期刊
NEUROCOMPUTING
卷 466, 期 -, 页码 139-147出版社
ELSEVIER
DOI: 10.1016/j.neucom.2021.09.040
关键词
Time-varying network; Time-varying neural network; Minimum spanning tree problem; Time-varying neuron; Delay neural network
资金
- National Natural Science Foundation of China [61673295]
- Natural Science Foundation of Tianjin for Distinguished Young Scholars [19JCJQJC61500]
- Natural Science Foundation of Tianjin (General Program) [18JCYBJC85200]
- Natural Science Foundation of Tianjin (Key Program) [18JCZDJC30700]
- National Key R&D Program of China [2018YFC0831405]
This study introduces a time-varying neural network (TVNN) for solving the time-varying minimum spanning tree problem with constraints (CTMST), which outperforms traditional algorithms in terms of parallel computing, response speed, and solution accuracy. Time-varying neurons play a key role in achieving these improvements, making the proposed algorithm more efficient on large-scale time-varying networks.
In this study, we propose a time-varying neural network (TVNN) for solving the time-varying minimum spanning tree problem with constraints (CTMST), which is a variant of the time-varying network minimum spanning tree problem (TNMSTP), a well-known NP-hard problem. Unlike traditional algorithms that use heuristic search, the proposed TVNN is based on time-varying neurons and can achieve parallel computing without any training requirements. Time-varying neurons are novel computational neurons designed in this work. They consist of six parts: input, wave receiver, neuron state, wave generator, wave sender, and output. The parallel computing strategy and self-feedback mechanism of the proposed algorithm greatly improve the response speed and solution accuracy on large-scale time-varying networks. The analysis of time complexity and experimental results on the New York City dataset show that the performance of the proposed algorithm is significantly improved compared with the existing methods. (c) 2021 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据