Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application
Abstract Deep learning has recently been utilized with great success in a large number of diverse application domains, such as visual and face recognition, natural language processing, speech recognition, and handwriting identification. Convolutional neural networks, that belong to the deep learning...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-09744-2 |
| _version_ | 1817988697462669312 |
|---|---|
| author | Nebojsa Bacanin Miodrag Zivkovic Fadi Al-Turjman K. Venkatachalam Pavel Trojovský Ivana Strumberger Timea Bezdan |
| author_facet | Nebojsa Bacanin Miodrag Zivkovic Fadi Al-Turjman K. Venkatachalam Pavel Trojovský Ivana Strumberger Timea Bezdan |
| author_sort | Nebojsa Bacanin |
| collection | DOAJ |
| description | Abstract Deep learning has recently been utilized with great success in a large number of diverse application domains, such as visual and face recognition, natural language processing, speech recognition, and handwriting identification. Convolutional neural networks, that belong to the deep learning models, are a subtype of artificial neural networks, which are inspired by the complex structure of the human brain and are often used for image classification tasks. One of the biggest challenges in all deep neural networks is the overfitting issue, which happens when the model performs well on the training data, but fails to make accurate predictions for the new data that is fed into the model. Several regularization methods have been introduced to prevent the overfitting problem. In the research presented in this manuscript, the overfitting challenge was tackled by selecting a proper value for the regularization parameter dropout by utilizing a swarm intelligence approach. Notwithstanding that the swarm algorithms have already been successfully applied to this domain, according to the available literature survey, their potential is still not fully investigated. Finding the optimal value of dropout is a challenging and time-consuming task if it is performed manually. Therefore, this research proposes an automated framework based on the hybridized sine cosine algorithm for tackling this major deep learning issue. The first experiment was conducted over four benchmark datasets: MNIST, CIFAR10, Semeion, and UPS, while the second experiment was performed on the brain tumor magnetic resonance imaging classification task. The obtained experimental results are compared to those generated by several similar approaches. The overall experimental results indicate that the proposed method outperforms other state-of-the-art methods included in the comparative analysis in terms of classification error and accuracy. |
| first_indexed | 2024-04-14T00:37:20Z |
| format | Article |
| id | doaj.art-ef4eb885de774c9085c9fc69fe66eb76 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-14T00:37:20Z |
| publishDate | 2022-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-ef4eb885de774c9085c9fc69fe66eb762022-12-22T02:22:19ZengNature PortfolioScientific Reports2045-23222022-04-0112112010.1038/s41598-022-09744-2Hybridized sine cosine algorithm with convolutional neural networks dropout regularization applicationNebojsa Bacanin0Miodrag Zivkovic1Fadi Al-Turjman2K. Venkatachalam3Pavel Trojovský4Ivana Strumberger5Timea Bezdan6Singidunum UniversitySingidunum UniversityArtificial Intelligence Engineering Department, Research Center for AI and IoT, AI and Robotics Institute, Near East UniversityDepartment of Applied Cybernetics, Faculty of Science, University of Hradec KrálovéDepartment of Applied Cybernetics, Faculty of Science, University of Hradec KrálovéSingidunum UniversitySingidunum UniversityAbstract Deep learning has recently been utilized with great success in a large number of diverse application domains, such as visual and face recognition, natural language processing, speech recognition, and handwriting identification. Convolutional neural networks, that belong to the deep learning models, are a subtype of artificial neural networks, which are inspired by the complex structure of the human brain and are often used for image classification tasks. One of the biggest challenges in all deep neural networks is the overfitting issue, which happens when the model performs well on the training data, but fails to make accurate predictions for the new data that is fed into the model. Several regularization methods have been introduced to prevent the overfitting problem. In the research presented in this manuscript, the overfitting challenge was tackled by selecting a proper value for the regularization parameter dropout by utilizing a swarm intelligence approach. Notwithstanding that the swarm algorithms have already been successfully applied to this domain, according to the available literature survey, their potential is still not fully investigated. Finding the optimal value of dropout is a challenging and time-consuming task if it is performed manually. Therefore, this research proposes an automated framework based on the hybridized sine cosine algorithm for tackling this major deep learning issue. The first experiment was conducted over four benchmark datasets: MNIST, CIFAR10, Semeion, and UPS, while the second experiment was performed on the brain tumor magnetic resonance imaging classification task. The obtained experimental results are compared to those generated by several similar approaches. The overall experimental results indicate that the proposed method outperforms other state-of-the-art methods included in the comparative analysis in terms of classification error and accuracy.https://doi.org/10.1038/s41598-022-09744-2 |
| spellingShingle | Nebojsa Bacanin Miodrag Zivkovic Fadi Al-Turjman K. Venkatachalam Pavel Trojovský Ivana Strumberger Timea Bezdan Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application Scientific Reports |
| title | Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application |
| title_full | Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application |
| title_fullStr | Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application |
| title_full_unstemmed | Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application |
| title_short | Hybridized sine cosine algorithm with convolutional neural networks dropout regularization application |
| title_sort | hybridized sine cosine algorithm with convolutional neural networks dropout regularization application |
| url | https://doi.org/10.1038/s41598-022-09744-2 |
| work_keys_str_mv | AT nebojsabacanin hybridizedsinecosinealgorithmwithconvolutionalneuralnetworksdropoutregularizationapplication AT miodragzivkovic hybridizedsinecosinealgorithmwithconvolutionalneuralnetworksdropoutregularizationapplication AT fadialturjman hybridizedsinecosinealgorithmwithconvolutionalneuralnetworksdropoutregularizationapplication AT kvenkatachalam hybridizedsinecosinealgorithmwithconvolutionalneuralnetworksdropoutregularizationapplication AT paveltrojovsky hybridizedsinecosinealgorithmwithconvolutionalneuralnetworksdropoutregularizationapplication AT ivanastrumberger hybridizedsinecosinealgorithmwithconvolutionalneuralnetworksdropoutregularizationapplication AT timeabezdan hybridizedsinecosinealgorithmwithconvolutionalneuralnetworksdropoutregularizationapplication |