Kinematic Detection of Anomalies in Human Trajectory Data
This work addresses the challenge of leveraging kinematic data for tasks like anomaly detection in human trajectories, which is incremental as it applies existing methods to a new aspect of trajectory data.
The paper tackled the problem of using kinematic features (how individuals move) from human trajectory data for individual identification and anomaly detection, showing that simple kinematic features with standard algorithms significantly improve results, such as identifying individuals with a strong signal.
Historically, much of the research in understanding, modeling, and mining human trajectory data has focused on where an individual stays. Thus, the focus of existing research has been on where a user goes. On the other hand, the study of how a user moves between locations has great potential for new research opportunities. Kinematic features describe how an individual moves between locations and can be used for tasks such as identification of individuals or anomaly detection. Unfortunately, data availability and quality challenges make kinematic trajectory mining difficult. In this paper, we leverage the Geolife dataset of human trajectories to investigate the viability of using kinematic features to identify individuals and detect anomalies. We show that humans have an individual "kinematic profile" which can be used as a strong signal to identify individual humans. We experimentally show that, for the two use-cases of individual identification and anomaly detection, simple kinematic features fed to standard classification and anomaly detection algorithms significantly improve results.