Almaarefa University
The authoritative source for research information and outputs is Elsevier Scopus, with researcher profile verification from the Deanship of Scientific Research.
ArticleOpen access20228 citation

An Optimization Approach for Convolutional Neural Network Using Non-Dominated Sorted Genetic Algorithm-II

Afia Zafar،Muhammad Aamir،Nazri Mohd Nawi،Arshad Ali،Saman Riaz،Abdulrahman Alruban ✉،Ashit Kumar Dutta،Badr Almutairi،Sultan Almotairi

Computers, materials & continua/Computers, materials & continua (Print) · vol. 74 (3) · 5641-5661 · 2022

Abstract

In computer vision, convolutional neural networks have a wide range of uses. Images represent most of today’s data, so it’s important to know how to handle these large amounts of data efficiently. Convolutional neural networks have been shown to solve image processing problems effectively. However, when designing the network structure for a particular problem, you need to adjust the hyperparameters for higher accuracy. This technique is time consuming and requires a lot of work and domain knowledge. Designing a convolutional neural network architecture is a classic NP-hard optimization challenge. On the other hand, different datasets require different combinations of models or hyperparameters, which can be time consuming and inconvenient. Various approaches have been proposed to overcome this problem, such as grid search limited to low-dimensional space and queuing by random selection. To address this issue, we propose an evolutionary algorithm-based approach that dynamically enhances the structure of Convolution Neural Networks (CNNs) using optimized hyperparameters. This study proposes a method using Non-dominated sorted genetic algorithms (NSGA) to improve the hyperparameters of the CNN model. In addition, different types and parameter ranges of existing genetic algorithms are used. A comparative study was conducted with various state-of-the-art methodologies and algorithms. Experiments have shown that our proposed approach is superior to previous methods in terms of classification accuracy, and the results are published in modern computing literature.

Details

Journal
Computers, materials & continua/Computers, materials & continua (Print)
Publisher
—
Volume
74
Issue
3
Pages
5641-5661
ISSN
1546-2218
Year
2022
Language
en
License
cc-by
Open access
diamond
Citations
8
Source
scopus

Topics

HyperparameterComputer scienceConvolutional neural networkHyperparameter optimizationGenetic algorithmArtificial intelligence

Metaheuristic Optimization Algorithms Research (Computer Science) · Advanced Neural Network Applications (Computer Science) · Evolutionary Algorithms and Applications (Computer Science)

Cite this

APA
Zafar, A., Aamir, M., Nawi, N. M., Ali, A., Riaz, S., Alruban, A., Dutta, A. K., Almutairi, B., Almotairi, S. (2022). An Optimization Approach for Convolutional Neural Network Using Non-Dominated Sorted Genetic Algorithm-II. Computers, materials & continua/Computers, materials & continua (Print), 74(3), 5641-5661. https://doi.org/10.32604/cmc.2023.033733
Harvard
Zafar, A., Aamir, M., Nawi, N. M., Ali, A., Riaz, S., Alruban, A., Dutta, A. K., Almutairi, B., Almotairi, S. 2022, 'An Optimization Approach for Convolutional Neural Network Using Non-Dominated Sorted Genetic Algorithm-II', Computers, materials & continua/Computers, materials & continua (Print), vol. 74(3), 5641-5661. Available at: https://doi.org/10.32604/cmc.2023.033733
Vancouver
Zafar A, Aamir M, Nawi NM, Ali A, Riaz S, Alruban A, Dutta AK, Almutairi B, Almotairi S. An Optimization Approach for Convolutional Neural Network Using Non-Dominated Sorted Genetic Algorithm-II. Computers, materials & continua/Computers, materials & continua (Print). 2022;74(3), 5641-5661.
BibTeX
@article{zafar20222130,
  title = {An Optimization Approach for Convolutional Neural Network Using Non-Dominated Sorted Genetic Algorithm-II},
  author = {Afia Zafar and Muhammad Aamir and Nazri Mohd Nawi and Arshad Ali and Saman Riaz and Abdulrahman Alruban and Ashit Kumar Dutta and Badr Almutairi and Sultan Almotairi},
  year = {2022},
  journal = {Computers, materials & continua/Computers, materials & continua (Print)},
  volume = {74},
  number = {3},
  pages = {5641-5661},
  doi = {10.32604/cmc.2023.033733},
  url = {https://doi.org/10.32604/cmc.2023.033733}
}
RIS
TY  - JOUR
AU  - Afia Zafar
AU  - Muhammad Aamir
AU  - Nazri Mohd Nawi
AU  - Arshad Ali
AU  - Saman Riaz
AU  - Abdulrahman Alruban
AU  - Ashit Kumar Dutta
AU  - Badr Almutairi
AU  - Sultan Almotairi
TI  - An Optimization Approach for Convolutional Neural Network Using Non-Dominated Sorted Genetic Algorithm-II
PY  - 2022
JO  - Computers, materials & continua/Computers, materials & continua (Print)
VL  - 74
IS  - 3
SP  - 5641-5661
DO  - 10.32604/cmc.2023.033733
UR  - https://doi.org/10.32604/cmc.2023.033733
ER  - 

Related outputs