Research Article
A Real Time Tracking Method for Intelligent Logistics Delivery Based on Recurrent Neural Network
@INPROCEEDINGS{10.1007/978-3-031-50552-2_8, author={Xunyan Bao and Dong’e Zhou}, title={A Real Time Tracking Method for Intelligent Logistics Delivery Based on Recurrent Neural Network}, proceedings={Advanced Hybrid Information Processing. 7th EAI International Conference, ADHIP 2023, Harbin, China, September 22-24, 2023, Proceedings, Part IV}, proceedings_a={ADHIP PART 4}, year={2024}, month={3}, keywords={Smart logistics Path planning Real time tracking}, doi={10.1007/978-3-031-50552-2_8} }- Xunyan Bao
Dong’e Zhou
Year: 2024
A Real Time Tracking Method for Intelligent Logistics Delivery Based on Recurrent Neural Network
ADHIP PART 4
Springer
DOI: 10.1007/978-3-031-50552-2_8
Abstract
In order to further improve the real-time tracking effect of intelligent logistics distribution, this paper proposes a real-time tracking method for intelligent logistics distribution based on recurrent neural networks. Firstly, relevant analysis was conducted on real-time tracking of intelligent logistics delivery, and the planning process of order information and road information was determined. Secondly, considering the dynamic real-time traffic conditions and constantly updated customer orders analyzed above, an online target tracking model based on recurrent neural networks was established to predict the status of each node, and then correct the corresponding target status. Finally, Hungarian algorithm is used to solve the data association problem to reduce the detector error to the tracking algorithm. Finally, the Loss function is used to optimize the model performance and achieve accurate real-time tracking of intelligent logistics distribution. The results indicate the feasibility of the proposed method in practical applications, and by comparing it with other similar methods in solving the objective function, the advantages of this method in real-time tracking of intelligent logistics distribution are further verified, with high tracking accuracy.
