Open Access

ARTICLE

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

by Afia Zafar¹, Muhammad Aamir², Nazri Mohd Nawi¹, Ali Arshad³, Saman Riaz³, Abdulrahman Alruban^4,*, Ashit Kumar Dutta⁵, Badr Almutairi⁶, Sultan Almotairi^7,8

1 Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Malaysia
2 School of Electronics, Computing and Mathematics, University of Derby, UK
3 Department of Computer Science, National University of Technology, Islamabad, Pakistan
4 Department of Information Technology, College of Computer and Information Sciences, Majmaah University, Al Majmaah, 11952, Saudi Arabia
5 Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University, Riyadh, 13713, Kingdom of Saudi Arabia
6 Department of Information Technology, College of Computer Sciences and Information Technology College, Majmaah University, Al-Majmaah, 11952, Saudi Arabia
7 Department of Natural and Applied Sciences, Faculty of Community College, Majmaah University, Majmaah, 11952, Saudi Arabia
8 Department of Information Systems, Faculty of Computer and Information Sciences, Islamic University of Madinah, Madinah, 42351, Saudi Arabia

* Corresponding Author: Abdulrahman Alruban. Email:

Computers, Materials & Continua 2023, 74(3), 5641-5661. https://doi.org/10.32604/cmc.2023.033733

Received 26 June 2022; Accepted 22 September 2022; Issue published 28 December 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.

---

Keywords

---