KLASIFIKASI POSTUR DUDUK BERBASIS CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK EVALUASI RESIKO ERGONOMI
Abstract
Improper sitting posture is one of the leading causes of musculoskeletal disorders among workers and students. Automatic sitting posture detection using artificial intelligence has the potential to serve as an effective and efficient monitoring solution. This study develops a sitting posture classification system based on deep learning using the MobileNetV2 architecture with a transfer learning approach. The dataset consists of 938 images across three posture classes, namely good_posture, forward_lean, and backward_lean, obtained from the Roboflow Universe platform. Training was conducted in two phases using a progressive fine-tuning strategy with optimization mechanisms including EarlyStopping, ModelCheckpoint, and ReduceLROnPlateau. Experimental results show that the model achieved a best validation accuracy of 97.33% and a test accuracy of 95.74% with a macro F1-score of 0.9565. The resulting model is lightweight and has been converted to TFLite format, making it ready for deployment on mobile devices. This study demonstrates that MobileNetV2-based transfer learning can accurately classify sitting postures even with a limited dataset, and has strong potential for further development as a real-time ergonomic monitoring system.
Downloads
References
S. W. Lerita, C. Roosarjani, and H. Laili, “Korelasi Sikap Duduk dan Durasi Duduk dengan Masalah Muskuloskeletal Pada Mahasiswa TBD Angkatan 7,” vol. 2, no. November 2024, pp. 1–10, 2025.
W. H. Organization, “Musculoskeletal health,” World Health Organization. Accessed: May 01, 2026. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/musculoskeletal-conditions
C. Tahun, D. Arihta, E. E. Sabaruddin, and R. Martya, “Keluhan Musculoskeletal Disorders (MSDs) Dengan Postur Kerja, Indeks Massa Tubuh (IMT) Dan Masa Kerja Pada Pekerja Packing Di Unit Tower PT. Bukaka Teknik Utama Tbk. Cileungsi Tahun 2023.,” vol. 13, no. 1, pp. 79–94, 2024.
A. N. Sudirman, N. U. I. Biahimo, M. Puspita, and S. Kai, “Hubungan Posisi Duduk Ergonomis Dengan Nyeri Punggung Bawah Pada Pengrajin Karawo,” pp. 1–11.
N. S. Nadhifa, D. Syauqy, and E. R. Widasari, “Pengembangan Sistem Wearable untuk Deteksi Postur Duduk Miring Berbasis Data Sensor MPU6050 dan Metode Support Vector Machine,” vol. 9, no. 3, pp. 1–10, 2025.
L. Alfarizy, D. Syauqy, and R. S. Perdana, “Sistem Monitoring Postur Duduk pada Pemain Game Online menggunakan Sensor Load Cell dan Ultrasonik dengan Metode K-Nearest Neighbor ( KNN ) berbasis Arduino,” vol. 7, no. 4, 2023.
A. A. Elngar, M. Arafa, A. Fathy, and B. Moustafa, “Image Classification Based On CNN : A Survey,” vol. 6, no. 1, pp. 18–50, 2021, doi: 10.5281/zenodo.4897990.
M. A. Hossain and M. S. A. Sajib, “Classification of Image using Convolutional Neural Network (CNN),” vol. 19, no. 2, 2019.
A. Taner and B. Öztekin, “Performance Analysis of Deep Learning CNN Models for Variety Classification in Hazelnut,” 2021.
T. R. Nugrahanto, I. Badruddin, and M. D. Amrulloh, “Perbandingan Random Forest , K-Nearest Neighbor , Support Vector Machine , dan Multi-Layer Perceptron untuk Deteksi Postur Duduk Berdasarkan Ekstraksi Pose MediaPipe,” no. November, pp. 26–37, 2025.
G. Vista, Y. Candra, D. P. Pamungkas, and P. Kasih, “Analisis Performa Metode CNN Dan LSTM Untuk Deteksi Gerakan Angkat Beban,” vol. 9, pp. 171–180, 2025.
M. R. Wedatama, L. J. E. Dewi, and N. W. Marti, “Klasifikasi Pose Yoga Surya Namaskar Menggunakan Algoritma Convolutional Neural Network Dengan Arsitektur VGG19,” vol. 14, no. 1, pp. 862–868.
A. Krizhevsky and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” pp. 1–9.
M. Sandler, A. Howard, M. Zhu, and A. Zhmoginov, “MobileNetV2 : Inverted Residuals and Linear Bottlenecks,” pp. 4510–4520.
N. Tajbakhsh et al., “Convolutional Neural Networks for Medical Image Analysis : Full Training or Fine Tuning ?,” vol. 35, no. 5, pp. 1299–1312, 2016.
C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, 2019, doi: 10.1186/s40537-019-0197-0.
D. M. W. Powers, “Evaluation : From Precision , Recall and F-Factor to ROC , Informedness , Markedness & Correlation,” no. December, 2007.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
