Multichannel-Based Multiview Shallow Fusion for Time Series Classification and Its Application in Fault Diagnosis
- 25 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 55 (6) , 4052-4063
Abstract
In the current time series classification (TSC) field, shallow concatenation, deep fusion, and hybrid ensemble multichannel frameworks (MCF) represented by convolution-based, deep learning, and hybrid methods have achieved competitive TSC performance. However, the massive kernels, deep fusion, and heterogeneous ensemble mechanisms, which are the core of the three frameworks, respectively, lead to overfitting risks. Therefore, in this article, a novel convolution-based TSC algorithm multichannel-based multiview shallow fusion (MC-MSF) within a new shallow fusion ensemble-based MCF is proposed. MC-MSF enhances feature diversity, quality, and classifier diversity while suppressing the overfitting risks via three shallow components. For feature diversity, the original series is mapped to the connected multichannel series spaces, and then diverse pooling features are extracted via a single-layer convolution with fewer kernels. For feature quality, the power of proportion of positive values (PPPV) features with adaptive powers are extracted based on alternating gradient descent, and the multiview shallow feature fusion is implemented to generate fused features. For classifier diversity, diverse linear classifiers are trained on the combined multiview feature vectors to ensemble homogeneously. The state-of-the-art TSC accuracy is achieved by MC-MSF via the sequential operation of three effective shallow components, as verified by comparative experiments on the public UCR and real excavator fault diagnosis application datasets.Keywords
Funding Information
- National Natural Science Foundation of China (62373128, 62203143)
This publication has 38 references indexed in Scilit:
- FT-FVC: fast transformation-based feature vector concatenation for time series classificationApplied Intelligence, 2023
- MultiRocket: multiple pooling operators and transformations for fast and effective time series classificationData Mining and Knowledge Discovery, 2022
- Random Dilated Shapelet Transform: A New Approach for Time Series Shapelets2022
- The FreshPRINCE: A Simple Transformation Based Pipeline Time Series Classifier2022
- On the Usage and Performance of the Hierarchical Vote Collective of Transformation-Based Ensembles Version 1.0 (HIVE-COTE v1.0)2020
- InceptionTime: Finding AlexNet for time series classificationData Mining and Knowledge Discovery, 2020
- ROCKET: exceptionally fast and accurate time series classification using random convolutional kernelsData Mining and Knowledge Discovery, 2020
- Proximity Forest: an effective and scalable distance-based classifier for time seriesData Mining and Knowledge Discovery, 2019
- The great time series classification bake off: a review and experimental evaluation of recent algorithmic advancesData Mining and Knowledge Discovery, 2016
- The Elements of Statistical Learning2009