DOI QR코드

DOI QR Code

Identification of Sweet Pepper Greenhouse by Analysis of Environmental Data in Greenhouse

온실 내 환경데이터 분석을 통한 파프리카 온실의 식별

  • Kim, Na-eun (Department of Bio-Systems Engineering, Graduate School of Gyeonsang National University) ;
  • Lee, Kyoung-geun (Gyeongsangnam-do Agricultural Research & Extension Services) ;
  • Lee, Deog-hyun (Department of Bio-Systems Engineering, Graduate School of Gyeonsang National University) ;
  • Moon, Byeong-eun (Institute of Smart Farm, Gyeongsang National University) ;
  • Park, Jae-sung (Institute of Smart Farm, Gyeongsang National University) ;
  • Kim, Hyeon-tae (Department of Bio-Industrial Machinery Engineering, Gyeongsang National University(Institute of Smart Farm))
  • 김나은 (경상대학교 대학원 바이오시스템공학과) ;
  • 이경근 (경상남도농업기술원) ;
  • 이덕현 (경상대학교 대학원 바이오시스템공학과) ;
  • 문병은 (경상대학교 스마트팜연구소) ;
  • 박재성 (경상대학교 스마트팜연구소) ;
  • 김현태 (경상대학교 생물산업기계공학과(스마트팜연구소))
  • Received : 2020.09.16
  • Accepted : 2020.12.24
  • Published : 2021.01.31

Abstract

In this study, analysis was performed to identify three greenhouses located in the same area using principal component analysis (PCA) and linear discrimination analysis (LDA). The environmental data in the greenhouse were from 3 farms in the same area, and the values collected at 1 hour intervals for a total of 4 weeks from April 1 to April 28 were used. Before analyzing the data, it was pre-processed to normalize the data, and the analysis was performed by dividing it into 80% of the training data and 20% of the test data. As a result of PCA and LDA analysis, it was found that PCA classification accuracy was 57.51% and LDA classification was 67.06%, indicating that it can be classified by greenhouse. Based on the farmhouse data classified in advance, the data of the new environment can be classified into specific groups to determine the tendency of the data. Such data is judged to be a way to increase the utilization of data by facilitating identification.

본 연구에서는 같은 지역에 위치한 온실 3곳의 식별을 위해 통계적인 방법으로 분류를 하고자 주성분 분석(PCA)과 선형 판별 분석(LDA)을 수행하였다. 온실 내의 환경데이터는 같은 지역의 온실 3곳을 대상으로 4월1일부터 4월28일 총4주간 1시간 간격으로 수집된 값을 사용하였다. 데이터를 분석하기 전, 데이터 정규화를 시키는 전처리를 거쳤으며, 전체의 80%인 훈련자료(training data)와 20%인 테스트 자료(test data)로 나누어 분석을 수행하였다. 분석을 수행한 결과, PC1은 57.51%의 설명력으로 PC1 = 0.7118112 × Tem. -0.6830065 × Humi. -0.1637892 × CO2.의 식을 가지며, LD1은 67.06%의 설명력으로 LD1 = 0.8622565 × Tem. -0.1805741 × Humi. + 1.4018140 × CO2. + 0.03040701의 식을 가지는 것으로 나타났다. 이렇게 미리 분류시켜놓은 온실의 데이터를 바탕으로 새로운 환경의 데이터를 입력하였을 때 특정 그룹으로의 분류가 가능함으로써 데이터의 성향을 파악할 수 있다. 이러한 데이터는 식별을 용이하게 함으로써 데이터의 활용도를 높여주는 방법이라고 판단된다.

Keywords

References

  1. Baudat G. and F. Anouar. 2000. Generalized Discriminant Analysis Using a Kernel Approach. Neural Computation 12:2385-2404. https://doi.org/10.1162/08997660030001498
  2. Cho H.J. and C.H. Kang. 2019. A study on the architectural planning of vertical smart farm. J. Korean Archit. Inst. Korea's Acad. Presentation Conference. 39:114-117 (in Korean).
  3. Choi G.H. 2019. A study on Strategies and Relevant Legislation for Responding to Climate Change by Using Core Technologies of the 4th Industrial Revolution - Focusing on Big Data -. Kangwon Law Rev. 58:779-815 (in Korean). https://doi.org/10.18215/kwlr.2019.58..779
  4. Hwang D.H. and G.J. Park. 2020. An Analysis on the Educational Needs for the Smart Farm: Focusing on SMEs in Jeon-nam Area. J. Korea Acad. Coop. Soc. 21:649-655 (in Korean).
  5. Jang I.H., Y.C., Choe, Y. Kwack, C.H. Chun, and T.W. Kim. 2016. Environmental Management Status of Domestic Field Greenhouses Through Analyzing the Aggregated Environmental and Actuator Data from Smartfarm Greenhouses. Hortic. Abstracts. p. 222-223 (in Koean).
  6. Jeong Y.K., J.G. Lee, E.K. Ahn, J.S. Seo, and Y.C. Yoon. 2020. Performance Improvement of a Temperature and Humidity Measuring System for Strawberry Cultivation Greenhouse. Protected Hort. Plant Fac. 29:110-119 (in Korean). https://doi.org/10.12791/KSBEC.2020.29.2.110
  7. Joung K.H., H.J. Jin, J.U. An, H.S. Yoon, S.S. Oh, C.S. Lim, Y.C. Um, H.D. Kim, and S.M. Park. 2018. Analysis of Growth Characteristics and Yield of Paprika Cupra and Fiesta for Yield Prediction. Hortic. Abstracts. p. 216-217 (in Korean).
  8. Kim D.W., T.H. Kim, J.W. Seok, and K.S. Bae. 2018. Sonar Target Classification using Generalized Discriminant Analysis. J. Korea Inst. Information Comm. Eng. 22:125-130 (in Korean). https://doi.org/10.6109/jkiice.2018.22.1.125
  9. Kim H.J., H.K. Noh, and T.H. Kang. 2020. Discriminant analysis to detect fire blight infection on pear trees using RGB imagery obtained by a rotary wing drone. Korean J. Agri. Sci. 47:349-360. https://doi.org/10.7744/ KJOAS.20200025
  10. Kim J.H., E.S. Lee, D.C. Choi, M.S. Kim, S.J. Kim, N.J. Choi, J.H. Choi, and J.D. Lee. 2020. Design and Implementation of Automatic Control Smartfarm Platform using IOT Technology. Proceedings of the Korean Society Computer Information Conference. 28:71-72 (in Korean).
  11. Kim M.H. 2015. Big Data Reality, Big Difference with Expectations. LGERI Report. p. 2-15 (in Korean).
  12. Kim T.S., D.S. Park, and H.J. Kim. 2018. Study of smart farm model using Big Data. Proceedings of Symposium of the Korean Institute of communications and Information Sciences. p. 1408-1409 (in Korean).
  13. Korean Statistical Information Service (KOSIS). 2019. Farm population survey http://kosis.kr/ (in Korean).
  14. Lee J.G., Y.K. Jeong, S.W. Yun, M.K. Choi, H.T. Kim, and Y.C. Yoon. 2018. Field Survey on Smart Greenhouse. Protected Hort. Plant Fac. 27:166-172 (in Korean). https://doi.org/10.12791/KSBEC.2018.27.2.166
  15. Lee K.G. 2020. Growth Interpretation of Paprika for Greenhouse Cultivation by Major Environmental Factors. PhD Dissertation, Gyeongsang National Univ. p. 10-24 (in Korean).
  16. Lee K.J., B.W. Lee, D.H. Choi, T.O. Kim, and D.I. Snin. 2014. A Study on Fault Detection Monitoring and Diagnosis System of CNG Stations based on Principal Component Analysis(PCA). J. Korean Inst. Gas, 18:53-59 (in Korean). https://doi.org/10.7842/kigas.2014.18.3.53
  17. Lee T.G. 2018. Analysis and visualization of basic environmental data using R. Korea. Book Publishing CIR. p. 107-110 (in Korean).
  18. Na J.H. 2017. R Application Multivariate Analysis. JaYooAcademy. Korea. p. 129-138 (in Korean).
  19. Nam D.S., J.W. Lee, T.W. Moon, and J.E. Son. 2017. Transpiration Prediction of Sweet Peppers Hydroponically-grown in Soilless Culture via Artificial Neural Network Using Environmental Factors in Greenhouse. Protected Hort. Plant Fac. 26:411-417 (in Korean). https://doi.org/10.12791/KSBEC.2017.26.4.411
  20. Park S.H., H.R. Lee, S.J. Park, and Y.B. Cho. 2019. Comparative Study on Environment and Growth Management of Strawberry Smart Farm by Greenhouse Type. Hortic. Abstracts. p. 186-186 (in Korean).
  21. Wise B.M. and N.B. Gallagher. 1996. The Process Chemometrics Approach to Process Monitoring and Fault Detection. J. Process Control 6:329-348. https://doi.org/10.1016/0959-1524(96)00009-1
  22. Yang H.C., J.S. Lee, H.D. Lee, and H.S. Kim. 2018. Automatic Detection of Paprika Diseases/Pests Outbroken during the Hydroponic Cultivation in Greenhouse using Artificial Intelligence. J. Inst. Control. Robot. Syst. 24:1020-1024 (in Korean). https://doi.org/10.5302/j.icros.2018.18.0165
  23. Yu Y.J., S.H. Moon, and S.H. Park. 2018. Measurement of the Visibility of the Smoke Images using PCA. J. Korea Inst. Information Comm. Eng. 22:1474-1480 (in Korean). https://doi.org/10.6109/JKIICE.2018.22.11.1474