Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction Service of Wild Animal Intrusions to the Farm Field based on VAR Model

VAR 모델을 이용한 야생 동물의 농장 침입 예측 서비스

  • Kadam, Ashwini L. (Department of Information & Communication Engineering, Changwon National University) ;
  • Hwang, Mintae (Department of Information & Communication Engineering, Changwon National University)
  • Received : 2021.03.18
  • Accepted : 2021.04.18
  • Published : 2021.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper contains the implementation and performance evaluation results of a system that collects environmental data at the time when the wild animal intrusion occurred at farms and then predicts future wild animal intrusions through a machine learning-based Vector Autoregression(VAR) model. To collect the data for intrusion prediction, an IoT-based hardware prototype was developed, which was installed on a small farm located near the school and simulated over a long period to generate intrusion events. The intrusion prediction service based on the implemented VAR model provides the date and time when intrusion is likely to occur over the next 30 days. In addition, the proposed system includes the function of providing real-time notifications to the farmers mobile device when wild animals intrusion occurs in the farm, and performance evaluation was conducted to confirm that the average response time was 7.89 seconds.

본 논문은 야생 동물들이 농장에 침입할 때 마다 당시의 환경 데이터를 수집한 다음 이를 이용한 벡터 자동 회귀(VAR) 모델 기반의 기계 학습을 통해 향후 야생 동물의 침입을 예측하는 서비스의 구현 및 성능 평가 결과를 담고 있다. 침입 예측을 위한 학습 데이터를 수집하기 위해 사물인터넷 기반의 하드웨어 프로토타입을 개발했으며, 이를 학교 인근에 위치한 소규모 농장에 설치하고서 침입 이벤트를 발생시키는 모의 시험을 장기간에 걸쳐 실시하였다. 구현한 벡터 자동 회귀 모델 기반의 침입 예측 서비스는 앞으로 30일간의 침입 발생 가능성이 높은 날짜와 시간을 제공한다. 더불어 제안 서비스는 야생 동물의 농장 침입 시 농장 주인의 모바일 기기에 실시간으로 알림을 제공하는 기능을 포함하며, 이에 대한 성능 평가를 실시하여 평균 7.89초의 응답 시간을 보여줌을 확인하였다.

Keywords

References

  1. S. Radhakrishnan and R. Ramanathan, "A support vector machine with Gabor features for animal intrusion detection in agriculture fields," Procedia computer science, vol. 1, no. 143, pp. 493-501, 2018. https://doi.org/10.1016/j.procs.2018.10.422
  2. W. Xu, T. Jiang, and J. Shi, "Animal intrusion detection based on convolutional neural network," International Symposium on Communications and Information Technologies, Cairns, Australia, pp. 1-5, 2017.
  3. V. Nithin, S. Mishra, P. Devarubiny, and S. Muthulakshmi, "IoT enabled farming assist and security using machine learning," Asian Research Publishing Network Journal of Engineering and Applied Sciences, vol. 14, no. 9, pp. 1809-1819, 2019.
  4. T. Trnovszky, P. Kamencay, R. Orjesek, M. Benco, and P. Sykora, "Animal recognition system based on convolutional neural network," Advances in Electrical and Electronic Engineering, vol. 15, no. 3, pp. 517-525, 2017.
  5. R. Nikhil, B. S. Anisha, and P. R. Kumar, "Real-time monitoring of agricultural land with crop prediction and animal intrusion prevention using internet of things and machine learning at edge," EasyChair, no. 3016, 2020.
  6. R. Varghese and S. Sharma, "Affordable smart farming using IoT and machine learning," Second International Conference on Intelligent Computing and Control Systems, Madurai, India, pp. 645-650, 2018.
  7. A. L. Kadam and M. Hwang, "Field test and pattern analysis of wild animals intrusions to the farm field," in Proceeding of The 13th International Conference on Future Information & Communication Engineering(ICFICE2020), Korea: Changwon, pp. 57-60, 2021.
  8. Vector Autoregression [Internet]. Available: https://en.wikipedia.org/wiki/Vector_autoregression/.