High-Accuracy and Real-Time Indoor Positioning System Based on Visible Light Communication and Mobile Robot

Li, Xianmin; Yan, Zihong; Huang, Linyi; Chen, Shihuan; Liu, Manxi

doi:10.1155/2020/3124970

Cited by 4 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the application of wireless communication, the two wireless nodes can be set to a visible environment [10][11][12]. In this case, a system state model based on the kinematics principle is established in this paper as the following:…”

Section: Genetic Optimizationmentioning

confidence: 99%

Multi-Source Data High-Performance Indoor Positioning considering Genetic Optimization Neural Network Algorithm

Chu

Zhang

Chen

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In order to effectively solve the problem of relatively large errors in individual positioning strategies in indoor environments, this paper applies the genetic optimization neural network algorithm to indoor location based on multi-source information fusion. The range of the geomagnetic fitness is constrained based on the results obtained by using the wireless WiFi positioning for combination and matching, which can reduce the value of the matching error effectively. Subsequently, the global optimal value of the indoor network is calculated based on the genetic algorithm, which can optimize the initial value and threshold of the neural network after genetic optimization so as to improve the accuracy of the network to the greatest extent possible while accelerating the convergence speed at the same time. After the optimization processing is completed, fusion training can be performed on the coordinates of the actual positions based on the obtained combination positioning situation and the predicted positioning result in the indoor network. Finally, the optimal positioning result can be obtained accordingly. Through the analysis of practical cases, it can be known that the mean square error predicted based on the genetic optimization neural network calculated by using the genetic algorithm can be effectively reduced by 76%, and the accuracy of the fusion positioning can be increased by 48% on average compared with the accuracy of a single positioning strategy. Hence, the method put forward in this paper has effectively improved the positioning accuracy, which suggests that its positioning performance is superior.

show abstract

Section: Genetic Optimizationmentioning

confidence: 99%