International Journal of Computational and Electronic Aspects in Engineering
Volume 7 · Issue 4 · August 2026 · pp. 350-361
Research Article · Peer Reviewed
Received: May 16, 2026 · Accepted: July 23, 2026 · Published: August 11, 2026
DOI: 10.26706/ijceae.7.4.20260804
Open Access · CC BY 4.0

Evolutionary CNN Channel Selection Using Online Genetic Algorithm: Brain Tumor MRI as a Case Study

Muthana Naser Hussein*
Dhi Qar Education Directorate, Ministry of Education, Iraq.

*Corresponding author: muthananaser6@gmail.com
Download PDF Cite this article Certificate Volume 7 Issue 4

Abstract

Deep convolutional neural networks generate huge of feature channels many of these features have limited discriminative information. Nowadays numerous optimization techniques have been proposed for deep feature selection and most of them are offline operation. This paper presents an online evolutionary method for CNN channel selection based on Hasan's Online Genetic Algorithm (OGA), where the optimization process operates directly on the channel representation extracted from a deep convolutional network. To evaluate the proposed approach, deep feature maps were extracted using a pretrained ResNet50 network and converted into channel descriptors through global average pooling then Hasan's OGA was applied to optimize channel selection, and the resulting channel subset was evaluated using a Support Vector Machine (SVM) classifier. Experimental evaluation on a publicly available four-class brain tumor MRI dataset demonstrated that the proposed evolutionary optimization reduced the original 2048-channel representation to only 954 channels, corresponding to a channel reduction ratio of 53.42%. Despite eliminating more than half of the available channels, the optimized representation achieved a test classification accuracy of 93.19%, with precision 93.82%, recall 93.19%, and F1-score 92.98%. The obtained results showed that proposed algorithm provides an effective and computationally efficient method to select channels in deep CNN, where it reduces channel redundancy by eliminating the useful channel and keeping only the effected ones.

Keywords

Channel Selection Deep Convolutional Neural Networks Hasan's Online Genetic Algorithm Feature Channel Optimization

References

  1. B. R. Kiran, I. Sobh, V. Talpaert, P. Mannion, A. A. A. Sallab, S. Yogamani, and P. Pérez, “Deep reinforcement learning for autonomous driving: A survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 6, pp. 4909–4926, Jun. 2022, doi: 10.1109/TITS.2021.3054625.
  2. X. Liu, K. Gao, B. Liu, C. Pan, K. Liang, L. Yan, J. Ma, F. He, S. Zhang, S. Pan, and Y. Yu, “Advances in deep learning-based medical image analysis,” Health Data Science, vol. 2021, Article ID 8786793, 2021, doi: 10.34133/2021/8786793.
  3. A. Voulodimos, N. Doulamis, A. Doulamis, and E. Protopapadakis, “Deep learning for computer vision: A brief review,” Computational Intelligence and Neuroscience, vol. 2018, pp. 1–13, 2018, doi: 10.1155/2018/7068349.
  4. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.
  5. G. Huang, Z. Liu, L. Van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 4700–4708, doi: 10.48550/arXiv.1608.06993.
  6. M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA, 2019, pp. 6105–6114, doi: 10.48550/arXiv.1905.11946.
  7. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” in Proc. International Conference on Learning Representations (ICLR), 2021, doi: 10.48550/arXiv.2010.11929.
  8. E. Dönmez, “Enhancing classification capacity of CNN models with deep feature selection and fusion: A case study on maize seed classification,” Data & Knowledge Engineering, vol. 141, Art. no. 102075, 2022, doi: 10.1016/j.datak.2022.102075.
  9. A. Kiraz, F. Djibrillah, and M. E. Yüksel, “Deep feature extraction, dimensionality reduction, and classification of medical images using combined deep learning architectures, autoencoder, and multiple machine learning models,” Turkish Journal of Electrical Engineering and Computer Sciences, vol. 31, no. 5, pp. 1113–1128, 2023, doi: 10.55730/1300-0632.4037.
  10. G. Atteia, E.-S. M. El-Kenawy, N. A. Samee, et al., “Adaptive dynamic dipper throated optimization for feature selection in medical data,” Computers, Materials & Continua, vol. 75, no. 1, pp. 1883–1900, 2023, doi: 10.32604/cmc.2023.031723.
  11. M. F. Dar and A. Ganivada, “Deep learning and genetic algorithm-based ensemble model for feature selection and classification of breast ultrasound images,” Image and Vision Computing, vol. 146, Art. no. 105018, June 2024, doi: 10.1016/j.imavis.2024.105018.
  12. Q. S. Hamad, H. Samma, and S. A. Suandi, “Feature selection of pre-trained shallow CNN using the QLESCA optimizer: COVID-19 detection as a case study,” Applied Intelligence, vol. 53, no. 15, pp. 18630–18652, 2023, doi: 10.1007/s10489-022-04446-8.
  13. O. Attallah, “Lung and Colon Cancer Classification Using Multiscale Deep Features Integration of Compact Convolutional Neural Networks and Feature Selection,” Technologies, vol. 13, no. 2, Art. no. 54, 2025, doi: 10.3390/technologies13020054.
  14. A. H. Hasan, “Genetic Algorithm with Reserved Elite Population for Identification and Adaptive Estimation Tasks,” Ph.D. dissertation, Tula State University, Tula, Russia, 2014.
  15. A. H. Hasan, A. N. Grachev, and S. J. Abbas, “State space parameters estimation using online genetic algorithms,” Iraqi Journal of Computers, Communications, Control and Systems Engineering, vol. 14, no. 3, 2014, doi: 10.33103/2617-3352.1320.
  16. S. Gochhait, “Feature selection with metaheuristic algorithms: A review of recent developments (2020–2025),” Metaheuristic Algorithms with Applications, vol. 2, no. 1, pp. 99–111, 2025, doi: 10.48313/maa.v2i1.34.
  17. M. Faizan and M. A. Mohammad, “Metaheuristic Algorithms for Feature Selection (2014–2024),” International Journal of Applied Metaheuristic Computing, vol. 16, no. 1, pp. 1–23, 2025, doi: 10.4018/IJAMC.397402.
  18. H. A. Alsalamah and W. N. Ismail, “Evolutionary Computation for Feature Optimization and Image-Based Dimensionality Reduction,” Mathematics, vol. 13, no. 23, Art. no. 3869, 2025, doi: 10.3390/math13233869.
  19. M. F. Dar and A. Ganivada, “Deep learning and genetic algorithm-based ensemble model for feature selection and classification of breast ultrasound images,” Image and Vision Computing, vol. 146, Art. no. 105018, 2024, doi: 10.1016/j.imavis.2024.105018.
  20. A. Naskar, S. Dey, and P. Roy, “Adaptive genetic algorithm based deep feature selector for cancer detection in lung histopathological images,” Sci. Rep., vol. 15, Art. no. 4803, 2025, doi: 10.1038/s41598-025-86361-8.
  21. Y. He, X. Zhang, and J. Sun, “Channel Pruning for Accelerating Very Deep Neural Networks,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2017, doi: 10.48550/arXiv.1707.06168.
  22. Z. Liu, H. Mu, X. Zhang, Z. Guo, X. Yang, K.-T. Cheng, and J. Sun, “MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
  23. B. Li, B. Wu, J. Su, G. Wang, and L. Lin, “EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning,” in Proc. European Conference on Computer Vision (ECCV), 2020, doi: 10.1007/978-3-030-58536-5_38.
  24. R. Humble, M. Shen, J. Albericio, E. Darve, and J. Alvarez, “Soft Masking for Cost-Constrained Channel Pruning,” in Proc. European Conference on Computer Vision (ECCV), 2022, doi: 10.1007/978-3-031-20083-0_38.
  25. Y. Li, K. Adamczewski, W. Li, S. Gu, R. Timofte, and L. Van Gool, “Revisiting Random Channel Pruning for Neural Network Compression,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 191–201, 2022, doi: 10.1109/CVPR52688.2022.00029.
  26. X. Liu, J. Cao, H. Yao, W. Sun, and Y. Zhang, “AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance,” arXiv:2109.06397, 2021.
  27. X. Wang, Y. Huang, X. Long, and Z. Ma, “Channel Pruning via Improved Grey Wolf Optimizer Pruner,” IEICE Transactions on Information and Systems, vol. E107-D, no. 7, pp. 894–897, 2024, doi: 10.1587/transinf.2024EDL8007.
  28. M. Park, D. Kim, C. Park, Y. Park, G. E. Gong, W. W. Ro, and S. Kim, “REPrune: channel pruning via kernel representative selection,” in Proc. 38th AAAI Conference on Artificial Intelligence, vol. 38, Art. no. 1622, pp. 14545–14553, 2024, doi: 10.1609/aaai.v38i13.29370.
  29. S. Chen and Y. Zhao, “MLPruner: pruning convolutional neural networks with automatic mask learning,” PeerJ Computer Science, vol. 11, e3132, 2025, doi: 10.7717/peerj-cs.3132.
  30. X. Zhou, Z. Wang, L. Feng, S. Liu, K.-C. Wong, and K. C. Tan, “Toward Evolutionary Multitask Convolutional Neural Architecture Search,” IEEE Transactions on Evolutionary Computation, 2024, doi: 10.1109/TEVC.2023.3348475.
  31. R. Al-Hajj, M. M. Fouad, and M. Zeki, “Evolutionary optimization framework to train multilayer perceptrons for engineering applications,” Mathematical Biosciences and Engineering, vol. 21, no. 2, pp. 2970–2990, 2024, doi: 10.3934/mbe.2024132.
  32. E. H. Abdulsaed, M. Alabbas, and R. S. Khudeyer, “Optimizing the Architecture of Convolutional Neural Networks Using Modified Swarm Intelligence,” Journal of Al-Qadisiyah for Computer Science and Mathematics, vol. 16, no. 1, pp. Comp.124–136, 2024, doi: 10.29304/jqcsm.2024.16.11450.