Analisis Kinerja Random Forest, Gradient Boosting, dan LightGBM dengan SMOTENC pada Klasifikasi Tingkat Obesitas
DOI:
https://doi.org/10.62712/juktisi.v5i1.1074Keywords:
klasifikasi obesitas, ketidakseimbangan data, ensemble learning, SMOTENC, LightGBMAbstract
Klasifikasi tingkat obesitas merupakan aspek penting dalam bidang kesehatan untuk mendukung deteksi dini dan pengambilan keputusan yang tepat. Namun, dataset obesitas umumnya memiliki distribusi kelas yang tidak seimbang, yang dapat menyebabkan bias model terhadap kelas mayoritas dan menurunkan kemampuan dalam mengenali kelas minoritas. Penelitian ini bertujuan untuk menganalisis kinerja algoritma ensemble learning dalam klasifikasi tingkat obesitas serta mengevaluasi pengaruh teknik penyeimbangan data terhadap performa model. Algoritma yang digunakan meliputi Random Forest, Gradient Boosting, dan Light Gradient Boosting Machine (LightGBM). Untuk mengatasi ketidakseimbangan data, diterapkan metode Synthetic Minority Over-sampling Technique for Nominal and Continuous (SMOTENC). Evaluasi model dilakukan menggunakan metrik accuracy, precision, recall, dan F1-score, serta didukung oleh analisis confusion matrix dan kurva Receiver Operating Characteristic (ROC). Hasil penelitian menunjukkan bahwa model LightGBM dengan SMOTENC menghasilkan performa terbaik dengan nilai accuracy sebesar 96,45%, precision sebesar 96,12%, recall sebesar 95,98%, dan F1-score sebesar 96,05%. Penerapan SMOTENC terbukti meningkatkan nilai recall dan F1-score pada kelas minoritas, sehingga menghasilkan klasifikasi yang lebih seimbang dan mengurangi bias terhadap kelas mayoritas.
Downloads
References
L. Bastida et al., “Promoting Obesity Prevention and Healthy Habits in Childhood: The OCARIoT Experience,” IEEE J. Transl. Eng. Heal. Med., vol. 11, no. February, pp. 261–270, 2023, doi: 10.1109/JTEHM.2023.3261899.
M. E. Piché, A. Tchernof, and J. P. Després, “Obesity Phenotypes, Diabetes, and Cardiovascular Diseases,” Circ. Res., vol. 126, no. 11, pp. 1477–1500, 2020, doi: 10.1161/CIRCRESAHA.120.316101.
M. Azad, M. F. K. Khan, and S. A. El-Ghany, “XAI-Enhanced Machine Learning for Obesity Risk Classification: A Stacking Approach With LIME Explanations,” IEEE Access, vol. 13, no. December 2024, pp. 13847–13865, 2025, doi: 10.1109/ACCESS.2025.3530840.
A. Salam and N. Abhinesh, “Revolutionizing dermatology: The role of artificial intelligence in clinical practice,” IP Indian J. Clin. Exp. Dermatology, vol. 10, no. 2, pp. 107–112, 2024, doi: 10.18231/j.ijced.2024.021.
B. Wang et al., “Diastolic and systolic right ventricular diameters for predicting pulmonary hypertension in children with congenital heart disease,” Clin. Imaging, vol. 70, no. March 2020, pp. 67–73, 2021, doi: 10.1016/j.clinimag.2020.10.027.
G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” Adv. Neural Inf. Process. Syst., vol. 2017-December, no. Nips, pp. 3147–3155, 2017.
M. M. Santoni, T. Basaruddin, K. Junus, and O. Lawanto, “Automatic Detection of Students’ Engagement During Online Learning: A Bagging Ensemble Deep Learning Approach,” IEEE Access, vol. 12, no. June, pp. 96063–96073, 2024, doi: 10.1109/ACCESS.2024.3425820.
M. Mukherjee and M. Khushi, “Smote-enc: A novel smote-based method to generate synthetic data for nominal and continuous features,” Appl. Syst. Innov., vol. 4, no. 1, pp. 1–15, 2021, doi: 10.3390/asi4010018.
G. A. Pradipta, R. Wardoyo, A. Musdholifah, and I. N. H. Sanjaya, “Radius-SMOTE: A New Oversampling Technique of Minority Samples Based on Radius Distance for Learning from Imbalanced Data,” IEEE Access, vol. 9, pp. 74763–74777, 2021, doi: 10.1109/ACCESS.2021.3080316.
S. Yin, Z. Li, D. Song, H. Mu, Y. Niu, and X. Wang, “Study on the Energy Evolution Law and Bursting Liability of Coal Failure with Different Joint Inclination Angles,” Appl. Sci., vol. 14, no. 3, 2024, doi: 10.3390/app14031120.
H. Javed, H. A. Muqeet, T. Javed, A. U. Rehman, and R. Sadiq, “Ethical Frameworks for Machine Learning in Sensitive Healthcare Applications,” IEEE Access, vol. 12, no. October 2023, pp. 16233–16254, 2024, doi: 10.1109/ACCESS.2023.3340884.
B. F. Wu, Y. C. Wu, L. W. Chiu, and H. P. Liu, “Soft Label With Channel Encoding for Dependent Facial Image Classification,” IEEE Access, vol. 10, pp. 10661–10672, 2022, doi: 10.1109/ACCESS.2022.3145195.
S. Ouaari, A. B. Ünal, M. Akgün, and N. Pfeifer, “Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach,” IEEE Access, vol. 13, no. July, pp. 151527–151537, 2025, doi: 10.1109/ACCESS.2025.3603429.
A. Tharwat and W. Schenck, “Active Learning for Handling Missing Data,” IEEE Trans. Neural Networks Learn. Syst., vol. 36, no. 2, pp. 3273–3287, 2025, doi: 10.1109/TNNLS.2024.3352279.
A. S. Desuky, Y. M. Elbarawy, S. Kausar, A. H. Omar, and S. Hussain, “Single-Point Crossover and Jellyfish Optimization for Handling Imbalanced Data Classification Problem,” IEEE Access, vol. 10, no. 3, pp. 11730–11749, 2022, doi: 10.1109/ACCESS.2022.3146424.
D. Muller, I. Soto-Rey, and F. Kramer, “An Analysis on Ensemble Learning Optimized Medical Image Classification with Deep Convolutional Neural Networks,” IEEE Access, vol. 10, no. June, pp. 66467–66480, 2022, doi: 10.1109/ACCESS.2022.3182399.
E. Santi et al., “High-Resolution Mapping of Soil Moisture by AMSR2 Data Disaggregation Based on Sentinel-1 and Machine Learning,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 17, pp. 15077–15088, 2024, doi: 10.1109/JSTARS.2024.3445111.
Y. Gao, L. Wang, G. Zhong, Y. Wang, and J. Yang, “Potential of Remote Sensing Images for Soil Moisture Retrieving Using Ensemble Learning Methods in Vegetation-Covered Area,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 16, pp. 8149–8165, 2023, doi: 10.1109/JSTARS.2023.3311096.
J. Erbani, P. É. Portier, E. Egyed-Zsigmond, and D. Nurbakova, “Confusion Matrices: A Unified Theory,” IEEE Access, vol. 12, no. October, pp. 181372–181419, 2024, doi: 10.1109/ACCESS.2024.3507199.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Kartika Handayani, Erni, Fuad Nur Hasan
This work is licensed under a Creative Commons Attribution 4.0 International License.
