Implementation of Genetic Algorithms in Convolutional Neural Networks for Object Detection and Classification

XVII International Conference on Systems, Automatic Control and Measurements, SAUM 2024 (pp. 161-164)

АУТОР(И) / AUTHOR(S): Nikola Ivačko , Ivan Ćirić , Ljiljana Radović, Žarko Ćojbašić 

Download Full Pdf  

DOI:  10.46793/SAUM24.161I

САЖЕТАК / ABSTRACT:

Convolutional Neural Networks (CNNs) have established themselves as a cornerstone in object detection and classification, delivering exceptional performance across many applications. However, the efficacy of CNNs is heavily dependent on the meticulous design and optimization of their architecture and hyperparameters, a process that is often labor-intensive and computationally demanding. Genetic Algorithms (GAs), inspired by the principles of natural evolution, present a viable solution to automate and enhance the optimization of CNNs. This survey reviews the integration of genetic algorithms into the development and refinement of CNN architecture for object detection and classification tasks. We explore a range of GA-based approaches, including architecture optimization, hyperparameter tuning, and ensemble methods, highlighting how these techniques improve CNN performance. The survey also delves into application areas of medical image analysis and agricultural monitoring, demonstrating the versatility and effectiveness of GA optimization strategies. By synthesizing findings from recent studies, this paper highlights key trends, identifies prevalent challenges, and outlines future research directions in the convergence of genetic algorithms and deep learning. This survey aims to provide researchers and practitioners with a consolidated understanding of how genetic algorithms can be leveraged to advance the performance and applicability of CNNs in object detection and classification.

КЉУЧНЕ РЕЧИ / KEYWORDS:

optimization, genetic algorithm, convolutional neural net- work, object detection

ЛИТЕРАТУРА / REFERENCE

  1. LeCun, K. Kavukcuoglu and C. Farabet, „Convolutional networks and applications in vision,“ Proceedings of 2010 IEEE International Symposium on Circuits and Systems, Paris, France, 2010, pp. 253-256, doi: 10.1109/ISCAS.2010.5537907.
  2. Girshick, „Fast R-CNN,“ Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1440-1448.
  3. Barik and M. Mondal, „Object identification for computer vision using image segmentation,“ 2010 2nd International Conference on Education Technology and Computer, vol. 2, IEEE, Piscataway, 2010, pp. V2-170.
  4. D. Zeiler and R. Fergus, „Visualizing and understanding convolutional networks,“ European Conference on Computer Vision, Springer, Cham, 2014, pp. 818-833.
  5. Sinha, A. Haidar, and B. Verma, „Particle swarm optimizationbased approach for finding optimal values of convolutional neural network parameters,“ 2018 IEEE Congress on Evolutionary Computation (CEC), 2018, pp. 1-6
  6. Lorenzo PR, Nalepa J, Kawulok M, Ramos LS, Pastor JR, Particle swarm optimization for hyperparameter selection in deep neural net- works, Proceedings of the Genetic and Evolutionary Computation Conference, 2017, pp 481-494
  7. Nair V, Hinton GE, Rectified linear units improve restricted Boltzmann machines, ICML, 2010
  8. Zunino and P. Gastaldo, „Analog implementation of the softmax function,“ in 2002 IEEE International Symposium on Circuits and Systems, vol. 2, Piscataway, NJ, USA, May 2002, pp. 17-20. doi: 10.1109/CAS.2002.1019310.
  9. Bacanin, T. Bezdan, E. Tuba, I. Strumberger, and M. Tuba, „Optimizing convolutional neural network hyperparameters by enhanced swarm intelligence metaheuristics,“ Algorithms, vol. 13, no. 3, p. 67, 2020.
  10. ] H. Tian, S. Pouyanfar, J. Chen, S.-C. Chen, and S. S. Iyengar, „Automatic convolutional neural network selection for image classification using genetic algorithms,“ in 2018 IEEE International Conference on Information Reuse and Integration (IRI), Salt Lake City, UT, USA, 2018, pp. 444–451. doi: 10.1109/IRI.2018.00071.
  11. Sun Y, Xue B, Zhang M, Yen GG, Lv J (2020) Automatically design- ing CNN architectures using the genetic algorithm for image classifi- cation. IEEE Trans Cybern 50(9):3840–3854
  12. Abdelfatah, Amr & Darwish, Saad & El-Sherbiny, Mohamed. (2020). A Novel Automatic CNN Architecture Design Approach Based on Genetic Algorithm. 10.1007/978-3-030-31129-2_43.
  13. H. Khalifa, et al., „Particle swarm optimization for deep learning of convolution neural network,“ in 2017 Sudan Conference on Computer Science and Information Technology (SCCSIT), 2017, pp. 1–5.
  14. R. Houck, J. Joines, and M. G. Kay, „A genetic algorithm for func- tion optimization: a Matlab implementation,“ NCSU-IE TR,1995
  15. Khan, A. Sohail, U. Zahoora, and A. S. Qureshi, „A survey of the recent architectures of deep convolutional neural networks,“ Artificial Intelligence Review, vol. 53, no. 8, pp. 5455–5516, 2020.
  16. Galván and P. Mooney, „Neuroevolution in deep neural networks: current trends and future challenges,“ IEEE Trans Artif Intell, vol. 2, no. 6, pp. 476–493, 2021.
  17. Liu et al., „A review of deep learning methods for cyber security, „IEEE Access, vol. 9, pp. 40115–40129, 2021.
  18. H. Zhan, J. Y. Li, and J. Zhang, „Evolutionary deep learning: a sur- vey,“ Neurocomputing, vol. 483, pp. 42–58, 2022.
  19. Mishra and L. Kane, „A survey of designing convolutional neural network using evolutionary algorithms,“ Artif. Intell. Rev., vol. 56, no. 6, pp. 5095–5132, Jun. 2023. doi: 10.1007/s10462-022-10303-4.
  20. Johnson, A. Valderrama, C. Valle, B. Crawford, R. Soto, and R. Ñanculef, „Automating Configuration of Convolutional Neural Network Hyperparameters Using Genetic Algorithm,“ IEEE Access, vol. 8, pp. 156139-156152, 2020
  21. Loussaief and A. Abdelkrim, „Convolutional Neural Network Hy- per-Parameters Optimization Based on Genetic Algorithms,“ International Journal of Advanced Computer Science and Applications, vol. 9, no. 10, pp. 252–266, 2018.
  22. Bakhshi, N. Noman, Z. Chen, M. Zamani, and S. Chalup, „Fast Automatic Optimization of CNN Architectures for Image Classification Using Genetic Algorithm,“ in 2019 IEEE Congress on Evolutionary Computation (CEC), Piscataway, NJ, USA, Jun. 2019, pp. 1283–1290.
  23. P. Ijjina and K. M. Chalavadi, „Human Action Recognition Using Genetic Algorithms and Convolutional Neural Networks,“ Pattern Recognition, vol. 59, pp.199–212,2016
  24. M. Aszemi and P. D. D. Dominic, „Hyperparameter Optimization in Convolutional Neural Network Using Genetic Algorithms,“ International Journal of Advanced Computer Science and Applications (IJACSA), vol. 10, no. 6, 2019, doi: 10.14569/IJACSA.2019.0100638.
  25. H. Yoo et al., „Optimization of Hyper-parameter for CNN Model Using Genetic Algorithm,“ in 2019 1st International Conference on Electrical, Control and Instrumentation Engineering (ICECIE), 2019, pp. 1-6.
  26. Ayan, „Genetic Algorithm-Based Hyperparameter Optimization for Convolutional Neural Networks in the Classification of Crop Pests,“ Arabian Journal for Science and Engineering, vol. 48, no. 3, pp. 3079- 3093, 2023.
  27. Fan, „High-Precision Tomato Maturity Detection Using a Genetic Algorithm Optimized Swin-YOLO Network,“ International Journal of Computer Science and Information Technology, vol. 2, no. 2, 2024.
  28. Pérez and S. Ventura, „An ensemble-based convolutional neural net- work model powered by a genetic algorithm for melanoma diagnosis,“ Neural Computing and Applications, vol. 34, pp. 10429–10448, 2022.
  29. F. Rodrigues, A. R. Backes, B. A. N. Travençolo, and G. M. B. de Oliveira, „Optimizing a deep residual neural network with genetic al- gorithm for acute lymphoblastic leukemia classification,“ Journal of Digital Imaging, vol. 35, no. 3, pp. 623-637, Jun.2022