An Adaptive Traffic Signal Control Method Based on Historical Error Backpropagation
An error back-propagation and traffic signal technology, applied in the field of intelligent transportation, can solve problems such as increasing huge costs and being unable to adapt to diversified transportation networks, and achieve the effect of reducing transmission delay, reducing space and other phenomena, and low cost.
Active Publication Date: 2022-05-13
广东工业大学华立学院
View PDF13 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, neither of these two methods can adapt to the diversified transportation network, and at the same time, it also increases the huge cost
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0074] Such as figure 1 with figure 2 Shown, the present invention, a kind of adaptive traffic signal control method based on historical error backpropagation, comprises the following steps:
[0075] S1. Collect data;
[0076] In this embodiment, the collected data is specifically collected environmental data, historical data and real-time data and used as a data set for neural network model training, using the set D={X|X 0 ,X 1 ,X 2} means; among them, X 0 represents the environment dataset, X 1 Indicates the real-time data set, X 2 Represents a historical data set; each data set includes the data factors shown in Table 1 below, and the data factor items can be appropriately added during actual implementation;
[0077]
[0078]
[0079] Table 1
[0080] In this embodiment, the data uses the data set of the intersection of Ningxi Road and Xingye Road in Zhuhai City of the Ministry of Transport of the People's Republic of China. Time) and other data, the time un...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an adaptive traffic signal control method based on historical error backpropagation, comprising the following steps: collecting data; data preprocessing, including data cleaning, data simplification and data normalization; constructing an adaptive error reverse Learning model, add CNN neural network to capture unnoticed features, and perform classification processing; model training, use the preprocessed data set as the input of the adaptive error reverse learning model to learn the error direction; The error reverse learning model is evaluated. If the expected error is reached, the training is stopped and used for actual traffic signal control, otherwise the training is continued. The present invention preprocesses the data through the existing sufficient data sets of the traffic department, constructs an adaptive control model, and repeatedly trains the data sets to obtain corresponding thresholds and weights, so that the duration of signal lights can be adaptively adjusted at any traffic intersection .
Description
technical field [0001] The invention belongs to the technical field of intelligent transportation, and in particular relates to an adaptive traffic signal control method based on historical error backpropagation. Background technique [0002] The existing traffic signal light control system has been generally intelligent, but there are few literatures to study the mathematical model of traffic light configuration. Both wireless sensor network and queuing theory have established a system mathematical model. Wireless sensor adaptive control mainly adopts the received signal strength indication distance measurement The algorithm tests the distance between traffic lights and waiting vehicles, and automatically adjusts the time indicated by traffic lights according to the distance. The system improves the traffic capacity of vehicles at intersections. However, due to the use of ZigBee wireless sensor networks, ZigBee has the characteristics of short-distance transmission. Applyin...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G08G1/01G08G1/07G08G1/095H04W84/18G06N3/04G06N3/08
CPCG08G1/0129G08G1/07G08G1/095H04W84/18G06N3/08G06N3/045
Inventor 李有红马静琪汤堡盛王祺森徐泽鹏梁浩楠
Owner 广东工业大学华立学院