Abstract
In the field of continuous engineering, Predictive models have been broadly emerged with Artificial Neural Networks (ANN) for data classification and prediction. Commonly, Neural Networks (NN) have been trained through the backpropagation algorithm, which is considered as a traditional approach. In optimization problems, Bat Algorithm (BA) has been extensively carried out with ANN to tackle different barriers. One of the prominent issues is the worst population initialization in terms of retrieving initial weights for each neuron in ANN. The advantage of a strong pattern of initiating the search vectors may lead to improve overall algorithm performance. In this article, we have proposed the novel variant of NN structure with BA probability distributions. The proposed initialization methods composed of Gamma distribution (G-BAT-NN), an Exponential distribution (E-BAT-NN), Beta distribution (B-BAT-NN), and finally the Weibull distribution (W-BAT-NN). We implemented the proposed techniques for the ANN classification of feed forward neural networks using BA and suggest the enhanced versions of BA for ANN classification. We verified the results on 8 real-world data sets taken from the UCI repository for the classification problem.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yang, X.: Nature-Inspired Metaheuristic Algorithms. Luniver Press, Bristol (2010)
Noel, M.M., Noel, M.: A new gradient based particle swarm optimization algorithm for accurate computation of global minimum. Appl. Soft Comput. 12, 353–359 (2012)
Das, S., Suganthan, P.N.: Differential evolution: a survey of the state-of-the-art. IEEE Trans. Evol. Comput. 15(1), 4–31 (2011)
Davis, L.: Handbook of Genetic Algorithms. Van Nostrand Reinhold, New York (1991)
Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of the 1995 IEEE International Conference on Neural Networks (1995)
Yang, X.S., Deb, S.: Cuckoo search via Lévy flights. In: World Congress on Nature & Biologically Inspired Computing, NaBIC 2009 (2009)
Geem, W.Z., Kim, J.H., Loganathan, G.V.: A new heuristic optimization algorithm: harmony search. Simulation 76(2), 60–68 (2001)
Yang, X.S.: A new metaheuristic bat-inspired algorithm. In: González, J.R., Pelta, D.A., Cruz, C., Terrazas, G., Krasnogor, N. (eds.) Nature Inspired Cooperative Strategies for Optimization (NICSO 2010). Springer, Heidelberg (2010)
Gandomi, A.H., Yang, X.-S., Talatahari, S., Alavi, A.H.: Metaheuristic algorithms in modeling and optimization. In: Metaheuristic Applications in Structures and Infrastructures, pp. 1–24 (2014)
Zhang, G.P.: Neural networks for classification: a survey. IEEE Trans. Syst. Man Cybern. 30(4), 451–462 (2000)
Elshorbagy, A., Corzo, G., Srinivasulu, S.: Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology – part 2: application. Hydrol. Earth Syst. Sci. 14(10), 1943–1961 (2010)
Wongseree, W., Chaiyaratana, N., Vichittumaros, K., Winichagoon, P., Fucharoen, S.: Thalassaemia classification by neural networks and genetic programming. Inf. Sci. 177(3), 771–786 (2007)
Al-kazemi, B., Mohan, C.K.: Training feedforward neural networks using multi-phase particle swarm optimization. In: Proceedings of the 9th International IEEE Conference on Neural Information Processing, ICNOIP 2002 (2002)
Nawi, N.M., Rehma, M.Z., Khan, A., Chiroma, H., Herawan, T.: A modified Bat algorithm based on Gaussian distribution for solving optimization problem. J. Comput. Theor. Nanosci. 13, 706–714 (2016)
Kora, P., Kalva, S.R.: Improved Bat algorithm for the detection of myocardial infarction. SpringerPlus 4, 666 (2015)
Thangaraj, R., Pant, M., Deep, K.: Initializing PSO with probability distributions and low-discrepancy sequences: the comparative results. In: World Congress on Nature & Biologically Inspired Computing, NaBIC 2009 (2009)
Yan, H., Jiang, Y., Zheng, J., et al.: A multilayer perceptron-based medical decision support system for heart disease diagnosis. Expert Syst. Appl. 30(2), 272–281 (2006)
De Falco, I., Della Cioppa, A., Tarantino, E.: Facing classification problems with particle swarm optimization. Appl. Soft Comput. 7(3), 652–658 (2007)
Subasi, A.: Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput. Biol. Med. 43(5), 576–586 (2013)
Bangyal, W.H., Ahmad, J., Rauf, H.T., Pervaiz, S.: An improved Bat algorithm based on novel initialization technique for global optimization problem. Int. J. Adv. Comput. Sci. Appl. (IJACSA) 9(7), 158–166 (2018)
Kiranyaz, S., Ince, T., Yildirim, A., et al.: Evolutionary artificial neural networks by multi-dimensional particle swarm optimization. Neural Netw. 22(10), 1448–1462 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shahzad, A., Rauf, H.T., Asghar, T., Hayat, U. (2021). Comparison of Probability Distributions for Evolving Artificial Neural Networks Using Bat Algorithm. In: Ahram, T. (eds) Advances in Artificial Intelligence, Software and Systems Engineering. AHFE 2020. Advances in Intelligent Systems and Computing, vol 1213. Springer, Cham. https://doi.org/10.1007/978-3-030-51328-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-51328-3_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-51327-6
Online ISBN: 978-3-030-51328-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)