한국전자통신학회논문지 (The Journal of the Korea institute of electronic communication sciences)

한국전자통신학회 (Korea Institute of Electronic Communication Science)
권호 표지
DOI QR코드

DOI QR Code

랜덤 포레스트 기계 학습 방법을 이용한 넙치의 복수 증상 분석

Analysis of Ascites Symptoms in Cultured Olive Flounder, Paralichthys Olivaceus, using a Random Forest Machine Learning Method

  • 김경임 (스마트수산양식연구센터) ;
  • 김성현 (수산질병관리진단전문연구소 피쉬케어) ;
  • 정희택 (전남대학교 문화콘텐츠학부) ;
  • 한순희 (전남대학교 문화콘텐츠학부) ;
  • 박정선 (전남대학교 문화콘텐츠학부)
  • 투고 : 2023.08.29
  • 심사 : 2023.12.27
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

복수는 물고기의 복강에 체액이 비정상적으로 축적되는 상태로써 넙치의 건강 상태를 나타내는 중요한 지표이다. 박테리아, 바이러스, 기생충 등의 감염 과정에서 복수가 생길 수 있으며, 이로 인해 복부의 팽만, 부진한 성장 및 체중 감소 등이 나타난다. 본 논문에서는 넙치의 복수 증상에 영향을 미치는 다른 증상 또는 질병과의 연관성을 찾고자 하였다. 실험 데이터로는 복수의 증상을 복수 없음, 복수 투명, 복수 불투명의 3가지 상태로 구분하고 7년 동안 수집한 양식넙치의 질병진단 데이터를 사용하였다. 랜덤 포레스트 기계 학습 방법을 위해 적절한 전처리 과정을 수행한 후 복수 증상과 관련 있는 다른 증상 및 질병 인자들을 추출하였으며, 제안된 모델이 복수 증상 관련 주요 인자들을 제시해 줄 수 있음을 확인하였다.

Ascites is a condition in which body fluids are abnormally accumulated in the fish's abdominal cavity, and is an important indicator of the health of flounder. Ascites can occur in the process of infection with bacteria, viruses, parasites, etc., which causes abdominal distension, sluggish growth, and weight loss. In this paper, we tried to find the correlation with other symptoms or diseases that affect ascites symptoms in flounder. As experimental data, ascites symptoms were divided into three states: no ascites, ascites transparent, and ascites opaque, and disease diagnosis data of cultured flounder collected for 7 years were used. After performing an appropriate preprocessing process for the random forest machine learning method, other symptoms and disease factors related to ascites were extracted, and it was confirmed that the proposed model could present the main factors related to ascites.

키워드

과제정보

본 논문은 2023년 해양수산부 재원으로 해양수산과학기술진흥원의 지원을 받아 수행된 연구임(스마트 수산양식 연구센터).

참고문헌

  1. H. Kim, S. Jung, S. Kim, J. Park, H. Ceong, and S. Han, "Data Mining for Scuticociliatosis Outbreak Patterns in Cultured Olive Flounder Paralichthys olivaceus in Jeju, Korea," Korean J. Fisheries and Aquattic Sciences, vol. 53, no. 5, 2020, pp. 740-751.
  2. K. Kim, S. Han, T. Kim, S. Jung, S. Kim, H. Ceong, and J. Park, "Pattern Analysis of Clinical Signs in Cultured Olive Flounder, Paralichthys Olivaceus, with Edwardsielosis using the Decision Tree Technique," J. of the Korea Institute of Electronic Communication Sciences, vol. 16, no. 4, 2021, pp. 661-674.
  3. A. Cutler, D. Cutler, and J. Stevens, "Random forests," Machine Learning, vol. 45, no. 1, 2011, pp. 157-176. https://doi.org/10.1007/978-1-4419-9326-7_5
  4. S. Zhao, S. Zhang, J. Liu, H. Wang, and R. Zhao, "Application of machine learning in intelligent fish aquaculture: a review," Aquaculture, vol. 540, 2021, pp. 724-736. https://doi.org/10.1016/j.aquaculture.2021.736724
  5. V. Lyubchenko, R. Matarneh, O. Kobylin, and V. Lyashenjo, "Digital image processing techniques for detection and diagnosis of fish diseases," Int. J. of Advanced Research in Computer Science and Software Engineering, vol. 6, no. 7, 2016, pp. 79-83.
  6. S. Malik, T. Kumar, and A. K. Sahoo, "A novel approach to fish disease diagnostic system based on machine learning," Advances in Image and Video Processing, vol. 5, no. 1, 2017, pp. 49-57. https://doi.org/10.14738/aivp.51.2809
  7. M. Ahmed, T. Aurpa, and M. Azad, "Fish disease detection using image based machine learning technique in aquaculture," J. King Saud Univ. Comp. Informat. Sci., vol. 34, 2022, pp. 5170-5182. https://doi.org/10.1016/j.jksuci.2021.05.003
  8. H. Son, H. Lim, and H. Choi, "A Study on Disease Prediction of Paralichthys Olivaceus using Deep Learning Technique," Smart Media J., vol. 11, no. 4, 2022, pp. 62-68. https://doi.org/10.30693/SMJ.2022.11.4.62
  9. J. Li, Z. Lian, Z. Wu, L. Zeng, L. Mu, Y. Yuan, H. Bai, Z. Guo, K. Mai, X. Tu, and J. Ye, "Artificial intelligence-based method for the rapid detection of fish parasites (Ichthyophthirius multifiliis, Gyrodactylus kobayashii, and Argulus japonicus)," Aquaculture, vol. 563, Part 1, 2023, Article ID 738790, pp. 1-9.
  10. M. Khan, A. Qayoom, M. Nizami, M. Siddiqui, S. Wasi, and S. Raazi, "Automated Prediction of Good Dictionary EXamples (GDEX): A Comprehensive Experiment with Distant Supervision, Machine Learning, and Word Embedding-Based Deep Learning Techniques," J. Complexity, vol. 2021, Article ID 2553199, 2021, pp. 1-18.
  11. M. Islam, M. Kashe, and J. Uddin, "Fish survival prediction in an aquatic environment using random forest model," IAES Int. J. of Artificial Intelligence (IJ-AI), nol. 10, no. 3, 2021, pp. 614-622. https://doi.org/10.11591/ijai.v10.i3.pp614-622
  12. J. Luan, C. Zhang, B. Xu, Y. Xue, and Y. Ren, "The predictive performances of random forest models with limited sample size and different species traits," Fisheries Research, vol. 227, Article ID 105534, 2020, pp. 1-10. https://doi.org/10.1016/j.fishres.2020.105534
  13. P. Swetha, A. H. K. P. Rasheed and V. P. Harigovindan, "Random Forest Regression based Water Quality Prediction for Smart Aquaculture," 4th Int. Conf. on Computing and Communication Systems (I3CS), Shillong, India, 2023, pp. 1-5.
  14. J. Kang, J. Park, S. Han, and K. Kim, "Development of Machine Learning based Flood Depth and Location Prediction Model," J. of the Korea Institute of Electronic Communication Sciences, vol. 18, no. 1, 2023, pp. 91-98.
  15. M. Park, H. Yoon, N. Kim, B. Kim, and H. Yoon, "A Comparative Study on Machine Learning Models for Red Tide Detection," J. of the Korea Institute of Electronic Communication Sciences, vol. 16, no. 6, 2021, pp. 1363-1371.