We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
基于自适应蝙蝠粒子滤波算法的 WSN 目标跟踪.
- Authors
郭 鲁; 魏 颖
- Abstract
In order to solve the problem of the low precision caused by sample dilution in wireless sensor network CWSN) target tracking based on particle filter (PF), the WSN target tracking method based on the adaptive bat particle filter is proposed. The resampling process of particle filtering is optimized by the improved bat algorithm, and combined with t he fitness function of the particle defined by the latest observations, the particle is guided to generally move to a higher random region. At the same time, the dynamic adaptive inertia weight is used to explore the position update for the new particle as the design mechanism, and the dynamic adaptive inertia weight value is introduced to effectively adjust the global and local exploration adaptability, improve the particle dilution and local extreme value, and increase the particle swarm diversification to improve the tracking performance. The experimental results show that the resampling method of the adaptive bat particle filter algorithm can prevent the degradation of particles, increase the diversity of particles, reduce the tracking error and the running time of the algorithm, and greatly improve the real-time tracking performance. IBAPF algorithm has the shortest computation time. Compared with the BA-PF algorithm and the PF algorithm, the IBAPF algorithm has the smallest mean square root error of the position and velocity (position by 0. 031 3 m, 0. 027 0 m, speed by 0. 020 21 m/s, 0. 010 2 m/s, respectively), the PF algorithm has the lowest tracking accuracy, and the IBAPF algorithm has the highest tracking accuracy. The IBAPF algorithm is proved to have the good tracking performance.
- Publication
Computer Measurement & Control, 2022, Vol 30, Issue 6, p168
- ISSN
1671-4598
- Publication type
Article
- DOI
10.16526/j.cnki.11-4762/tp.2022.06.026