A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation

Abstract Intelligent transportation (e.g., intelligent traffic light) makes our travel more convenient and efficient. With the development of mobile Internet position technologies, it is reasonable to collect spatio-temporal data then leverage these achieve goal transportation, here, prediction plays an important role. In this paper, we provide a comprehensive survey on prediction, which from layer application layer. At first, split whole research scope into four parts bottom up, where are, respectively, data, preprocessing, application. Later, review existing work parts. First, summarize five types according their difference spatial temporal dimensions. Second, focus significant preprocessing techniques: map-matching, cleaning, storage compression. Third, three kinds problems (i.e., classification, generation estimation/forecasting). particular, challenges discuss how methods address challenges. Fourth, list typical applications. Lastly, emerging opportunities. We believe that can help partitioners understand methods, further encourage them solve