기계학습을 활용한 오리사 바닥재 수분 발생량 분석
Estimation of Duck House Litter Evaporation Rate Using Machine Learning
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Duck industry had a rapid growth in recent years. Nevertheless, researches to improve duck house environment are still not sufficient enough. Moisture generation of duck house litter is an important factor because it may cause severe illness and low productivity. However, the measuring process is difficult because it could be disturbed with animal excrements and other factors. Therefore, it has to be calculated according to the environmental data around the duck house litter. To cut through all these procedures, we built several machine learning regression model forecasting moisture generation of litter by measured environment data (air temperature, relative humidity, wind velocity and water contents). 5 models (Multi Linear Regression, k-Nearest Neighbors, Support Vector Regression, Random Forest and Deep Neural Network). have been selected for regression. By using R-Square, RMSE and MAE as evaluation metrics, the best accurate model was estimated according to the variables for each machine learning model. In addition, to address the small amount of data acquired through lab experiments, bootstrapping method, a technique utilized in statistics, was used. As a result, the most accurate model selected was Random Forest, with parameters of n-estimator 200 by bootstrapping the original data nine times.
Abstract
Duck industry had a rapid growth in recent years. Nevertheless, researches to improve duck house environment are still not sufficient enough. Moisture generation of duck house litter is an important factor because it may cause severe illness and low productivity. However, the measuring process is difficult because it could be disturbed with animal excrements and other factors. Therefore, it has to be calculated according to the environmental data around the duck house litter. To cut through all these procedures, we built several machine learning regression model forecasting moisture generation of litter by measured environment data (air temperature, relative humidity, wind velocity and water contents). 5 models (Multi Linear Regression, k-Nearest Neighbors, Support Vector Regression, Random Forest and Deep Neural Network). have been selected for regression. By using R-Square, RMSE and MAE as evaluation metrics, the best accurate model was estimated according to the variables for each machine learning model. In addition, to address the small amount of data acquired through lab experiments, bootstrapping method, a technique utilized in statistics, was used. As a result, the most accurate model selected was Random Forest, with parameters of n-estimator 200 by bootstrapping the original data nine times.
참고문헌 (40)
- A report of research on the improvement of duck breeding facilities I. Duck Village 195, "Korean Duck Association", 24~35 (2019)
- A report of research on the improvement of duck breeding facilities II. Duck Village 196, "Korean Duck Association", 20~40 (2019)
- A report of research on the improvement of duck breeding facilities III Duck Village 197, "Korean Duck Association", 30~51 (2019)
- Statistics Korea, "Results of the farm and fishery household economy survey in 2020", ~ (2020)
- Statistics Korea, "2020 Livestock production cost survey", ~ (2020)
- Bang, H. T., "A study on the productivity and environmental change according to duck house litter", Korean Society of Poultry Science, 27, pp.132~134 (2010)
- 방한태, "오리사 바닥 형태가 육용오리의 생산성 및 사육환경에 미치는 영향", 한국가금학회지, 40(3), pp.253~262 (2013), 한국가금학회
- 여욱현, "전산유체역학을 이용한 표준 오리사 설계안에 대한 환기효율성 분석", 한국농공학회논문집, 57(5), pp.51~60 (2015), 한국농공학회
- Kim, Y. H., "Analysis of ventilation efficiency of standard duck house using computational fluid dynamics", pp.2017
- 홍의철, "고상식 오리사에서 다양한 사육밀도가 토종 실용오리의 생산성 및 균일도에 미치는 영향", 한국가금학회지, 46(4), pp.215~221 (2019), 한국가금학회[DOI]
- 이상연, "오리사 바닥재의 수분 증발량 평가", 한국농공학회논문집, 61(5), pp.101~108 (2019), 한국농공학회[DOI]
- Sang-Yeon Lee, "Dynamic energy modelling for analysis of the thermal and hygroscopic environment in a mechanically ventilated duck house", Biosystems Engineering, 200, pp.431~449 (2020), Elsevier BV[DOI]
- 권경석, "오리사 바닥 깔짚자동살포장치 개발 및 실증", 한국농공학회논문집, 63(1), pp.37~48 (2021), 한국농공학회[DOI]
- Bernhart, M., "Moisture effect on the storage, handling and flow properties of poultry litter", Waste Management, 29, pp.1392~1398 (2009)[DOI]
- K. R. Brye, "Short-term Effects of Poultry Litter Form and Rate on Soil Bulk Density and Water Content", Communications in Soil Science and Plant Analysis, 35(15-16), pp.2311~2325 (2011), Informa UK Limited[DOI]
- 최인학, "깔짚에 두 가지의 다른 화학제제를 첨가하였을 때 육계의 생산성과 계사내의 이산화탄소 가스 발생에 미치는 영향", 한국가금학회지, 31(3), pp.171~176 (2004), 한국가금학회
- Wadud, S., "Bacterial and fungal community composition over time in chicken litter with high or low moisture content", British Poultry Science, 53(5), pp.561~569 (2012)[DOI]
- Dunlop, M. W., "Water addition, evaporation and water holding capacity of poultry litter", Science of the Total Environment, 538, pp.979~985 (2015)[DOI]
- Dunlop, M. W., "Water activity of poultry litter : relationship to moisture content during a grow-out", Journal of Environmental Management, 172, pp.201~206 (2016)[DOI]
- Kim, S. H., "Effect of feeding lactobacillus reuteri to broiler on growing performance, intestinal microflora and environmental factor", Korean Society of Poultry Science, 30(1), pp.17~28 (2003)
- Miles, D. M., "Litter ammonia generation : moisture content and organic versus inorganic bedding materials", Poultry Science, 90, pp.1162~1169 (2011)[DOI]
- 이웅섭, "기계학습을 이용한 돈사 급수량 예측방안 개발", 한국정보통신학회논문지, 21(8), pp.1560~1566 (2017), 한국정보통신학회[DOI]
- 이웅섭, "목걸이형 센서를 이용한 머신러닝 기반 가축상태 모니터링", 한국정보통신학회논문지, 22(11), pp.1421~1427 (2018), 한국정보통신학회[DOI]
- 이웅섭, "목부착형 센서를 이용한 기계학습 기반 소 심부체온 예측방안", 한국정보통신학회논문지, 22(12), pp.1611~1617 (2018), 한국정보통신학회[DOI]
- 이웅섭, "기계학습기반 양돈생산성 예측방안", 한국정보통신학회논문지, 24(1), pp.130~133 (2020), 한국정보통신학회[DOI]
- Gorczyca, M. T., "Machine learning algorithms to predict core, skin and hair-coat temperatures of piglets", Computers and Electronics in Agriculture, 151, pp.286~294 (2018)[DOI]
- Gorczyca, M. T., "Machine learning applications for monitoring heat stress in livestock", pp.2019
- Wang, Y., "The design of an intelligent livestock production monitoring and management system", 2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS), pp.1~5 (2018)
- ASTM, "Standard test methods for laboratory determination of water (moisture) content of soil and rock by mass (Designation: D2216-10)", ~
- 홍성은, "ConvLSTM을 사용한 토마토 생산량 및 성장량 예측 모델에 관한 연구", 한국정보기술학회논문지, 18(1), pp.1~10 (2020), 한국정보기술학회[DOI]
- Shakoor, M. T, "Agricultural production output prediction using supervised machine learning techniques", 2017 1st International Conference on Next Generation Computing Applications (NextComp), pp.182~187 (2017)
- Alhnaity, B., "Using deep learning to predict plant growth and yield in greenhouse environments", Acta Hortic, 1296, pp.425~432 (2020)[DOI]
- Cho, Y. H., "Study on the activation functions for efficient learning in DNN", The Institute of Electronics and Information Engineers, pp.800~803 (2016)
- 신현엽, "전력 소모 절감을 위한 딥 러닝기반의 지능형 그린 하우스 제어 시스템", 전기전자학회논문지, 22(1), pp.53~60 (2018), 한국전기전자학회[DOI]
- Efron B., "An Introduction to the bootstrap. Monographs on statistics and applied probability 57", pp.1998, Chapman & Hall
- Akinoglu, B. G., "A review of sunshine-based models used to estimate monthly average global solar radiation", Renewable Energy, 1(3), pp.479~497 (1991)
- Bakay, M. S., "Electricity production based forecasting of greenhouse gas emissions in turkey with deep learning, Support Vector Machine and Artificial Neural Network algorithms", Journal of Cleaner Production, 285, pp.1~18 (2021)
- Gouda, S. G., "Model selection for accurate daily global solar radiation prediction in China", Journal of Cleaner Production, 221, pp.132~144 (2019)[DOI]
- Bakirci, K, "Correlations for estimation of daily global solar radiation with hours of bright sunshine in Turkey", Energy, 34, pp.485~501 (2009)[DOI]
- Wang, H. K., "Recurrent Neural Network model for prediction of microclimate in solar greenhouse", IFAC PapersOnLine, 51(17), pp.790~795 (2018)[DOI]