Modeling Bedoyo Majapahit Dance Motion Using HMM Emission Families
DOI:
https://doi.org/10.24036/jtip.v19i1.1070Keywords:
Hidden Markov Model, GMM-HMM, Motion capture, Traditional dance, Computational modelingAbstract
This study investigates three types of emission families in Hidden Markov Models (HMMs) for reconstructing Bedoyo Majapahit dance motion captured using a markerless system. The recorded skeleton data, consisting of 3,341 frames and 33 joints per frame, were normalized and reduced into a 30-dimensional latent space using Principal Component Analysis (PCA). Three emission variants were evaluated: single-Gaussian HMM, Gaussian-mixture HMM (GMM-HMM), and Multinomial HMM. The evaluation employed a tri-metric scheme consisting of Mean Squared Error (MSE), Dynamic Time Warping (DTW), and Fréchet distance to measure reconstruction fidelity. The experimental results showed that GMM-HMM consistently outperformed the other two models, achieving the lowest reconstruction error and the closest alignment to the original temporal and geometric motion profiles. The Gaussian HMM demonstrated moderate performance but tended to underestimate motion amplitude, while the Multinomial HMM produced the weakest results due to the discretization of continuous pose data. These findings indicate that multimodal emission functions provide a more expressive representation for continuous dance motion. The study highlights the suitability of GMM-HMM for traditional dance preservation through computational modeling and contributes to the development of digital motion archiving for cultural heritage.
References
M. R. Reshma, B. Kannan, V. P. Jagathy Raj, and S. Shailesh, “Cultural heritage preservation through dance digitization: A review,” Digit. Appl. Archaeol. Cult. Herit., vol. 28, p. e00257, Mar. 2023, doi: 10.1016/J.DAACH.2023.E00257.
M. Tanaka, H. Saito, and K. Fujimoto, “Evaluation of Traditional Japanese Dance Using 3D Motion Capture and Machine Learning,” Entertain. Comput., vol. 44, p. 100545, 2023.
Y. Zhang and L. Wang, “Hybrid HMM and Neural Models for Human Motion Prediction,” Pattern Recognit. Lett., vol. 169, pp. 15–22, 2023.
Y. Peng, “Research on Dance Teaching Based on Motion Capture System,” Math. Probl. Eng., vol. 2022, no. 1, p. 1455849, Jan. 2022, doi: 10.1155/2022/1455849.
F. Rossi, G. Bianchi, and M. Esposito, “Combining PCA and HMM for Sports Motion Analysis,” Comput. Biol. Med., vol. 158, p. 106856, 2023.
T. Nguyen, H. Pham, and C. Vo, “AI-Based Dance Education Systems Using Motion Capture and HMM,” Educ. Inf. Technol., vol. 29, pp. 11045–11063, 2024.
A. K. Adisusilo, E. Wahyuningtyas, and F. W. Y. Untoro, “Analisis Pergerakan Lengan Tari Bedoyo Majapahit Berbasis Motion Capture,” TEMATIK, vol. 11, no. 2, pp. 172–181, Dec. 2024, doi: 10.38204/TEMATIK.V11I2.2089.
Y. Zeng and S. Zhao, “Application of real-time motion capture technology in street dance movement analysis and optimization,” Appl. Math. Nonlinear Sci., vol. 9, no. 1, 2024, doi: 10.2478/amns-2024-1913.
J. Huang, M. Li, and Q. Chen, “Motion Capture Sensor-Based Pose Estimation for Dance Canonical Movements,” Appl. Math. Nonlinear Sci., vol. 9, no. 1, 2024, doi: 10.2478/amns-2024-1154.
L. Qianwen, “Application of motion capture technology based on wearable and recognition in dance,” Meas. Sensors, vol. 320, p. 1055, 2024, doi: 10.1016/j.measen.2024.1055.
S. Lee, H. Kim, and J. Park, “Markerless Motion Capture Using Deep Learning for Cultural Dance Preservation,” J. Cult. Herit., vol. 64, pp. 112–120, 2023.
R. Zeng, X. Chen, J. Liang, H. Wu, G. Cao, and Y. Guo, “Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions,” Mar. 2024, Accessed: Oct. 24, 2025. [Online]. Available: https://arxiv.org/pdf/2403.20254v1
S. Auer, F. Süß, and S. Dendorfer, “Using markerless motion capture and musculoskeletal models: An evaluation of joint kinematics,” Technol. Health Care, vol. 32, no. 5, pp. 3433–3442, 2024, doi: 10.3233/THC-240202.
L. A. Espitia-Mora, M. A. Vélez-Guerrero, and M. Callejas-Cuervo, “Development of a Low-Cost Markerless Optical Motion Capture System for Gait Analysis and Anthropometric Parameter Quantification,” Sensors 2024, Vol. 24, Page 3371, vol. 24, no. 11, p. 3371, May 2024, doi: 10.3390/S24113371.
K. Sun, “Research on Dance Motion Capture Technology for Visualization Requirements,” Sci. Program., vol. 2022, 2022, doi: 10.1155/2022/2062791.
I. T. Jolliffe, Principal Component Analysis, 2nd ed. Springer, 2002.
Y. Yu, M. Li, L. Liu, Y. Li, and J. Wang, “Clinical big data and deep learning: Applications, challenges, and future outlooks,” Big Data Min. Anal., vol. 2, no. 4, pp. 288–305, 2019, doi: 10.26599/BDMA.2019.9020007.
G. Xia, W. Ye, P. Xue, Y. Sun, and Q. Liu, “Motion Compression Using Structurally Connected Neural Network,” IEEE Trans. Circuits Syst. Video Technol., vol. 34, no. 6, pp. 4299–4310, Jun. 2024, doi: 10.1109/TCSVT.2023.3332911.
N. Zhao, W. Mio, and X. Liu, “A hybrid PCA-LDA model for dimension reduction,” Proc. Int. Jt. Conf. Neural Networks, pp. 2184–2190, 2011, doi: 10.1109/IJCNN.2011.6033499.
N. Manouchehri and N. Bouguila, “Human Activity Recognition with an HMM-Based Generative Model,” Sensors 2023, Vol. 23, Page 1390, vol. 23, no. 3, p. 1390, Jan. 2023, doi: 10.3390/S23031390.
O. Darwin and S. Kiefer, “Equivalence of hidden markov models with continuous observations,” Leibniz Int. Proc. Informatics, LIPIcs, vol. 182, Dec. 2020, doi: 10.4230/LIPIcs.FSTTCS.2020.43.
S. Mildiner Moraga and E. Aarts, “Go Multivariate: Recommendations on Bayesian Multilevel Hidden Markov Models with Categorical Data,” Multivariate Behav. Res., vol. 59, no. 1, pp. 17–45, 2024, doi: 10.1080/00273171.2023.2205392.
D. E. Moreno-Villamarín, A. Hilsmann, and P. Eisert, “Multi-Resolution Generative Modeling of Human Motion from Limited Data,” Proc. - CVMP 2024 21st ACM SIGGRAPH Conf. Vis. Media Prod., vol. 1, Nov. 2024, doi: 10.1145/3697294.3697309.
G. Ng and J. Andrysek, “Hidden Markov model-based similarity measure (HMM-SM) for gait quality assessment of lower-limb prosthetic users using inertial sensor signals,” J. Neuroeng. Rehabil., vol. 22, no. 1, pp. 1–18, Dec. 2025, doi: 10.1186/S12984-025-01638-4/TABLES/6.
M. Shokoohi-Yekta, J. Hu, H. Jin, N. Wang, and E. Keogh, “Generalizing DTW to the Multi-Dimensional Case Requires an Adaptive Approach,” Data Min. Knowl. Discov., vol. 31, pp. 1–31, 2017.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jurnal Teknologi Informasi dan Pendidikan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
.png)
