A Hybrid ECEEMDAN-LGBM Framework for Knee Joint Vibroarthrographic Signal Classification

Krishna Sundeep Basavaraju; T. Kishore Kumar; K. Ashoka Reddy

doi:10.48084/etasr.17260

Authors

Krishna Sundeep Basavaraju National Institute of Technology Warangal, India
T. Kishore Kumar National Institute of Technology Warangal, India
K. Ashoka Reddy Kakatiya Institute of Technology & Science, Warangal, India

Volume: 16 | Issue: 2 | Pages: 33753-33759 | April 2026 | https://doi.org/10.48084/etasr.17260

Received: 30 December 2025 | Revised: 26 January 2026 | Accepted: 7 February 2026 | Online: 26 February 2026

Corresponding author: Krishna Sundeep Basavaraju

Abstract

The significance of early diagnosis and adaptability to non-invasive procedures for detecting knee disorders has become very prominent. Vibroarthrography is one of the prominent non-invasive methods that uses signals produced during the movement of the knee joint to assess its degradation. This study presents a comprehensive approach that combines Enhanced Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ECEEMDAN) for signal decomposition and the Light Gradient Boosting Machine (LGBM) classifier for the analysis and classification of Vibroarthrographic (VAG) signals. The proposed approach focuses on identifying the significant frequency components by decomposing these vibration signals into Intrinsic Mode Functions (IMFs), followed by a novel energy-correlation-kurtosis-based adaptive IMF selection strategy for effective signal reconstruction. Entropy features, such as Approximate Entropy (ApEn), Sample Entropy (SampEn), and Shannon Entropy (ShEn), are extracted for the reconstructed signals and the decomposed sub-bands. Several machine learning classifiers, such as Decision Tree (DT), XGBoost (XGB), Gradient Boosting (GB), Random Forest (RF), SVM, and Light Gradient Boosting Machines (LGBM), are used for classification. Based on test results, the LGBM classifier achieved good levels of accuracy at 90.56%, AUROC at 0.9120, sensitivity at 92.10%, specificity at 90.23%, positive predictive value at 87.56%, and negative predictive value at 93.95%.

Keywords:

Vibroarthrographic (VAG) signals, empirical mode decomposition, Intrinsic Mode Functions (IMFs), entropy features, Light Gradient Boosting Machine (LGBM) classifier

Downloads

Download data is not yet available.

References

R. Karpiński et al., "Articular Cartilage: Structure, Biomechanics, and the Potential of Conventional and Advanced Diagnostics," Applied Sciences, vol. 15, no. 12, June 2025, Art. no. 6896.

A. C. Gelber, "Knee Osteoarthritis," Annals of Internal Medicine, vol. 177, no. 9, pp. ITC129–ITC144, Sept. 2024.

Ł. Bryliński et al., "Trace Elements—Role in Joint Function and Impact on Joint Diseases," International Journal of Molecular Sciences, vol. 26, no. 15, Aug. 2025, Art. no. 7493.

R. M. Rangayyan, S. Krishnan, G. D. Bell, C. B. Frank, and K. O. Ladly, "Parametric representation and screening of knee joint vibroarthrographic signals," IEEE Transactions on Biomedical Engineering, vol. 44, no. 11, pp. 1068–1074, Nov. 1997.

S. Krishnan, R. M. Rangayyan, G. D. Bell, C. B. Frank, and K. O. Ladly, "Adaptive filtering, modelling and classification of knee joint vibroarthrographic signals for non-invasive diagnosis of articular cartilage pathology," Medical & Biological Engineering & Computing, vol. 35, no. 6, pp. 677–684, Nov. 1997.

M. M. Shidore, S. S. Athreya, S. Deshpande, and R. Jalnekar, "Screening of knee-joint vibroarthrographic signals using time and spectral domain features," Biomedical Signal Processing and Control, vol. 68, July 2021, Art. no. 102808.

Y. Wu et al., "Quantification of knee vibroarthrographic signal irregularity associated with patellofemoral joint cartilage pathology based on entropy and envelope amplitude measures," Computer Methods and Programs in Biomedicine, vol. 130, pp. 1–12, July 2016.

E. Mascarenhas, S. Nalband, A. R. J. Fredo, and A. A. Prince, "Analysis and Classification of Vibroarthrographic Signals using Tuneable ‘Q’ Wavelet Transform," in 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN), Feb. 2020, pp. 65–70.

Y. Athavale and S. Krishnan, "A telehealth system framework for assessing knee-joint conditions using vibroarthrographic signals," Biomedical Signal Processing and Control, vol. 55, Jan. 2020, Art. no. 101580.

N. Befrui et al., "Vibroarthrography for early detection of knee osteoarthritis using normalized frequency features," Medical & Biological Engineering & Computing, vol. 56, no. 8, pp. 1499–1514, Aug. 2018.

S. Gharehbaghi, D. C. Whittingslow, L. A. Ponder, S. Prahalad, and O. T. Inan, "Acoustic Emissions From Loaded and Unloaded Knees to Assess Joint Health in Patients With Juvenile Idiopathic Arthritis," IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 9, pp. 3618–3626, Sept. 2021.

R. E. Andersen, L. Arendt-Nielsen, and P. Madeleine, "Knee joint vibroarthrography of asymptomatic subjects during loaded flexion-extension movements," Medical & Biological Engineering & Computing, vol. 56, no. 12, pp. 2301–2312, Dec. 2018.

D. Moreira, J. Silva, M. V. Correia, and M. Massada, "Classification of knee arthropathy with accelerometer-based vibroarthrography," in Studies in Health Technology and Informatics, IOS Press, 2016.

A. Łysiak, M. Szmajda, D. Bączkowicz, and D. Borzucka, "Transforming vibroarthrogram to the angle domain improves function–structure integration," Biomedical Signal Processing and Control, vol. 113, Mar. 2026, Art. no. 109112.

A. Łysiak et al., "Regression analysis of the vibroarthrogram in the external load conditions," Advances in Science and Technology Research Journal, vol. 19, no. 10, pp. 238–251, Oct. 2025.

R. Karpiński and A. Syta, "Application of encoder-based motion analysis and machine learning for knee osteoarthritis detection: A pilot study," Applied Computer Science, vol. 21, no. 4, pp. 21–31, Dec. 2025.

R. Karpiński, "Knee Joint Osteoarthritis Diagnosis based on Selected Acoustic Signal Discriminants Using Machine :earning," Applied Computer Science, vol. 18, no. 2, pp. 71–85, June 2022.

A. Machrowska, R. Karpiński, M. Maciejewski, J. Jonak, and P. Krakowski, "Application of EEMD-DFA Algorithms and ANN Classification for Detection of Knee Osteoarthritis Using Vibroarthrography," Applied Computer Science, vol. 20, no. 2, pp. 90–108, June 2024.

R. Karpiński, P. Krakowski, J. Jonak, A. Machrowska, and M. Maciejewski, "Comparison of Selected Classification Methods Based on Machine Learning as a Diagnostic Tool for Knee Joint Cartilage Damage Based on Generated Vibroacoustic Processes," Applied Computer Science, vol. 19, no. 4, pp. 136–150, Dec. 2023.

A. Machrowska, R. Karpiński, M. Maciejewski, J. Jonak, P. Krakowski, and A. Syta, "Application of Recurrence Quantification Analysis in the Detection of Osteoarthritis of the Knee with the Use of Vibroarthrography," Advances in Science and Technology Research Journal, vol. 18, no. 5, pp. 19–31, Sept. 2024.

K. Kręcisz, "Correlation between Linear and Non-Linear Vibroartrographic Parameters," Przeglad Elektrotechniczny, vol. 1, no. 7, pp. 182–187, July 2023.

K. S. Basavaraju, T. K. Kumar, K. A. Reddy, and K. R. K. Reddy, "Analysis of Vibroarthrographic signals for classification of knee disorders using Empirical Wavelet Transform based on Statistical measures," in 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), May 2023, pp. 1–6.

K. S. Basavaraju, T. K. Kumar, and K. A. Reddy, "Vibroarthrographic Signal Classification for Knee Joint Disorder Detection using Tunable Q-factor Wavelet Transform based on Entropy Measures," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19953–19958, Feb. 2025.

S. Cai et al., "Detrending knee joint vibration signals with a cascade moving average filter," in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Aug. 2012, pp. 4357–4360.

M. S. Calvo and H. S. Lee, "Enhanced COMPLETE ENSEMBLE EMD with superior noise handling capabilities: A robust signal decomposition method for power systems analysis," Engineering Reports, vol. 6, no. 11, Nov. 2024, Art. no. e12862.

N. E. Huang et al., "The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis," Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, vol. 454, no. 1971, pp. 903–995, Mar. 1998.

Z. Wu and N. E. Huang, "Ensemble Empirical Mode Decomposition: A Noise-Assisted Data Analysis Method," Advances in Adaptive Data Analysis, vol. 01, no. 01, pp. 1–41, Jan. 2009.

M. A. Colominas, G. Schlotthauer, and M. E. Torres, "Improved complete ensemble EMD: A suitable tool for biomedical signal processing," Biomedical Signal Processing and Control, vol. 14, pp. 19–29, Nov. 2014.

S. M. Pincus, "Approximate entropy as a measure of system complexity.," Proceedings of the National Academy of Sciences, vol. 88, no. 6, pp. 2297–2301, Mar. 1991.

J. S. Richman and J. R. Moorman, "Physiological time-series analysis using approximate entropy and sample entropy," American Journal of Physiology-Heart and Circulatory Physiology, vol. 278, no. 6, pp. H2039–H2049, June 2000.

M. Ibl and J. Čapek, "Measure of Uncertainty in Process Models Using Stochastic Petri Nets and Shannon Entropy," Entropy, vol. 18, no. 1, Jan. 2016, Art. no. 33.

S. Krishnan, R. M. Rangayyan, G. D. Bell, and C. B. Frank, "Adaptive time-frequency analysis of knee joint vibroarthrographic signals for noninvasive screening of articular cartilage pathology," IEEE Transactions on Biomedical Engineering, vol. 47, no. 6, pp. 773–783, June 2000.

R. M. Rangayyan and Y. Wu, "Screening of knee-joint vibroarthrographic signals using probability density functions estimated with Parzen windows," Biomedical Signal Processing and Control, vol. 5, no. 1, pp. 53–58, Jan. 2010.

K. Umapathy and S. Krishnan, "Modified Local Discriminant Bases Algorithm and Its Application in Analysis of Human Knee Joint Vibration Signals," IEEE Transactions on Biomedical Engineering, vol. 53, no. 3, pp. 517–523, Mar. 2006.

S. Nalband, A. Prince, and A. Agrawal, "Entropy‐based feature extraction and classification of vibroarthographic signal using complete ensemble empirical mode decomposition with adaptive noise," IET Science, Measurement & Technology, vol. 12, no. 3, pp. 350–359, May 2018.