Korean Journal of Artificial Intelligence (한국인공지능학회지)

Korea Artificial Intelligence Association (한국인공지능학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Performance Improvement of MLP Model for Kodály Hand Sign Scale Recognition

  • Received : 2024.04.14
  • Accepted : 2024.09.05
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we explore the application of Kodaly hand signs in enhancing children's music education, performances, and auditory assistance technologies. This research focuses on improving the recognition rate of Multilayer Perceptron (MLP) models in identifying Kodaly hand sign scales through the integration of Artificial Neural Networks (ANN). We developed an enhanced MLP model by augmenting it with additional parameters and optimizing the number of hidden layers, aiming to substantially increase the model's accuracy and efficiency. The augmented model demonstrated a significant improvement in recognizing complex hand sign sequences, achieving a higher accuracy compared to previous methods. These advancements suggest that our approach can greatly benefit music education and the development of auditory assistance technologies by providing more reliable and precise recognition of Kodaly hand signs. This study confirms the potential of parameter augmentation and hidden layers optimization in refining the capabilities of neural network models for practical applications.

Keywords

References

  1. Bae, Seong-jun and Kim, Hyung-seok. (2018). A Study on the Improvement of Gesture Recognition Rate in IMU Sensor Systems Using Deep Learning. Proceedings of the Korean Institute of Communications and Information Sciences Conference, 304-305.18). Proceedings of the Korean Institute of Communications and Information Sciences Conference, 304-305.
  2. Ha Shim-hyeong, Lim Syeong-bin, Choi Woo-kyung, Seo Jae-yong, Jeon Hong-tae. (2006). Development of a Motion Pattern Classification System Using Neural Networks. Proceedings of the Korean Institute of Electrical Engineers Conference, 897-898.
  3. Jang, Min-seon, Choi, Hyun-ho, Kim, Ji-hwan, Lee, Sung-il. (2012). Development of a Hand Gesture Recognition System Using Neural Networks. Proceedings of the Korea HCI Conference, 676-681.
  4. Kim Gwang - jin, Lee Chil-woo (2022). Time Series Prediction for Music Generation Using a Bi-LSTM Model. Smart Media Journal, 11(10), 65-75.
  5. Kim Jung-kyun, Lee Kang-bok, Hong, Sang-ki. (2016). Action Recognition Using Deep Neural Networks Based on IMU Sensors. Proceedings of the Korean Institute of Information Scientists and Engineers, 532-534.
  6. Kwon Yong-sung. (2023). Study on CRNN Structure for Dynamic Hand Gesture Recognition. Master's Thesis, Kumoh National Institute of Technology, Graduate School. 49.
  7. Lee Hyung-kyu. (2022). Hand Gesture Recognition Technology Based on Lightweight Artificial Neural Networks Using Wearable Sensors. Journal of the Korean Society of Embedded Systems, 17(4), 229-237, DOI: 10.14372/IEMEK.2022.17.4.229
  8. Lee Soo-jin and Kang Ji-heon. (2023). Lightweight Deep Learning Model for Hand Gesture Recognition Based on mmWave Radar Point Cloud. Journal of the Institute of Control, Robotics and Systems, 29(9), 711-716, DOI: 10.5302/J.ICROS.2023.23.0096.
  9. T.Pedro & L.Jorge. (2011). Distributed Accelerometers for Gesture Recognition and Visualization. Advanced in information and Communication Technology, Vol. 349/2011, 215-223.
  10. Yun,Young Bae, Kwon,Young Man, Lim, Myung Jae, Park, Jeong Jun & Chung, Dong Kun. (2021). Development of Kodaly Hand Sign Educational Tools using Multi-Layer Perceptron. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(13).