TOWARDS GLOBAL OPTIMIZATION OF NEURAL NETWORK: A COMPARATIVE ANALYSIS USING GENETIC AND WHALE OPTIMIZATION ALGORITHMS
Keywords:Artificial Neural Networks, Genetic Algorithms, Optimization, Whale Optimization Algorithm
The intelligence and adaptability features of the neural network has made it a technique that is widely used to solve problems in diverse areas such as; detection, monitoring, prediction, diagnostics, data mining, classification, recognition, robotics, biomedicine, etc. However, determination of the optimal number of hidden layers of neural network and other parameters are still a difficult task. Usually, these parameters are decided by trial-and-error which increases the computational complexity and it is human dependent in obtaining the optimal model and parameters alike for any particular task. Optimization has received enormous attention in recent years, primarily because of the rapid progress in computer technology, including the development and availability of user-friendly software, high-speed and parallel processors, and artificial neural networks. This research work is to propose a neuro-evolutionary model using the computational intelligence techniques by combining ANN, GA and WOA for binary classification problems. The proposed optimized ANN-GA and WOA models is to circumvent the problem that is characterized in the trade-off between smoothness and accuracies in selecting the models and optimal parameters of neural network.
. Negnevitsky, M. (2005). Artificial Intelligence: A Guide to Intelligent Systems. Addison-Wesley, Harlow.
. Qin, H and Tang, S. (2009). A Solution to Dimensionality Curse of BP Network in Pattern Recognition Based on RS Theory. International Joint Conference on Computational Sciences and Optimization, 636-638.
. Azzini, A (2006), A New Genetic Approach for Neural Network Design and Optimization, Ph.D. Thesis.
. Adhirai, S., Mahapatra, R.P. and Singh, P. (2018). The Whale Optimization Algorithm and Its Implementation in MATLAB. International Scholarly and Scientific Research & Innovation. Vol. 12, No: 10.
. Svozil, D., Kvasnicka, V. and Pospichal, J. (1997). Introduction to Multi-Layer Feed-forward Neural Networks. Chemometrics and Intelligent Laboratory Systems, 39, 43-62.
. Mirjalili, S. and Lewis, A. (2016). The Whale Optimization Algorithm. Advances in Engineering Software. 51-67.
. Goldberg, D.E. (1989). Genetic Algorithm in Search, Optimization and Machine Learning, New York: Addison-Wesley.
. Yang X-S (ed.) (2014). Random Walks and Optimization. In: Nature inspired Optimization Algorithms, Chap 3. Elsevier, Oxford. Pp. 45-65.
. Aljarah I., Faris, H. and Mirjalili, S. (2016). Optimizing Connection Weights in Neural Networks Using the Whale Optimization Algorithm. Soft Comput. Springer.
. Nasiri, J. and Khiyabani, M. (2018). A Whale Optimization Algorithm (WOA) Approach for Clustering.Cogent Mathematics & Statistics. pp. 1-13.
. Hussien, A.G., Hassanien, A.E., Houssein, E.H., Hoissien, E.H., Amin, M and Azar, T.A. (2019). New Binary Whale Optimization Algorithm for Discrete Optimization Problems. Engineering Optimization. http://doi.org/10.1080/0305215x.2019.1624740.
. Mirjalili, S. and Lewis, A. (2016). The Whale Optimization Algorithm. Advances in Engineering Software, Vol. 95, pp51-57.
. Eng, M.H., Li, Y and Wang, Q-G. (2008). Forecast Foresx With ANN Using Fundamental Data. International Conference on Information Management, Innovation Management and Industrial Engineering, 279-282.
. Abhiishek, K., Kumar, A., Ranjan, R. and Kumar, S. (2012). A rainfall prediction model using artificial neural network, Conference: Control and System Graduate Research Colloquium (ICSGRC), 2012 IEEE,DOI 10.1109/ICSGRC.2012.6287140
. Thomas, A.J., Miltos, P., Simon, D. W., Saeed, M. G. and Robert, E. M. (2015). On Predicting the Optimal Number of Hidden Nodes. International Conference on Computational Science and Computational Intelligence, pp 565-570.
. Salgotra, R., Singh, U and Saha, S. (2019). On Some Improved Versions of Whale Optimization Algorithm. Arbian Journal for Science and Engineering. http://doi.org/10.1007/s13369-019-04016-0.
. Kumar J. Bansal A. and Jha M.K. (2007). Comparison of statistical and neural network techniques in predicting physical proper ties of various mixtures of diesel and biodiesel. In: Ao SI, Douglas C, Grundfest WS, Schruben L, Wu X, editors. Proceedings of the World Congress on Engineering and Computer Science (WCECS 2007); 2007 Oct 24–26; San Francisco. Hong Kong: Newswood Limited, IAENG; 2000. p. 95–98
. Nienhold, D., Schwab, K., and Hanne, T. (2015). Effects of Weight Initialization in a Feedforward Neural Network for Classification Using a Modified Genetic Algorithm. 3rd International Symposium on Computational and Business Intelligence. Pp 6-12.
. Bishop C. (1995). Neural networks for pattern recognition. Oxford (UK): Oxford University Press.
. Abdalla, O.A., Osman, A., and Mohammed, Y. (2014). Optimizing the multilayer Feed-Forward Artificial Neural Networks Architecture and Training Parameters Using Genetic Algorithm. International Journal of Computer Applications. Vol.99, No.10, 42-48.
. Ferentinos, K.P. (2005). Biological Engineering Applications of Feedforward Neural Networks Designed and Parameterized by Genetic Algorithms. Elsevier. Pp. 934-950.
. Panchai, G., Ganatra, A., Kosta, Y. P. and Panchai, D. (2011). Challenges to Multi-Layer Feed Forward Neural Networks in Intrusion Detection. International Journal of Computer Theory and Engineering, Vol.3(2), pp332-337.
. Batchis, P. (2013). An Evolutionary Algorithm for Neural Network Learning Using Direct Encoding. Resource 53, Chinese Digital Library, Available Online: www.es.rutgets.edu/~mlittman/courses/ml03/iCML03/.../batchis.pdf. Accessed 25th August, 2018.
. Sewsynker-Sukai, Y., Faloye, F., and Gueguim, E.B. (2017). Artificial Neural Networks: An Efficient Tool for Modeling and Optimization of Biofuel Production (a mini review). Biotechnology and Biotechnological Equipment, 31:2, 221-235.
. Fischer, M. M. and Leung, Y. (1998). A Genetic-Algorithm Based Evolutionary Computational Neural Network for Modeling Spatial Interaction Data. European Regional Science Association, 38th European Congress, Vienna, Austria, pp1-25.
. Kokko, T. (2013). Neural Networks for Computationally Expensive Problems. Master’s Thesis. Negnevitsky, M. (2005). Artificial Intelligence: A Guide to Intelligent Systems. Addison-Wesley, Harlow.
. Geron, A. (2019). Hands-On Machine Learning with Scikit-Leaming, Keras, and Tensor Flow: Concepts, Tools and Techniques to Build Intelligent Systems. 2nd Edition. O’reilly
. Palit, A.K., and Popovic, D. (2005) Computational Intelligence in Time Series Forecasting: Theory and Engineering Applications. Springer.
. Deepa, S.N and Sivanandam, S.N. (2008). Introduction to Genetic Algorithms. Springer. New York.
. Devaraj, D., and Roselyn, J.P. (2007). Improved Genetic Algorithm for Voltage Security Constrained Optimal Power Flow Problem. Int. J. Energy Technology and Policy, Vol. 5, No. 4. Pp475-488.
. Devaraj, D. and Yagnanarayana, B. (2000). A Combined Genetic Algorithm Approach for Optimal Power Flow. Proc. Of 11th National Conference on Power Systems. pp524-528
. Bouktir, T., Slimani, L. and Belkacemi, M. (2004). A Genetic Algorithm for Solving the Optimal Power Flow Problem. Leonardo Journal of Sciences. Issue 4, pp.44-58.
. Rothlauf, F. (2006). Representations of Genetic and Evolutionary Algorithms. Springer.
. Delima, A.J.P., Sison, A.M. and Medina, R.P. (2019). A Modified Genetic Algorithm with a New Crossover Mating Scheme. Indonesian Journal of Electrical Engineering and Informatics (IJEEI). Vol. 7, No. 2, pp. 165-181.
How to Cite
Copyright (c) 2021 Kingsley Ukaoha, Igodan, E. C., Oliomogbe, S. O.
This work is licensed under a Creative Commons Attribution 4.0 International License.