Particle Swarm Optimization for Parameter Tuning in Machine Learning Algorithms

Rukhsar  H. Qadir; Nzar  A. Ali

doi:10.25098/6.2.29

Authors

Rukhsar H. Qadir Department of Statistics and Informatics, University of Sulaimani, Sulaimaniya, Iraq
Nzar A. Ali Department of Statistics and Informatics University of Sulaimani, Sulaimaniya, Iraq, Department of Computer Scince, Cihan University- Sulaimaniya, Sulaimaniya, Iraq

DOI:

https://doi.org/10.25098/6.2.29

Keywords:

Heart Disease, Support Vector Machines, Artificial Intelligence, Machine Learning, Particle Swarm Optimization

Abstract

Heart disease is one of the leading causes of death. One area where machine learning can be used is in the prediction of heart disease. In the medical area, classification is one of the Machine Learning techniques employed because of its high accuracy. The utilization of features and dimensions in the dataset affects the accuracy of the classification algorithm.

In this paper using the PSO algorithm, we present an optimization strategy for tuning support vector machine (SVM) parameter values to classify a dataset of heart disease.

The test results show that the classification using SVM with PSO can improve accuracy better than the classification using SVM without PSO, namely the determination of the parameters randomly. Results show that heart disease data classification without PSO accuracy is 0.7711 in time heart disease dataset classification with PSO accuracy increased to 0.8159 after optimizing the main two parameters of SVM C and gamma.

References

- Dahl, Ø., & Starren, A. (2019). The future role of big data and machine learning for health and safety inspection efficiency. EU-OSHA: Bilbao, Spain.

- Habibi, R. (2021). Svm performance optimization using PSO for breast cancer classification. Budapest International Research in Exact Sciences (BirEx) Journal, 3(1), 28-41.

- Alsaeedi, A. H., Aljanabi, A. H., Manna, M. E., & Albukhnefis, A. L. (2020). A proactive meta heuristic model for optimizing weights of artificial neural network. Indonesian Journal of Electrical Engineering and Computer Science, 20(2), 976-984.

- N. I. Indera, I. M. Yassin, A. Zabidi, and Z. I. Rizman, “Non-Linear Autoregressive with Exogeneous Input (Narx) Bitcoin Price Prediction Model Using Pso-Optimized Parameters and Moving Average Technical Indicators,” J. Fundam. Appl. Sci., vol. 9, pp. 791– 808, 2017.

- R. A. Jamous, “Modifications of Particle Swarm Optimization Techniques and Its Application on Stock Market : A Survey,” vol. 6, no. 3, pp. 99–108, 2015.

- Sahu, B., Panigrahi, A., Mohanty, S., & Sobhan, S. (2020). A hybrid cancer classification based on SVM optimized by PSO and reverse firefly algorithm. International Journal of Control and Automation, 13(4), 506-517.

- Dai, H., Li, J., Kuang, Y., Liao, J., Zhang, Q., & Kang, Y. (2021). Multiscale Fuzzy Entropy and PSO-SVM Based Fault Diagnoses for Airborne Fuel Pumps. Hum. Cent. Comput. Inf. Sci, 11, 25.

- Sethy, P. K., Barpanda, N. K., & Rath, A. K. (2019). Detection and identification of rice leaf diseases using multiclass SVM and particle swarm optimization technique. Int. J. Innovative Tech. and Exploring Eng. (IJITEE), 8(6S2), 108-120.

-URL:https://www.javatpoint.com/normalization-in-machine learning#:~:text=Normalization%20is%20a%20scaling%20technique,learning%20models%20have%20different%20ranges.june/2022

- Cho, M. Y., & Hoang, T. T. (2017). Feature selection and parameters optimization of SVM using particle swarm optimization for fault classification in power distribution systems. Computational intelligence and neuroscience, 2017.

- Li, X., Wu, S., Li, X., Yuan, H., & Zhao, D. (2020). Particle swarm optimization-support vector machine model for machinery fault diagnoses in high-voltage circuit breakers. Chinese Journal of Mechanical Engineering, 33(1), 1-10.

- Khalaf, T. Z., Çağlar, H., Çağlar, A., & Hanoon, A. N. (2020). Particle swarm optimization based approach for estimation of costs and duration of construction projects. Civil Engineering Journal, 6(2), 384-401.

-Habibi, R. (2021). Svm performance optimization using PSO for breast cancer classification. Budapest International Research in Exact Sciences (BirEx) Journal, 3(1), 28-41.

- R. A. Jamous, “Modifications of Particle Swarm Optimization Techniques and Its Application on Stock Market: A Survey,” vol. 6, no. 3, pp. 99–108, 2015.

-Khanesar M. A., Teshnehlab M., and Soorehdeli M.A.: A Novel Binary Particle Swarm

Optimization. In: Proc. 15Th Mediterranean Conference on Control and Automation, (2007)

-Yun, H. (2021). Prediction model of algal blooms using logistic regression and confusion matrix. International Journal of Electrical and Computer Engineering (IJECE), 11(3), 2407-2413.

-URL:https://statisticsbyjim.com/regression/mean-squared-error-mse///ByJimFrost//June/2022

-Daniel Peralta, Sara del R´ıo, Sergio Ram´ırez-Gallego, Isaac Triguero, Jose M Benitez, and Francisco Herrera. Evolutionary feature selection for big data classification: A mapreduce approach. Mathematical Problems in Engineering, 2015, 2015.