Reliability Analysis of Surface Tracking Method Using Classification Methods (svm, random forest, XGBoost) with Whale Optimization Algorithm

Year 2025, Volume: 17 Issue: 2, 408 - 417, 30.12.2025

Ertuğrul Adıgüzel , Nadir Subaşı , Aysel Ersoy

https://doi.org/10.47000/tjmcs.1724786

Abstract

This study presents a comprehensive reliability analysis of a surface tracking methodology integrating
machine learning classifiers—Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient
Boosting (XGBoost)—optimized via the Whale Optimization Algorithm (WOA). The framework addresses surface
degradation detection by leveraging experimental data from epoxy/MgO nanocomposite materials subjected
to hydro-aging and electrical tracking conditions. Features representing physical and electrical behaviors were
engineered and subjected to advanced preprocessing and classification workflows. WOA was employed for hyperparameter
tuning and feature importance calibration, aiming to improve model robustness and accuracy. Results
indicate that XGBoost, when optimized with WOA, outperforms SVM and RF in all metrics, achieving 92.3% accuracy
and a macro F1-score of 0.94, with enhanced generalizability and resilience to class imbalance. The dataset
consists of 180 samples, categorized into three reliability classes (‘low’, ‘medium’, and ‘high’) based on the quartile
thresholds of reliability scores. The study underlines the critical importance of nature-inspired optimization in
classification pipelines and provides a robust blueprint for predictive modeling in materials reliability applications.

Keywords

Surface tracking , Reliability analysis , Whale Optimization Algorithm (WOA) , Machine learning classification , XGBoost , Hyperparameter tuning

Thanks

We would like to thank Kaancan Kırkağaç for sharing his experimental results with us for enabling their evaluation using artificial intelligence models.

References

• Basudhar, A., Missoum, S., Reliability assessment using probabilistic support vector machines, International Journal of Reliability and Safety, 7(2)(2013), 156.
• Buchholz, M.X., The Whale optimization algorithm for solving constrained problems in C++, Medium, (2005).
• Chen, X., Wu, H., Xie, X., Online ensemble of exemplar-SVMs for visual tracking, Proc. IEEE ICDH, (2012), 293–297.
• Eslami, N., Rahbar, M., Bozorgi, S. M., Yazdani, S., Whale optimization algorithm and its application in machine learning, Handbook of Whale Optimization Algorithm, (2024), 69–80.
• Fassi, A., Ivaldi, G., Meaglia, I., Porcu, P., Fatis, P. et al., Response to: reproducibility of the external surface position in left-breast DIBH radiotherapy with spirometer-based monitoring: methodological mistake, Journal of Applied Clinical Medical Physics, 15(4)(2014), 401–401.
• Gao, H., Bai, G., Vibration reliability analysis for aeroengine compressor blade based on support vector machine response surface method, Journal of Central South University, 22(5)(2015), 1685–1694.
• Gao, X., Liu, F., Robust visual tracking based on support vector machine and weighted sampling method, International Journal on Smart Sensing and Intelligent Systems, 8(1)(2015), 255–271.
• Goodlich, B., Vecchio, A., Kavanagh, J., Motor unit tracking using blind source separation filters and waveform cross-correlations: reliability under physiological and pharmacological conditions, (2023).
• Guo, S., Comparison between generative model and discriminant model based on support vector machine algorithm, Machine Learning Theory and Practice, 3(1)(2022).
• Hao, Y., Huang, B., Sułowicz, M., A practical prediction model for surface deformation of open-pit mine slopes based on artificial intelligence, Elektronika Ir Elektrotechnika, 30(3)(2024), 46–53.
• Hu, Z., Hu, Z., Du, X., One-class support vector machines with a bias constraint and its application in system reliability prediction, Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 33(3)(2019), 346–358.
• Huang, C., Wu, J., Shan, Z., Wang, Q., Yu, Z., Reliability prediction for new prefabricated track structures based on the fuzzy failure modes, effects, and criticality analysis method, Applied Sciences, 14(12)(2024), 5338.
• Hussein, M.K., Alkahla, L.T., Jameel, E.A., Diabetes prediction using XGBoost and hyperparameter algorithms, Lecture Notes in Networks and Systems, (2025), 205–216.
• Hwang, Y., Chiang, C., Simple surface-tracking methods for grain burnback analysis, Journal of Propulsion and Power, 31(5)(2015), 1436–1444.
• Kırkağac¸, K., Ispirli, M.M., Ersoy, A., The effect of water on tracking failure of epoxy/MgO samples, Electrical Engineering, 104(6)(2022), 4137–4147.
• Leeuwen, B., Toubman, A., Pal, J., Pool, D., Prediction models for individuals’ control skill development and retention using XGBoost and SHAP, (2023).
• Li, S., Hong, Z., Zhang, Z., Relevance vector machine-based response surface for slope reliability analysis, International Journal for Numerical and Analytical Methods in Geomechanics, 41(11)(2017), 1332–1346.
• Odya, P., G´orski, F., Czy˙zewski, A., User authentication by eye movement features employing SVM and XGBoost classifiers, IEEE Access, 11(2023), 93341–93353.
• Shen, W., Zhang, Q., Fan, W., Analysis of dynamic system reliability based on adaptive response surface method, Proc. ICMEA, (2018).
• Shrestha, K., Jabed Omur Rifat, H.M., Biswas, U., Tiang, J.J., Abdullah-Al Nahid, Predicting the recurrence of differentiated Thyroid Cancer using Whale optimization-based XGBoost algorithm, Diagnostics, 15(13)(2025), 1684–1684.
• Wang, Y., Yu, X., Du, X., Improved reliability-based optimization with support vector machines and its application in aircraft wing design, Mathematical Problems in Engineering, (2015), 1–14.
• Weng, S., Liu, Z., Fan, Z., Zhang, G., A whale optimization algorithm-based ensemble model for power consumption prediction, Electrical Engineering, 107(2)(2024), 1659–1670.
• Xu, Z., Zhang, X., Shearer reliability prediction using support vector machine based on chaotic particle swarm optimization algorithm, (2022).
• Yang, T., Wang, S., Liu, H., Tunnel failure evolution and system reliability analysis based on the β-unzipping method, Applied Sciences, 11(8)(2021), 3373.
• Ye, X., Luo, Y., Li, Z., Liu, X., A quantitative detection method for surface cracks on slab track based on infrared thermography, Applied Sciences, 13(11)(2023), 6681.
• Yu, X., Yan, Q., Reliability analysis of self-anchored suspension bridge by improved response surface method, Applied Mechanics and Materials, 90–93(2011), 869–873.
• Zhang, C., Liu, J., Lu, C., Liu, B., Wang, A. et al., Double response surface method of reliability analysis for mechanism, Proc. IEEE IEEM, (2015).
• Zhang, J., Xiao, M., Gao, L., Chu, S., Probability and interval hybrid reliability analysis based on adaptive local approximation of projection outlines using support vector machine, Computer-Aided Civil and Infrastructure Engineering, 34(11)(2019), 991–1009.
• Zhao, Z., Han, Y., Xu, T., Li, X., Song, H. et al., A reliable and real-time tracking method with color distribution, Sensors, 17(10)(2017), 2303.
• Zuo, W., Wu, X., Lin, L., Zhang, L., Yang, M., Learning support correlation filters for visual tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(5)(2019), 1158–1172.