Generating Hierarchical Structures for Improved Time Series Classification Using Stochastic Splitting Functions

TL;DR

This paper presents a new hierarchical clustering method with stochastic splitting functions that improves multi-class time series classification by automatically generating hierarchies without prior knowledge, tested on 46 datasets.

Contribution

Introduces a stochastic splitting function-based hierarchical clustering approach that constructs hierarchies without prior information, enhancing classification performance in time series datasets.

Findings

Significant performance improvements with Rocket and SVM classifiers on multiple datasets.

The number of classes and flat classification scores are key factors influencing HC performance.

Different splitting functions affect the hierarchy quality and classification results.

Abstract

This study introduces a novel hierarchical divisive clustering approach with stochastic splitting functions (SSFs) to enhance classification performance in multi-class datasets through hierarchical classification (HC). The method has the unique capability of generating hierarchy without requiring explicit information, making it suitable for datasets lacking prior knowledge of hierarchy. By systematically dividing classes into two subsets based on their discriminability according to the classifier, the proposed approach constructs a binary tree representation of hierarchical classes. The approach is evaluated on 46 multi-class time series datasets using popular classifiers (svm and rocket) and SSFs (potr, srtr, and lsoo). The results reveal that the approach significantly improves classification performance in approximately half and a third of the datasets when using rocket and svm as the classifier, respectively. The study also explores the relationship between dataset features and HC performance. While the number of classes and flat classification (FC) score show consistent significance, variations are observed with different splitting functions. Overall, the proposed approach presents a promising strategy for enhancing classification by generating hierarchical structure in multi-class time series datasets. Future research directions involve exploring different splitting functions, classifiers, and hierarchy structures, as well as applying the approach to diverse domains beyond time series data. The source code is made openly available to facilitate reproducibility and further exploration of the method.