Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning

TL;DR

This paper introduces RL4OASD, a reinforcement learning approach for online detection of anomalous subtrajectories on road networks, overcoming limitations of existing methods by not requiring labels and enabling fine-grained anomaly detection.

Contribution

The paper presents a novel RL-based framework that detects anomalous subtrajectories without supervision, improving accuracy and efficiency over state-of-the-art methods.

Findings

Achieves 20-30% better detection accuracy than existing methods.

Processes each data point in less than 0.1ms, enabling real-time detection.

Effectively detects fine-grained anomalies in real-world datasets.

Abstract

Detecting anomalous trajectories has become an important task in many location-based applications. While many approaches have been proposed for this task, they suffer from various issues including (1) incapability of detecting anomalous subtrajectories, which are finer-grained anomalies in trajectory data, and/or (2) non-data driven, and/or (3) requirement of sufficient supervision labels which are costly to collect. In this paper, we propose a novel reinforcement learning based solution called RL4OASD, which avoids all aforementioned issues of existing approaches. RL4OASD involves two networks, one responsible for learning features of road networks and trajectories and the other responsible for detecting anomalous subtrajectories based on the learned features, and the two networks can be trained iteratively without labeled data. Extensive experiments are conducted on two real datasets, and the results show that our solution can significantly outperform the state-of-the-art methods (with 20-30% improvement) and is efficient for online detection (it takes less than 0.1ms to process each newly generated data point).