Journal of information and communication convergence engineering

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Use of Artificial Bee Swarm Optimization (ABSO) for Feature Selection in System Diagnosis for Coronary Heart Disease

  • Wiharto (Department of Informatics, Sebelas Maret University) ;
  • Yaumi A. Z. A. Fajri (Department of Informatics, Sebelas Maret University) ;
  • Esti Suryani (Department of Informatics, Sebelas Maret University) ;
  • Sigit Setyawan (Department of Medicine, Sebelas Maret University)
  • Received : 2022.10.15
  • Accepted : 2023.03.26
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

The selection of the correct examination variables for diagnosing heart disease provides many benefits, including faster diagnosis and lower cost of examination. The selection of inspection variables can be performed by referring to the data of previous examination results so that future investigations can be carried out by referring to these selected variables. This paper proposes a model for selecting examination variables using an Artificial Bee Swarm Optimization method by considering the variables of accuracy and cost of inspection. The proposed feature selection model was evaluated using the performance parameters of accuracy, area under curve (AUC), number of variables, and inspection cost. The test results show that the proposed model can produce 24 examination variables and provide 95.16% accuracy and 97.61% AUC. These results indicate a significant decrease in the number of inspection variables and inspection costs while maintaining performance in the excellent category.

Keywords

References

  1. A. Bommert, X. Sun, B. Bischl, J. Rahnenfuhrer, and M. Lang, "Benchmark for filter methods for feature selection in highdimensional classification data," Computational Statistics & Data Analysis, vol. 143, no. 2020. p. 106839, Mar. 2020, DOI: 10.1016/j.csda.2019.106839.
  2. R. Akbari, A. Mohammadi, and K. Ziarati, "A novel bee swarm optimization algorithm for numerical function optimization," Communications in Nonlinear Science and Numerical Simulation, vol. 15, no. 10, pp. 3142-3155, Oct. 2010. DOI: 10.1016/j.cnsns.2009.11.003.
  3. N. Karaboga, "A new design method based on artificial bee colony algorithm for digital IIR filters," Journal of the Franklin Institute, vol. 346, no. 4, pp. 328-348, May 2009. DOI: 10.1016/j.jfranklin.2008.11.003.
  4. D. Teodorovic, "Bee Colony Optimization (BCO)," Innovations in Swarm Intelligence, Springer Berlin Heidelberg, pp. 39-60, 2009. DOI: 10.1007/978-3-642-04225-6_3.
  5. D. T. Pham, M. Castellani, and A. A. Fahmy, "Learning the inverse kinematics of a robot manipulator using the Bees Algorithm," in 2008 6th IEEE International Conference on Industrial Informatics, Daejeon, South Korea, pp. 493-498. 2008. DOI: 10.1109/INDIN.2008.4618151.
  6. D. Karaboga and B. Basturk, "A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm," Journal of Global Optimization, vol. 39, no. 3, pp. 459-471, Oct. 2007, DOI: 10.1007/s10898-007-9149-x.
  7. X-S. Yang, "Engineering Optimizations via Nature-Inspired Virtual Bee Algorithms," in Artificial Intelligence and Knowledge Engineering Applications: A Bioinspired Approach, Las Palmas, Canary Islands, Spain, pp. 317-323, 2005. DOI: 10.1007/11499305_33.
  8. K. Sundareswaran and V. T. Sreedevi, "Development of novel optimization procedure based on honey bee foraging behavior," in 2008 IEEE International Conference on Systems, Man and Cybernetics, Singapore, pp. 1220-1225, 2008. DOI: 10.1109/ICSMC.2008.4811449.
  9. D. Karaboga and B. Akay, "A comparative study of Artificial Bee Colony algorithm," Applied Mathematics and Computation, vol. 214, no. 1, pp. 108-132, Aug. 2009. DOI: 10.1016/j.amc.2009.03.090.
  10. D. Chaudhary, B. Kumar, S. Sakshi, and R. Khanna, "Improved Bee Swarm Optimization Algorithm for Load Scheduling in Cloud Computing Environment," in Data Science and Analytics, Springer Singapore, pp. 400-413. 2018. DOI: 10.1007/978-981-10-8527-7_33.
  11. R. Akbari, A. Mohammadi, and K. Ziarati, "A powerful bee swarm optimization algorithm," in 2009 IEEE 13th International Multitopic Conference, Islamabad, Pakistan, pp. 1-6, 2009. DOI: 10.1109/INMIC.2009.5383155.
  12. S. Sadeg, L. Hamdad, K. Benatchba, and Z. Habbas, "BSO-FS: Bee Swarm Optimization for Feature Selection in Classification," in Advances in Computational Intelligence, Springer International Publishing, pp. 387-399, 2015. DOI: 10.1007/978-3-319-19258-1_33.
  13. H. Djellali, A. Djebbar, N. G. Zine, and N. Azizi, "Hybrid Artificial Bees Colony and Particle Swarm on Feature Selection," in Computational Intelligence and Its Applications, Springer International Publishing, pp. 93-105, 2018. DOI: 10.1007/978-3-319-89743-1_9.
  14. S. Sadeg, L. Hamdad, A. R. Remache, M. N. Karech, K. Benatchba, and Z. Habbas, "QBSO-FS: A Reinforcement Learning Based Bee Swarm Optimization Metaheuristic for Feature Selection," in Advances in Computational Intelligence, Springer International Publishing, pp. 785-796, 2019. DOI: 10.1007/978-3-030-20518-8_65.
  15. Wiharto, E. Suryani, S. Setyawan, and B. P. Putra, "The Cost-Based Feature Selection Model for Coronary Heart Disease Diagnosis System Using Deep Neural Network," IEEE Access, vol. 10, pp. 29687-29697, 2022. DOI: 10.1109/ACCESS.2022.3158752.
  16. Wiharto, E. Suryani, and S. Setyawan, "Framework Two-Tier Feature Selection on the Intelligence System Model for Detecting Coronary Heart Disease," Ingenierie des systemes d information, vol. 26, no. 6, pp. 541-547, Dec. 2021. DOI: 10.18280/isi.260604.
  17. W. Wiharto, E. Suryani, S. Setyawan, and B. P. Putra, "Hybrid Feature Selection Method Based on Genetic Algorithm for the Diagnosis of Coronary Heart Disease," Journal of Information and Communication Convergence Engineering, vol. 20, no. 1, pp. 31-40, Mar. 2022. DOI: 10.6109/JICCE.2022.20.1.31.
  18. B. A. Tama, S. Im, and S. Lee, "Improving an Intelligent Detection System for Coronary Heart Disease Using a Two-Tier Classifier Ensemble," BioMed Research International, vol. 2020, pp. 1-10, Apr. 2020. DOI: 10.1155/2020/9816142.
  19. U. Kilic and M. Kaya Keles, "Feature Selection with Artificial Bee Colony Algorithm on Z-Alizadeh Sani Dataset," in 2018 Innovations in Intelligent Systems and Applications Conference (ASYU), Adana, Turkey, pp. 1-3, 2018. DOI: 10.1109/ASYU.2018.8554004.
  20. B. Subanya and R. R. Rajalaxmi, "Feature selection using artificial bee colony for cardiovascular disease classification," in 2014 International Conference on Electronics and Communication Systems (ICECS), Coimbatore, India, pp. 1-6, 2014. DOI: 10.1109/ECS.2014.6892729.
  21. N-C. Yang and D. Mehmood, "Multi-Objective Bee Swarm Optimization Algorithm with Minimum Manhattan Distance for Passive Power Filter Optimization Problems," Mathematics, vol. 10, no. 1, p. 133, Jan. 2022. DOI: 10.3390/math10010133.
  22. A. Askarzadeh and A. Rezazadeh, "Artificial bee swarm optimization algorithm for parameters identification of solar cell models," Applied Energy, vol. 102, pp. 943-949, Feb. 2013. DOI: 10.1016/j.apenergy.2012.09.052.
  23. R. Spencer, F. Thabtah, N. Abdelhamid, and M. Thompson, "Exploring feature selection and classification methods for predicting heart disease," DIGITAL HEALTH, vol. 6, p. 205520762091477, Jan. 2020. DOI: 10.1177/2055207620914777.
  24. M. S. Pathan, A. Nag, M. M. Pathan, and S. Dev, "Analyzing the impact of feature selection on the accuracy of heart disease prediction," Healthcare Analytics, vol. 2, p. 100060, Nov. 2022. DOI: 10.1016/j.health.2022.100060.
  25. J. H. Joloudari, E. H. Joloudari, H. Saadatfar, M. Ghasemigol, S. M. Razavi, A. Mosavi, N. Nabipour, S. Shamshirband, and L. Nadai, "Coronary Artery Disease Diagnosis; Ranking the Significant Features Using a Random Trees Model," International Journal of Environmental Research and Public Health, vol. 17, no. 3, p. 731, Jan. 2020. DOI: 10.3390/ijerph17030731.
  26. Z. Arabasadi, R. Alizadehsani, M. Roshanzamir, H. Moosaei, and A. A. Yarifard, "Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm," Computer Methods and Programs in Biomedicine, vol. 141, no. 2017, pp. 19-26, ?. 2017. DOI: 10.1016/j.cmpb.2017.01.004.
  27. B. Kolukisa, H. Hacilar, G. Goy, M. Kus, B. Bakir-Gungor, A. Aral, and V, C. Gungor, "Evaluation of Classification Algorithms, Linear Discriminant Analysis and a New Hybrid Feature Selection Methodology for the Diagnosis of Coronary Artery Disease," in 2018 IEEE International Conference on Big Data (Big Data), Seattle, USA, pp. 2232-2238, 2018. DOI: 10.1109/BigData.2018.8622609.
  28. B. Kolukisa et al., "Coronary Artery Disease Diagnosis Using Optimized Adaptive Ensemble Machine Learning Algorithm," International Journal of Bioscience, Biochemistry and Bioinformatics, vol. 10, no. 1, pp. 58-65, 2020. DOI: 10.17706/ijbbb.2020.10.1.58-65.
  29. B. Senliol, G. Gulgezen, L. Yu, and Z. Cataltepe, "Fast Correlation Based Filter (FCBF) with a different search strategy," in 2008 23rd International Symposium on Computer and Information Sciences, Istanbul, Turkey, pp. 1-4, 2008. DOI: 10.1109/ISCIS.2008.4717949.
  30. M. Hassoon, M. S. Kouhi, M. Zomorodi-Moghadam, and M. Abdar, "Using PSO Algorithm for Producing Best Rules in Diagnosis of Heart Disease," in 2017 International Conference on Computer and Applications (ICCA), Doha, Qatar, pp. 306-311, Sep. 2017. DOI:10.1109/COMAPP.2017.8079784.
  31. F. Babic, J. Olejar, Z. Vantova, and J. Paralic, "Predictive and Descriptive Analysis for Heart Disease Diagnosis," in 2017 Federated Conference on Computer Science and Information Systems (FedCSIS), Prague, Czech Republic, pp. 155-163, 2017. DOI: 10.15439/2017F219