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

  • 제26권3호
  • /
  • Pages.374-380
  • /
  • 2022
  • /
  • 2234-4772(pISSN)
  • /
  • 2288-4165(eISSN)
한국정보통신학회 (The Korea Institute of Information and Commucation Engineering)
권호 표지
DOI QR코드

DOI QR Code

LSTM 알고리즘을 이용한 양식장 해수 상태 변화 예측

Prediction of Sea Water Condition Changes using LSTM Algorithm for the Fish Farm

  • Rijayanti, Rita (Department of Information and Communication Engineering, Changwon National University) ;
  • Hwang, Mintae (Department of Information and Communication Engineering, Changwon National University)
  • 투고 : 2021.12.24
  • 심사 : 2022.02.14
  • 발행 : 2022.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문은 기계학습 기반의 LSTM(Long Short Term Memory) 알고리즘을 이용해 바다 양식장의 해수 상태 변화를 예측하는 연구 결과를 보여주고 있다. 바다 양식장의 해수 상태 정보를 수집하기 위해 용존산소량, 염도, 질소이온 농도 및 수온 측정 센서들을 사용해 하드웨어를 구현했으며, LoRa 통신을 이용해 클라우드 기반의 Firebase 데이터베이스로 전달해 저장하도록 구현하였다. 개발한 하드웨어를 이용해 통영과 거제 지역 양식장들 주변 해수 상태 정보들을 수집하였으며, 이들 실제 데이터셋을 사용한 학습 결과에다 LSTM 알고리즘을 적용하여 87%의 정확도를 보여주는 예측 결과를 얻어낼 수 있었다. 용존산소량을 비롯한 4가지 파라미터별 예측 결과를 사용자에게 제공하기 위해 Flask와 REST API를 사용했으며, 이러한 예측 결과는 어민들에게 바다 양식장의 해수 상태 변화를 미리 제공할 수 있어 어류 집단 폐사로 인한 큰 피해를 줄이는 데 도움이 될 것이라 기대한다.

This paper shows the results of a study that predicts changes in seawater conditions in sea farms using machine learning-based long short term memory (LSTM) algorithms. Hardware was implemented using dissolved oxygen, salinity, nitrogen ion concentration, and water temperature measurement sensors to collect seawater condition information from sea farms, and transferred to a cloud-based Firebase database using LoRa communication. Using the developed hardware, seawater condition information around fish farms in Tongyeong and Geoje was collected, and LSTM algorithms were applied to learning results using these actual datasets to obtain predictive results showing 87% accuracy. Flask and REST APIs were used to provide users with predictive results for each of the four parameters, including dissolved oxygen. These predictive results are expected to help fishermen reduce significant damage caused by fish group death by providing changes in sea conditions in advance.

키워드

과제정보

This work was supported by Gyeongnam SW Convergence Cluster 2.0 under the contract.

참고문헌

  1. A. Doni, C. Murthy and M. Z. Kurian, "Survey on multi sensor based air and water quality monitoring using IoT," Journal of Scientific Research in Science (JSRS), vol. 17, no. 2, pp. 147-153, 2018.
  2. M. Ahmed, M. O. Rahaman, M. Rahman, and M. A. Kashem, "Analyzing the Quality of Water and Predicting the Suitability for Fish Farming based on IoT in the Context of Bangladesh," in Proceeding of International Conference on Sustainable Technologies for Industry 4.0 (STI), Dhaka: Bangladesh, Dec. 2019.
  3. Recurrent Neural Network Tutorial Part1-Introduction to RNNs [Internet]. Available: https://m.blog.naver.com/PostView.naver?isHttpsRedirect=true&blogId=rkdwnsdud555&logNo=221222845536.
  4. S. I. Ranapurwala, J. E. Cavanaugh, T. Young, H. Wu, C. Peek-Asa, and M. R. Ramirez, "Public health application of predictive modeling: an example from farm vehicle crashes," Journal of Injury Epidemiology (Part of Springer Nature), vol. 6, no. 1, pp. 1-11, Jun. 2019.
  5. A. Tamang and S. Shukla, "Water Demand Prediction Using Support Vector Machine Regression," in Proceeding of International Conference on Data Science and Communication (IconDSC), India : Bangalore, pp. 1-5, 2019.
  6. J. Zhang, Z. Zhang, Y. Weng, S. Gosling, H. Yang, C. Yang, W. Le, and Q. Ma, "Using Recurrent Neural Network for Intelligent Prediction of Water Level in Reservoir," in Proceeding IEEE 44th Annual Computer, Software, and Applications Conference (COMPSAC), Spain : Madrid, pp. 1125-1126, 2020.
  7. R. Rijayanti, A. Kadam, A. B. Wahyutama, B. Lee, and M. Hwang, "Design of the Environmental Data Monitoring and Prediction System for the Fish Farms," in Proceeding of KIICE Spring Conference, Korea : Yeosu City, pp. 178-180, 2021.
  8. S.A. Ludwig, "Comparison of Time Series Approaches applied to Greenhouse Gas Analysis: ANFIS, RNN, and LSTM," in Proceeding of IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), USA: New Orleans, pp. 1-6, 2019.