Improvise approach for respiratory pathologies classification with multilayer convolutional neural networks.
Saved in:
| Title: | Improvise approach for respiratory pathologies classification with multilayer convolutional neural networks. |
|---|---|
| Authors: | Borwankar S; Institute of Technology, Nirma University, Ahmedabad, Gujarat India., Verma JP; Institute of Technology, Nirma University, Ahmedabad, Gujarat India., Jain R; IT department, Bhagwan Parshuram Institute of Technology, New Delhi, India., Nayyar A; Graduate School, Faculty of Information Technology, Duy Tan University, Da Nang, 550000 Vietnam. |
| Source: | Multimedia tools and applications [Multimed Tools Appl] 2022; Vol. 81 (27), pp. 39185-39205. Date of Electronic Publication: 2022 Apr 28. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: Kluwer Academic Publishers Country of Publication: United States NLM ID: 101555932 Publication Model: Print-Electronic Cited Medium: Print ISSN: 1380-7501 (Print) Linking ISSN: 13807501 NLM ISO Abbreviation: Multimed Tools Appl Subsets: PubMed not MEDLINE |
| Imprint Name(s): | Original Publication: Hingham, MA ; Dordrecht, Netherlands : Kluwer Academic Publishers |
| Abstract: | Every respiratory-related checkup includes audio samples collected from the individual, collected through different tools (sonograph, stethoscope). This audio is analyzed to identify pathology, which requires time and effort. The research work proposed in this paper aims at easing the task with deep learning by the diagnosis of lung-related pathologies using Convolutional Neural Network (CNN) with the help of transformed features from the audio samples. International Conference on Biomedical and Health Informatics (ICBHI) corpus dataset was used for lung sound. Here a novel approach is proposed to pre-process the data and pass it through a newly proposed CNN architecture. The combination of pre-processing steps MFCC, Melspectrogram, and Chroma CENS with CNN improvise the performance of the proposed system, which helps to make an accurate diagnosis of lung sounds. The comparative analysis shows how the proposed approach performs better with previous state-of-the-art research approaches. It also shows that there is no need for a wheeze or a crackle to be present in the lung sound to carry out the classification of respiratory pathologies. (© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022.) |
| Competing Interests: | Conflict of InterestsThe authors declare that they have no conflict of interest. |
| Contributed Indexing: | Keywords: CENS (Chroma energy normalized statistics); CNN (Convolutional neural network); MFCC (Mel-frequency cepstral coefficients); Melspectrogram; Respiratory pathologies classification |
| Entry Date(s): | Date Created: 20220504 Latest Revision: 20221020 |
| Update Code: | 20250114 |
| PubMed Central ID: | PMC9047583 |
| DOI: | 10.1007/s11042-022-12958-1 |
| PMID: | 35505670 |
| Database: | MEDLINE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | Every respiratory-related checkup includes audio samples collected from the individual, collected through different tools (sonograph, stethoscope). This audio is analyzed to identify pathology, which requires time and effort. The research work proposed in this paper aims at easing the task with deep learning by the diagnosis of lung-related pathologies using Convolutional Neural Network (CNN) with the help of transformed features from the audio samples. International Conference on Biomedical and Health Informatics (ICBHI) corpus dataset was used for lung sound. Here a novel approach is proposed to pre-process the data and pass it through a newly proposed CNN architecture. The combination of pre-processing steps MFCC, Melspectrogram, and Chroma CENS with CNN improvise the performance of the proposed system, which helps to make an accurate diagnosis of lung sounds. The comparative analysis shows how the proposed approach performs better with previous state-of-the-art research approaches. It also shows that there is no need for a wheeze or a crackle to be present in the lung sound to carry out the classification of respiratory pathologies.<br /> (© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022.) |
|---|---|
| ISSN: | 1380-7501 |
| DOI: | 10.1007/s11042-022-12958-1 |