A CNN-Based Information System for Balinese Dance Classification with Hyperparameter Optimization

Nengah Widya Utami; Made Adi Paramartha Putra; I Gede Juliana Eka Putra; Gabriel Avelino Sampedro

doi:10.59395/ijadis.v6i2.1402

Authors

Nengah Widya Utami Faculty of Information Technology and Design, Primakara University, Indonesia
Made Adi Paramartha Putra Faculty of Information Technology and Design, Primakara University, Indonesia
I Gede Juliana Eka Putra Faculty of Information Technology and Design, Primakara University, Indonesia
Gabriel Avelino Sampedro Department of Computer Science, University of the Philippines Diliman, Quezon City, Philippines

DOI:

https://doi.org/10.59395/ijadis.v6i2.1402

Keywords:

Convolutional Neural Networks (CNN), Balinese Dance, Hyperparameter Optimization, Information System

Abstract

Balinese dance classification presents challenges due to limited datasets, complex postures, and the lack of real-world implementation. Existing studies often focus on model development while overlooking deployment aspects. This research proposes a lightweight Convolutional Neural Network (CNN) designed for Balinese dance classification and compares it with MobileNetV2, ResNet50, and VGG16 using consistent training settings. Data augmentation was applied to enhance generalization, and training epochs were optimized based on model convergence. The proposed CNN achieved a validation accuracy of 99.00%, with a precision of 92.55%, recall of 89.88%, and F1-score of 91.1%, using only 590 thousand trainable parameters and the fastest inference time of 476 milliseconds. Although others pretrained model, MobileNetV2 slightly outperformed in some metrics, the proposed model offered a better tradeoff between performance and efficiency. The trained model was deployed in a web-based application, demonstrating practical usability. This work supports the preservation of Balinese dance through accessible and efficient AI integration.

1005 696

Downloads

Download data is not yet available.

References

[1] M. W. A. Kesiman, I. M. D. Maysanjaya, I. M. A. Pradnyana, I. M. G. Sunarya, and P. H. Suputra, "Profiling Balinese Dances with Silhouette Sequence Pattern Analysis," in 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM), 2020, pp. 423-428. https://doi.org/10.1109/CENIM51130.2020.9297893 DOI: https://doi.org/10.1109/CENIM51130.2020.9297893

[2] I. P. P. B. Lantara, I. P. D. Payana, G. A. S. Pratama, W. E. A. Munayana, K. S. Nopiani, and I. N. R. Hendrawan, "GETARI: dataset untuk Klasifikasi Gerakan Dasar Tari Bali Perempuan," J. Nas. Pendidik. Tek. Inform. JANAPATI, vol. 11, no. 3, pp. 290-300, 2022. https://doi.org/10.23887/janapati.v11i3.52598 DOI: https://doi.org/10.23887/janapati.v11i3.52598

[3] N. M. R. Maryati, M. W. A. Kesiman, and I. M. G. Sunarya, "Deteksi Persamaan Pola Gerakan pada Koreografi Tari Bali," J. Teknol. Inf. dan Ilmu Komput., vol. 10, no. 5, pp. 1015-1026, 2023. https://doi.org/10.25126/jtiik.20231057012 DOI: https://doi.org/10.25126/jtiik.20231057012

[4] N. M. P. Erawati, "Mengenal Ragam Gerak Dan Jalinan Estetika Tari Bali," Widyadari, vol. 19, no. 2, 2018.

[5] K. I. Parasari, I. K. Sariada, and N. N. M. Suryani, "Edukasi Dasar Tari Bali Perempuan oleh Ni Ketut Arini," J. Igel J. Danc., vol. 3, no. 2, pp. 131-137, 2023.

[6] N. M. D. Widiastuti, "Inovasi aplikasi media pembelajaran tari Bali berbasis android," Mudra J. Seni Budaya, vol. 33, no. 2, pp. 287-295, 2018. https://doi.org/10.31091/mudra.v33i2.336 DOI: https://doi.org/10.31091/mudra.v33i2.336

[7] I. Perbawa, M. Sudarma, and I. M. A. Suyadnya, "Aplikasi Pembelajaran Gerakan Dasar Tarian Bali dengan Simulasi Model 3D Berbasis Android," J. SPEKTRUM, vol. 1, no. 1, pp. 40-45, 2014.

[8] A. A. G. B. Ariana, I. K. A. G. Wiguna, I. P. Y. Indrawan, A. A. Iswara, I. P. H. Permana, and N. L. K. R. I. D., "Balinese Dance Attributes Utilizing Augmented Reality with Marker Based Tracking Method," in 2024 IEEE International Symposium on Consumer Technology (ISCT), 2024, pp. 30-34. https://doi.org/10.1109/ISCT62336.2024.10791199 DOI: https://doi.org/10.1109/ISCT62336.2024.10791199

[9] J. Fesl, J. Jelnek, K. Hornkov, Z. Nevailov, M. Konopa, and M. Feslov, "AI-based System for Cultural Heritage Objects Identification from Real Photos," in 2022 12th International Conference on Advanced Computer Information Technologies (ACIT), 2022, pp. 476-479.

https://doi.org/10.1109/ACIT54803.2022.9912752 DOI: https://doi.org/10.1109/ACIT54803.2022.9912752

[10] J. Mitric, I. Radulovic, T. Popovic, Z. Scekic, and S. Tinaj, "AI and Computer Vision in Cultural Heritage Preservation," in 2024 28th International Conference on Information Technology (IT), 2024, pp. 1-4. https://doi.org/10.1109/IT61232.2024.10475738 DOI: https://doi.org/10.1109/IT61232.2024.10475738

[11] S. Tiribelli, S. Pansoni, E. Frontoni, and B. Giovanola, "Ethics of Artificial Intelligence for Cultural Heritage: Opportunities and Challenges," IEEE Trans. Technol. Soc., vol. 5, no. 3, pp. 293-305, 2024. https://doi.org/10.1109/TTS.2024.3432407 DOI: https://doi.org/10.1109/TTS.2024.3432407

[12] A. K. Sharma and H. Foroosh, "Slim-CNN: A Light-Weight CNN for Face Attribute Prediction," in 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), 2020, pp. 329-335. https://doi.org/10.1109/FG47880.2020.00085 DOI: https://doi.org/10.1109/FG47880.2020.00085

[13] A. Ammar, A. Chebbah, H. B. Fredj, and C. Souani, "Comparative Study of latest CNN based Optical Flow Estimation," in 2022 International Conference on Intelligent Systems and Computer Vision (ISCV), 2022, pp. 1-6. https://doi.org/10.1109/ISCV54655.2022.9806070 DOI: https://doi.org/10.1109/ISCV54655.2022.9806070

[14] I. Jaya, M. W. A. Kesiman, and I. M. G. Sunarya, "Detecting the same pattern in choreography balinese dance using convolutional neural network and analysis suffix tree," J. Ilm. Tek. Elektro Komput. Inform.(JITEKI), vol. 8, no. 3, pp. 410-421, 2022. https://doi.org/10.26555/jiteki.v8i3.24461 DOI: https://doi.org/10.26555/jiteki.v8i3.24461

[15] H. Ramdan, M. A. Soeleman, P. Purwanto, B. Imran, and R. A. Pramunendar, "Semantic segmentation of pendet dance images using multires U-Net architecture," Ilk. J. Ilm., vol. 14, no. 3, pp. 329-338, 2022. https://doi.org/10.33096/ilkom.v14i3.1316.329-338 DOI: https://doi.org/10.33096/ilkom.v14i3.1316.329-338

[16] A. G. Howard et al., "Mobilenets: Efficient convolutional neural networks for mobile vision applications," arXiv Prepr. arXiv1704.04861, 2017.

[17] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778. https://doi.org/10.1109/CVPR.2016.90 DOI: https://doi.org/10.1109/CVPR.2016.90

[18] H. Kim, H. Lee, J.-S. Kim, and S.-H. Ahn, "Image-based failure detection for material extrusion process using a convolutional neural network," Int. J. Adv. Manuf. Technol., vol. 111, no. 5, pp. 1291-1302, 2020. https://doi.org/10.1007/s00170-020-06201-0 DOI: https://doi.org/10.1007/s00170-020-06201-0