A Hierarchical Piecewise Approximation Framework for Pattern-Based Sequence Learning

Patrick Van der Spiegel, Johan Loeckx

Track: Type A (Regular Papers)

Keywords: pattern recognition, sequence learning, anomaly detection

Abstract: Several existing anomaly detection (AD) algorithms that work on sequence data employ similar pipelines that convert subsequences into piecewise approximations before aggregating these into a model. However, choices in sequence segmentation, representation, distance calculation, and modelling approaches affect detection performance across different anomaly types. We propose a framework that formalises these pipeline components and their parameters, enabling systematic evaluation of pipeline configurations across specific sequence learning tasks. Through this formalisation, we introduce a novel hierarchical piecewise approximation model based on nested words. As far as we know, we are the first to use nested words in this context. Using the UCR Time Series Anomaly Archive, we demonstrate that specific framework configurations effectively identify subsequences corresponding to specific anomaly definitions. On this benchmark, the pipelines implemented using our framework achieve performance comparable to state-of-the-art methods, including deep learning approaches. We provide our framework as an open-source Python module to facilitate the exploration of pipeline configurations across various sequence learning tasks.

Serve As Reviewer: ~Patrick_Van_der_Spiegel1

Submission Number: 72