Time series and mel frequency analyses of wet and dry cough signals: A neural net classification

Ammini Renjini, Mohanachandran Nair Sindhu Swapna, Krishnan Nair Satheesh Kumar and Sankaranarayana Iyer Sankararaman

Physica A: Statistical Mechanics and its Applications, 2023, vol. 626, issue C

Abstract: The present study proposes a method for detecting and classifying wet (WC) and dry (DC) cough signals using spectral, cepstral, fractal, and nonlinear time-series analyses. Spectral analysis reveals multiple low-intensity frequency components in WC, leading to a broader spectral spread observed through periodogram, wavelet, and mel spectrograms. Cepstral analysis extracts important information from the cepstra of WC and DC, reducing dimensionality in the signal feature space. Complex phase portraits and higher values of nonlinear time-series parameters (maximal Lyapunov exponent, sample entropy, fractal dimension, and Hurst exponent) highlight the respiratory tract’s internal morphological changes due to complex airflow dynamics in WC. A supervised machine learning technique, neural network pattern recognition, utilizes these nonlinear parameters and cepstral coefficients as input predictors, achieving an impressive prediction accuracy of 99%. This research could significantly contribute to cough sound analysis, particularly in COVID-19 symptom identification, as the dry cough is one of the symptoms of the disease.

Keywords: Wet cough; Dry cough; Phase portrait; Mel coefficients; Fractal dimension; Neural network (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378437123005940
Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:phsmap:v:626:y:2023:i:c:s0378437123005940

DOI: 10.1016/j.physa.2023.129039

Access Statistics for this article

Physica A: Statistical Mechanics and its Applications is currently edited by K. A. Dawson, J. O. Indekeu, H.E. Stanley and C. Tsallis

More articles in Physica A: Statistical Mechanics and its Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().