• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Tools with Artificial Intelligence >Optimization of Traffic Lights Timing Based on Multiple Neural Networks
【24h】

Optimization of Traffic Lights Timing Based on Multiple Neural Networks

机译：基于多神经网络的交通信号灯时序优化

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper presents a neural networks based traffic light controller for urban traffic road intersection called EOM-MNN Controller (Environment Observation Method based on Multiple Neural Networks Controller). Traffic congestion leads to problems like delays and higher fuel consumption. Consequently, alleviating congested situation is not only good to economy but also to environment. The problem of traffic light control is very challenging. Traditional mathematical methods have some limitations when they are applied in traffic control. Thus, modern artificial intelligent ways have gained more and more attentions. In this work, EOM is a very interesting mathematical method for determining traffic lights timing that was developed by Ejzenberg [4]. However, this method has some implications in which multiple neural networks were proposed to improve such problems. The solution was compared with the conventional method through scenario of simulation in microscopic traffic simulation software.
机译：本文提出了一种基于神经网络的交通信号灯控制器，用于城市交通道路交叉口，称为EOM-MNN控制器（基于多神经网络控制器的环境观测方法）。交通拥堵导致诸如延误和更高的燃油消耗之类的问题。因此，缓解拥挤状况不仅有利于经济，而且有利于环境。交通信号灯控制的问题非常具有挑战性。传统数学方法在交通控制中的应用存在一定的局限性。因此，现代人工智能方式越来越受到人们的关注。在这项工作中，EOM是由Ejzenberg [4]开发的一种非常有趣的用于确定交通信号灯正时的数学方法。但是，此方法具有一定的含义，其中提出了多个神经网络来改善此类问题。通过微观交通仿真软件中的仿真场景，将该解决方案与传统方法进行了比较。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号