Title :
The city taxi quantity prediction via GM-BP model
Author :
Zhang Xuewu;Liu Yongjun
Author_Institution :
Department of Computer Science, Changshu Institute of Technology, Changshu, China
fDate :
6/1/2015 12:00:00 AM
Abstract :
Influenced by many factors, the variation process of city taxi quantity is nonlinear, grey and random. So, the single prediction model can only reflect part information of variation process, and its prediction accuracy is low. In order to improve prediction accuracy, the grey neural network method is put forward based on the analysis of city taxi quantity variation process. First, GM(1,1) model is used to predict the variation trend of city taxi quantity; then, the BP neural network is trained through the prediction errors of GM(1,1), and trained model is used to predict the nonlinear and uncertain variation of city taxi quantity; finally, two results are combined to calculate the final predicting result. Grey neural network was used to predict taxi quantity of Nanjing. The experimental results indicated that the grey neural network can improve city taxi quantity prediction accuracy, describe the variation rule of the city taxi quantity, and have widespread application prospect in the field of nonlinear prediction.
Keywords :
"Predictive models","Public transportation","Cities and towns","Neural networks","Data models","Accuracy","Mathematical model"
Conference_Titel :
Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2015 IEEE International Conference on
Print_ISBN :
978-1-4799-8728-3
DOI :
10.1109/CYBER.2015.7288183