Shape-CD: Change-Point Detection in Time-Series Data with Shapes and Neurons
This addresses improved accuracy and efficiency in change-point detection for dynamic time-series applications, though it appears incremental as it builds on shape-based and neural methods.
The paper tackles the problem of change-point detection in complex time-series data with varied patterns, proposing Shape-CD, which achieved 7-60% higher AUC and faster speed compared to existing methods.
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.