Dealing with Imbalanced Data for GPS Trajectory Outlier Detection
Nguyen Van Chien, Van-Hau Nguyen, Le Van Quoc Anh · Annals of Computer Science and Information Systems · 2022
Abstract4Detecting 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.