DOI QR코드

DOI QR Code

A Study on the Search of Optimal Aquaculture farm condition based on Machine Learning

머신러닝 기반의 최적 양식장 조건 검색에 관한 연구

  • 강민수 (을지대학교 의료IT마케팅학과) ;
  • 정용규 (을지대학교 의료IT마케팅학과) ;
  • 장두환 (영진글로지텍(주))
  • Received : 2017.02.15
  • Accepted : 2017.04.07
  • Published : 2017.04.30

Abstract

The demand for aquatic products in the domestic and overseas is increased, so that the aquaculture industry can achieve high performance by controlling and standardizing the production even with a relatively small amount of resources compared with existing fisheries. However, traditional method has problems of low productivity such as natural disasters and ecosystem pollution, and it is necessary to develop a new culture system that can move to the optimal culture site. In order to find the optimal location, you need to collect and analyze the necessary data such as temperature and DO in real time. Data analysis was performed by using K-means clustering method based on machine learning, so that it was possible to decision when and where to move the farm by repeated unsupervised learning. The proposed research could solve the problems of low productivity such as natural disasters and ecosystem pollution if applied to regressive fish farmers.

세계 수산시장은 초과 수요적 현상으로 이러한 경향은 지속적으로 가속화 될 것으로 전망하고 있다. 수산물 수요가 증가되는 양식업은 어업과 비교해 볼 때 비교적 적은 자원의 투입으로도 생산량의 조절 및 표준화 등이 가능하여 높은 성과를 얻을 수 있는 산업이다. 그러나 전통적인 양식은 자연재해, 생태계 오염 등 저생산성의 문제점을 안고 있어 최적의 양식장소로 이동할 수 있는 새로운 양식시스템의 개발이 필요하다. 최적의 장소를 찾기 위해서는 온도, 산소 용존량 등 필요한 데이터를 실시간으로 수집하고 분석해야 한다. 데이터 분석은 머신러닝 기반의 K-means 클러스터링 기법을 적용하여 반복된 자기학습으로 언제, 어디로 양식장을 이동할지 스스로 판단할 수 있도록 하였다. 제시한 연구결과가 어류 양식업 종사자에게 적용된다면 최적의 양식장소를 스스로 찾아감으로써 자연재해, 생태계 오염 등 저생산성의 문제점을 해결 할 수 있을 것이다.

Keywords

References

  1. Steinhaus, H., "Sur la division des corps materiels en parties". 'Bull. Acad. Polon. Sci.' (French) 4 (12): pp. 801-804. MR 0090073. Zbl 0079.16403.1957
  2. MacQueen, J. B. "Some Methods for classification and Analysis of Multivariate Observations", Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability. University of California Press. pp. 281-297. 1967.
  3. Lloyd, S. P. "Least square quantization in PCM", Bell Telephone Laboratories Pape, Published in journal 1957.
  4. Lloyd., S. P.. "Least squares quantization in PCM"."IEEE Transactions on Information Theory" Vol.28 No.2, pp.129-137. 1982, doi:10.1109/ TIT.1982.1056489.
  5. E.W. Forgy., "Cluster analysis of multivariate data: efficiency versus interpretability of classifications". Biometrics Vol.21, pp. 768-769. 1965.
  6. J.A. Hartigan "Clustering algorithms", John Wiley & Sons, Inc., 1975.
  7. Hartigan, J. A.; Wong, M. A., "Algorithm AS 136: A K-Means Clustering Algorithm", Journal of the Royal Statistical Society, Series C, Vol.28 No.1: pp.100-108.1979
  8. https://en.wikipedia.org/wiki/K-means_clustering
  9. Woosaeng Kim, Sooyoung Kim, "Document Clustering Technique by K-means Algorithm and PCA", pp625-630, JKIICE, Vol.18, No.3, 2014.
  10. https://en.wikipedia.org/wiki/DBSCAN
  11. Gye Sung Lee, In Kook Kim, "A Study on Simplification of Machine Learning Model", The Journal of The Institute of Internet, Broadcasting and Communication (JIIBC), Vol.16, No.4, pp.147-152, 2016. https://doi.org/10.7236/JIIBC.2016.16.4.147
  12. Jae Young Chang, "Automatic Retrieval of SNS Opinion Document Using Machine Learning Technique", The Journal of The Institute of Internet, Broadcasting and Communication (JIIBC), Vol.13, No.5, pp.27-35, 2013. https://doi.org/10.7236/JIIBC.2013.13.5.27
  13. Seongrae Jo, Haengnam Sung, Byung-Hyuk Ahn "A Comparative Study on the Performance of SVM and an Artificial Neural Network in Intrusion Detection", Journal of the Korea Academia-Industrial cooperation Society, Vol.17, No.2, pp703-711, 2016. DOI : http://dx.doi.org/10.5762/KAIS.2016.17.2.703