Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Real-time Dog Behavior Analysis and Care System Using Sensor Module and Artificial Neural Network

센서 모듈과 인공신경망을 활용한 실시간 반려견 행동 분석 및 케어 시스템

  • 이희래 (덕성여자대학교 소프트웨어전공) ;
  • 김선경 (덕성여자대학교 소프트웨어전공) ;
  • 이형규 (덕성여자대학교 소프트웨어전공)
  • Received : 2024.07.01
  • Accepted : 2024.08.21
  • Published : 2024.08.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we propose a method for real-time recognition and analysis of dog behavior using a motion sensor and deep learning techonology. The existing home CCTV (Closed-Circuit Television) that recognizes dog behavior has privacy and security issues, so there is a need for new technologies to overcome them. In this paper, we propose a system that can analyze and care for a dog's behavior based on the data measured by the motion sensor. The study compares the MLP (Multi-Layer Perceptron) and CNN (Convolutional Neural Network) models to find the optimal model for dog behavior analysis, and the final model, which has an accuracy of about 82.19%, is selected. The model is lightened to confirm its potential for use in embedded environments.

본 연구에서는 움직임 센서 모듈과 딥러닝을 활용하여 반려견의 행동을 실시간으로 인식하고 분석하는 방법을 제안한다. 일반적으로 반려견의 행동을 파악하는 홈 CCTV(Closed-Circuit Television)는 개인의 사생활 보호 문제와 보안 이슈가 있어 이를 극복하기 위한 새로운 기술의 필요성이 제기되고 있다. 본 논문에서는 움직임 센서에서 측정되는 데이터를 기반으로 반려견의 행동을 분석하고 케어할 수 있는 시스템을 제안한다. 본 연구에서는 MLP(Multi-Layer Perceptron)와 CNN(Convolutional Neural Network) 모델을 비교하여 반려견 행동 분석에 적합한 모델을 선정하고 최적화를 하였으며, 실험 결과, 제안된 MLP 모델은 평균 82.19%의 정확도를 보이는 것을 확인하였으며, 모델 경량화를 통해 임베디드 환경에서 효율적으로 활용될 수 있음을 확인하였다.

Keywords

References

  1. Ha, T. Y. (2020). A Study on the Smart Healthcare through Human Pose Estimation Based on Artificial Intelligence, Dissertation, Graduate School of Hanseong University, Seoul, Korea.
  2. Jung, W. and Lee, H. G. (2020). Design and Performance Analysis of ML Techniques for Finger Motion Recognition, Journal of Korea Society of Industrial Information Systems, 25(2), 129-136.
  3. Jeong, T. M., Choi, W. K., Kim, S. J., Kim, Y. M., Ha, S. H. and Jeon, H. T. (2007). Study for Human Behavior Classification using Soft-Computing Method, Proceedings of the Korean Institute of Intelligent Systems Conference, Apr. 20-21, Mokpo, Korea, pp. 257-260.
  4. Kim, D. Y., Jeon, S. H., Kang, S. Y. and Kim, N. H. (2011). Customized Estimating Algorithm of Physical Activities Energy Expenditure using a Tri-axial Accelerometer, Journal of the Korea Contents Association, 11(12), 103-111.
  5. Kim, H. J. (2018). A Study on Behavior Classification Enhancement of Dogs for Human-Dog Communication, Thesis, Graduate School of Konkuk University, Seoul, Korea.
  6. Kosar, E. and Barshan, B. (2023). A New CNN-LSTM Architecture for Activity Recognition Employing Wearable Motion Sensor Data: Enabling Diverse Feature Extraction, Engineering Applications of Artificial Intelligence, 124, 106259.
  7. Moon, H. W. and Jeong, H. C. (2023). Dog Detection and Behavior Classification Using Deep Learning, The Korea Institute of Communications and Information Sciences, Feb. 8-10, Pyeongchang, Korea. pp. 1041-1042.
  8. Oh, H. W and Kim, W. S. (2022). A Study on the Small Motion Classification Model based on Time Serial Data, Proceedings of the Korea Institute of Communications and Information Sciences Conference, Feb. 9-11, Pyeongchang, Korea, pp. 949-950.
  9. Park, J. S., Ha, G. S. and Kwon, H. D. (2022) Total Care System for Pets with Two-Way Communication, Proceedings of the Korean Society of Manufacturing Technology Engineers, Dec. 11-14, Jeju, Korea, pp. 2.
  10. Park, J. S., Cha, K. and Choi, A. (2023), 3D ResNet-based Children's Behavior Recognition Method Using Video Image Sequence, Journal of Korea Society of Industrial Information Systems, 28(3), 1-10.
  11. Park, M. S. and Kim, J. S. (2017). Research on Testing Methods for Malicious Process Execution Control Products for IoT Devices, Journal of Information Security. 27(6), 29-32.