A Dynamic Traffic Network Monitoring Algorithm

During the past few years, various traffic forecasting models have been developed to monitor traffic in network. However, these strategies rest on the assumption that the pattern that has been identified will continue into the future. Such these strategies cannot be expected to give good predictions unless this assumption is valid. In this paper, we combine an ARIMA model and SVM model for obtaining a better forecasting performance. In addition, we also introduce judgmental adjustment (JA) technique that has an effect on correcting irregular and infrequent future events. Our approach can improve the prediction power in traffic flow