Estimasi Gerakan Olahraga Push Up Menggunakan Multilayer Perceptron Classifier dan Mediapipe Pose
DOI:
https://doi.org/10.30872/atasi.v5i2.5102Keywords:
Push Up, Multilayer Perceptron, Mediapipe, Exercise, estimationAbstract
Olahraga push up sangat diminati masyarakat untuk melatih kekuatan otot lengan dan dada. Penelitian ini bertujuan mengembangkan dan mengevaluasi model berbasis Multilayer Perceptron (MLP) dan MediaPipe Pose untuk mengestimasi teknik gerakan push up. Model memanfaatkan keypoints tubuh manusia yang diekstrak dari dataset gambar, yang diklasifikasikan ke dalam tiga kelas: fase ascend, descend, dan non-pushup. Pengujian model menggunakan confusion matrix dan macro average menunjukkan akurasi sebesar 89,8%, serta nilai recall, precision, dan F1-score masing-masing sebesar 88,8%, 89,7%, dan 89,2%. Selain itu, evaluasi kesesuaian gerakan (form) diuji menggunakan video dari tiga sudut pandang berbeda berdasarkan jumlah poin dan average confidence. Hasilnya menunjukkan performa model paling optimal pada sudut pandang samping dan diagonal dibandingkan sudut depan. Penelitian ini berkontribusi dalam menyediakan model berbasis keypoints untuk mendeteksi form push up secara lebih objektif.
References
Arwintoro, M., Sanjaya, A., & Ramadhani, R. (2025, July 10). Deteksi Gerakan Fitness Menggunakan Pose Estimation Dan YOLOv11 . Prosiding SEMNAS INOTEK.
Attar, A., Farida, I., & Swanjaya, D. (2025, July 10). Penerapan Pose Estimation dan LSTM dalam Analisis Gerakan Gym untuk Optimalisasi Teknik Latihan . Prosiding SEMNAS INOTEK.
Barbieri, D., & Zaccagni, L. (2013). Strength Training for Children and Adolescents: Benefits and Risks. In Coll. Antropol (Vol. 37).
Bernardo, J. S., Divinagracia, E. F., & Go, K. K. (2023). Determining Exercise Form Correctness in Real Time using Human Pose Estimation. ACM International Conference Proceeding Series, 83–88. https://doi.org/10.1145/3591156.3591168
Bonilla, D. A., Cardozo, L. A., Vélez-Gutiérrez, J. M., Arévalo-Rodríguez, A., Vargas-Molina, S., Stout, J. R., Kreider, R. B., & Petro, J. L. (2022). Exercise Selection and Common Injuries in Fitness Centers: A Systematic Integrative Review and Practical Recommendations. In International Journal of Environmental Research and Public Health (Vol. 19, Number 19). MDPI. https://doi.org/10.3390/ijerph191912710
Chai, J., Zeng, H., Li, A., & Ngai, E. W. T. (2021). Deep learning in computer vision: A critical review of emerging techniques and application scenarios. Machine Learning with Applications, 6, 100134. https://doi.org/10.1016/j.mlwa.2021.100134
Contreras, B., Schoenfeld, B., Mike, J., Tiryaki-Sonmez, G., Cronin, J., & Vaino, E. (2012). The Biomechanics of the Push-up. Strength & Conditioning Journal, 34(5), 41–46. https://doi.org/10.1519/SSC.0b013e31826d877b
Costa, T., Guerreiro, M., Puchta, E., Tadano, Y. de S., Alves, T., Kaster, M., & Siqueira, H. (2023). Multilayer Perceptron. In L. Minku, G. Cabral, M. Martins, & M. Wagner (Eds.), Introduction to Computational Intelligence (pp. 108–109). IEEE Computational Intelligence Society Open Book.
Farhadpour, S., Warner, T. A., & Maxwell, A. E. (2024). Selecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices. Remote Sensing, 16(3), 533. https://doi.org/10.3390/rs16030533
Indriani, Harris, Moh., & Agoes, A. S. (2021). Applying Hand Gesture Recognition for User Guide Application Using MediaPipe. https://doi.org/10.2991/aer.k.211106.017
Jess Fassnidge. (2025, April 23). Strength Training. Www.Scienceforsport.Com. https://www.scienceforsport.com/strength-training/
Kementrian Pemuda dan Olahraga. (2024). Laporan Indeks Pembangunan Olahraga 2024. 92–92.
Kowalski, K. L., Connelly, D. M., Jakobi, J. M., & Sadi, J. (2022). Shoulder electromyography activity during push-up variations: a scoping review. Shoulder & Elbow, 14(3), 325–339. https://doi.org/10.1177/17585732211019373
Kwon, Y., & Kim, D. (2022). Real-Time Workout Posture Correction using OpenCV and MediaPipe. The Journal of Korean Institute of Information Technology, 20(1), 199–208. https://doi.org/10.14801/jkiit.2022.20.1.199
Markoulidakis, I., Rallis, I., Georgoulas, I., Kopsiaftis, G., Doulamis, A., & Doulamis, N. (2021). Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem. Technologies, 9(4), 81. https://doi.org/10.3390/technologies9040081
Mubayyin, M. T., Anantacia, E. M. A., Salsabila, C., & Hidayattullah, M. F. (2025). Klasifikasi dan deteksi pose pilates menggunakan mediapipe dan random forest classifier. Teknosains: Media Informasi Sains Dan Teknologi, 19(1), 56–63. https://doi.org/10.24252/teknosains.v19i1.53698
Parmar, P., Gharat, A., & Rhodin, H. (2022). Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment.
Rainio, O., Teuho, J., & Klén, R. (2024). Evaluation metrics and statistical tests for machine learning. Scientific Reports, 14(1), 6086. https://doi.org/10.1038/s41598-024-56706-x
Remiro, M. Á., Gil-Martín, M., & San-Segundo, R. (2023). Improving Hand Pose Recognition Using Localization and Zoom Normalizations over MediaPipe Landmarks †. Engineering Proceedings, 58(1). https://doi.org/10.3390/ecsa-10-16215
San Juan, J. G., Suprak, D. N., Roach, S. M., & Lyda, M. (2015). The effects of exercise type and elbow angle on vertical ground reaction force and muscle activity during a push-up plus exercise. BMC Musculoskeletal Disorders, 16(1), 23. https://doi.org/10.1186/s12891-015-0486-5
Suraju, G., Sahertian, J., & Irawan, R. (2025, July 10). Analisis Sistem Deteksi Gerakan Push-up Berbasis Pengolahan Citra untuk Pemantauan Latihan Mandiri . Prosiding SEMNAS INOTEK.
World Health Organization. (2024). Physical activity. https://www.who.int/initiatives/behealthy/physical-activity
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Adopsi Teknologi dan Sistem Informasi (ATASI)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
