Accurate prediction of bus arrival times is a challenging problem in the public transportation field. Previous studies have shown that to improve prediction accuracy, more heterogeneous measurements provide better results. So what other factors should be added into the prediction model? Traditional prediction methods mainly use the arrival time and the distance between stations, but do not make full use of dynamic factors such as passenger number, dwell time, bus driving efficiency, etc. We propose a novel approach that takes full advantage of dynamic factors. Our approach is based on a Recurrent Neural Network (RNN). The experimental results indicate that a variety of prediction algorithms (such as Support Vector Machine, Kalman filter, Multilayer Perceptron, and RNN) have significantly improved performance after using dynamic factors. Further, we introduce RNN with an attention mechanism to adaptively select the most relevant input factors. Experiments demonstrate that the prediction accuracy of RNN with an attention mechanism is better than RNN with no attention mechanism when there are heterogeneous input factors. The experimental results show the superior performances of our approach on the data set provided by Jinan Public Transportation Corporation.

Aiming at the problems of poor time performance and accuracy in bus stops network optimization, this paper proposes an algorithm based on complex network and graph theory and Beidou Vehicle Location to measure the importance of bus stops. This method narrows the scope of points and edges to be optimized and is applied to the Jinan bus stop network. In this method, the bus driving efficiency, which can objectively reflect actual road conditions, is taken as the weight of the connecting edges in the network, and the network is optimized through the network efficiency. The experimental results show that, compared with the original network, the optimized network time performance is good and the optimized network bus driving efficiency is improved.