https://doi.org/10.1140/epjp/s13360-025-06569-6
Regular Article
A novel multivariate feature extraction method based on MVMD and optimized multivariate slope entropy
1
School of Automation and Information Engineering, Xi’an University of Technology, 710048, Xi’an, China
2
Key Laboratory of Ocean Observation Technology, Ministry of Natural Resources, 300112, Tianjin, China
Received:
13
November
2024
Accepted:
22
June
2025
Published online:
30
June
2025
Multivariate slope entropy (mvSloEn) has emerged as an effective nonlinear index for assessing the complexity of multi-channel signals and has been extensively applied for feature extraction across various domains. However, its threshold values influence symbol division, affecting feature extraction effectiveness. To solve this problem, optimized multivariate slope entropy (OmvSloEn), which uses a snake optimizer to fine-tune threshold values, is proposed. Furthermore, a novel multivariate feature extraction method has been proposed based on multivariate variational mode decomposition (MVMD) and OmvSloEn, which facilitates parallel processing and information fusion of multi-channel signals, making it easier to explore the differences in complexity of these signals across different frequency bands. Simulation experiments reveal that OmvSloEn outperforms other multivariate entropies in distinguishing noise signals. Experiments conducted on two public datasets show that the proposed feature extraction technique attains superior recognition rates for distinguishing between various bearing and ship-radiated noise signals.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.