首页> 外文会议>Engineering applications of bio-inspired artificial neural networks >Artificial Neural Networks as Useful Tools for the Optimization of the Relative Offest between Two Consecutive Sets of Traffic Lights
【24h】

Artificial Neural Networks as Useful Tools for the Optimization of the Relative Offest between Two Consecutive Sets of Traffic Lights

机译:人工神经网络是优化两个连续交通信号灯之间相对距离的有用工具

获取原文
获取原文并翻译 | 示例

摘要

In this paper we present the most important results of our experimentation with artificial neural networks for correcting offset relative error between two consecutive sets of traffic lights. Neural networks allow us to estimate the length of the queue of vehicles stooped in front of the stop line waiting for the red light to change to green. We will check that this length is an essential parameter fo solving the offset problem. Training data and test data for the ANN are provided by a simulator specifically built up for this purpose. The performance of the simulator is tested with real data. An algorithm to improve the offset based on the queue length provided by the ANN was proposed. Finally, it was proved that its proposals provide a path to the optimal offset.
机译:在本文中,我们介绍了人工神经网络用于校正两组连续交通信号灯之间的偏移相对误差的实验的最重要结果。神经网络使我们能够估计在红线变为绿色之前停在停车线前弯腰的车辆队列的长度。我们将检查该长度是否是解决偏移问题的必要参数。 ANN的训练数据和测试数据由专门为此目的而构建的模拟器提供。模拟器的性能已通过实际数据进行了测试。提出了一种基于人工神经网络提供的队列长度来提高偏移量的算法。最终,证明了其建议为最佳补偿提供了一条途径。

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