The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Proposal of Optimized Neural Network-Based Wireless Sensor Node Location Algorithm

최적화된 신경망 기반 무선 센서 노드위치 알고리즘 제안

  • Received : 2022.10.12
  • Accepted : 2022.12.17
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study leads to the shortcoming that the RSSI distance measurement method is easily affected by the external environment and the position error is large, leading to the problem of optimizing the distance values measured by the RSSI distance measurement nodes in this three-dimensional configuration environment. We proposed the CA-PSO-BP algorithm, which is an improved version of the CA-PSO algorithm. The proposed algorithm allows setting unknown nodes in WSN 3D space. In addition, since CA-PSO was applied to the BP neural network, it was possible to shorten the learning time of the BP network and improve the convergence speed of the algorithm through learning. Through the algorithm proposed in this study, it was proved that the precision of the network location can be increased significantly (15%), and significant results were obtained.

본 연구는 RSSI의 거리측정 방법이 외부 환경에 의해 쉽게 영향을 받아 위치 오차가 크다는 결점을 도출하였고 이 3차원 배치 환경에서 RSSI의 거리측정 노드에서 측정한 거리값을 최적화하는 문제에 대해 향상된 CA-PSO 알고리즘을 개선한 CA-PSO-BP 알고리즘을 제안하였다. 제안된 알고리즘은 3차원 무선센서네트워크(WSN) 공간에서 인식할 수 없는 노드를 설정할 수 있도록 하였다. 또한, CA-PSO를 BP 신경망에 응용하므로, 학습을 통해 BP 네트워크의 학습시간 단축과 알고리즘의 수렴 속도를 제고 할 수 있었다. 본 연구에서 제안한 알고리즘을 통해 네트워크의 위치의 정밀도를 현저(15%)하게 높일 수 있다는 것을 증명하였고 유의미한 결과를 얻을 수 있었다.

Keywords

References

  1. Cao Li, Cai Yong, Yue Yinggao, Cai Shaotang,Hang Bo. A Novel Data Fusion Strategy Based on Extreme Learning Machine Optimized by Bat Algorithm for Mobile Heterogeneous Wireless Sensor Networks[J] IEEE Access. 2020.
  2. H. Kim and Y. Jeong, " GPS Accuracy Revision Using RSSI and AoA in Wireless Sensor Network" J. of The Korea Institute of Electronic Communication Sciences, vol. 17, no. 05, 2022, pp. 889-896.
  3. AldinN B, E. Ercelebi,and M. Aykac. "An Accurate Indoor RSSI Localization Algonithm Based on Active RFID System with Reference Tags[J]". Wireless Personal Communications,2017,vol. 97, no. 3, pp1-19. https://doi.org/10.1007/s11277-017-4261-9
  4. K. Jiang, L. Yao, and J. Feng. "Wireless Sensor Networks Target Localization Based on Least Square Method and DV-Hop Algorithm", Journal of Networks, vol.1, no.2, 2014. pp.62-70.
  5. Shalaby M,Shokair, and M,Messiha N W." Perfornance Enhancement of TOA Localized Wireless Sensor Networks[J]". Wireless Personal Communications,vol. 95, no. 4, 2017,pp. 4667-4679. https://doi.org/10.1007/s11277-017-4112-8
  6. Soonho K, Daeoh and K, Jihye L, Performance Analysis of 3D Localization for a Launch Vehicle Using TOA, AOA, and BAS:beetle antennae search algorithm for optimization problems. Jiang X Y, Li S. https://arxiv.org/abs/1710.10724. 2018.
  7. Ju Lee, Hyo Lee, and Jae Oh, "Design for interworking with payment system using short-range wireless communication method" J. of The Korea Institute of Electronic Communication Sciences, vol. 15, no. 06, 2020, pp. 1031-1036.
  8. Caiqing Wang,Shubin Wang. Research on Uneven Clustering APTEEN in CWSN Based on Ant Colony Algorithm.[J] . IEEE Access . 2019.
  9. H. Z.-D., and J Cao."An Improvement of DV-Hop Localization Algorithm for Wireless Sensor Network", Computer & Modemization, vol. 53, no.1, 2014, pp.13-18.
  10. Yick Jennifer, Mukherjee Biswanath, Ghosal Dipak,."Wireless sensor network survey", Computer Networks, vol.52, no.12, 2008. pp. 2292-2330. https://doi.org/10.1016/j.comnet.2008.04.002
  11. Lalit Chettri,Rabindranath Bera, A Comprehensive Survey on Internet of Things (IoT) Toward 5G Wireless Systems[J]. IEEE Internet of Things Journal. vol(1), 2020.
  12. T. Kim, S. Hwang, "Cascade AOA Estimation Using Uniform Rectangular Array Antenna," Journal of the Korea Institute of Electronic Communication Science, vol 13, no. 5, Oct. 2018, pp. 923-930. https://doi.org/10.13067/JKIECS.2018.13.5.923