A time-delay neural network for solving time-dependent shortest path problem
A time-delay neural network for solving time-dependent shortest path problem
复制标题
求解时间相关最短路径问题的时滞神经网络
DOI：
10.1016/j.neunet.2017.03.002
复制
发表时间：
2017-06
期刊：
影响因子：
7.8
通讯作者：
Wei Wang
中科院分区：
文献类型：
--
作者：
Wei Huang;Chunwang Yan;Jinsong Wang;Wei Wang
针对时间依赖的最短路径问题，采用Dijkstra等经典最短路径方法和脉冲耦合神经网络（PCNN）难以得到全局最优解的问题，提出了一种基于时间依赖的最短路径优化方法。在这项研究中，我们提出了一个时间延迟神经网络（TDNN）框架，具有全局最优的解决方案时，解决时间相关的最短路径问题。TDNN的基本思想来自以下机制：最短路径取决于到达目的节点的最早自动波（从起始节点开始）。在TDNN的设计中，网络上的每个节点都被看作是一个神经元，它有两种形式：时间窗口单元和自动波单元。时间窗单元用于在每个时间窗内产生自动波，而自动波单元用于更新自动波的状态。自动波是否离开节点（神经元）取决于自动波的状态。基于在线公共Cordeau实例和纽约路实例对所提方法的性能进行了评估。建议TDNN的质量进行了比较，如Dijkstra和PCNN的经典方法。
This paper concerns the time-dependent shortest path problem, which is difficult to come up with global optimal solution by means of classical shortest path approaches such as Dijkstra, and pulse-coupled neural network (PCNN). In this study, we propose a time-delay neural network (TDNN) framework that comes with the globally optimal solution when solving the time-dependent shortest path problem. The underlying idea of TDNN comes from the following mechanism: the shortest path depends on the earliest auto-wave (from start node) that arrives at the destination node. In the design of TDNN, each node on a network is considered as a neuron, which comes in the form of two units: time-window unit and auto-wave unit. Time-window unit is used to generate auto-wave in each time window, while auto-wave unit is exploited here to update the state of auto-wave. Whether or not an auto-wave leaves a node (neuron) depends on the state of auto-wave. The evaluation of the performance of the proposed approach was carried out based on online public Cordeau instances and New York Road instances. The proposed TDNN was also compared with the quality of classical approaches such as Dijkstra and PCNN.
登录
查看更多内容
DOI：
10.1016/s0020-0255(00)00071-2
发表时间：
2000-11
期刊：
Inf. Sci.
影响因子：
--
作者：
Jzau-Sheng Lin;M. Liu;N. Huang
通讯作者：
Jzau-Sheng Lin;M. Liu;N. Huang
影响因子：
6
作者：
Dongming Zhou;Rencan Nie;Dongfeng Zhao
通讯作者：
Dongming Zhou;Rencan Nie;Dongfeng Zhao
DOI：
10.1090/dimacs/074
发表时间：
2009-07
期刊：
--
影响因子：
--
作者：
C. Demetrescu;A. Goldberg;David S. Johnson
通讯作者：
C. Demetrescu;A. Goldberg;David S. Johnson
DOI：
10.1016/j.physa.2009.10.005
发表时间：
2010-02
影响因子：
3.3
作者：
Feng Yu;Yanjun Li;Tie-Jun Wu
通讯作者：
Feng Yu;Yanjun Li;Tie-Jun Wu
DOI：
10.1109/hpcc.2008.113
发表时间：
2008-09
期刊：
2008 10th IEEE International Conference on High Performance Computing and Communications
影响因子：
--
作者：
Yuxin Tang;Yunquan Zhang;Hu Chen
通讯作者：
Yuxin Tang;Yunquan Zhang;Hu Chen