RESEARCHarXiv CS.LG·8d ago
A Novel Evaluation Metric for Unsupervised Learning in AIS-Based Maritime Anomaly Detection: MADQI
This paper introduces a new framework for detecting anomalies in maritime Automatic Identification System (AIS) datasets, focusing on abnormal vessel behaviors. It proposes a novel quality metric, MADQI, to evaluate the performance of unsupervised learning models in detecting these anomalies without requiring labeled data.
27