기계학습 모델을 이용한 실험 돈사 내 온도 예측
Prediction of Indoor Temperature in an Experimental Pig Barn by Using Machine Learning Model
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구는 돼지 간 거리(PD), 돈사 내 상대 습도(RRH), 돈사 내 이산화탄소(RCO2) 세 가지 변수를 사용하여, 네 개의 데이터 세트를 구성하고,이를 다중 선형 회귀(MLR), 서포트 벡터 회귀(SVR) 및 랜덤 포레스트 회귀(RFR) 세 가지 모델 기계학습(ML)에 적용하여, 돈사 내 온도(RT)를예측하고자 한다. 2022년 10월 5일부터 11월 19일까지 실험을 진행하였다. Hik-vision 2D카메라를 사용하여, 돈사 내 영상을 기록하였다. 이후ArcMap 프로그램을 사용하여, 돈사 내 영상에서 추출한 이미지 안 돼지의 PD를 계산하였다. 축산환경관리시스템(LEMS) 센서를 사용하여, RT,RRH 및 RCO2를 측정하였다. 연구 결과 각 변수 간 상관분석 시 RT와 PD 간의 강한 양의 상관관계가 나타났다(r > 0.75). 네 가지 데이터세트 중 데이터 세트 3을 사용한 ML 모델이 높은 정확도가 나타났으며, 세 가지 회귀 모델 중에서 RFR 모델이 가장 우수한 성능을 보였다
Abstract
This study aims to predict the room temperature (RT) in pig barn using three machine learning (ML) models: multiple linear regression(MLR), support vector regression (SVR), and random forest regression (RFR) models. These models were applied across four datasets,with the input parameters including the distance between each pig (PD), room relative humidity (RRH), and room carbon dioxide (RCO2)levels in the pig barn. The experiment was conducted from October 5th to November 19th, 2022. A Hik-vision 2D camera was usedto record pig videos, and the ArcMap program was utilized to calculate PD using images extracted from these videos. Moreover, aLivestock Environment Management System (LEMS) sensor was used to measure RT, RRH, and RCO2. The results of the study revealeda strong positive correlation between RT and PD (r > 0.75). Among the four datasets constructed through different input combinations,ML models using dataset 3 observed high accuracy, and among the three regression models, the RFR model exhibited the best performance.
참고문헌 (13)
- Arulmozhi E, "Machine learning-based microclimate model for indoor air temperature and relative humidity prediction in a swine building", Animals, 11, pp.222~ (2021)
- Basak JK, "Artificial neural networks and multiple linear regression as potential methods for modelling body surface temperature of pig", J. of Applied Animal Research, 48(1), pp.207~219 (2020)
- Basak JK, "Prediction of body composition in growing-finishing pigs using ultrasound based back-fat depth approach and machine learning algorithms", Computers and Electronics in Agriculture, 213, pp.108269~ (2023)
- Bhujel A, "Deeplearning-based automatic monitoring of Pigs’ Physicotemporal activities at different greenhouse gas concentrations", Animals, 11, pp.3089~ (2021)
- Huynh TTT, "Thermal behaviour of growing pigs in response to high temperature and humidity", Applied Animal Behaviour Science, 9, pp.1~16 (2004)
- Jung JM, "The development of infrared thermal imaging safety diagnosis system using Pearson’s correlation coefficient", J. of Korean Solar Energy Society, 39(6), pp.55~65 (2019)
- Kim BH, "Effects of ammonia exposure on behavior change of growing-finishing pigs", J. of the Korea Academia-Industrial cooperation Society, 24(9), pp.589~595 (2023)
- Kim HT, "Image processing algorithm for behavior classification of pigs under the different environment conditions", J. of Agriculture &Life Science, 51(3), pp.119~127 (2017)
- Lee HM, "Statics-based tractor fuel consumption prediction machine learning model", J. of Agriculture & Life Science, 57(1), pp.133~142 (2022)
- Lee WS, "Prediction of water usage in pig farm based on machine learning", J. of the Korea Institute of Information and Communication Engineering, 21(8), pp.1560~1566 (2017)
- Moon BE, "A fundamental study for development of unglazed transpired collector control system in windowless pig house", J. of Agriculture & Life Science, 50(2), pp.175~185 (2016)
- "Rural Development Administration in Korea", ~ (2020)
- Sin SH, "Random forest-based training dataset supplementation and prediction of lithium-ion battery capacity", The Transactions of the Korean Institute of Power Electronics, 28(5), pp.353~360 (2023)