Journals / Black Sea Journal of Engineering and Science / 2026 / Cilt: 9 Sayı: 5

Comparative Evaluation of Random, Sobol, and Dragon-Family-Guided PSO and Quantum Inspired PSO on CEC 2022 Benchmarks and Cleveland Heart Disease Wrapper Feature Selection

Serkan Örücü(KARAMANOĞLU MEHMETBEY ÜNİVERSİTESİ, TEKNİK BİLİMLER MESLEK YÜKSEKOKULU)0000-0001-9905-2908
Pages
2491–2526
Publication Date
2026-09-15
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These results show that initialization, QI candidate generation, and dragon-based guidance vary with problem representation and evaluation dimension.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In Particle Swarm Optimization (PSO) and Quantum Inspired PSO (QI-PSO), the initialization source can shape early population diversity, search coverage, convergence behavior, and the later response of candidate generation operators.
📊
Key Findings & Data:This effect becomes important in both continuous optimization, where particles move in a real-valued search space, and wrapper feature selection, where candidate solutions are evaluated as binary feature masks through classifier performance.
💡
Conclusion & Impact:These results show that initialization, QI candidate generation, and dragon-based guidance vary with problem representation and evaluation dimension.
🔬Design:Modeling & Simulation
📍Scope:2022 Verileri
⚙️Variables:CEC 2022 · Dragon curve guidance · Heart disease

Abstract

In Particle Swarm Optimization (PSO) and Quantum Inspired PSO (QI-PSO), the initialization source can shape early population diversity, search coverage, convergence behavior, and the later response of candidate generation operators. This effect becomes important in both continuous optimization, where particles move in a real-valued search space, and wrapper feature selection, where candidate solutions are evaluated as binary feature masks through classifier performance. Dragon curves offer another way to define structured search sources because their ordered point sequences can be mapped into a normalized search domain and reused as geometric guides. Based on this idea, this study examines whether random initialization, Sobol initialization, QI candidate generation, and dragon-curve-based geometric guidance change method behavior across continuous optimization and wrapper feature selection. The PSO variant set included Random-PSO, Sobol-PSO, Heighway-PSO, Twindragon-PSO, and Terdragon-PSO, while the QI-PSO variant set included Random-QI-PSO, Sobol-QI-PSO, Heighway-QI-PSO, Twindragon-QI-PSO, and Terdragon-QI-PSO. Heighway, Twindragon, and Terdragon curves were used as ordered geometric sources for particle initialization and stagnation-triggered perturbation. The methods were tested on CEC 2022 benchmark functions in 10-dimensional and 20-dimensional settings and on the UCI Cleveland Heart Disease dataset through wrapper feature selection with KNN-based fitness and additional SVM evaluation. In CEC 2022, the PSO variants produced lower average ranks and lower average mean fitness values than the QI-PSO variants. Random-PSO achieved the lowest average rank and runtime, whereas Terdragon-PSO produced the lowest average mean fitness and the lowest mean best fitness trajectory among the PSO variants. Dragon-guided PSO variants produced more best mean fitness records, but with higher computational cost. In the Cleveland task, Sobol-QI-PSO produced the highest observed mean balanced accuracy among the wrapper FS methods under both KNN and SVM. However, the Holm-corrected comparisons indicated statistically similar balanced accuracy across the compared wrapper methods. Terdragon-PSO produced the highest feature subset stability, while Random-PSO produced the most compact subsets. These results show that initialization, QI candidate generation, and dragon-based guidance vary with problem representation and evaluation dimension. Future studies should evaluate new metaheuristic components through final fitness, runtime, classifier response, selected feature count, selection frequency, and feature subset stability rather than through one performance measure.

Özet

In Particle Swarm Optimization (PSO) and Quantum Inspired PSO (QI-PSO), the initialization source can shape early population diversity, search coverage, convergence behavior, and the later response of candidate generation operators. This effect becomes important in both continuous optimization, where particles move in a real-valued search space, and wrapper feature selection, where candidate solutions are evaluated as binary feature masks through classifier performance. Dragon curves offer another way to define structured search sources because their ordered point sequences can be mapped into a normalized search domain and reused as geometric guides. Based on this idea, this study examines whether random initialization, Sobol initialization, QI candidate generation, and dragon-curve-based geometric guidance change method behavior across continuous optimization and wrapper feature selection. The PSO variant set included Random-PSO, Sobol-PSO, Heighway-PSO, Twindragon-PSO, and Terdragon-PSO, while the QI-PSO variant set included Random-QI-PSO, Sobol-QI-PSO, Heighway-QI-PSO, Twindragon-QI-PSO, and Terdragon-QI-PSO. Heighway, Twindragon, and Terdragon curves were used as ordered geometric sources for particle initialization and stagnation-triggered perturbation. The methods were tested on CEC 2022 benchmark functions in 10-dimensional and 20-dimensional settings and on the UCI Cleveland Heart Disease dataset through wrapper feature selection with KNN-based fitness and additional SVM evaluation. In CEC 2022, the PSO variants produced lower average ranks and lower average mean fitness values than the QI-PSO variants. Random-PSO achieved the lowest average rank and runtime, whereas Terdragon-PSO produced the lowest average mean fitness and the lowest mean best fitness trajectory among the PSO variants. Dragon-guided PSO variants produced more best mean fitness records, but with higher computational cost. In the Cleveland task, Sobol-QI-PSO produced the highest observed mean balanced accuracy among the wrapper FS methods under both KNN and SVM. However, the Holm-corrected comparisons indicated statistically similar balanced accuracy across the compared wrapper methods. Terdragon-PSO produced the highest feature subset stability, while Random-PSO produced the most compact subsets. These results show that initialization, QI candidate generation, and dragon-based guidance vary with problem representation and evaluation dimension. Future studies should evaluate new metaheuristic components through final fitness, runtime, classifier response, selected feature count, selection frequency, and feature subset stability rather than through one performance measure.

🔖

Cite This Article

Örücü, S. (2026). Comparative Evaluation of Random, Sobol, and Dragon-Family-Guided PSO and Quantum Inspired PSO on CEC 2022 Benchmarks and Cleveland Heart Disease Wrapper Feature Selection. Black Sea Journal of Engineering and Science, Cilt: 9 Sayı: 5, 2491–2526. https://doi.org/10.34248/bsengineering.1992510

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (52)

  1. Agrawal, U. K., & Panda, N. (2025). Quantum-inspired adaptive mutation operator enabled PSO (QAMO-PSO) for parallel optimization and tailoring parameters of Kolmogorov–Arnold network. The Journal of Supercomputing, 81(14), Article 1310. https://doi.org/10.1007/s11227-025-07810-w
  2. Agushaka, O. J., & Ezugwu, A. E. S. (2020). Influence of initializing Krill Herd Algorithm with low-discrepancy sequences. IEEE Access, 8, 210886–210909. https://doi.org/10.1109/ACCESS.2020.3039602
  3. Alelyani, S. (2021). Stable bagging feature selection on medical data. Journal of Big Data, 8(1), Article 11. https://doi.org/10.1186/s40537-020-00385-8
  4. Asha, M. M., & Ramya, G. (2025). Artificial flora algorithm-based feature selection with support vector machine for cardiovascular disease classification. IEEE Access, 13, 7293–7309. https://doi.org/10.1109/ACCESS.2024.3524577
  5. Bajaj, A., Abraham, A., Ratnoo, S., & Gabralla, L. A. (2022). Test case prioritization, selection, and reduction using improved quantum-behaved particle swarm optimization. Sensors, 22(12), Article 4374. https://doi.org/10.3390/s22124374
  6. Balicki, J. (2022). Many-objective quantum-inspired particle swarm optimization algorithm for placement of virtual machines in smart computing cloud. Entropy, 24(1), Article 58. https://doi.org/10.3390/e24010058
  7. Bangyal, W. H., Nisar, K., Ag. Ibrahim, A. A., Haque, M. R., Rodrigues, J. J. P. C., & Rawat, D. B. (2021). Comparative analysis of low discrepancy sequence-based initialization approaches using population-based algorithms for solving the global optimization problems. Applied Sciences, 11(16), Article 7591. https://doi.org/10.3390/app11167591
  8. Bangyal, W. H., Nisar, K., Soomro, T. R., Ag Ibrahim, A. A., Mallah, G. A., Hassan, N. U., & Rehman, N. U. (2023). An improved particle swarm optimization algorithm for data classification. Applied Sciences, 13(1), Article 283. https://doi.org/10.3390/app13010283
  9. Biedrzycki, R. (2024). Revisiting CEC 2022 ranking: A new ranking method and influence of parameter tuning. Swarm and Evolutionary Computation, 89, Article 101623. https://doi.org/10.1016/j.swevo.2024.101623
  10. Biedrzycki, R. (2026). Analysis and simplification of the winner of the CEC 2022 optimization competition on single objective bound constrained search. Evolutionary Computation, 34(2), 195–212. https://doi.org/10.1162/EVCO.a.27
  11. Chen, S., & Zheng, J. (2023). Sand cat arithmetic optimization algorithm for global optimization engineering design problems. Journal of Computational Design and Engineering, 10(6), 2122–2146. https://doi.org/10.1093/jcde/qwad094
  12. Clerc, M., & Kennedy, J. (2002). The particle swarm - explosion, stability, and convergence in a multidimensional complex space. IEEE Transactions on Evolutionary Computation, 6(1), 58–73. https://doi.org/10.1109/4235.985692
  13. Cuevas, E., González-Sánchez, Ó. A., Escobar, H., Ayala, L. E., & Zaldívar, D. (2025). Filling space swarm optimization (FSSO): A metaheuristic algorithm with divided agent strategies and diamond crossover. The Journal of Supercomputing, 81(11), Article 1172. https://doi.org/10.1007/s11227-025-07645-5
  14. Deepika, D., & Balaji, N. (2022). Effective heart disease prediction with Grey-wolf with Firefly algorithm-differential evolution (GF-DE) for feature selection and weighted ANN classification. Computer Methods in Biomechanics and Biomedical Engineering, 25(12), 1409–1427. https://doi.org/10.1080/10255842.2022.2078966
  15. Derrac, J., García, S., Molina, D., & Herrera, F. (2011). A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm and Evolutionary Computation, 1(1), 3–18. https://doi.org/10.1016/j.swevo.2011.02.002
  16. Fang, N., & Cao, Q. (2024). Leaf in wind optimization: A new metaheuristic algorithm for solving optimization problems. IEEE Access, 12, 56291–56308. https://doi.org/10.1109/ACCESS.2024.3390670
  17. Gupta, A., Kumar, R., Arora, H. S., & Raman, B. (2022). C-CADZ: Computational intelligence system for coronary artery disease detection using Z-Alizadeh Sani dataset. Applied Intelligence, 52(3), 2436–2464. https://doi.org/10.1007/s10489-021-02467-3
  18. Hancer, E., Xue, B., Zhang, M., Karaboga, D., & Akay, B. (2018). Pareto front feature selection based on artificial bee colony optimization. Information Sciences, 422, 462–479. https://doi.org/10.1016/j.ins.2017.09.028
  19. Henderson, N., De Moura Menezes, A. A., Sacco, W. F., & Barufatti, N. E. (2015). Computation of critical points of mixtures using particle swarm optimization with low-discrepancy sequences. Chemical Engineering Communications, 202(11), 1478–1492. https://doi.org/10.1080/00986445.2014.947365
  20. Holm, S. (1979). A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics, 6(2), 65–70. http://www.jstor.org/stable/4615733
  21. Janosi, A., Steinbrunn, W., Pfisterer, M., & Detrano, R. (1989). Heart Disease [Data set]. UCI Machine Learning Repository. https://doi.org/10.24432/C52P4X
  22. Jiang, L., Haiminen, N., Carrieri, A.-P., Huang, S., Vázquez-Baeza, Y., Parida, L., Kim, H.-C., Swafford, A. D., Knight, R., & Natarajan, L. (2022). Utilizing stability criteria in choosing feature selection methods yields reproducible results in microbiome data. Biometrics, 78(3), 1155–1167. https://doi.org/10.1111/biom.13481
  23. Kennedy, J., & Eberhart, R. (1995). Particle swarm optimization. In Proceedings of ICNN'95 - International Conference on Neural Networks (Vol. 4, pp. 1942–1948). IEEE. https://doi.org/10.1109/ICNN.1995.488968
  24. Khan, M. A., Mazhar, T., Mateen Yaqoob, M., Badruddin Khan, M., Jilani Saudagar, A. K., Ghadi, Y. Y., Khattak, U. F., & Shahid, M. (2024). Optimal feature selection for heart disease prediction using modified Artificial Bee colony (M-ABC) and K-nearest neighbors (KNN). Scientific Reports, 14(1), Article 26241. https://doi.org/10.1038/s41598-024-78021-1
  25. Lee, C.-Y., & Zhuo, G.-L. (2021). Localization of rolling element faults using improved binary particle swarm optimization algorithm for feature selection task. Mathematics, 9(18), Article 2302. https://doi.org/10.3390/math9182302
  26. Li, Y., Zhao, D., Xu, Z., Heidari, A. A., Chen, H., Jiang, X., Liu, Z., Wang, M., Zhou, Q., & Xu, S. (2023). bSRWPSO-FKNN: A boosted PSO with fuzzy K-nearest neighbor classifier for predicting atopic dermatitis disease. Frontiers in Neuroinformatics, 16, Article 1063048. https://doi.org/10.3389/fninf.2022.1063048
  27. Lin, R., Xu, Z., Yu, L., & Wei, T. (2025). EABC-AS: Elite-driven artificial bee colony algorithm with adaptive population scaling. Swarm and Evolutionary Computation, 94, Article 101893. https://doi.org/10.1016/j.swevo.2025.101893
  28. Logofătu, D., Sobol, G., Andersson, C., Stamate, D., Balabanov, K., & Cejrowski, T. (2020). Particle swarm optimization algorithms for autonomous robots with deterministic leaders using space filling movements. Evolving Systems, 11(4), 629–645. https://doi.org/10.1007/s12530-020-09339-9
  29. Łukaszuk, T., & Krawczuk, J. (2024). Importance of feature selection stability in the classifier evaluation on high-dimensional genetic data. PeerJ, 12, Article e18405. https://doi.org/10.7717/peerj.18405
  30. Mienye, I. D., & Sun, Y. (2021). Improved heart disease prediction using particle swarm optimization based stacked sparse autoencoder. Electronics, 10(19), Article 2347. https://doi.org/10.3390/electronics10192347
  31. Mohamed, A. W., Hadi, A. A., Mohamed, A. K., Agrawal, P., Kumar, A., & Suganthan, P. N. (2020). Problem definitions and evaluation criteria for the CEC 2021 special session and competition on single objective bound constrained numerical optimization (Technical Report). Nanyang Technological University.
  32. Mohammed, A. G., & El-Khamy, S. E. (2024). Innovative chaotic dragon fractal (ChDrFr) shapes for efficient encryption applications: A new highly secure image encryption algorithm. Multimedia Tools and Applications, 83(17), 50449–50475. https://doi.org/10.1007/s11042-023-17183-y
  33. Naik, B. B., Priyanka, B., & Ansari, M. S. A. (2025). Energy-efficient task offloading and efficient resource allocation for edge computing: A quantum inspired particle swarm optimization approach. Cluster Computing, 28(3), Article 155. https://doi.org/10.1007/s10586-024-04833-5
  34. Ngai, S.-M., & Nguyen, N. (2003). The Heighway dragon revisited. Discrete & Computational Geometry, 29(4), 603–623. https://doi.org/10.1007/s00454-003-0778-7
  35. Nogueira, S., Sechidis, K., & Brown, G. (2017). On the stability of feature selection algorithms. Journal of Machine Learning Research, 18(1), 6345–6398.
  36. Noori, M. S., Sahbudin, R. K. Z., Sali, A., & Hashim, F. (2024). Multi-objective multi-exemplar particle swarm optimization algorithm with local awareness. IEEE Access, 12, 125809–125834. https://doi.org/10.1109/ACCESS.2024.3426104
  37. Noroozi, Z., Orooji, A., & Erfannia, L. (2023). Analyzing the impact of feature selection methods on machine learning algorithms for heart disease prediction. Scientific Reports, 13(1), Article 22588. https://doi.org/10.1038/s41598-023-49962-w
  38. Örücü, S. (2026). A comparative study of quantum-inspired PSO and EA with their binary variants for heart disease classification. Scientific Reports, 16, Article 57736. https://doi.org/10.1038/s41598-026-57736-3
  39. Pathak, S., Mani, A., & Chatterjee, A. (2024). A cooperative hybrid quantum-inspired salp swarm and differential evolution for solving CEC 2022 benchmark and controller placement problems in software defined networks. IEEE Access, 12, 90331–90344. https://doi.org/10.1109/ACCESS.2024.3414930
  40. Phan, H. T., Bui, D. M., Than, C. T., & Phan, T. V. (2025). Mechanical attributes of fractal dragons. Mathematics and Mechanics of Solids, 30(6), 1282–1294. https://doi.org/10.1177/10812865241289528
  41. Preskill, J. (2018). Quantum computing in the NISQ era and beyond. Quantum, 2, Article 79. https://doi.org/10.22331/q-2018-08-06-79
  42. Rashed, A. E. E., Badawy, M., Elhosseini, M. A., & Bahgat, W. M. (2025). An autoencoder-based approach for feature engineering in cardiovascular disease prediction. Neural Computing and Applications, 37(28), 23185–23218. https://doi.org/10.1007/s00521-025-11484-z
  43. Roșu, I.-A., Rovithakis, A., Grillakis, M., Petrakis, M. P., & Voulgarakis, A. (2025). Fractal modeling of wildfire spread using environmental parameter fields across Mediterranean landscapes. International Journal of Wildland Fire, 34(12), Article WF25199. https://doi.org/10.1071/WF25199
  44. Seghir, F., Drif, A., Selmani, S., & Cherifi, H. (2023). Wrapper-based feature selection for medical diagnosis: The BTLBO-KNN algorithm. IEEE Access, 11, 61368–61389. https://doi.org/10.1109/ACCESS.2023.3287484
  45. Stanovov, V., Kazakovtsev, L., & Semenkin, E. (2023). Crossover rate sorting in adaptive differential evolution. Algorithms, 16(3), Article 133. https://doi.org/10.3390/a16030133
  46. Stanovov, V., Kazakovtsev, L., & Semenkin, E. (2024). Hyper-heuristic approach for tuning parameter adaptation in differential evolution. Axioms, 13(1), Article 59. https://doi.org/10.3390/axioms13010059
  47. Storn, R., & Price, K. (1997). Differential evolution – A simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization, 11(4), 341–359. https://doi.org/10.1023/A:1008202821328
  48. Talin, I. A., Abid, M. H., Khan, M. A.-M., Kee, S.-H., & Nahid, A.-A. (2022). Finding the influential clinical traits that impact on the diagnosis of heart disease using statistical and machine-learning techniques. Scientific Reports, 12(1), Article 20199. https://doi.org/10.1038/s41598-022-24633-4
  49. Wadhawan, S., & Maini, R. (2022). ETCD: An effective machine learning based technique for cardiac disease prediction with optimal feature subset selection. Knowledge-Based Systems, 255, Article 109709. https://doi.org/10.1016/j.knosys.2022.109709
  50. Wang, J., Wang, X., Li, X., & Yi, J. (2023). A hybrid particle swarm optimization algorithm with dynamic adjustment of inertia weight based on a new feature selection method to optimize SVM parameters. Entropy, 25(3), Article 531. https://doi.org/10.3390/e25030531
  51. Wang, X., Snášel, V., Mirjalili, S., Pan, J.-S., Kong, L., & Shehadeh, H. A. (2024). Artificial Protozoa Optimizer (APO): A novel bio-inspired metaheuristic algorithm for engineering optimization. Knowledge-Based Systems, 295, Article 111737. https://doi.org/10.1016/j.knosys.2024.111737
  52. Xie, H., Zhang, L., Lim, C. P., Yu, Y., & Liu, H. (2021). Feature selection using enhanced particle swarm optimisation for classification models. Sensors, 21(5), Article 1816. https://doi.org/10.3390/s21051816