2020/07/22 by Varsha Suresh, Wei Tsang Ooi, Suresh, Varsha +1
Computer Science · #Anomaly Detection Techniques and Applications #Data Visualization and Analytics #FOS: Computer and information sciences #Machine Learning (cs.LG) #Time Series Analysis and Forecasting #cs.LG
paper · pdf · doi:10.48550/arxiv.2007.11985
The authors have withdrawn this paper as it needs a major revision. An error in the evaluation code invalidates the reported results
openalex publication_date 2020/07/22 · arxiv created 2020/08/01 · arxiv updated 2020/08/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Change-point detection in a time series aims to discover the time points at which some unknown underlying physical process that generates the time-series data has changed. We found that existing approaches become less accurate when the underlying process is complex and generates large varieties of patterns in the time series. To address this shortcoming, we propose Shape-CD, a simple, fast, and accurate change point detection method. Shape-CD uses shape-based features to model the patterns and a conditional neural field to model the temporal correlations among the time regions. We evaluated the performance of Shape-CD using four highly dynamic time-series datasets, including the ExtraSensory dataset with up to 2000 classes. Shape-CD demonstrated improved accuracy (7-60% higher in AUC) and faster computational speed compared to existing approaches. Furthermore, the Shape-CD model consists of only hundreds of parameters and require less data to train than other deep supervised learning models.