Geodesic
A Methodology to Rank Importance of Frequencies and Channels in Electromyography Data with Decision Tree Classifiers
Russian journal of nonlinear dynamics, Tome 20 (2024) no. 5, pp. 895-906.

Voir la notice de l'article provenant de la source Math-Net.Ru

This study presents a methodology for identifying the most informative frequencies and channels in electromyography (EMG) data to evaluate muscle recovery using Decision Tree classifiers. EMG signals, recorded from the vastus lateralis muscle during squat exercises, were analyzed across varying rest intervals to assess optimal recovery periods. By employing single Decision Tree classifiers, the study enhances interpretability, offering insights into feature importance — essential for applications in medical and sports settings where transparency is critical. The experimental protocol utilized a grid search for hyperparameter tuning and cross-validation to address class imbalance, ultimately achieving a reliable classification of rest intervals based on power spectral density features. The results indicate that a limited subset of highly informative features provides sufficient accuracy, suggesting that streamlined, interpretable models are effective for the evaluation of muscle recovery. This approach can guide future research in developing compact, robust models adapted to EMG-based diagnostics.
Keywords: electromyography (EMG), Decision Tree Classifier, tree-based models, machine learning, resting interval analysis, feature importance, ensemble methods, data preprocessing, grid search, cross-validation, interpretability, frequency analysis, biomedical signal processing, muscle recovery
Mots-clés : signal classification 
@article{ND_2024_20_5_a11,
     author = {A. A. Nasybullin and N. Abdullaev and M. A. Baranov and V. V. Koshman and V. A. Mahonin},
     title = {A {Methodology} to {Rank} {Importance} of {Frequencies} and {Channels} in {Electromyography} {Data} with {Decision} {Tree} {Classifiers}},
     journal = {Russian journal of nonlinear dynamics},
     pages = {895--906},
     publisher = {mathdoc},
     volume = {20},
     number = {5},
     year = {2024},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/ND_2024_20_5_a11/}
}
TY  - JOUR
AU  - A. A. Nasybullin
AU  - N. Abdullaev
AU  - M. A. Baranov
AU  - V. V. Koshman
AU  - V. A. Mahonin
TI  - A Methodology to Rank Importance of Frequencies and Channels in Electromyography Data with Decision Tree Classifiers
JO  - Russian journal of nonlinear dynamics
PY  - 2024
SP  - 895
EP  - 906
VL  - 20
IS  - 5
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ND_2024_20_5_a11/
LA  - en
ID  - ND_2024_20_5_a11
ER  - 
%0 Journal Article
%A A. A. Nasybullin
%A N. Abdullaev
%A M. A. Baranov
%A V. V. Koshman
%A V. A. Mahonin
%T A Methodology to Rank Importance of Frequencies and Channels in Electromyography Data with Decision Tree Classifiers
%J Russian journal of nonlinear dynamics
%D 2024
%P 895-906
%V 20
%N 5
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ND_2024_20_5_a11/
%G en
%F ND_2024_20_5_a11
A. A. Nasybullin; N. Abdullaev; M. A. Baranov; V. V. Koshman; V. A. Mahonin. A Methodology to Rank Importance of Frequencies and Channels in Electromyography Data with Decision Tree Classifiers. Russian journal of nonlinear dynamics, Tome 20 (2024) no. 5, pp. 895-906. http://geodesic.mathdoc.fr/item/ND_2024_20_5_a11/

[1] Seyidbayli, C., Salhi, F., and Akdogan, E., “Comparison of Machine Learning Algorithms for EMG Signal Classification”, Period. Eng. Nat. Sci., 8:2 (2020), 1165–1176

[2] Ramírez-Pérez, V., Guerrero-Díaz-de-León, J. A., and Macías-Díaz, J. E., “On the Detection of Activity Patterns in Electromyographic Signals via Decision Trees”, Evol. Intel., 17:1 (2024), 577–588 | DOI

[3] Abdullah, A. A., Subasi, A., and Qaisar, S. M., “Surface EMG Signal Classification by Using WPD and Ensemble Tree Classifiers”, CMBEBIH 2017: Proceedings of the International Conference on Medical and Biological Engineering, IFMBE Proc., 62, ed. A. Badnjevic, Springer, Singapore, 2017, 475–481, xix, 806 pp. | DOI

[4] Valeriano, R., Bottaro, M., Cruz, L., Dutra, M., Lima, F., Vieira, C., Battaglini, C., and de Oliveira, R. J., “Impact of Rest Interval Duration on Muscle Performance in Hodgkin's Lymphoma Survivors”, J. Phys. Educ. Sport., 23:10 (2023), 2835–2841

[5] McMahon, G., Best, N., Coulter, T., and Erskine, R. M., “Increased Neuromuscular Activity, Force Output, and Resistance Exercise Volume When Using 5-Minute Compared with 2-Minute Rest Intervals between the Sets”, J. Strength Cond. Res., 38:9 (2024), 1527–1534 | DOI

[6] Merletti, R. and Muceli, S., “Tutorial. Surface EMG Detection in Space and Time: Best Practices”, J. Electromyogr. Kinesiol., 49 (2019), Art. 102363, 16 pp. | DOI

[7] Darmawan, R. I., Surtono, A., Apriyanto, D. K., and Supriyanto, A., “Design of Computer Based 12 Lead ECG Using STM32F401 Microcontroller”, J. Eng. Mater. Technol., 3:4 (2022), 147–156

[8] Komorowski, D., Mika, B., and Kaczmarek, P., “A New Approach to Preprocessing of EMG Signal to Assess the Correctness of Muscle Condition”, Scientific Papers of Silesian University of Technology. Organization and Management Series, 2023, no. 186, 217–238 | DOI

[9] Cavalcanti Garcia, M. A. and Vieira, T. M. M., “Surface Electromyography: Why, When and How to Use It”, Rev. Andal. Med. Deport., 4:1 (2011), 17–28

[10] Jamal, M. Z., “Signal Acquisition Using Surface EMG and Circuit Design Considerations for Robotic Prosthesis”, Computational Intelligence in Electromyography Analysis: A Perspective on Current Applications and Future Challenges, ed. G. R. Naik, InTech, Rijeka, 2012, 427–448, 462 pp.

[11] Sriraam, N., “EMG-Based Essential Tremor Detection Using PSD Features with Recurrent Feedforward Back Propogation Neural Network”, Int. J. E-Health Med. Commun., 12:6 (2021), 1–16 | DOI

[12] Bhoi, A. K., Sherpa, K. S., and Mallick, P. K., “A Comparative Analysis of Neuropathic and Healthy EMG Signal Using PSD”, International Conference on Communication and Signal Processing (ICCSP, Melmaruvathur, Tamilnadu, India, Apr 2014), 1375–1379