An automated Covid-19 respiratory sound classification method based on novel local symmetric Euclidean distance pattern and ReliefF iterative MRMR feature selector

Abstract

Covid-19 is a new variety of coronavirus that affects millions of people around the world. This virus infected millions of people and hundreds of thousands of people have passed away. Due to the panic caused by Covid-19, recently several researchers have tried to understand and to propose a solution to Covid-19 problem. Especially, researches in machine learning (ML) have been proposed to detect Covid-19 by using X-ray images. In this study, 10 classes of respiratory sounds, including respiratory sounds diagnosed with Covid-19 disease, were collected and ML methods were used to tackle this problem. The proposed respiratory sound classification method has been proposed in this study from feature generation network through hybrid and iterative feature selection to classification phases. A novel multileveled feature generating network is presented by gathering multilevel one-dimensional wavelet transform and a novel local symmetric Euclidean distance pattern (LSEDP). An automated hybrid feature selection method is proposed using ReliefF and ReliefF Iterative Maximum Relevancy Minimum Redundancy (RIMRMR) to select the optimal number of features. Four known classifiers were used to test the capability of our approach for lung disease detection in respiratory sounds. K nearest neighbors (kNN) method has achieved an accuracy of 91.02%.

Keywords

• Covid-19
• LSEDP
• Lung Disease Detection
• Respiratory Sounds
• RFIMRMR

References

1. 1. Zhang, J.-f., et al., SARS-CoV-2 turned positive in a discharged patient with COVID-19 arouses concern regarding the present standard for discharge. International Journal of Infectious Diseases, 2020. 97: p. 212-214.
2. 2. Pindiprolu, S.K.S. and S.H. Pindiprolu, Plausible mechanisms of Niclosamide as an antiviral agent against COVID-19. Medical Hypotheses, 2020. 140: p. 109765.
3. 3. Shereen, M.A., et al., COVID-19 infection: origin, transmission, and characteristics of human coronaviruses. Journal of Advanced Research, 2020. 24: p. 91-98.
4. 4. Tu, H., et al., The epidemiological and clinical features of COVID-19 and lessons from this global infectious public health event. Journal of Infection, 2020. 81: p. 1-9.
5. 5. Saif, L.J., Vaccines for COVID-19: perspectives, prospects, and challenges based on candidate SARS, MERS, and animal coronavirus vaccines. Euro. Med. J., 2020. 24: p. 1-7.
6. 6. Bellitti, P., et al., A Wearable and Wirelessly Powered System for Multiple Finger Tracking. IEEE Transactions on Instrumentation and Measurement, 2020. 69(5): p. 2542-2551.
7. 7. Vellingiri, B., et al., COVID-19: a promising cure for the global panic. Science of the Total Environment, 2020. 725: p. 138277.
8. 8. Singh, A., et al., COVID-19: From bench to bed side. Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 2020. 14(4): p. 277-281.

9. 9. Xie, M. and Q. Chen, Insight into 2019 novel coronavirus—an updated intrim review and lessons from SARS-CoV and MERS-CoV. International Journal of Infectious Diseases, 2020. 94: p. 119-124.
10. 10. Hui Huang, Y., et al., The respiratory sound features of COVID-19 patients fill gaps between clinical data and screening methods. medRxiv, 2020. 4(7): p. 1-12.
11. 11. Abd El-Aziz, T.M. and J.D. Stockand, Recent progress and challenges in drug development against COVID-19 coronavirus (SARS-CoV-2)-an update on the status. Infection, Genetics and Evolution, 2020. 83(1): p. 104327
12. 12. Shoenfeld, Y., Corona (COVID-19) time musings: Our involvement in COVID-19 pathogenesis, diagnosis, treatment and vaccine planning. Autoimmunity Reviews, 2020. 19(6): p. 102538.
13. 13. Chakraborty, I. and P. Maity, COVID-19 outbreak: Migration, effects on society, global environment and prevention. Science of The Total Environment, 2020. 728: p. 138882.
14. 14. Taghizadeh-Hesary, F. and H. Akbari, The Powerful Immune System Against Powerful COVID-19: A Hypothesis. Medical Hypotheses, 2020. 140: p. 109762.
15. 15. Ali, I. and O.M. Alharbi, COVID-19: Disease, management, treatment, and social impact. Science of The Total Environment, 2020. 728: p. 138861.
16. 16. Aykanat, M., et al., Classification of lung sounds using convolutional neural networks. EURASIP Journal on Image and Video Processing, 2017. 2017(1): p. 65.
17. 17. Don, S., Random Subset Feature Selection and Classification of Lung Sound. Procedia Computer Science, 2020. 167: p. 313-322.
18. 18. Bardou, D., K. Zhang, and S.M. Ahmad, Lung sounds classification using convolutional neural networks. Artificial intelligence in medicine, 2018. 88: p. 58-69.
19. 19. Naves, R., B.H. Barbosa, and D.D. Ferreira, Classification of lung sounds using higher-order statistics: A divide-and-conquer approach. Computer methods and programs in biomedicine, 2016. 129: p. 12-20.
20. 20. Kandaswamy, A., et al., Neural classification of lung sounds using wavelet coefficients. Computers in biology and medicine, 2004. 34(6): p. 523-537.
21. 21. Ucar, F. and D. Korkmaz, COVIDiagnosis-Net: Deep Bayes-SqueezeNet based Diagnostic of the Coronavirus Disease 2019 (COVID-19) from X-Ray Images. Medical Hypotheses, 2020. 140: p. 109761.
22. 22. Narin, A., C. Kaya, and Z. Pamuk, Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks. Pattern Analysis and Applications, 2020. 24: p. 1207-1220.
23. 23. Uwadaira, Y., et al., Logistic regression analysis for identifying the factors affecting development of non-invasive blood glucose calibration model by near-infrared spectroscopy. Chemometrics and Intelligent Laboratory Systems, 2015. 148: p. 128-133.
24. 24. Sethy, P.K. and S.K. Behera, Detection of coronavirus Disease (COVID-19) based on Deep Features. Preprints, 2020. 22.
25. 25. Medzcool. Lung and Breath Sounds. [18 March 2020]; Available from: https://www.youtube.com/watch?v=3Kkp6ZM35As&list=PL3n8cHP87ijAalXtLG2YbDpuwjxuJRR-A&index=9.
26. 26. EMTprep. Lung Sounds Collection [28 December 2019]; Available from: https://www.youtube.com/watch?v=KRtAqeEGq2Q&feature=youtu.be.
27. 27. The Know Show. Physiological pathological breath sounds. [10 May 2013]; Available from: https://www.youtube.com/watch?v=64bLgnv1mHA&feature=youtu.be.
28. 28. Alhadapediatrics. Breath Sounds [04 March 2010]; Available from: https://www.youtube.com/watch?v=MzTcy6M3poM&feature=youtu.be.
29. 29. Tzanetakis, G., G. Essl, and P. Cook. Audio analysis using the discrete wavelet transform. in Proc. Conf. in Acoustics and Music Theory Applications. 2001.
30. 30. Saravanan, N. and K. Ramachandran, Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN). Expert systems with applications, 2010. 37(6): p. 4168-4181.
31. 31. Hothorn, T. and B. Lausen, Bundling classifiers by bagging trees. Computational Statistics & Data Analysis, 2005. 49(4): p. 1068-1078.
32. 32. Fraz, M., et al. Retinal image analysis aimed at extraction of vascular structure using linear discriminant classifier. in 2013 International Conference on Computer Medical Applications (ICCMA). 2013. IEEE.
33. 33. Liao, Y. and V.R. Vemuri, Use of k-nearest neighbor classifier for intrusion detection. Computers & security, 2002. 21(5): p. 439-448.
34. 34. Tahir, M.A., A. Bouridane, and F. Kurugollu, Simultaneous feature selection and feature weighting using Hybrid Tabu Search/K-nearest neighbor classifier. Pattern Recognition Letters, 2007. 28(4): p. 438-446.
35. 35. Lau, K. and Q. Wu, Online training of support vector classifier. Pattern Recognition, 2003. 36(8): p. 1913-1920.
36. 36. Robnik-Šikonja, M. and I. Kononenko, Theoretical and empirical analysis of ReliefF and RReliefF. Machine learning, 2003. 53(1-2): p. 23-69.
37. 37. Ojala, T., M. Pietikäinen, and T. Mäenpää. A generalized local binary pattern operator for multiresolution gray scale and rotation invariant texture classification. in International Conference on Advances in Pattern Recognition. 2001. Springer.
38. 38. Zhang, Y., et al., Revealing the traces of median filtering using high-order local ternary patterns. IEEE Signal Processing Letters, 2014. 21(3): p. 275-279.
39. 39. Ren, J., X. Jiang, and J. Yuan. Relaxed local ternary pattern for face recognition. in 2013 IEEE international conference on image processing. 2013. IEEE.
40. 40. Raghu, S. and N. Sriraam, Classification of focal and non-focal EEG signals using neighborhood component analysis and machine learning algorithms. Expert Systems with Applications, 2018. 113: p. 18-32.
41. 41. Tuncer, T., S. Dogan, and F. Ertam, Automatic voice based disease detection method using one dimensional local binary pattern feature extraction network. Applied Acoustics, 2019. 155: p. 500-506.
42. 42. Rosenberg, A. Classifying skewed data: Importance weighting to optimize average recall. in Thirteenth Annual Conference of the International Speech Communication Association. 2012. Portland, OR, USA.
43. 43. Bernecker, D., et al. Representation learning for cloud classification. in German Conference on Pattern Recognition. 2013. Springer.
44. 44. Polat, Ö., Determination of highly effective attributes in fold level classification of proteins. International Advanced Researches and Engineering Journal, 2019. 3(1): p. 32-39.
45. 45. Cinar, A., B. Topuz, and S. Ergin, A new region-of-interest (ROI) detection method using the chan-vese algorithm for lung nodule classification. International Advanced Researches and Engineering Journal, 2021. 5(2): p. 281-291.
46. 46. Mouawad, P., T. Dubnov, and S. Dubnov, Robust Detection of COVID-19 in Cough Sounds. SN Computer Science, 2021. 2(1): p. 1-13.
47. 47. Sharma, N., et al., Coswara--A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis. Inter Speech, 2020. 2768: p. 1-5.
48. 48. Nessiem, M.A., et al. Detecting COVID-19 from Breathing and Coughing Sounds using Deep Neural Networks. in 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS). 2021. Aveiro, Portugal: IEEE.