Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose
Breath pattern analysis based on an electronic nose (e-nose), which is a noninvasive, fast, and low-cost method, has been continuously used for detecting human diseases, including the coronavirus disease 2019 (COVID-19). Nevertheless, having big data with several available features is not always ben...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier B.V.
2022
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/278872/1/Hybrid%20learning%20method%20based%20on%20feature%20clustering%20and%20scoring%20for%20enhanced%20COVID-19%20breath%20analysis%20by%20an%20electronic%20nose.pdf |
| _version_ | 1826050337920778240 |
|---|---|
| author | Hidayat, Shidiq Nur Julian, Trisna Dharmawan, Agus Budi Puspita, Mayumi Chandra, Lily Rohman, Abdul Julia, Madarina Rianjanu, Aditya Nurputra, Dian Kesumapramudya Triyana, Kuwat Wasisto, Hutomo Suryo |
| author_facet | Hidayat, Shidiq Nur Julian, Trisna Dharmawan, Agus Budi Puspita, Mayumi Chandra, Lily Rohman, Abdul Julia, Madarina Rianjanu, Aditya Nurputra, Dian Kesumapramudya Triyana, Kuwat Wasisto, Hutomo Suryo |
| author_sort | Hidayat, Shidiq Nur |
| collection | UGM |
| description | Breath pattern analysis based on an electronic nose (e-nose), which is a noninvasive, fast, and low-cost method, has been continuously used for detecting human diseases, including the coronavirus disease 2019 (COVID-19). Nevertheless, having big data with several available features is not always beneficial because only a few of them will be relevant and useful to distinguish different breath samples (i.e., positive and negative COVID-19 samples). In this study, we develop a hybrid machine learning-based algorithm combining hierarchical agglomerative clustering analysis and permutation feature importance method to improve the data analysis of a portable e-nose for COVID-19 detection (GeNose C19). Utilizing this learning approach, we can obtain an effective and optimum feature combination, enabling the reduction by half of the number of employed sensors without downgrading the classification model performance. Based on the cross-validation test results on the training data, the hybrid algorithm can result in accuracy, sensitivity, and specificity values of (86 ± 3)%, (88 ± 6)%, and (84 ± 6)%, respectively. Meanwhile, for the testing data, a value of 87% is obtained for all the three metrics. These results exhibit the feasibility of using this hybrid filter-wrapper feature-selection method to pave the way for optimizing the GeNose C19 performance. |
| first_indexed | 2024-03-14T00:02:23Z |
| format | Article |
| id | oai:generic.eprints.org:278872 |
| institution | Universiti Gadjah Mada |
| language | English |
| last_indexed | 2024-03-14T00:02:23Z |
| publishDate | 2022 |
| publisher | Elsevier B.V. |
| record_format | dspace |
| spelling | oai:generic.eprints.org:2788722023-10-17T08:53:25Z https://repository.ugm.ac.id/278872/ Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose Hidayat, Shidiq Nur Julian, Trisna Dharmawan, Agus Budi Puspita, Mayumi Chandra, Lily Rohman, Abdul Julia, Madarina Rianjanu, Aditya Nurputra, Dian Kesumapramudya Triyana, Kuwat Wasisto, Hutomo Suryo Paediatrics Mathematics and Applied Sciences Pharmacology and Pharmaceutical Sciences Pharmaceutical Sciences Breath pattern analysis based on an electronic nose (e-nose), which is a noninvasive, fast, and low-cost method, has been continuously used for detecting human diseases, including the coronavirus disease 2019 (COVID-19). Nevertheless, having big data with several available features is not always beneficial because only a few of them will be relevant and useful to distinguish different breath samples (i.e., positive and negative COVID-19 samples). In this study, we develop a hybrid machine learning-based algorithm combining hierarchical agglomerative clustering analysis and permutation feature importance method to improve the data analysis of a portable e-nose for COVID-19 detection (GeNose C19). Utilizing this learning approach, we can obtain an effective and optimum feature combination, enabling the reduction by half of the number of employed sensors without downgrading the classification model performance. Based on the cross-validation test results on the training data, the hybrid algorithm can result in accuracy, sensitivity, and specificity values of (86 ± 3)%, (88 ± 6)%, and (84 ± 6)%, respectively. Meanwhile, for the testing data, a value of 87% is obtained for all the three metrics. These results exhibit the feasibility of using this hybrid filter-wrapper feature-selection method to pave the way for optimizing the GeNose C19 performance. Elsevier B.V. 2022-05-17 Article PeerReviewed application/pdf en https://repository.ugm.ac.id/278872/1/Hybrid%20learning%20method%20based%20on%20feature%20clustering%20and%20scoring%20for%20enhanced%20COVID-19%20breath%20analysis%20by%20an%20electronic%20nose.pdf Hidayat, Shidiq Nur and Julian, Trisna and Dharmawan, Agus Budi and Puspita, Mayumi and Chandra, Lily and Rohman, Abdul and Julia, Madarina and Rianjanu, Aditya and Nurputra, Dian Kesumapramudya and Triyana, Kuwat and Wasisto, Hutomo Suryo (2022) Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose. Artificial Intelligence In Medicine, 129. pp. 1-13. ISSN 09333657 https://www.sciencedirect.com/science/article/pii/S0933365722000884?via%3Dihub https://doi.org/10.1016/j.artmed.2022.102323 |
| spellingShingle | Paediatrics Mathematics and Applied Sciences Pharmacology and Pharmaceutical Sciences Pharmaceutical Sciences Hidayat, Shidiq Nur Julian, Trisna Dharmawan, Agus Budi Puspita, Mayumi Chandra, Lily Rohman, Abdul Julia, Madarina Rianjanu, Aditya Nurputra, Dian Kesumapramudya Triyana, Kuwat Wasisto, Hutomo Suryo Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose |
| title | Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose |
| title_full | Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose |
| title_fullStr | Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose |
| title_full_unstemmed | Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose |
| title_short | Hybrid learning method based on feature clustering and scoring for enhanced COVID-19 breath analysis by an electronic nose |
| title_sort | hybrid learning method based on feature clustering and scoring for enhanced covid 19 breath analysis by an electronic nose |
| topic | Paediatrics Mathematics and Applied Sciences Pharmacology and Pharmaceutical Sciences Pharmaceutical Sciences |
| url | https://repository.ugm.ac.id/278872/1/Hybrid%20learning%20method%20based%20on%20feature%20clustering%20and%20scoring%20for%20enhanced%20COVID-19%20breath%20analysis%20by%20an%20electronic%20nose.pdf |
| work_keys_str_mv | AT hidayatshidiqnur hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT juliantrisna hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT dharmawanagusbudi hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT puspitamayumi hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT chandralily hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT rohmanabdul hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT juliamadarina hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT rianjanuaditya hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT nurputradiankesumapramudya hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT triyanakuwat hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose AT wasistohutomosuryo hybridlearningmethodbasedonfeatureclusteringandscoringforenhancedcovid19breathanalysisbyanelectronicnose |