Abstract

This paper proposes a novel application of Fireworks Algorithm in Artificial Neural Network training. Fireworks Algorithm is a recently developed Swarm Intelligence algorithm for function optimization. Fireworks Algorithm mimics the explosion process of fireworks. In this paper, Fireworks Algorithm is applied in training of Multi-Layer Perceptron for classification task in medical data mining. The classification task is carried out on 5 well-known medical data sets from UCI machine learning repository. A comparative study has been made with classical optimization algorithm Levenberg-Marquardt Method and another Swarm Intelligence algorithm Particle Swarm Optimizer. The experimental results show that the proposed method performs better than other algorithms in classification.

References

• Amato F., Lopez A., Pe~na-Mendez E. M., Vanhara P., Hampl A. and Havel J. 2013. Artificial neural networks in medical diagnosis, J. Appl. Biomed., Vol. 11, 47–58, DOI:10.2478/v10136-012-0031-x
• Kennedy J. and Eberhart R. C. 1995. Particle swarm optimization, Proceedings of the IEEE International Conference on Neural Networks, Piscataway, NJ, 1942–1948.
• Shi Y. and Eberhart R. C. 1998. A modified particle swarm optimizer, In Proceedings of the IEEE Congress on Evolutionary Computation (CEC 1998), Piscataway, NJ, 69–73.
• Haykin S. 2011. Neural Networks And Learning Machines, PHI, 3rd Eds.
• Si T. and Sujauddin Sk. 2016. A Comparison of Grammatical Bee Colony and Neural Networks in Medical Data Mining, International Journal of Computer Applications, 134(6), 1–4.
• Si T., Hazra S. , and Jana N. D. 2012. Artificial Neural Network Training Using Differential Evolutionary Algorithm for Classification, in S.C. Satapathy et al. (Eds.): Proceedings of the InConINDIA 2012, AISC 132, 769–778.
• Shah H. and Ghazali R. 2011. Prediction of Earthquake Magnitude by an Improved ABC-MLP, In Proceedings of the Developments in E-systems Engineering (DeSE), 2011, Dubai, IEEE, 312–317, DOI:10.1109/DeSE.2011.37
• Si T. and Ghose R. 2015. Explosion sparks generation using adaptive transfer function in firework algorithm, In Proceedings of the IEEE Third International Conference on Signal Processing, Communication and Networking (ICSCN), 1–9.
• Yao X. and Liu Y. 1997. A new evolutionary system for evolving artificial neural networks, IEEE Transactions on Neural Networks, Vol. 8, Issue 3, 694–713.
• Yao X. 1999. Evolving artificial neural networks, Proceedings of The IEEE, Vol. 87 , Issue 9, 1423–1447.
• Lee Y. S., Shamsuddin S. M. and Hamed H. N. 2008. Bounded PSO Vmax Function in Neural Network Learning, In Proceedings of the IEEE Eighth International Conference on Intelligent Systems Design and Applications, 474–479.
• Tan Y. and Zhu Y. 2010. Firework Algorithm for Optimization, In: Y. Tan et al. (Eds): ICSI 2010, Part I, LNCS 6145, 355–364, Springer-Verlag Berlin Heidelberg.
• Liu J., Zheng S. and Tan Y. 2013. The improvement on controlling exploration and exploitation of Firework Algorithm, In: Y. Tan et al.(Eds): ICSI 2013, Part I, LNCS 7928, 11–23, Springer-Verlag Berlin Heidelberg.
• Han L., Kamber M. and Pei J. 2011. Data Mining: Concepts and Techniques, The Morgan Kaufmann Series in Data Management Systems Morgan Kaufmann Publishers.
• http://cml.ics.uci.edu.
• Barandela R., Sanchez J.S., Garca V. and Rangel E. 2003. Strategies for learning in class imbalance problems, Pattern Recognition, 36, 849–851.