With the acceleration of urbanization and the increase in the number of motor vehicles, more and more social problems such as traffic congestion have emerged. Accordingly, efficient and accurate traffic flow prediction has become a research hot spot in the field of intelligent transportation. However, traditional machine learning algorithms cannot further optimize the model with the increase of the data scale, and the deep learning algorithms perform poorly in mobile application or real-time application; how to train and update deep learning models efficiently and accurately is still an urgent problem since they require huge computation resources and time costs. Therefore, an incremental learning-based CNN-LTSM model, IL-TFNet, is proposed for traffic flow prediction in this study. The lightweight convolution neural network-based model architecture is designed to process spatiotemporal and external environment features simultaneously to improve the prediction performance and prediction efficiency of the model. Especially, the K-means clustering algorithm is applied as an uncertainty feature to extract unknown traffic accident information. During the model training, instead of the traditional batch learning algorithm, the incremental learning algorithm is applied to reduce the cost of updating the model and satisfy the requirements of high real-time performance and low computational overhead in short-term traffic prediction. Furthermore, the idea of combining incremental learning with active learning is proposed to fine-tune the prediction model to improve prediction accuracy in special situations. Experiments have proved that compared with other traffic flow prediction models, the IL-TFNet model performs well in short-term traffic flow prediction.

Traffic breakdown is the transition of traffic flow from an uncongested state to a congested state. During peak hours, when a large number of on-ramp vehicles merge with mainline traffic, it can cause a significant drop in speed and subsequently lead to traffic breakdown. Therefore, ramp meters have been used to regulate the traffic flow from the ramps to maintain stable traffic flow on the mainline. However, existing traffic breakdown prediction models do not consider on-ramp traffic flow. In this paper, an algorithm based on artificial neural networks (ANN) is developed to predict the probability of a traffic breakdown occurrence on freeway segments with merging traffic, considering temporal and spatial correlations of the traffic conditions from the location of interest, the ramp, and the upstream and downstream segments. The feature selection analysis reveals that the traffic condition of the ramps has a significant impact on the occurrence of traffic breakdown on the mainline. Therefore, the traffic flow characteristics of the on-ramp, along with other significant features, are used to build the ANN model. The proposed ANN algorithm can predict the occurrence of traffic breakdowns on freeway segments with merging traffic with an accuracy of 96%. Furthermore, the model has been deployed at a different location, which yields a predictive accuracy of 97%. In traffic operations, the high probability of the occurrence of a traffic breakdown can be used as a trigger for the ramp meters.

With the development of urbanization, the number of residents’ motor vehicles has increased sharply, and traffic congestion problem has become increasingly serious. The construction of Intelligent Traffic System (ITS) has become the main means to alleviate traffic congestion. Short-term traffic flow prediction has guiding significance for residents’ travel planning and intelligent management of transportation, and has become one of the research hotspots in intelligent transportation field.Therefore, A short-term traffic flow prediction method based on the spatio-temporal characteristics of complex road networks is proposed to further improve the prediction accuracy and reduce the prediction cost. Firstly, a graph convolutional network (GCN) capable of processing non-Euclidean data structures is used to extract the spatial characteristics of traffic flow data. Then, the long and short-term memory (LSTM) neural network is used to process the time characteristics. Finally, the two are combined to realize the effective processing of the spatio-temporal characteristics of traffic flow data. Experimental results on the real traffic flow dataset prove the feasibility and effectiveness of the proposed method, and can provide a basis for intelligent traffic control and smart city construction.