Prediction of bus arrival time is an important part of intelligent transportation systems. Accurate prediction can help passengers make travel plans and improve travel efficiency. Given the nonlinearity, randomness, and complexity of bus arrival time, this paper proposes the use of a wavelet neural network (WNN) model with an improved particle swarm optimization algorithm (IPSO) that replaces the gradient descent method. The proposed IPSO-WNN model overcomes the limitations of the gradient-based WNN which can easily produce local optimum solutions and stop the training process and thus improves prediction accuracy. Application of the model is illustrated using operational data of an actual bus line. The results show that the proposed model is capable of accurately predicting bus arrival time, where the root-mean square error and the maximum relative error were reduced by 42% and 49%, respectively.

Limited by the low-frequency data acquisition, vehicle global positioning system (GPS) data are difficult to implement in the area of microtraffic simulation. Based on the functional design of mobile phone positioning technology, mobile phones can be used to acquire bus GPS data every second. In this paper, an analytical model is proposed to determine the parameters of signal coordination for bus priority along an arterial based on GPS data of mobile phones. First, bus priority evaluation indicators are established using bus GPS data, which are acquired by mobile phones. Second, the signal timing parameters of the arterial road are optimized, and a preliminary timing plan is developed by evaluating small changes in the plan. Finally, the corresponding final plan is developed using VISSIM micro simulation software. The feasibility of the analytical model is verified by simulating an actual arterial in Fuzhou city, China.

The collaborative development of conventional buses and urban metro has become an important research topic for the priority development of urban public transport. The topic of collaborative optimization of feeder bus route design and operation is studied in this study. The objective function is to minimize the total travel time of passengers and the operation cost of feeder buses. The improved particle swarm optimization (PSO) algorithm is used to solve the collaborative optimization model, and the effectiveness of the model and algorithm is verified through the case study. The research shows that it is feasible in model construction and algorithm to carry out collaborative optimization of feeder bus route design and operation. Compared with the multiple-to-one (M to 1) mode, the multiple-to-multiple (M to M) mode can better satisfy the needs of passengers from different places of departure and destinations to achieve a more reasonable and realistic goal. The case study is based on two metro stations and 16 feeder bus stops on Fuzhou Metro line 2 to obtain two bus routes and a corresponding operation scheme. Under the same topology road network, the operation time of the improved PSO algorithm is much shorter than the DFS algorithm, the total cost error of the feeder bus is 0.04%, and the departure frequency error is 4.6%, which is within the reasonable error range. Therefore, the collaborative optimization model proposed in this study is feasible and effective in optimizing the feeder bus routes and operation.

The subjectivity of selecting training parameters is an important factor affecting the accuracy of short‐term passenger flow prediction of rail transit by long short‐term memory (LSTM) neural network. In order to improve the prediction accuracy, an improved particle swarm optimization (IPSO) algorithm is proposed to optimize the LSTM. The size of the learning factor of the particle swarm optimization (PSO) algorithm is controlled by dynamic adjustment method to improve the global optimization and convergence ability of the algorithm. The number of hidden layer nodes, learning rate and iteration times of the LSTM are optimized by IPSO. The passenger flow data of Dongjiekou station of Fuzhou Metro Line 1 are selected for verification, and the proposed model is compared with the traditional prediction model. The results show that the LSTM optimized by the improved particle swarm optimization algorithm can effectively predict the short‐term passenger flow of rail transit. Compared with the PSO‐LSTM model, the root mean square error predicted by the IPSO‐LSTM model decreases by 10.87% in the peak period and by 26% in the off‐peak period. The results can provide theoretical and technical support for the optimization of rail transit operation scheme.

Accurate and stable short‐term passenger flow prediction is an indispensable part of current intelligent transportation systems. This paper proposes two deep learning prediction models based on convolutional neural networks (CNN) and long short‐term memory neural network (LSTM). Combining the CNN characteristics and the LSTM, the ConvXD‐LSTM extracts passenger flow features through CNN and then inputs the time series into the LSTM. The ConvLSTM converts the weight calculation of the LSTM into convolution operation to realize short‐term passenger flow prediction. Fuzhou Metro Line 1 passenger flow data was used for verification. The models were used to predict the passenger flow of subway stations and cross‐sections and compared with the traditional prediction models. In terms of prediction accuracy, ConvLSTM has the highest accuracy, followed by ConvXD‐LSTM. In terms of running time, ConvXD is the fastest and LSTM takes the longest. ConvXD‐LSTM and ConvLSTM are in the middle of the two models, achieving a good balance between accuracy and efficiency. Compared with ConvXD‐LSTM, ConvLSTM has a relatively simple network structure, which reduces the computational burden and improves the prediction accuracy.