The invention provides an optimization method for traffic information estimation, and the method comprises the steps: constructing a neural network model for optimization, and the neural network model comprises an input layer, an output layer and six middle layers; required parameters are input through an input layer, each parameter is input through a neuron, and the required parameters comprise the number of cellular network signals of a current cell, the number of cellular network signals of a previous cell, the number of cellular network signals of a latter cell and at least one piece of estimated traffic information. The traffic information comprises traffic flow or vehicle speed; the input parameters are optimized through the middle layer; and outputting the optimized estimated traffic information through an output layer. The method has the advantages that estimation errors caused by randomness can be effectively reduced, and therefore it is ensured that traffic information estimation is more accurate.
本发明提供一种交通信息估计的优化方法,方法包括构建用于优化的神经网络模型,神经网络模型包括一个输入层、一个输出层和六个中间层;通过输入层输入所需的参数,且每一个参数均通过一个神经元进行输入,所需的参数包括当前小区的蜂窝网络信号的数量、前一个小区的蜂窝网络信号的数量和后一个小区的蜂窝网络信号的数量以及至少一个估计得到的交通信息,交通信息包括交通流量或车速;通过中间层对输入的参数进行优化;通过输出层输出优化后的估计交通信息。本发明的优点:能够有效降低随机性带来的估计误差,从而确保交通信息估计更加准确。
Optimization method for traffic information estimation
一种交通信息估计的优化方法
2023-09-08
Patent
Electronic Resource
Chinese
Traffic information estimation device and traffic information estimation method
European Patent Office | 2018
|TRAFFIC INFORMATION ESTIMATION DEVICE AND TRAFFIC INFORMATION ESTIMATION METHOD
European Patent Office | 2017
|TRAFFIC INFORMATION ESTIMATION DEVICE AND TRAFFIC INFORMATION ESTIMATION METHOD
European Patent Office | 2016
|TRAFFIC INFORMATION ESTIMATION DEVICE AND TRAFFIC INFORMATION ESTIMATION METHOD
European Patent Office | 2018
|