Research Article

Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for sEMG Gesture Recognition

Volume: 17 Number: 3 October 16, 2026
TR EN

Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for sEMG Gesture Recognition

Abstract

Accurate recognition of surface electromyography (sEMG) signals is essential for intuitive human–machine interaction and myoelectric prosthetic control. However, the inherently transient, nonstationary, and low-amplitude nature of sEMG signals limits the effectiveness of conventional time–frequency representations and deep learning models, which often struggle to capture short-duration neuromuscular events and the multi-scale spectral–temporal characteristics of muscle activity. To address these challenges, this study introduces the quadratic morphing morlet (QMM) wavelet, a newly formulated and fully admissible wavelet designed to enhance transient resolution and spectral selectivity. Building upon this improved representation, a hybrid deep-learning architecture, the multi-scale frequency-attentive temporal network (MFATNet), is proposed as a novel hybrid deep learning architecture. MFATNet integrates tri-branch multi-scale spectral encoding, frequency-wise attention, and dilated temporal modeling to jointly capture spectral diversity, frequency adaptivity, and gesture dynamics within a unified framework. The proposed QMM–MFATNet pipeline is evaluated on the 52-class hand-gesture corpus of the NinaPro DB1 dataset, comprising sEMG recordings from 27 subjects, wherein QMM-based continuous wavelet transform (CWT) representations are used to generate high-resolution scalograms for subsequent model training. Experimental results indicate that QMM provides sharper and more discriminative scalograms than classical Morlet, Gaussian, and Mexican Hat wavelets. Additionally, MFATNet outperforms standard CNN, ResNet, and MobileNet models, achieving the highest accuracy (93.13%) and F1-score (93.15%). Comparisons of different wavelet types further demonstrate the superiority of QMM, which yields a mean accuracy of 0.9313 ± 0.0194, surpassing all traditional kernels.

Keywords

Ethical Statement

This study was conducted using the publicly available NinaPro DB1 dataset. No new experiments involving human participants or animals were performed by the authors. The dataset was collected and published by its original creators under their own ethical approvals and data collection procedures. Therefore, no additional ethical approval was required for this study. All analyses were carried out on anonymized data in accordance with relevant research and publication ethics principles.

References

  1. [1] A. Vijayvargiya, B. Singh, R. Kumar, and J. M. R. S. Tavares, “Human lower limb activity recognition techniques, databases, challenges and its applications using sEMG signal: An overview,” Biomed. Eng. Lett., vol. 12, no. 4, pp. 343–358, Jun. 2022, DOI: 10.1007/S13534-022-00236-W.
  2. [2] S. Karheily, A. Moukadem, J. B. Courbot, and D. O. Abdeslam, “sEMG time–frequency features for hand movements classification,” Expert Syst. Appl., vol. 210, Dec. 2022, Art. no. 118282, DOI: 10.1016/J.ESWA.2022.118282.
  3. [3] J. M. Lopez-Villagomez, J. M. Lopez-Hernandez, R. I. Mata-Chavez, C. Rodriguez-Donate, Y. Guzman-Castro, and E. Cabal-Yepez, “Comparative evaluation of EMG signal classification techniques across temporal, frequency, and time-frequency domains using machine learning,” Appl. Sci., vol. 16, no. 2, Jan. 2026, Art. no. 1058, DOI: 10.3390/APP16021058.
  4. [4] S. M. Sid’El Moctar, I. Rida, and S. Boudaoud, “Comprehensive review of feature extraction techniques for sEMG signal classification: From handcrafted features to deep learning approaches,” IRBM, vol. 45, no. 6, Dec. 2024, Art. no. 100866, DOI: 10.1016/J.IRBM.2024.100866.
  5. [5] T. Zaim, S. Abdel-Hadi, R. Mahmoud, A. Khandakar, S. M. Rakhtala, and M. E. H. Chowdhury, “Machine learning- and deep learning-based myoelectric control system for upper limb rehabilitation utilizing EEG and EMG signals: A systematic review,” Bioengineering, vol. 12, no. 2, Feb. 2025, Art. no. 144, DOI: 10.3390/BIOENGINEERING12020144.
  6. [6] T. Prabhavathy, V. K. Elumalai, E. Balaji, and D. Sandhiya, “A surface electromyography based hand gesture recognition framework leveraging variational mode decomposition technique and deep learning classifier,” Eng. Appl. Artif. Intell., vol. 130, Apr. 2024, Art. no. 107669, DOI: 10.1016/J.ENGAPPAI.2023.107669.
  7. [7] M. A. Ozdemir, D. H. Kisa, O. Guren, and A. Akan, “Hand gesture classification using time–frequency images and transfer learning based on CNN,” Biomed. Signal Process. Control, vol. 77, Aug. 2022, Art. no. 103787, DOI: 10.1016/J.BSPC.2022.103787.
  8. [8] L. Wang, J. Fu, H. Chen, and B. Zheng, “Hand gesture recognition using smooth wavelet packet transformation and hybrid CNN based on surface EMG and accelerometer signal,” Biomed. Signal Process. Control, vol. 86, Sep. 2023, Art. no. 105141, DOI: 10.1016/J.BSPC.2023.105141.

Details

Primary Language

English

Subjects

Deep Learning, Machine Learning (Other), Biomedical Engineering (Other)

Journal Section

Research Article

Publication Date

October 16, 2026

Submission Date

April 8, 2026

Acceptance Date

August 5, 2026

Published in Issue

Year 2026 Volume: 17 Number: 3

APA
Tekin, H. (2026). Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for sEMG Gesture Recognition. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 17(3). https://doi.org/10.24012/dumf.1926196
AMA
1.Tekin H. Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for sEMG Gesture Recognition. DUJE. 2026;17(3). doi:10.24012/dumf.1926196
Chicago
Tekin, Hazret. 2026. “Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for SEMG Gesture Recognition”. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi 17 (3). https://doi.org/10.24012/dumf.1926196.
EndNote
Tekin H (October 1, 2026) Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for sEMG Gesture Recognition. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi 17 3
IEEE
[1]H. Tekin, “Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for sEMG Gesture Recognition”, DUJE, vol. 17, no. 3, Oct. 2026, doi: 10.24012/dumf.1926196.
ISNAD
Tekin, Hazret. “Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for SEMG Gesture Recognition”. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi 17/3 (October 1, 2026). https://doi.org/10.24012/dumf.1926196.
JAMA
1.Tekin H. Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for sEMG Gesture Recognition. DUJE. 2026;17. doi:10.24012/dumf.1926196.
MLA
Tekin, Hazret. “Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for SEMG Gesture Recognition”. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, vol. 17, no. 3, Oct. 2026, doi:10.24012/dumf.1926196.
Vancouver
1.Hazret Tekin. Quadratic Morphing Morlet Transform and Multi-Scale Frequency-Attentive Temporal Network for sEMG Gesture Recognition. DUJE. 2026 Oct. 1;17(3). doi:10.24012/dumf.1926196