As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Traffic prediction is an important application in intelligent transportation system (ITS) that leverages data mining and machine learning technologies to tackle traffic challenges such as low efficiency, disorder, congestion and so on. Thanks to the development and popularization of advanced apparatuses, data of traffic conditions are generated every minute in modern traffic system. In our research, we construct a specially designed deep learning model for traffic time series data to predict conditions in different locations. We involve an external data set of travel records, using transfer learning technique to extract and exploit dependencies that are implied by origin-destination information of each record. In the end, we test our model in real data experiment and achieve the best performance among multiple baseline methods.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.