his B.S. degree from Shandong University of Science and Technology, Qingdao, China, in 2019. Currently he is pursuing his M.S. degree at Nanjing University of Aeronautics and Astronautics. His research interests include artificial intelligence and sensor fusion.E-mail: 893792696@qq.com||WU Honglan was born in 1969. She received her Ph.D. degree from Nanjing University of Aeronautics and Astronautics Nanjing, China, in 2011. She is a senior engineer at the Civil Aviation College. Her research interests include reliability engineering and intelligent transportation. E-mail: wuhonglan@126.com||SUN Youchao was born in 1965. He received his Ph.D. degree from Nanjing University of Aeronautics and Astronautics Nanjing, China in 1998. He is now a professor at the Civil Aviation College of Nanjing University of Aeronautics and Astronautics. His research interests include reliability engineering, maintain ability engineering, and virtual design. E-mail: sunyc@nuaa.deu.cn
  • Supported by:
    This work was supported by the Aviation Science Foundation(ASFC-20181352009)

Abstract:

The existing active tag-based radio frequency identification (RFID) localization techniques show low accuracy in practical applications. To address such problems, we propose a chaotic adaptive genetic algorithm to align the passive tag arrays. We use chaotic sequences to generate the intersection points, the weakest single point intersection is used to ensure the convergence accuracy of the algorithm while avoiding the optimization jitter problem. Meanwhile, to avoid the problem of slow convergence and immature convergence of the algorithm caused by the weakening of individual competition at a later stage, we use adaptive rate of change to improve the optimization efficiency. In addition, to remove signal noise and outliers, we preprocess the data using Gaussian filtering. Experimental results demonstrate that the proposed algorithm achieves higher localization accuracy and improves the convergence speed.

Key words: radio frequency identification (RFID) positioning, improved genetic algorithm, Gaussian filter, passive tags