Pemodelan Klasifikasi Efisiensi Kalori Berbasis Data Aktivitas dan Kondisi Fisiologis Menggunakan Random Forest dan SMOTE
Keywords:
Random Forest, SMOTE, Machine Learning, Multiclass ClassificationAbstract
Calorie efficiency classification based on activity data and physiological conditions has become an important approach in data-driven fitness analysis. The dataset used is categorized into three classes: High Efficiency (0), Low Efficiency (1), and Moderate (2). The main challenge addressed in this study is the class imbalance problem, which can negatively affect the performance of classification models. To overcome this issue, the Synthetic Minority Over-sampling Technique (SMOTE) was applied to balance the number of samples in each class. After applying SMOTE, each class contained an equal number of samples, totaling 750,594 instances. A classification model was then developed using the Random Forest algorithm, which is well-known for handling complex data and reducing overfitting. The evaluation results show that the model achieved an accuracy of 87.17%. The best performance was observed in the Low Efficiency class, with a precision of 0.95, recall of 0.92, and an f1-score of 0.93. In contrast, the Moderate and High Efficiency classes showed lower performance, particularly in recall values of 0.25 and 0.09, respectively. The macro-average f1-score of 0.45 indicates that the model's performance across classes is still imbalanced, while the weighted-average f1-score of 0.89 reflects good overall performance. In conclusion, the combination of Random Forest and SMOTE improves classification accuracy, although further improvements are needed to enhance performance on minority classes.
Downloads
References
[1] R. S. Pratama, I. Ramadhan, A. Wardhana, and T. N. Abdillah, “Analisis Literatur tentang Penggunaan Wearable IoT (Smart Watch, Smart Clothes, Smart Ring) untuk Optimalisasi Aktivitas Olahraga,” J. Penelit. Inov., vol. 5, no. 2, pp. 1857–1864, Jun. 2025, doi: 10.54082/jupin.1551.
[2] W. H. Al Qindy, J. Y. Damaira, and S. H. L. Siregar, “Analisis langkah jalan bulanan dan kalori yang dihasilkan pada pemahaman konsep energi dan metabolisme individu,” Tak. J. Pendidikan, Sains, dan Hum., vol. 4, no. 2, pp. 247–256, Aug. 2025, doi: 10.56113/takuana.v4i2.143.
[3] Y. N. A. Lestari and N. Amin, “Hubungan Status Gizi, Tingkat Kecukupan Energi dan Zat Gizi dengan Kecepatan pada Atlet Hockey Kota Surabaya,” Sport Nutr. J., vol. 1, no. 1, pp. 19–26, Jul. 2019, doi: 10.15294/spnj.v1i1.31275.
[4] A. Riansah, O. Nurdiawan, and R. Herdiana, “PENERAPAN ALGORITMA RANDOM FOREST DAN DECISION TREE UNTUK MENINGKATKAN AKURASI KLASIFIKASI PENJUALAN PADA TOKO BANGUNAN,” JATI (Jurnal Mhs. Tek. Inform., vol. 9, no. 3, pp. 4242–4249, May 2025, doi: 10.36040/jati.v9i3.13622.
[5] J. J. Hidayat and S. Hasanudin, “Prediksi Volatilitas IHSG Dengan Hybrid Model GARCH–Random Forest Berbasis Machine Learning,” J. Manaj. Inform. Teknol., vol. 6, no. 1 SE-Articles, pp. 130–140, 2026, doi: 10.51903/mifortekh.v6i1.1134.
[6] J. M. Johnson and T. M. Khoshgoftaar, “Survey on deep learning with class imbalance,” J. Big Data, vol. 6, no. 1, p. 27, Dec. 2019, doi: 10.1186/s40537-019-0192-5.
[7] E. Erlin, Y. Desnelita, N. Nasution, L. Suryati, and F. Zoromi, “Dampak SMOTE terhadap Kinerja Random Forest Classifier berdasarkan Data Tidak seimbang,” MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 21, no. 3, pp. 677–690, Jul. 2022, doi: 10.30812/matrik.v21i3.1726.
[8] A. Nugroho and D. Harini, “Teknik Random Forest untuk Meningkatan Akurasi Data Tidak Seimbang,” JSITIK J. Sist. Inf. dan Teknol. Inf. Komput., vol. 2, no. 2, pp. 128–140, Jun. 2024, doi: 10.53624/jsitik.v2i2.379.
[9] M. D. I. Amin, J. J. Hidayat, C. Setyowati, E. K. Fitri, A. N. Anggraini, and A. P. Werdana, “Implementasi Model LSTM Untuk Peramalan Curah Hujan Di Bekasi Dengan Pemanfaatan Data Cuaca BMKG,” J. Teknol. Inf. Digit., vol. 1, no. 2, pp. 90–99, [Online]. Available: https://jurnal.ipdig.id/index.php/jtid/article/view/200
[10] A. H. Anshor and A. T. Zy, “Implementasi Metode Decision Tree pada Sistem Prediksi Status Kualitas Produk Minuman A,” J. Ilm. Inform. Glob., vol. 15, no. 1, pp. 17–22, Apr. 2024, doi: 10.36982/jiig.v15i1.3778.
[11] N. Surojudin, S. Butsianto, and A. Firmansyah, “Perbandingan Kinerja Naïve Bayes dengan dan Tanpa SMOTE untuk Klasifikasi Gangguan Kecemasan Mahasiswa pada Data Tidak Seimbang,” Bull. Comput. Sci. Res., vol. 6, no. 2 SE-, pp. 804–812, Feb. 2026, doi: 10.47065/bulletincsr.v6i2.1021.
[12] A. M. Rifai, S. Raharjo, E. Utami, and D. Ariatmanto, “Analysis for diagnosis of pneumonia symptoms using chest X-ray based on MobileNetV2 models with image enhancement using white balance and contrast limited adaptive histogram equalization (CLAHE),” Biomed. Signal Process. Control, vol. 90, p. 105857, Apr. 2024, doi: 10.1016/j.bspc.2023.105857.
[13] M. Danny and M. Fatchan, “Model Prediksi Ketercapaian Learning Outcome Based Education Mahasiswa di Program Studi Teknik Informatika Menggunakan Algoritma Machine Learning,” J. Inform. Ekon. Bisnis, pp. 684–691, Sep. 2025, doi: 10.37034/infeb.v7i3.1259.
[14] J. J. Hidayat, C. Setyowati, and A. P. Werdana, “Perancangan Sistem Prediksi Penyakit pada Tanaman Padi Berbasis Image Processing Menggunakan Algoritma VGG-16 Transfer Learning dan K-Means Segmentation,” J. Pract. Comput. Sci., vol. 5, no. 1, pp. 1–15, May 2025, doi: 10.37366/jpcs.v5i1.5759.
[15] S. Arti and E. Suherlan, “Evaluasi Kinerja Machine Learning dalam Memprediksi Kemampuan Adaptasi Mahasiswa pada Lingkungan Pembelajaran Daring,” J. Pustaka AI (Pusat Akses Kaji. Teknol. Artif. Intell., vol. 5, no. 1, pp. 50–57, Apr. 2025, doi: 10.55382/jurnalpustakaai.v5i1.901.
[16] A. Bengnga and R. Ishak, “Implementasi Seleksi Fitur Klasifikasi Waktu Kelulusan Mahasiswa Menggunakan Correlation Matrix with Heatmap,” Jambura J. Electr. Electron. Eng., vol. 4, no. 2, pp. 169–174, Jul. 2022, doi: 10.37905/jjeee.v4i2.14403.
[17] D. P. Sari, R. Risman, F. Maulana, L. Efrizoni, and R. Rahmaddeni, “Model Prediksi Dampak Perubahan Iklim pada Ketahanan Pangan Menggunakan Algoritma Support Vector Machine and K-Nearest Neighbors,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. 3, pp. 851–861, Jun. 2025, doi: 10.57152/malcom.v5i3.1975.
