• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2022, Volume: 15, Issue: 21, Pages: 1041-1051

Original Article

Fractal and Time-series A nalyses based Rhonchi and Bronchial Auscultation: A Machine Learning Approach

Received Date:19 March 2022, Accepted Date:01 May 2022, Published Date:21 June 2022


Objectives: The present work reports the study of 34 rhonchi (RB) and Bronchial Breath (BB) signals employing machine learning techniques, time-frequency, fractal, and non-linear time-series analyses. Methods: The time-frequency analyses and the complexity in the dynamics of airflow in BB and RB are studied using both Power Spectral Density (PSD) features and non-linear measures. For accurate prediction of these signals, PSD and non-linear measures are fed as input attributes to various machine learning models. Findings: The spectral analyses reveal fewer, low-intensity frequency components along with its overtones in the intermittent and rapidly damping RB signal. The complexity in the dynamics of airflow in BB and RB is investigated through the fractal dimension, Hurst exponent, phase portrait, maximal Lyapunov exponent, and sample entropy values. The greater value of entropy for the RB signal provides an insight into the internal morphology of the airways containing mucous and other obstructions. The Principal Component Analysis (PCA) employs PSD features, and Linear Discriminant Analysis (LDA) along with Pattern Recognition Neural Network (PRNN) uses non-linear measures for predicting BB and RB. Signal classification based on phase portrait features evaluates the multidimensional aspects of signal intensities, whereas that based on PSD features considers mere signal intensities. The principal components in PCA cover about 86.5% of the overall variance of the data class, successfully distinguishing BB and RB signals. LDA and PRNN that use non-linear time-series parameters identify and predict RB and BB signals with 100% accuracy, sensitivity, specificity, and precision. Novelty: The study divulges the potential of non-linear measures and PSD features in classifying these signals enabling its application to be extended for low-cost, non-invasive COVID-19 detection and real-time health monitoring.

Keywords: lung signal, fractal analysis, sample entropy, non­linear time­series, machine learning techniques


  1. Jung SY, Liao CH, Wu YS, Yuan SM, Sun CT. Efficiently Classifying Lung Sounds through Depthwise Separable CNN Models with Fused STFT and MFCC FeaturesDiagnostics2021;11(4):732. Available from: https://doi.org/10.3390/diagnostics11040732
  2. Feng Y, Wang Y, Zeng C, Mao H. Artificial Intelligence and Machine Learning in Chronic Airway Diseases: Focus on Asthma and Chronic Obstructive Pulmonary DiseaseInternational Journal of Medical Sciences2021;18(13):28712889.
  3. Rao A, Huynh E, Royston TJ, Kornblith A, Roy S. Acoustic Methods for Pulmonary DiagnosisIEEE Reviews in Biomedical Engineering2019;12:221239. doi: 10.1109/RBME.2018.2874353
  4. Kim Y, Hyon Y, Jung SS, Lee S, Yoo G, Chung C, et al. Respiratory sound classification for crackles, wheezes, and rhonchi in the clinical field using deep learningScientific Reports2021;11(1):111. Available from: https://doi.org/10.1038/s41598-021-96724-7
  5. Pal R, Barney A. Iterative envelope mean fractal dimension filter for the separation of crackles from normal breath soundsBiomedical Signal Processing and Control2021;66:102454. Available from: https://doi.org/10.1016/j.bspc.2021.102454
  6. Swapna MS, Renjini A, Raj V, Sreejyothi S, Sankararaman S. Time series and fractal analyses of wheezing: a novel approachPhysical and Engineering Sciences in Medicine2020. Available from: http://link.springer.com/10.1007/s13246-020-00937-5
  7. Raj V, Renjini A, Swapna MS, Sreejyothi S, Sankararaman S. Nonlinear time series and principal component analyses: Potential diagnostic tools for COVID-19 auscultationChaos, Solitons & Fractals2020;140:110246. doi: 10.1016/j.chaos.2020.110246
  8. Komalasari R, Rizal A, Suratman FY. Classification of Normal and Murmur Hearts Sound using the Fractal MethodInternational Journal of Advanced Trends in Computer Science and Engineering2020;9(5):81788183. Available from: https://doi.org/10.30534/ijatcse/2020/181952020
  9. Erickson B, Wrigley D, French W, O'Brien T. Easyauscultation. 2021. Available from: https://www.easyauscultation.com/cases?coursecaseorder=1&courseid=201
  10. MedzcoolGassner B, Selbak R. Rhonchi Lung Sounds. 2019. Available from: https://youtu.be/YgDiMpCZo0w
  11. Williams S, Gassner B, Selbak R. Lung Sounds Collection. 2020. Available from: https://emtprep.com/free-training/video/lung-sounds-collection
  12. Osgood BG. Lectures on the Fourier Transform and its Applications. Rhode Island, USA. American Mathematical Society. 2019.
  13. Rhif M, Abbes AB, Farah I, Martínez BR, Sang Y. Wavelet Transform Application for/in Non-Stationary Time-Series Analysis: A ReviewApplied Sciences2019;9(7):1345. Available from: https://doi.org/10.3390/app9071345
  14. Las NLGMD, Requena J. Different methodologies and uses of the Hurst exponent in econophysicsStudies of Applied Economics2019;37(2):113.
  15. Zhang Q, Ding J, Kong W, Liu Y, Wang Q, Jiang T. Epilepsy prediction through optimized multidimensional sample entropy and Bi-LSTMBiomedical Signal Processing and Control2021;64:102293.
  16. Chen C, Sun S, Cao Z, Shi Y, Sun B, Zhang XD. A comprehensive comparison and overview of R packages for calculating sample entropyBiology Methods and Protocols2019;4(1). doi: 10.1093/biomethods/bpz016
  17. Kulkarni A, Chong D, Batarseh FA. Foundations of data imbalance and solutions for a data democracyData Democracy2020;2020:83106. Available from: https://linkinghub.elsevier.com/retrieve/pii/B9780128183663000058
  18. Baghel N, Nangia V, Dutta MK. ALSD-Net: Automatic lung sounds diagnosis network from pulmonary signalsNeural Computing and Applications2021;33(24):1710317118. Available from: https://doi.org/10.1007/s00521-021-06302-1
  19. Hasan B, Abdulazeez AM. A review of principal component analysis algorithm for dimensionality reductionJournal of Soft Computing and Data Mining2021;2(1):2030.
  20. Hassan M, Ali S, Alquhayz H, Safdar K. Developing intelligent medical image modality classification system using deep transfer learning and LDAScientific Reports2020;10(1):114.


© 2022 Renjini et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.