Novel multi input parameter time delay neural network model for traffic flow prediction

2016 ◽  
Author(s):  
Kumar Abhishek
Keyword(s):  
Neural Network ◽  
Time Delay ◽  
Traffic Flow ◽  
Network Model ◽  
Neural Network Model ◽  
Input Parameter ◽  
Traffic Flow Prediction ◽  
Flow Prediction

scholarly journals Short-term traffic flow prediction based on cuckoo search-wavelet neural network

2021 ◽  
Author(s):  
Haibo Lv ◽  
Yuheng Kang ◽  
Zhou Shen
Keyword(s):  
Neural Network ◽  
Traffic Flow ◽  
Network Model ◽  
Cuckoo Search ◽  
Wavelet Neural Network ◽  
Urban Traffic ◽  
Prediction Algorithm ◽  
Step Size ◽  
Traffic Flow Prediction ◽  
Flow Prediction

Abstract The nonlinear fluctuation and uncertainty that characterize urban traffic flow are well-known. An Improved Cuckoo Search-Wavelet Neural Network (ICS-WNN) prediction model for urban traffic flow is suggested in order to increase the accuracy of traffic flow predictions. After the original traffic flow data have been cleaned up and normalized, the traffic flow prediction network model is built by optimizing the wavelet neural network weights and wavelet shrinkage and translation factors based on the adaptive step size and discovery probability of the cuckoo algorithm, and then adding the neural network momentum factor. The traffic flow prediction network model is built in two stages. The results of the experimental simulations demonstrate that the ICS-WNN prediction algorithm has a better fit and accuracy than numerous common optimization prediction techniques, which is encouraging.

scholarly journals An Incremental Learning Based Convolutional Neural Network Model for Large-Scale and Short-Term Traffic Flow

2021 ◽  
Vol 11 (2) ◽  
pp. 143-151
Author(s):  
Feng Yu ◽  
◽  
Jinglong Fang ◽  
Bin Chen ◽  
Yanli Shao
Keyword(s):  
Neural Network ◽  
Traffic Flow ◽  
Neural Network Model ◽  
Incremental Learning ◽  
Prediction Accuracy ◽  
Large Scale ◽  
Flow Data ◽  
Short Term ◽  
Traffic Flow Prediction ◽  
Flow Prediction

Traffic flow prediction is very important for smooth road conditions in cities and convenient travel for residents. With the explosive growth of traffic flow data size, traditional machine learning algorithms cannot fit large-scale training data effectively and the deep learning algorithms do not work well because of the huge training and update costs, and the prediction accuracy may need to be further improved when an emergency affecting traffic occurs. In this study, an incremental learning based convolutional neural network model, TF-net, is proposed to achieve the efficient and accurate prediction of large-scale and short-term traffic flow. The key idea is to introduce the uncertainty features into the model without increasing the training cost to improve the prediction accuracy. Meanwhile, based on the idea of combining incremental learning with active learning, a certain percentage of typical samples in historical traffic flow data are sampled to fine-tune the prediction model, so as to further improve the prediction accuracy for special situations and ensure the real-time requirement. The experimental results show that the proposed traffic flow prediction model has better performance than the existing methods.

Sign in / Sign up

Export Citation Format

Share Document