COMPARATIVE ANALYSIS OF ENSEMBLE CLASSIFICATION MODELS AND SUPPORT VECTOR MACHINES IN MEASURING STRESS LEVELS BASED ON EEG SIGNALS
Abstract
Stress is a physiological and psychological response that can develop into serious health issues when prolonged. EEG-based stress detection has become an important approach; however, many studies still lack validation for multilevel classification and real-world conditions. This study focuses on inmates at Binjai Correctional Facility and compares the performance of Support Vector Machine (SVM), Random Forest (RF), and a combined ensemble model of Random Forest and AdaBoost for classifying three stress levels: stressed, relaxed, and neutral, using EEG signals. Experimental results show that the SVM model achieved an accuracy of 81% with a Minimum Classification Error (MCE) of 0.16. The Random Forest model significantly improved performance, reaching 96% accuracy and an MCE of 0.04. The best performance was obtained by the ensemble model combining Random Forest and AdaBoost, which achieved an accuracy of 97% and reduced the MCE to 0.03, indicating a 1% improvement over Random Forest alone.
References
V. Firhana, M. Riliani, R. Arwinda, and S. N. Riani, “Hubungan antara Tingkat Stres dengan Penyakit Gastritis pada Siswa SMA Negeri 2 Tambun Selatan dan Tinjauannya Menurut Pandangan Islam,” Jr. Med. J., vol. 2, no. 11, pp. 1295–1302, 2024.
I. Triastuti, W. S. Nurfauziah, and I. Noviyanti, “Tingkat Stres Pada Gen Z Terhadap Pengaruh Media Sosial,” vol. 4, no. 1, pp. 264–272, 2025.
E. Choi, H. J. Seo, K. H. Kim, and S. Y. Jung, “Gender-specific secular trends and related factors of high perceived stress level among Korean older adults: a nation-wide serial cross-sectional study,” BMC Public Health, vol. 25, no. 450, pp. 1–10, 2025, doi: 10.1186/s12889-025-21644-4.
Y. Badr, U. Tariq, F. Al-Shargie, F. Babiloni, F. Al Mughairbi, and H. Al-Nashash, “A review on evaluating mental stress by deep learning using EEG signals,” Neural Comput. Appl., vol. 36, no. 21, pp. 12629–12654, 2024, doi: 10.1007/s00521-024-09809-5.
A. Hemakom, D. Atiwiwat, and P. Israsena, “ECG and EEG based detection and multilevel classification of stress using machine learning for specified genders : A preliminary study,” PLoS One, vol. 18, no. 9, pp. 1–24, 2023, doi: 10.1371/journal.pone.0291070.
S. Chatterjee and Y. C. Byun, “EEG-Based Emotion Classification Using Stacking Ensemble Approach,” Sensors, vol. 22, no. 21, pp. 1–15, 2022, doi: 10.3390/s22218550.
A. Sundaresan, B. Penchina, S. Cheong, V. Grace, A. Valero-Cabré, and A. Martel, “Evaluating deep learning EEG-based mental stress classification in adolescents with autism for breathing entrainment BCI,” Brain Informatics, vol. 8, no. 13, pp. 1–12, 2021, doi: 10.1186/s40708-021-00133-5.
H. Ghodang and Hantono, Metode Penelitian Kuantitatif Konsep Dasar & Aplikasi Analisis Regresi Dengan Jalur SPSS. Medan: PT. Penerbit Mitra Grup, 2020.
F. Rachmawati, J. Jaenudin, N. B. Ginting, and P. Laksono, “Machine Learning for the Model Prediction of Final Semester Assessment (FSA) using the Multiple Linear Regression Method,” J. Tek. Inform., vol. 17, no. 1, pp. 1–9, 2024, doi: 10.15408/jti.v17i1.28652.
T. Hidayat, S. S. Anelia, R. I. Pratiwi, N. Salsabila, and D. S. Prasvita, “Perbandingan Akurasi Klasifikasi Penyakit Diabetes Menggunakan Algoritma Adaboost- Random Forest Dan Adaboost- Decision Tree Dengan Imputasi Median Dan Knn,” Semin. Nas. Mhs. Ilmu Komput. dan Apl., no. April, pp. 616–623, 2021.
B. Wijaya, D. Sitanggang, B. Lee, V. Angie, and Eric Simon Giovanni Siahaan, “Application of Support Vector Machine in Measuring Stress Levels Based on EEG Signals,” J. Teknol. dan Ilmu Komput. Prima, vol. 8, no. 1, pp. 12–25, 2025.
Andi, C. Juliandy, R. Robet, O. Pribadi, and R. Wijaya, “Image Authentication Application with Blockchain to Prevent and Detect Image Plagiarism,” 2021 6th Int. Conf. Informatics Comput. ICIC 2021, no. December, 2021, doi: 10.1109/ICIC54025.2021.9632966.
M. A. Muslim et al., Data Mining Algoritma C4.5. 2019.
Andi, R. Purba, and R. Yunis, “Application of Blockchain Technology to Prevent The Potential Of Plagiarism in Scientific Publication,” 2019, doi: 10.1109/ICIC47613.2019.8985920.
A. H. Bik, F. T. Anggraeny, and E. Y. Puspaningrum, “Klasifikasi Penyakit Ginjal Menggunakan Algoritma Hibrida CNN-ELM,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 3, pp. 3836–3844, 2024, doi: 10.36040/jati.v8i3.9807.
M. R. F. Nur and S. I. Oktora, “Analisis Kurva Roc Pada Model Logit Dalam Pemodelan Determinan Lansia Bekerja Di Kawasan Timur Indonesia,” Indones. J. Stat. Its Appl., vol. 4, no. 1, pp. 116–135, 2020, doi: 10.29244/ijsa.v4i1.524.
Andi, Thamrin, A. Susanto, E. Wijaya, and D. Djohan, “Analysis of the random forest and grid search algorithms in early detection of diabetes mellitus disease,” J. Mantik, vol. 7, no. 2, pp. 2685–4236, 2023, doi: 10.35335/mantik.v7i2.3981.
R. Katmah, F. Al-shargie, U. Tariq, F. Babiloni, F. Al-mughairbi, and H. Al-nashash, “A Review on Mental Stress Assessment Methods Using EEG Signals,” MDPI Sensors, vol. 21, no. 15, 2021.
A. Hag, D. Handayani, M. Altalhi, T. Pillai, T. Mantoro, and M. H. Kit, “Enhancing EEG-Based Mental Stress State Recognition Using an Improved Hybrid Feature Selection Algorithm,” MDPI Sensors, vol. 21, no. 24, 2021.
F. I. S. Ms, F. A. Bachtiar, and B. H. Prasetio, “Analyzing Eeg Signals for Stress Detection Using Random Forest Algorithm,” J. NeutrinoJurnal Fis. dan Apl., vol. 17, no. 1, pp. 29–36, 2024, doi: 10.18860/neu.v17i1.28471.
DOI: https://doi.org/10.33387/jiko.v9i1.11151
Refbacks
- There are currently no refbacks.