Ensemble machine learning approach for electronic nose signal processing
Electronic nose (e-nose) systems have been reported to be used in many areas as rapid, low-cost, and non-invasive instruments. Especially in meat production and processing, e-nose system is a powerful tool to process volatile compounds as a unique ‘fingerprint’. The ability of the pattern recognitio...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | Sensing and Bio-Sensing Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214180422000241 |
| _version_ | 1818547894894985216 |
|---|---|
| author | Dedy Rahman Wijaya Farah Afianti Anditya Arifianto Dewi Rahmawati Vassilis S. Kodogiannis |
| author_facet | Dedy Rahman Wijaya Farah Afianti Anditya Arifianto Dewi Rahmawati Vassilis S. Kodogiannis |
| author_sort | Dedy Rahman Wijaya |
| collection | DOAJ |
| description | Electronic nose (e-nose) systems have been reported to be used in many areas as rapid, low-cost, and non-invasive instruments. Especially in meat production and processing, e-nose system is a powerful tool to process volatile compounds as a unique ‘fingerprint’. The ability of the pattern recognition algorithm to analyze e-nose signals is the key to the success of the e-nose system in many applications. On the other hand, ensemble methods have been reported for favorable performances in various data sets. This research proposes an ensemble learning approach for e-nose signal processing, especially in beef quality assessment. Ensemble methods are not only used for learning algorithms but also sensor array optimization. For sensor array optimization, three filter-based feature selection algorithms (FSAs) are used to build ensemble FSA such as reliefF, chi-square, and gini index. Ensemble FSA is developed to deal with different or unstable outputs of a single FSA on homogeneous e-nose data sets in beef quality monitoring. Moreover, ensemble learning algorithms are employed to deal with multi-class classification and regression tasks. Random forest and Adaboost are used that represent bagging and boosting algorithms, respectively. The results are also compared with support vector machine and decision tree as single learners. According to the experimental results, our ensemble approach has good performance and generalization in e-nose signal processing. Optimized sensor combination based on filter-based FSA shows stable results both in classification and regression tasks. Furthermore, Adaboost as a boosting algorithm produces the best prediction even though using a smaller number of sensors. |
| first_indexed | 2024-12-12T08:12:45Z |
| format | Article |
| id | doaj.art-87b2a09eff84465a8d1b98fa3e025e60 |
| institution | Directory Open Access Journal |
| issn | 2214-1804 |
| language | English |
| last_indexed | 2024-12-12T08:12:45Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Sensing and Bio-Sensing Research |
| spelling | doaj.art-87b2a09eff84465a8d1b98fa3e025e602022-12-22T00:31:42ZengElsevierSensing and Bio-Sensing Research2214-18042022-06-0136100495Ensemble machine learning approach for electronic nose signal processingDedy Rahman Wijaya0Farah Afianti1Anditya Arifianto2Dewi Rahmawati3Vassilis S. Kodogiannis4School of Applied Science, Telkom University, Bandung, Indonesia; Corresponding author at: Jalan Telekomunikasi, Terusan Buah Batu, Bandung City, West Java 40257, Indonesia.School of Computing, Telkom University, Bandung, IndonesiaSchool of Computing, Telkom University, Bandung, IndonesiaInstitut Teknologi Telkom Surabaya, Surabaya, IndonesiaSchool of Computer Science & Engineering, University of Westminster, London W1W 6UW, United KingdomElectronic nose (e-nose) systems have been reported to be used in many areas as rapid, low-cost, and non-invasive instruments. Especially in meat production and processing, e-nose system is a powerful tool to process volatile compounds as a unique ‘fingerprint’. The ability of the pattern recognition algorithm to analyze e-nose signals is the key to the success of the e-nose system in many applications. On the other hand, ensemble methods have been reported for favorable performances in various data sets. This research proposes an ensemble learning approach for e-nose signal processing, especially in beef quality assessment. Ensemble methods are not only used for learning algorithms but also sensor array optimization. For sensor array optimization, three filter-based feature selection algorithms (FSAs) are used to build ensemble FSA such as reliefF, chi-square, and gini index. Ensemble FSA is developed to deal with different or unstable outputs of a single FSA on homogeneous e-nose data sets in beef quality monitoring. Moreover, ensemble learning algorithms are employed to deal with multi-class classification and regression tasks. Random forest and Adaboost are used that represent bagging and boosting algorithms, respectively. The results are also compared with support vector machine and decision tree as single learners. According to the experimental results, our ensemble approach has good performance and generalization in e-nose signal processing. Optimized sensor combination based on filter-based FSA shows stable results both in classification and regression tasks. Furthermore, Adaboost as a boosting algorithm produces the best prediction even though using a smaller number of sensors.http://www.sciencedirect.com/science/article/pii/S2214180422000241E-noseEnsembleFeature selectionBeef quality |
| spellingShingle | Dedy Rahman Wijaya Farah Afianti Anditya Arifianto Dewi Rahmawati Vassilis S. Kodogiannis Ensemble machine learning approach for electronic nose signal processing Sensing and Bio-Sensing Research E-nose Ensemble Feature selection Beef quality |
| title | Ensemble machine learning approach for electronic nose signal processing |
| title_full | Ensemble machine learning approach for electronic nose signal processing |
| title_fullStr | Ensemble machine learning approach for electronic nose signal processing |
| title_full_unstemmed | Ensemble machine learning approach for electronic nose signal processing |
| title_short | Ensemble machine learning approach for electronic nose signal processing |
| title_sort | ensemble machine learning approach for electronic nose signal processing |
| topic | E-nose Ensemble Feature selection Beef quality |
| url | http://www.sciencedirect.com/science/article/pii/S2214180422000241 |
| work_keys_str_mv | AT dedyrahmanwijaya ensemblemachinelearningapproachforelectronicnosesignalprocessing AT farahafianti ensemblemachinelearningapproachforelectronicnosesignalprocessing AT andityaarifianto ensemblemachinelearningapproachforelectronicnosesignalprocessing AT dewirahmawati ensemblemachinelearningapproachforelectronicnosesignalprocessing AT vassilisskodogiannis ensemblemachinelearningapproachforelectronicnosesignalprocessing |