Araştırma Makalesi

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

Cilt: 17 Sayı: 3 16 Ekim 2026
PDF İndir
TR EN

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

Öz

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.

Anahtar Kelimeler

Etik Beyan

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.

Kaynakça

  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.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Derin Öğrenme, Makine Öğrenme (Diğer), Biyomedikal Mühendisliği (Diğer)

Bölüm

Araştırma Makalesi

Yayımlanma Tarihi

16 Ekim 2026

Gönderilme Tarihi

8 Nisan 2026

Kabul Tarihi

5 Ağustos 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 17 Sayı: 3

Kaynak Göster

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. DÜMF MD. 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 (01 Ekim 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”, DÜMF MD, c. 17, sy 3, Eki. 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 (01 Ekim 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. DÜMF MD. 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, c. 17, sy 3, Ekim 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. DÜMF MD. 01 Ekim 2026;17(3). doi:10.24012/dumf.1926196
DUJE tarafından yayınlanan tüm makaleler, Creative Commons Atıf 4.0 Uluslararası Lisansı ile lisanslanmıştır. Bu, orijinal eser ve kaynağın uygun şekilde belirtilmesi koşuluyla, herkesin eseri kopyalamasına, yeniden dağıtmasına, yeniden düzenlemesine, iletmesine ve uyarlamasına izin verir. 24456