A Genetic Optimization Resampling Based Particle Filtering Algorithm for Indoor Target Tracking

Abstract

In indoor target tracking based on wireless sensor networks, the particle filtering algorithm has been widely used because of its outstanding performance in coping with highly non-linear problems. Resampling is generally required to address the inherent particle degeneracy problem in the particle filter. However, traditional resampling methods cause the problem of particle impoverishment. This problem degrades positioning accuracy and robustness and sometimes may even result in filtering divergence and tracking failure. In order to mitigate the particle impoverishment and improve positioning accuracy, this paper proposes an improved genetic optimization based resampling method. This resampling method optimizes the distribution of resampled particles by the five operators, i.e., selection, roughening, classification, crossover, and mutation. The proposed resampling method is then integrated into the particle filtering framework to form a genetic optimization resampling based particle filtering (GORPF) algorithm. The performance of the GORPF algorithm is tested by a one-dimensional tracking simulation and a three-dimensional indoor tracking experiment. Both test results show that with the aid of the proposed resampling method, the GORPF has better robustness against particle impoverishment and achieves better positioning accuracy than several existing target tracking algorithms. Moreover, the GORPF algorithm owns an affordable computation load for real-time applications.

[Retracted] Research on Wireless Sensor Network Positioning Based on Genetic Algorithm

“…Based on the constraint of X j in equation ( 5), the genetic algorithm in this paper randomly generates pop positions ðx i , y i Þ as the initial population, where ðj = 1, 2 ⋯ PopÞ [13][14][15].…”

Bio-Inspired Hybridization of Artificial Neural Networks: An Application for Mapping the Spatial Distribution of Soil Texture Fractions

“…However, this model has several considerable shortcomings, such as inconsistent architectures for different applications, coupled with the process required to tune and fit a neural network, which is a time-consuming procedure that is largely based on trial and error [27,28]. Conventionally, ANNs have been fitted using a backpropagation (BP) algorithm; however, state-of-the-art approaches using bio-inspired, metaheuristic, optimization algorithms have become increasingly prevalent, including the genetic algorithm (GA) [29], particle swarm optimization (PSO) [30], ant lion optimization (ALO) [31], spotted hyena optimizer (SHO) [32], binary spring search algorithm (BSSA) [33], grey wolf algorithm (GWO) [34], genetic optimization resampling based particle filtering (GORPF) algorithm [35], and ant colony optimization (ACO) [16]-all of which may be hybridized with ANNs to address the aforementioned disadvantages.…”

Floor Map-Aware Particle Filtering Based Indoor Navigation System

“…A KF is a well-known estimation method in the Bayesian framework, but can only deal with linear problems with Gaussian models. The extended Kalman filter (EKF) and unscented Kalman filter (UKF) are two KF alternatives that can be used in indoor navigation, although these two estimation methods have some limitations [30]. For instance, both EKF and UKF have challenges in coping with non-Gaussian model problems and require known prior initial position information.…”