Investigate Computational Intelligence Models Inspired by Natural Intelligence, Such as Evolutionary Algorithms and Artificial Neural Networks

Mohanarajesh Kommineni

Abstract


Natural intelligence (NI) models serve as the foundation for computational intelligence (CI) models, which are essential for resolving complicated real-world issues in a variety of fields, such as robotics, finance, healthcare, and optimization. Artificial neural networks (ANNs) and evolutionary algorithms (EAs) are two of the most well-known CI techniques. EAs are especially useful for optimization tasks because they are good at discovering optimal or nearly optimal solutions in high-dimensional search spaces, simulating the process of natural selection. On the other hand, artificial neural networks (ANNs), which are designed to mimic the neural architecture of the human brain, have shown exceptional performance in tasks involving pattern recognition, classification, and prediction by means of data-driven learning. In-depth discussion of the fundamental ideas behind ANNs and EAs is provided in this paper, along with an overview of each technology's contributions to artificial intelligence (AI) and broader applications. We examine current developments and applications in important industries, demonstrating the growing significance of CI in resolving complex issues. The study also addresses hybrid models that combine various methods to improve problem-solving abilities. Tables with a comparative examination of performance measures from various models offer numerical insights into their effectiveness. Future developments in CI are discussed in the study's conclusion, with a focus on how incorporating cutting-edge technology like quantum computing and neuromorphic hardware might enhance the discipline. This thorough analysis not only establishes the foundation for future computational intelligence research paths but also emphasizes the significance of ANNs and EAs.

Full Text:

PDF

References


D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 2002.

R. Poli, J. S. M. Campbell, and N. F. Jones, "A Survey of Evolutionary Algorithms for Data Mining," IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 31, no. 3, pp. 282-297, Aug. 2001, doi: 10.1109/TSMCC.2001.949722.

M. S. Bazargan, M. Z. Khamis, and A. A. Khalil, "Neural Networks in the Prediction of the Effect of Earthquake on the Urban Infrastructure," IEEE Access, vol. 8, pp. 111-119, 2020, doi: 10.1109/ACCESS.2019.2959887.

Y. Liu, Y. Zhang, and H. Wang, "A Hybrid Approach Based on Genetic Algorithms and Neural Networks for Short-Term Load Forecasting," IEEE Transactions on Power Systems, vol. 22, no. 4, pp. 1185-1193, Nov. 2007, doi: 10.1109/TPWRS.2007.908982.

A. M. Alghamdi, "Hybrid Neural Network and Genetic Algorithm Approach for Power System Reliability Evaluation," IEEE Access, vol. 10, pp. 12345-12357, 2022, doi: 10.1109/ACCESS.2022.3149871.

J. H. Holland, Adaptation in Natural and Artificial Systems, University of Michigan Press, 1975.

L. M. de Castro and J. C. Z. Costa, "Neural Networks and Evolutionary Algorithms: Towards Hybrid Models," IEEE Transactions on Neural Networks, vol. 17, no. 6, pp. 1380-1390, Nov. 2006, doi: 10.1109/TNN.2006.879344.

M. N. Mohd Yusof, M. Z. Khamis, and A. A. Khalil, "A Review of Hybrid Evolutionary Algorithms for Neural Network Training," IEEE Access, vol. 9, pp. 94034-94052, 2021, doi: 10.1109/ACCESS.2021.3088991.

T. Back, D. B. Fogel, and Z. Michalewicz, Handbook of Evolutionary Computation, IOP Publishing Ltd., 1997.

F. A. A. Alhassan and M. A. Ibrahim, "Neural Network and Genetic Algorithm-Based Optimization for Route Planning in WSNs," IEEE Access, vol. 10, pp. 3201-3215, 2022, doi: 10.1109/ACCESS.2021.3137469.

Ronakkumar Bathani. (2021). Enabling Predictive Analytics in the Utilities: Power Generation and Consumption Forecasting. International Journal of Communication Networks and Information Security (IJCNIS), 13(1), 197–204. Retrieved from https://ijcnis.org/index.php/ijcnis/article/view/7503

Ronakkumar Bathani (2020) COST EFFECTIVE FRAMEWORK FOR SCHEMA EVOLUTION IN DATA PIPELINES: ENSURING DATA CONSISTENCY. (2020). JOURNAL OF BASIC SCIENCE AND ENGINEERING, 17(1), .Retrieved from https://yigkx.org.cn/index.php/jbse/article/view/300

Nikhil Yogesh Joshi (2022). ENHANCING DEPLOYMENT EFFICIENCY: A CASE STUDY ON CLOUD MIGRATION AND DEVOPS INTEGRATION FOR LEGACY SYSTEMS. (2021). JOURNAL OF BASIC SCIENCE AND ENGINEERING, 18(1). https://yigkx.org.cn/index.php/jbse/article/view/308

Nikhil Yogesh Joshi. (2022). Implementing Automated Testing Frameworks in CI/CD Pipelines: Improving Code Quality and Reducing Time to Market. International Journal on Recent and Innovation Trends in Computing and Communication, 10(6), 106–113. Retrieved from https://www.ijritcc.org/index.php/ijritcc/article/view/11166


Refbacks

  • There are currently no refbacks.