Optimized bio-inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification
The function of enzymes is performed differently depending on their bio-chemical mechanisms and important to the prediction of protein structure and function. In order to overcome the weaknesses of imbalance data distribution in subclasses prediction we proposed Bio-Twin Support Vector Machine (Bio-...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Triveni Enterprises
2019
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/88772/1/SKGuramand2019_OptimizedBioInspiredKernelswithTwinSupport.pdf |
| _version_ | 1796864696772460544 |
|---|---|
| author | Guramand, S. K. Saedudin, R. D. R. Hassan, R. Kasim, S. Ramlan, R. Salim, B. W. |
| author_facet | Guramand, S. K. Saedudin, R. D. R. Hassan, R. Kasim, S. Ramlan, R. Salim, B. W. |
| author_sort | Guramand, S. K. |
| collection | ePrints |
| description | The function of enzymes is performed differently depending on their bio-chemical mechanisms and important to the prediction of protein structure and function. In order to overcome the weaknesses of imbalance data distribution in subclasses prediction we proposed Bio-Twin Support Vector Machine (Bio-TWSVM). The TWSVM approach as also allow for kernel optimization where in this study we have introduced the bio-inspired kernels such as the Fisher, spectrum and mismatch kernels which at the same time incorporate the biological information regarding the protein evolution in the classification process. |
| first_indexed | 2024-03-05T20:45:44Z |
| format | Article |
| id | utm.eprints-88772 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T20:45:44Z |
| publishDate | 2019 |
| publisher | Triveni Enterprises |
| record_format | dspace |
| spelling | utm.eprints-887722020-12-29T04:19:09Z http://eprints.utm.my/88772/ Optimized bio-inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification Guramand, S. K. Saedudin, R. D. R. Hassan, R. Kasim, S. Ramlan, R. Salim, B. W. QA75 Electronic computers. Computer science The function of enzymes is performed differently depending on their bio-chemical mechanisms and important to the prediction of protein structure and function. In order to overcome the weaknesses of imbalance data distribution in subclasses prediction we proposed Bio-Twin Support Vector Machine (Bio-TWSVM). The TWSVM approach as also allow for kernel optimization where in this study we have introduced the bio-inspired kernels such as the Fisher, spectrum and mismatch kernels which at the same time incorporate the biological information regarding the protein evolution in the classification process. Triveni Enterprises 2019-05 Article PeerReviewed application/pdf en http://eprints.utm.my/88772/1/SKGuramand2019_OptimizedBioInspiredKernelswithTwinSupport.pdf Guramand, S. K. and Saedudin, R. D. R. and Hassan, R. and Kasim, S. and Ramlan, R. and Salim, B. W. (2019) Optimized bio-inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification. Journal of Environmental Biology, 40 (3). pp. 563-576. ISSN 0254-8704 http://dx.doi.org/10.22438/jeb/40/3(SI)/Sp-21 DOI:10.22438/jeb/40/3(SI)/Sp-21 |
| spellingShingle | QA75 Electronic computers. Computer science Guramand, S. K. Saedudin, R. D. R. Hassan, R. Kasim, S. Ramlan, R. Salim, B. W. Optimized bio-inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification |
| title | Optimized bio-inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification |
| title_full | Optimized bio-inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification |
| title_fullStr | Optimized bio-inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification |
| title_full_unstemmed | Optimized bio-inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification |
| title_short | Optimized bio-inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification |
| title_sort | optimized bio inspired kernels with twin support vector machine using low identity sequences to solve imbalance multiclass classification |
| topic | QA75 Electronic computers. Computer science |
| url | http://eprints.utm.my/88772/1/SKGuramand2019_OptimizedBioInspiredKernelswithTwinSupport.pdf |
| work_keys_str_mv | AT guramandsk optimizedbioinspiredkernelswithtwinsupportvectormachineusinglowidentitysequencestosolveimbalancemulticlassclassification AT saedudinrdr optimizedbioinspiredkernelswithtwinsupportvectormachineusinglowidentitysequencestosolveimbalancemulticlassclassification AT hassanr optimizedbioinspiredkernelswithtwinsupportvectormachineusinglowidentitysequencestosolveimbalancemulticlassclassification AT kasims optimizedbioinspiredkernelswithtwinsupportvectormachineusinglowidentitysequencestosolveimbalancemulticlassclassification AT ramlanr optimizedbioinspiredkernelswithtwinsupportvectormachineusinglowidentitysequencestosolveimbalancemulticlassclassification AT salimbw optimizedbioinspiredkernelswithtwinsupportvectormachineusinglowidentitysequencestosolveimbalancemulticlassclassification |