Stochastic time–frequency-entropy feature extraction method
Source abstract
Abstract
Entropy-based feature extraction methods have shown marked effectiveness across various fields. However, entropy measures are susceptible to noise interference and typically consider only time-domain information, which leads to suboptimal feature extraction performance. To address these limitations, this paper proposes a novel method: stochastic time–frequency entropy feature extraction. First, the signal-to-noise ratio of the input signal is enhanced through stochastic resonance; then, the time–frequency representation is obtained via wavelet transforms and converted into multivariate signals. Ultimately, the complexity of the multivariate signal is calculated via multivariate slope entropy. Validated through simulation and experimental data analysis, stochastic time–frequency entropy demonstrates superior feature extraction capabilities, outperforming existing methods in terms of performance and robustness.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Blind Source Separation Techniques · Wireless Signal Modulation Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Automation and Information Engineering, Xi’an University of Technology , Xi’an 710048,
Funding
National Nature Science Foundation of China · Xi’an University of Technology Excellent Seed Fund
References (35)
Show source-provided references
1. Multibranch feature extraction and feature multiplexing network for pansharpening10.1109/TGRS.2021.3074624 ↗
2. An event-based motion scene feature extraction framework10.1016/j.patcog.2024.111320 ↗
3. Discriminative approximate regression projection for feature extraction10.1016/j.inffus.2025.103088 ↗
4. An unknow fault diagnosis scheme: A novel random deep forest for fault diagnosis of HVACs10.1016/j.enbuild.2024.114660 ↗
5. Fault diagnosis for permanent magnet synchronous motor with demagnetization fault and sensor fault10.1109/TIM.2024.3460886 ↗
6. A normal-fault sample translator for fault diagnosis with insufficient fault samples10.1016/j.eswa.2024.126109 ↗
7. Two-stage attention network for fault diagnosis and retrieval of fault logs10.1016/j.eswa.2024.123365 ↗
8. Fault monitoring and remaining useful life prediction framework for multiple fault modes in prognostics10.1016/j.ress.2020.107028 ↗
9. TERMA framework for biomedical signal analysis: An economic-inspired approach10.3390/bios6040055 ↗
10. A survey on modulation techniques in molecular communication via diffusion10.1109/COMST.2020.3048099 ↗
11. Extension of high-fidelity time-domain spectral element formulation for phase-field modeling of fracture: A static analysis10.1016/j.engfracmech.2025.110908 ↗
12. Double-optimized symmetric geometric mode decomposition with dispersion entropy and its application in feature extraction10.1016/j.sigpro.2025.110046 ↗
13. Time-frequency self-similarity enhancement network and its application in wind turbines fault analysis10.1016/j.aei.2025.103322 ↗
14. A comparative analysis of soft tissue volumetric alterations utilizing root mean square and positive and negative average calculations through two software10.1016/j.jdent.2025.105730 ↗
15. Joint time-vertex fractional Fourier transform10.1016/j.sigpro.2025.109944 ↗
16. Seismic attenuation estimation using the centroid frequency shift and divergence10.1109/LGRS.2019.2912190 ↗
17. Classification of ictal and interictal EEG using RMS frequency, dominant frequency, root mean instantaneous frequency square and their parameters ratio10.1016/j.bspc.2018.04.007 ↗
18. Anti-strong pipeline vibration method combining frequency variance and amplitude feature for vortex flowmeter10.1016/j.measurement.2020.108193 ↗
19. Succinct and fast empirical mode decomposition10.1016/j.ymssp.2016.09.031 ↗
20. Span entropy: A novel time series complexity measurement with a redesigned phase space reconstruction10.1016/j.aei.2026.104631 ↗
21. An entropy framework for randomness and fuzziness10.1016/j.eswa.2023.122431 ↗
22. Detection of ship echo signals in reverberation background based on sample entropy and multiscale sample entropy10.1016/j.jsv.2024.118910 ↗
23. Spatial permutation entropy distinguishes resting brain states10.1016/j.chaos.2023.113453 ↗
24. A new multi-domain entropy signal classification method10.1016/j.apacoust.2024.110521 ↗
25. Interpolation multiscale amplitude sensitivity permutation Lempel–Ziv complexity and its application to mechanical fault diagnosis10.1109/TIM.2026.3655899 ↗
26. FAHFD: Fractional-order adaptive Higuchi fractal dimension for signal recognition10.1016/j.asoc.2026.114721 ↗
27. Multivariate multiscale sample entropy of traffic time series10.1007/s11071-016-2901-3 ↗
28. Multivariate multiscale variations dispersion entropy and multivariate multiscale variations fuzzy dispersion entropy for time-series analysis10.1109/JSEN.2025.3544242 ↗
29. Double-refined symplectic geometry mode decomposition10.1109/tim.2026.3655946 ↗
30. An entropy fusion method for feature extraction of EEG10.1007/s00521-016-2594-z ↗
31. Multiscale similarity fuzzy Lempel-Ziv complexity and its application in bearing fault diagnosis10.1109/TIM.2026.3660417 ↗
32. Forty years of stochastic resonance10.1038/s42254-021-00401-7 ↗
33. Multiscale symbolic fuzzy entropy: An entropy denoising method for weak feature extraction of rotating machinery10.1016/j.ymssp.2021.108052 ↗
34. Multi-stage image denoising with the wavelet transform10.1016/j.patcog.2022.109050 ↗
35. Multivariate weighted Tsallis slope entropy for rolling bearing fault diagnosis10.1016/j.apacoust.2025.110914 ↗