COVID-19 Diagnosis Using Spectral and Statistical Analysis of Cough Recordings Based on the Combination of SVD and DWT
Main Article Content
Abstract
Healthcare professionals routinely use audio signals, generated by the human body, to help diagnose disease or assess its progression. With new technologies, it is now possible to collect human-generated sounds, such as coughing. Audio-based machine learning technologies can be adopted for automatic analysis of collected data. Valuable and rich information can be obtained from the cough signal and extracting effective characteristics from a finite duration time interval that changes as a function of time. This article presents a proposed approach to the detection and diagnosis of COVID-19 through the processing of cough collected from patients suffering from the most common symptoms of this pandemic. The proposed method is based on adopting a combination of Singular Value Decomposition (SVD), and Discrete Wavelet Transform (DWT). The combination of these two signal processing techniques is gaining lots of interest in the field of speaker and speech recognition. As a cough recognition approach, we found it well-performing, as it generates and utilizes an efficient minimum number of features. Mean and median frequencies, which are known to be the most useful features in the frequency domain, are applied to generate an effective statistical measure to compare the results. The hybrid structure of DWT and SVD, adopted in this approach adds to its efficiency, where a 200 times reduction, in terms of the number of operations, is achieved. Despite the fact that symptoms of the infected and non-infected people used in the study are having lots of similarities, diagnosis results obtained from the application of the proposed approach show high diagnosis rate, which is proved through the matching with relevant PCR tests. The proposed approach is open for more improvements with its performance further assured by enlarging the dataset, while including healthy people.
Received 3/9/2021
Accepted 11/5/2022
Published Online First 20/9/2022
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
Sultan H, Sultan A, Maded Z, Sultan H. A Descriptive Study of Covid-19 Infection Among Symptomatic Patients in Al-Hawija District-Kirkuk-Iraq. Int. J. Psychosoc. Rehabilitation. 2020;24(10):4403-10. DOI: 10.37200/IJPR/V24I10/PR300435.
Alafif T, Bajaba S, Barnawi Ahmed. Machine and deep learning towards COVID-19 diagnosis and treatment: survey, challenges, and future directions. Int J Environ Res. 2021; 18: 1117-19. https://doi.org/10.3390/ijerph18031117
Guan W, Ni Z, Hu Y, Liang W, Ou C, He J, et al. Clinical Characteristics of Coronavirus Disease 2019 in China. N Engl J Med. 2020; 382: 1708-20. https://www.nejm.org/doi/full/10.1056/nejmoa2002032#:~:text=DOI%3A%2010.1056/NEJMoa2002032
European Society of Medical Imaging Informatics. Automated Diagnosis and Quantitative Analysis of COVID-19 on Imaging 2020. Available online: https://imagingcovid19ai.eu/ (accessed on 1 August 2021).
Chen N, Zhou M, Dong X, Qu J, Gong F, Han Y, et al. Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study. Lancet 2020; 395: 507–13. https://doi.org/10.1016/S0140-6736(20)30211-7
Kumar V, Doshi K, Khan W, Rathore A. COVID-19 pandemic: mechanism, diagnosis, and treatment. J Chem Technol Biotechnol. 2020 Dec 96(2); 278-93. https://doi.org/10.1002/jctb.6641
Lawrence R, Juang B. Fundamentals of speech recognition. Pearson College Div; United States 1st Edition. 1993. Chap2: 11-68. ISBN-13: 978-0130151575. https://www.Amazon.Com/Fundamentals-Speech-Recognition-Lawrence-Rabiner/Dp/0130151572
Dengpan Y, Shunzhi J, Huang J. Heard More Than Heard: An Audio Steganography Method Based on GAN. arXiv preprint arXiv:1907.2019; 04986. https://doi.org/10.48550/arXiv.1907.04986
Zehtabian A, Hassanpour H, Zehtabian S. Singular Vector Based Approaches for Speech Enhancement, Chapter 12 of Signal Processing: New Research, 2013; 257-279. Nova Science Publishers, Inc.ISBN: 978-1-62808-141-1. https://www.researchgate.net/publication/287341403_Singular_vector_based_approaches_for_speech_enhancement
Kour B, Singh R, Lehana P, Rajput P. Effect of Singular Value Decomposition Based Processing On Speech Perception. IJNLC., 2013; (2):1:9-16. https://airccse.org/journal/ijnlc/papers/2113ijnlc04.pdf
Elizabeth A. Compton and Stacey L. Ernstberger, Singular Value Decomposition: Applications to Image Processing, J Undergrad Res. 2020; 17: 99-105. https://www.lagrange.edu/academics/undergraduate/undergraduate-research/citations/18-Citations2020.Compton.pdf
Khan M, Rahman M, Sarker M. Digital Watermarking for Image Authentication Based on Combined DCT, DWT and SVD Transformation, arixv.org, 2013, https://arxiv.org/ftp/arxiv/papers/1307/1307.6328.pdf.
Kusumaningrum D, Rachmawanto E, Sari C, Pradana R. DWT-SVD Combination Method for Copyrights Protection. J Info Sci. 2020; 7(1): 113-124. https://journal.unnes.ac.id/nju/index.php/sji/article/view/21050
Al-Ani M, Mohammed T, Aljebory K. Speaker Identification: A Hybrid Approach Using Neural Networks and Wavelet Transform. Science publications. J Comput Sci. 2007; 3 (5): 404-409. doi:10.3488/jcssp.2007.304.309, 2007.
Aniruddha K, Aghila G. A DCT–SVD-based speech steganography in voiced frames. Circuits, Syst. Signal Process. 2018; 37(11): 5049-5068. DOI:10.1007/S00034-018-0805-9
Aniruddha K, Aghila G. DCT based audio steganography in voiced and un-voiced frames. Proc. Int Conf Eng Sci. Appl. 2016:1-4. https://doi.org/10.1145/2980258.2980360
Thanki R, Borisagar K, Dwivedi V. A Hybrid Signal Compression Technique using CS Theory and Various Transform for Speech and ECG. Int Conf Intell Syst Sig Proc. (ISSP 2017). G.H. Patel of Engineering. India :1-14. https://link.springer.com/chapter/10.1007/978-981-10-6977-2_1
Yuhui L, Gou W, Li B. A new digital watermark algorithm based on the DWT and SVD. 10th Int Symp Dist Comput Appl Bus Eng Sci. 2011. DOI 10. 1109/DCABES. 2011. 7
Mohammed T, Al Jebory K, Abdul Rasheed M, Al-Ani M, Sagheer A. Analysis of Methods and Techniques Used for Speaker Identification, Recognition and Verification: A Study on Quarter-Century Research Outcomes. Iraqi J Sci. 2021; 62(9). https://doi.org/10.24996/ijs.2021.62.9.38
Baithoon N, Combined DWT and DCT Image Compression Using Sliding RLE Technique. Baghdad Sci J. 2011; 8(3): 832-83. https://doi.org/10.21123/bsj.2011.8.3.832-839
Abdelwahab, K, El-atty S, Brisha, Ayman M, El-Samie F, Efficient cancelable speaker identification system based on a hybrid structure of DWT and SVD. Int J Speech Technol. 2022. https://doi.org/10.1007/s10772-020-09778-9
Kumar KP, Kanhe A. Secured Speech Watermarking with DCT Compression and Chaotic Embedding Using DWT and SVD. Arab J Sic Eng. 2022 Jan 27:1-22. https://doi.org/10.1007/s13369-021-06431-8.
Jane O, Elbasi E. A new approach of nonblind watermarking methods based on DWT and SVD via LU decomposition. Turk J Elec Eng Comp Sci. 2014; 22(5): 1354-1366. doi:10.3906/elk-1212-75.
Rassem T, Makbol N, Khoo B. Performance Evaluation of RDWT-SVD and DWT-SVD Watermarking schemes. Int Conf Adv Sci, Eng Tech. 2015 AIP Conf. Proc. 1774, 050021-1–050021-9; doi: 10.1063/1.4965108.
Fonseca E, Guido R, Junior S, Dezani H, Gati R, Mosconi P, et al. Acoustic investigation of speech pathologies based on the discriminative paraconsistent machine (DPM). Biomed Signal Process Control. 2019; 55: 1746-8094. DOI: 10.1016/j.bspc.2019.101615
Amami A, Smiti A. An incremental method combining density clustering and support vector machines for voice pathology detection. Comput Electr Eng. 2016; 57: 257-265. https://doi.org/10.1016/j.compeleceng.2016.08.021
Muhammad G, Altuwaijri G, Alsulaiman M, Ali Z, Mesallam T A, Farahat, et al. Automatic voice pathology detection and classification using vocal tract area irregularity. Biocybern Biomed Eng. 2016; 36(2): 309-317. http://dx.doi.org/10.1016/j.bbe.2016.01.004
Bendal M, Soni J, Chhugani G, Sahu N, Choubey N, Bothe S. Voice Based Disease Identification System. Turk J. Comput Math Educ. 2021; 12(1): 96-105. https://doi.org/10.17762/turcomat.v12i1S.1568
Chung K, Widdicombe J. Cough. Murray and Nadel's Textbook of Respiratory Medicine: 2-Volume Set. 5th ed.: Elsevier Health Sciences; 2010: 628-645. URL: https://sites.dartmouth.edu/odame/files/2017/06/Technologies-for-Developing-Ambulatory-Cough-Monitoring-Devices-1sl9s7w.pdf
Amoh J, Odame K. Technologies for Developing Ambulatory Cough Monitoring Devices. Analog Laboratory, Thayer School of Engineering, Dartmouth College. Crit Rev Biomed Eng. 2013;41(6):457-68. https://pubmed.ncbi.nlm.nih.gov/24940659/
Al-Ani M, Mohammed T, Sultan A, Sultan H, Alheeti K, Aljebory K. Detection and Diagnostic Approach of COVID-19 Based on Cough Sound Analysis. J Comput Sci. 2021; 17 (6): 580-597 DOI: .3844/jcssp.2021.580.597.
Salah H A, Ahmed S A. Coronavirus Disease Diagnosis, Care and Prevention (COVID-19) Based on Decision Support System. Baghdad Sci J. 2021;18(3):593-613. https://doi.org/10.21123/bsj.2021.18.3.0593
Renard X , S. Imtiaz E. Rodriguez-Villegas. A Cough-Based Algorithm for Automatic Diagnosis of Pertussis. PLoS one. 2016; 11(9). doi: 10.1371/journal.pone.0162128.
Zealouk O, Satori H, Hamidi M,Laaidi N,Salek A ,Satori K. Analysis of COVID-19 Resulting Cough using Formants and Automatic Speech Recognition System. J Voice. 2021; doi: https://doi.org/10.1016/j.jvoice.2021.05.015.
Brown C, Chauhan J, Grammenos A, Han J, Hasthanasombat A, Spathis D et al. Exploring Automatic Diagnosis of COVID-19 from Crowd sourced Respiratory Sound Data. KDD ‘20, August 23–27, 2020, Virtual Event, USA. https://doi.org/10.1145/3394486.3412865
Mouawad P, Dubnov T, Dubnov S. Robust Detection of Covid 19 In Cough Sounds Using Recurrence Dynamics and Variable Markov Model. SN Comput Sci. 2021;2(1):34. doi:10.1007/S42979-020-00422-6