In reality, readings of sensors on highways are usually missing at various unexpected moments due to some sensor or communication errors. These missing values do not only influence the real-time traffic monitoring but also prevent further traffic data mining. In this paper, we propose a multi-view learning method to estimate the missing values for traffic-related time series data. The model combines data-driven algorithms (long-short term memory and support vector regression) and collaborative filtering techniques. It can consider the local and global variation in temporal and spatial views to capture more information from the existing data. The estimations of missing values from four views are aggregated to obtain a final value with a kernel function. Data from a highway network are used to evaluate the performance of the proposed model in terms of accuracy, precision, and agreement. The results indicate that our proposed model outperforms other baselines, especially for block missing pattern with a high missing ratio. Furthermore, the sensitivity of the parameters is analyzed. We can conclude that combining different views can improve the performance of the imputation.

Metro passenger flow forecasting is an essential component of intelligent transportation system. To enhance the forecasting accuracy and explainable of traditional models, a hybrid model combining symbolic regression and Autoregressive Integrated Moving Average Model (ARIMA) was proposed in this paper. It can take unique strength of each single model to capture the complexity patterns beneath data structure. Using the real data from Xi’an metro line 1, the performance of the hybrid model was compared with the ARIMA model and Back Propagation (BP) neural networks. The results show that the hybrid model outperforms other two models. Mean Absolute Percentage Error (MAPE) of hybrid models have an extra 54.24%, 58.98% increase over the BP neural networks and an extra 64.44%, 68.27% increase over the ARIMA models for entrance and exit respectively. In addition, the t-test of MAPE during workday and holiday reflects the hybrid model possesses comparable forecasting ability under different conditions. Moreover, with the increase of the prediction steps, the superiority of the proposed model is more significant.