Detecting abnormal GPS trajectories derived by the mobility of people, cars, buses, and taxis plays a crucial role in developing applications for intelligent transportation systems. Outlier detection based on classification models is among promising approaches but it faces the imbalanced data problem, where instances labeled as abnormal have a very low number of observations. In this paper, we propose a framework that employs methods to deal with imbalanced data to the problem of GPS trajectory outlier detection. Our experiments show that dealing with imbalanced data beforehand can improve the performance of outlier detection models.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.