Detection of Knee Joint Disorders using SVM Classifier

Authors

  • Alphonsa Salu S. J.  Department of Electronics and Communication Engineering, St. Xaviers Catholic College of Engineering, Chunkankadai, Tamil Nadu, India
  • Jeraldin Auxillia D  Department of Electronics and Communication Engineering, St. Xaviers Catholic College of Engineering, Chunkankadai, Tamil Nadu, India

DOI:

https://doi.org/10.32628/IJSRST218535

Keywords:

Vibroarthrography, Wavelet decomposition, Feature extraction, Principal Component Analysis, support Vector Machine.

Abstract

A non-invasive technique using knee joint vibroarthographic (VAG) signals can be used for the early diagnosis of knee joint disorders. Among the algorithms devised for the detection of knee joint disorders using VAG signals, algorithms based on entropy measures can provide better performance. In this work, the VAG signal is preprocessed using wavelet decomposition into sub band signals. Features of the decomposed sub bands such as approximate entropy, sample entropy & wavelet energy are extracted as a quantified measure of complexity of the signal. A feature selection based on Principal Component Analysis (PCA) is performed in order to select the significant features. The extracted features are then used for classification of VAG signal into normal and abnormal VAG using support vector machine. It is observed that the classifier provides a better accuracy with feature selection using principal component analysis. And the results show that the classifier was able to classify the signal with an accuracy of 82.6%, error rate of 0.174, sensitivity of 1.0 and specificity of 0.888.

References

  1. McCoy G., McCrea J., Beverland D., Kernohan W., Mollan R., (1987) ‘Vibration arthrography as a diagnostic aid in diseases of the knee’. A preliminary report, J. Bone Jt. Surg. Br. Vol.69-B, No.2, pp.288–293.
  2. Saif Nalband., Sreekrishna R.R., Amaline Prince A., (2016), ‘Analysis of knee joint vibration signals using ensemple empirical mode decomposition’, In proceedings of Twelfth International Multi-conference on Information Processing, Vol.89, pp.820-827.
  3. Daubechies I., (1990), ‘Wavelet transform, time-frequency localization and signal analysis’, IEEE Trans. On Information Theory, Vol.36, No.1, pp. 2-8.
  4. Elif Derya Ubeyil (2009), ‘Combined neural network model employing wavelet coefficients for signal classification’, Journal on Digital Signal Processing, Vol.19, pp.297-308
  5. Mingyang Li., Wanzhong Chen., Tao Zhang., (2017), ‘Classification of epilepsy EEG signals using DWT-based envelope analysis and neural network ensemble’, Journal on Biomedical Signal Processing, Vol.31, No.1, pp.357-365
  6. Kaizhi Liu., Xin Luo., Shanshan Yang., Suxian Cai., Fang Zheng., Yunfeng Wu., (2014), ‘Classification of knee joint vibroarthrographic signals using K nearest neighbor algorithm’, IEEE Trans., Vol.36, No.1, pp.273-279.
  7. Yungfen wu., Suxian Cai., Shanshan Yang., Fang Zheng., Nin Xiang., (2013), ‘Classification of knee joint vibration signals using bivariate feature distribution estimation and maximal posterior probability decision criterion’, Journal on Entropy, Vol.15, pp.1375-1387.
  8. Yungfen Wu., Pinnan Chen., Xin Luo., Hui Hang., Lifang Liao., Yuchen Yao., Meihong Wu., Rangaraj Rangayyan M., (2016), ‘Quantification of knee joint VAG signal irregularity associated with patellofemoral joint cartilage pathology based on entropy and envelope amplitude measures’, Journal on Computer methods and programs in Biomedicine, Vol.130, pp.1-12.
  9. Tingting Mu., Ashoke Nandi K., Rangaraj Rangayyan M., (2008), ‘Screening of knee joint VAG signals using the strict-2 surface proximal classifier and genetic algorithm’, Journal on Computers and biology in Medicine, Vol.38, No.1, pp.1103-1111.
  10. Ahmed Taher Azar., Hanna Ismail Elshazly., Aboul Ella Hassanien., Abeer Mohamed Elkorany., (2014), ‘A random forest classifier for lymph diseases’, Comput. Methods Progr. Biomed., Vol.113, No.2, pp.465-473.
  11. Jasmin Kevric and Abdulhamit Subasi (2017), ‘Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system’, Journal of Biomedical Signal Processing, Vol.36, No.1, pp.273-279.
  12. Yentes J.M., Hunt N., Schmid K.K., Kaipust J.P., McGrath D., Stergiou N., (2013), ‘The appropriate use of approximate entropy and sample entropy with short data sets’, Ann. Biomed. Eng., Vol.41, No.2, pp.349-365.
  13. Pincus S., (1991), ‘Approximate entropy as a measure of system complexity’, -In proceedings of the National Academy of Sciences Vol.88 , No.6, pp.2297-2301.
  14. Dengyong Zhang., Shanshan Wang., Feng Li., Jin Wang., Arun Kumar Sangaiah., Victor S. Sheng., Xiangling Ding., (2019), ‘An ECG signal denoising approach based on wavelet energy and sub-band smoothing filter’, Applied Sciences, Vol.9, 4698, doi:10.3390/app9224968.
  15. Arosha Senanayake S.M.N., Owais Ahmed Malik., Mohammad Iskandar., Danish Zaheer., (2014), ‘A knowledge based intelligent framework for anterior cruciate ligament rehabilitation monitoring’, Journal on applied Soft Computing, Vol.20, No.2, pp.127-141.
  16. Nitesh Singh Malan., Shiru Sharma., (2019), “Feature selection using regularized neighbourhood component analysis to enhance the classification performance of motor imagery signals”, Computers in biology and medicine, Vol.107, pp.118-126.
  17. Sridhar Krishnan., Rangaraj Rangayyan M., Douglas Bell G., Cyril B., (2000), ‘Adaptive time-frequency analysis of knee joint VAG signals for noninvasive screening of articular parthology’, IEEE Trans. On Biomedical Engineering, Vol.47, No.6, pp.243-265.
  18. Le Hoang Son., Mumtaz Ali., Nguyen Dang., Nguyen Van Minh., (2015), ‘A Neutrosophic recommender system for medical diagnosis based on algebraic neutrosophic measures’, Journal of Biomedical Informatics, Vol.54, No.2, pp. 220-229.
  19. Xie S., Krishnan S., (2013), ‘Wavelet-based sparse functional linear model with applications to EEGs seizure detection and epilepsy diagnosis’, Med. Biol. Eng. Comput. Vol.51, No.10 pp.49–60.
  20. Parvinnia E., Sabeti M., Zolghadri Jahromi M., Boostani R., (2014), ‘Classification of EEG signals using adaptive weighted distance nearest neighbor algorithm’, Journal of Computer and Information Sciences, Vol.26, pp.1-6.
  21. Erick Odhiambo Omuya., George Onyango Okeyo., Michael Waema Kimwele., (2021), ”Feature selection for classification using principal component analysis and information gain”, Expert systems with applications, Vol.174, 114765.
  22. Karthikeyan Umapathy and Sridhar Krishnan (2006), ‘Modified local discriminant algorithm and its applications in analysis of human knee joint vibration signals’, IEEE Trans. Biomed Eng., Vol.53, No.3, pp.517-523.
  23. Saif Nalband., Aditya Sundar., Amalin Prince A., Anita Agarwal., (2016), ‘’Feature selection and classification for the detection of knee joint disorders’’, Computer methods and programs in biomedicine, Vol.16, 1169-2607.
  24. Keo Sik Kim., Jeong Hwan Seo., Jin U. Kang., Chul Gyn Song., (2009), ‘An enhanced algorithm for knee joint sound classification using feature extraction based on time-frequency analysis’, Comput. Methods Progr. Biomed. Vol.94, No.2, pp.198–206.
  25. Shanshan Yang., suxian Cai., Fang Zheng., Kaizhi Liu., Meihong Wu., Quan Zou., Jian Chen., (2014), ‘Representation of fluctuation features in pathological knee joint vibroarthrographic signals using kernel density modeling method’, Med. Eng. Phys. Vol.36, No.9, pp.1305-1311.

International Journal of Scientific Research in Science and Technology

Downloads

Published

2021-10-30

Issue

Volume 8, Issue 5, September-October-2021

Section

Research Articles

License

Copyright (c) IJSRST

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Alphonsa Salu S. J., Jeraldin Auxillia D "Detection of Knee Joint Disorders using SVM Classifier" International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011,Volume 8, Issue 5, pp.261-271, September-October-2021. Available at doi : https://doi.org/10.32628/IJSRST218535