Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals
As one of the most reliable and significant indicators, Chronic Obstructive Pulmonary Disease (COPD) becomes a robust predictor of lung cancer early detection, the world's leading cause of cancer death. One of the methods is to analyze the Volatile Organic Compounds (VOCs) in exhaled breath usi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/283942/1/Putro_MIPA.pdf |
| _version_ | 1826050716491317248 |
|---|---|
| author | Avian, Cries Mahali, Muhammad Izzuddin Putro, Nur Achmad Sulistyo Prakosa, Setya Widyawan Leu, Jenq-Shiou |
| author_facet | Avian, Cries Mahali, Muhammad Izzuddin Putro, Nur Achmad Sulistyo Prakosa, Setya Widyawan Leu, Jenq-Shiou |
| author_sort | Avian, Cries |
| collection | UGM |
| description | As one of the most reliable and significant indicators, Chronic Obstructive Pulmonary Disease (COPD) becomes a robust predictor of lung cancer early detection, the world's leading cause of cancer death. One of the methods is to analyze the Volatile Organic Compounds (VOCs) in exhaled breath using electronic noses (E-noses), which have become emerging tools for analyzing breath because of their potential and promising technology for diagnosing. However, the signal processing of the E-Nose sensor becomes vital in exposing information about the subject condition, which most researchers strive to accomplish. We proposed a Convolutional Neural Network (CNN) architecture to classify COPD in smokers and non-smokers, healthy subjects, and smokers from E-Nose signals to contribute to this field. Two models were constructed following E-Nose signal processing state-of-the-arts. One was by combined feature extraction and classifier, and the second was by CNN, which directly processed the raw signal. In addition, various feature extraction and classifier (Machine Learning and CNN) used in prior research were investigated. Using 3K and 5K Fold cross-validation results demonstrated that our proposed models outperformed in Kernel Principal Component Analysis (KPCA) with Fx-ConvNet and Pure-ConvNet. They all reached maximum F1-Score with zero standard deviation values indicating a consistent result. Further experiments also showed that KPCA contributed to the increasing performance of some classifiers with average F1-Score 0.933 and 0.068 as standard deviation values. |
| first_indexed | 2024-03-14T00:08:59Z |
| format | Article |
| id | oai:generic.eprints.org:283942 |
| institution | Universiti Gadjah Mada |
| language | English |
| last_indexed | 2024-03-14T00:08:59Z |
| publishDate | 2022 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oai:generic.eprints.org:2839422023-11-24T04:13:02Z https://repository.ugm.ac.id/283942/ Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals Avian, Cries Mahali, Muhammad Izzuddin Putro, Nur Achmad Sulistyo Prakosa, Setya Widyawan Leu, Jenq-Shiou Information and Computing Sciences Mathematics and Applied Sciences As one of the most reliable and significant indicators, Chronic Obstructive Pulmonary Disease (COPD) becomes a robust predictor of lung cancer early detection, the world's leading cause of cancer death. One of the methods is to analyze the Volatile Organic Compounds (VOCs) in exhaled breath using electronic noses (E-noses), which have become emerging tools for analyzing breath because of their potential and promising technology for diagnosing. However, the signal processing of the E-Nose sensor becomes vital in exposing information about the subject condition, which most researchers strive to accomplish. We proposed a Convolutional Neural Network (CNN) architecture to classify COPD in smokers and non-smokers, healthy subjects, and smokers from E-Nose signals to contribute to this field. Two models were constructed following E-Nose signal processing state-of-the-arts. One was by combined feature extraction and classifier, and the second was by CNN, which directly processed the raw signal. In addition, various feature extraction and classifier (Machine Learning and CNN) used in prior research were investigated. Using 3K and 5K Fold cross-validation results demonstrated that our proposed models outperformed in Kernel Principal Component Analysis (KPCA) with Fx-ConvNet and Pure-ConvNet. They all reached maximum F1-Score with zero standard deviation values indicating a consistent result. Further experiments also showed that KPCA contributed to the increasing performance of some classifiers with average F1-Score 0.933 and 0.068 as standard deviation values. Elsevier 2022-09 Article PeerReviewed application/pdf en https://repository.ugm.ac.id/283942/1/Putro_MIPA.pdf Avian, Cries and Mahali, Muhammad Izzuddin and Putro, Nur Achmad Sulistyo and Prakosa, Setya Widyawan and Leu, Jenq-Shiou (2022) Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals. Computers in Biology and Medicine, 148 (105913). pp. 1-15. ISSN 00104825 https://www.sciencedirect.com/science/article/pii/S0010482522006564?via%3Dihub https://doi.org/10.1016/j.compbiomed.2022.105913 |
| spellingShingle | Information and Computing Sciences Mathematics and Applied Sciences Avian, Cries Mahali, Muhammad Izzuddin Putro, Nur Achmad Sulistyo Prakosa, Setya Widyawan Leu, Jenq-Shiou Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals |
| title | Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals |
| title_full | Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals |
| title_fullStr | Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals |
| title_full_unstemmed | Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals |
| title_short | Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals |
| title_sort | fx net and purenet convolutional neural network architecture for discrimination of chronic obstructive pulmonary disease from smokers and healthy subjects through electronic nose signals |
| topic | Information and Computing Sciences Mathematics and Applied Sciences |
| url | https://repository.ugm.ac.id/283942/1/Putro_MIPA.pdf |
| work_keys_str_mv | AT aviancries fxnetandpurenetconvolutionalneuralnetworkarchitecturefordiscriminationofchronicobstructivepulmonarydiseasefromsmokersandhealthysubjectsthroughelectronicnosesignals AT mahalimuhammadizzuddin fxnetandpurenetconvolutionalneuralnetworkarchitecturefordiscriminationofchronicobstructivepulmonarydiseasefromsmokersandhealthysubjectsthroughelectronicnosesignals AT putronurachmadsulistyo fxnetandpurenetconvolutionalneuralnetworkarchitecturefordiscriminationofchronicobstructivepulmonarydiseasefromsmokersandhealthysubjectsthroughelectronicnosesignals AT prakosasetyawidyawan fxnetandpurenetconvolutionalneuralnetworkarchitecturefordiscriminationofchronicobstructivepulmonarydiseasefromsmokersandhealthysubjectsthroughelectronicnosesignals AT leujenqshiou fxnetandpurenetconvolutionalneuralnetworkarchitecturefordiscriminationofchronicobstructivepulmonarydiseasefromsmokersandhealthysubjectsthroughelectronicnosesignals |