Short-term traffic volume prediction is crux for alleviating traffic gridlock. Considering the insufficiently extracted spatiotemporal and periodic characteristics of traffic stream in existing traffic volume forecast studies, this research presents a short-term traffic volume forecast model (WRNCLTCL) that considers spatiotemporal and periodic characteristics. Firstly, the wavelet threshold is used to denoise the initial traffic stream data. Secondly, the CNN-LSTM model is employed to capture the spatiotemporal features of the traffic stream. Considering the degradation problem that may be caused by the model with the increase of network depth, add residual neural units based on CNN. We employ the TCNLSTM model to acquire the periodic characteristics of the traffic stream. Finally, we combine the extracted spatiotemporal and periodic features, and utilize the fully connected layer to obtain the ultimate forecasted results. WRNCL-TCL is applied to real data sets in two different scenarios to validate the forecasting capability of the suggested model. Compared to the benchmark model and the ablation experiment, the consequences suggest that the proposed model exhibits favorable predictive capabilities and can serve as a theoretical foundation for traffic control.

Traffic volume forecast the key to alleviating traffic congestion. However, the relationship between traffic data and outside factors makes the problem more complex. Existing traffic flow forecasting studies seldom consider the relationship between traffic data and outside factors. Therefore, we propose SGA-KGCN-LSTM to solve this problem. The model combines Savitzky-Golay (SG) filter, Knowledge Graph (KG), Graph Convolution Network (GCN), Long Short-Term Memory (LSTM), and Self-Attention Mechanism. Firstly, the SG filter can be employed to reduce the noise of traffic volume data. Then, aiming at the relationship between traffic data and outside factors, the KG theory is introduced, and the knowledge representation is applied to get the embedding of relevant knowledge. Secondly, new road features are obtained by integrating embedded information and traffic flow characteristics. GCN can be employed to acquire the spatial characteristic of traffic stream, and LSTM can be employed to extract the temporal characteristics of traffic stream. Finally, the input feature information is given enough weight by self-attention mechanism. The outcome is subsequently acquired by utilizing the fully connected layer to attain the ultimate consequence. The trajectory data of the Luohu taxi in Shenzhen are used in the experiment. The experimental consequence indicate that the SGA-KGCN-LSTM has high forecasting precision compared with the benchmark model and the ablation experiment.

Pointing at the bounded rationality problem of passenger travel choice in the railway corridor, this paper proposes a travel choice theory considering passengers psychological expectation, and establishes the travel mode decision model based on prospect theory. With the comprehensive prospect value combined by analyzing the travel time, travel expenses and the comfort degree of the psychological reference point, it obtains the passengers travel mode choice results. Taking railway transport corridor from Baoji to Lanzhou as an example, by calculating the comprehensive prospect value, and analyzing the punctuality, the scheduled arrival time, price and the sensitivity from speed on travel choice, it finds out that the passengers tend to choose high-speed rail travel with a higher punctuality rate and tend to a mode with relatively lower fares and faster speed. When the predetermined arrival time is abundant, the travel proportion of choosing the general rail travel with longer travel time and better economy is gradually increasing.