Structural Classification of Locally Stationary Time Series Based on Second-order Characteristics
Preprint
Abstract
Time series classification is crucial for numerous scientific and engineering applications. In this article, we present a numerically efficient, practically competitive, and theoretically rigorous classification method for distinguishing between two classes of locally stationary time series based on their time-domain, second-order characteristics. Our approach builds on the autoregressive approximation for locally stationary time series, combined with an ensemble aggregation and a distance-based threshold for classification. It imposes no requirement on the training sample size, and is shown to achieve zero misclassification error rate asymptotically when the underlying time series differ only mildly in their second-order characteristics. The new method is demonstrated to outperform a variety of state-of-the-art solutions, including wavelet-based, tree-based, convolution-based methods, as well as modern deep learning methods, through intensive numerical simulations and a real EEG data analysis for epilepsy classification.Keywords
All Related Versions
This publication has 41 references indexed in Scilit:
- Reaching the ceiling? Empirical scaling behaviour for deep EEG pathology classificationComputers in Biology and Medicine, 2024
- Hydra: competing convolutional kernels for fast and accurate time series classificationData Mining and Knowledge Discovery, 2023
- MultiRocket: multiple pooling operators and transformations for fast and effective time series classificationData Mining and Knowledge Discovery, 2022
- ROCKET: exceptionally fast and accurate time series classification using random convolutional kernelsData Mining and Knowledge Discovery, 2020
- Deep learning for time series classification: a reviewData Mining and Knowledge Discovery, 2019
- Time series representation and similarity based on local autopatternsData Mining and Knowledge Discovery, 2015
- Using dynamic time warping distances as features for improved time series classificationData Mining and Knowledge Discovery, 2015
- Time series classification with ensembles of elastic distance measuresData Mining and Knowledge Discovery, 2014
- Classification of time series by shapelet transformationData Mining and Knowledge Discovery, 2013
- Using derivatives in time series classificationData Mining and Knowledge Discovery, 2012