Predicting indoor air temperature for IoT sensors of a model pig barn

( Elanchezhian Arulmozhi ),( Jayanta Kumar Basak ),( Byeong Eun Moon ),( Thavisack Sihalath ),( Hyeon Tae Kim ) 한국농업기계학회 2020 한국농업기계학회 학술발표논문집 Vol.25 No.2

Intensive swine production requires an environmental control system to guarantee the welfare and profitable. Indoor air temperature (IAT) is a highly influential variable of the indoor microclimate since that has a direct impact on animal growth, feed utilization, and wellbeing. The swine building environment is an uncertain nonlinear system in which classical modeling methods require several input variables to solve it. Therefore, the foremost goal of the current study is to develop a non-complex Machine Learning (ML) model to predict inside AT (IAT) in a naturally ventilated model swine building at Gyeongsang National University, Jinju, South Korea. Six group-housed Yorkshire x Duroc crossbred pigs were utilized for the present trial. A real-time sensor that collects IAT data was assigned as response data sets for the prediction model. A weather station comprising a data logger managed the acquisition of outdoor weather data for every 10 min interval. Three kinds of different input dataset named M1 (all outdoor parameters), M2 (all outdoor parameters including indoor humidity), and M3 (only the selected features) were used for the modeling. The performance of the model was evaluated with the coefficient of determination (R2), the root mean square error (RMSE), and the mean absolute error (MAE). Furthermore, the efficiency of the model was apprised by comparison with a traditional classical model. From the results the ML model along with M3 input performed better (R2 = 0.99; RMSE = 0.76; MAE = 0.61) than the classical model. The performance of the model was validated with a four-fold cross-validation method during the evaluation. The present study developed a simple and powerful ML model to predict the IAT of the swine building, which may integrate into livestock building controller devices through cloud technology in the future.

Impacts of Nipple Drinker Position on Water Intake, Water Wastage and Drinking Duration of Pigs

( Elanchezhian Arulmozhi ),( Jayanta Kumar Basak ),( Fawad Khan ),( Jihoon Park ),( Frank Gyan Okyere ),( Yong Jin Lee ),( Hyeon Tae Kim ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.2

Water determines the life-quality of pigs however, adequate measures need to be taken in order to reduce wastage while the animals are drinking. The current study hypothesized and examined a suitable position at which to fix the nipple drinker to provide sufficient drinking water to pigs while also limiting water wastage. Additionally, this study describes both the drinking pattern and drinking duration of pigs. The height to place the drinker was calculated based on the neck movement of the pigs (neck movement angle, NMA). According to the NMA, three independent treatments were investigated with angles placed at clockwise 30°, 0°, and counter clockwise 30°. These positions will be correspondingly referred to as T1, T2, and T3, respectively. To understand the diurnal drinking pattern and drinking duration, along with each pig’s drinking cycle, the number of visits to the drinker was recorded with a camera. The outcome shows that T3 had less water wastage and a higher average daily gain compared to T1 and T2. Further, the number of visits to the drinker and drinking duration were affected by the treatments. The research affirmed that the nipple drinker with a counter clockwise 30° angle at a proper height is the best at reducing water wastage for finishing pigs. Correspondingly, the T3 treatment might create opportunities to drink more water in group-housed pigs.

The application of Machine learning to estimate microclimate of a model pig barn

( Elanchezhian Arulmozhi ),( Jayanta Kumar Basak ),( Thavisack Sihalath ),( Byeong Eun Moon ),( Hyeon Tae Kim ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.1

Indoor air temperature (IAT) and indoor relative humidity (IRH) are the prominent microclimatic variables; still, potential contributors that influence the homeostasis of livestock animals reared in closed barns. Further, predicting IAT and IRH encourages farmers to think ahead actively and to prepare the optimum solutions. Therefore, the primary objective of the current literature is to build and investigate extensive performance analysis between popular ML models in practice used for IAT and IRH predictions. Meanwhile, multiple linear regression (MLR), multilayered perceptron (MLP), random forest regression (RFR), decision tree regression (DTR), and support vector regression (SVR) models were utilized for the prediction. This study used accessible factors such as external environmental data to simulate the models. In addition, three different input datasets named S1, S2, and S3 were used to assess the models. From the results, RFR models performed better results in both IAT (R2 = 0.9913; RMSE = 0.476; MAE = 0.3535) and IRH (R2 = 0.9594; RMSE = 2.429; MAE = 1.47) prediction among other models particularly with S3 input datasets. In addition, it has been proven that selecting the right features from the given input data builds supportive conditions under which the expected results are available. Overall, the current study demonstrates a better model among other models to predict IAT and IRH of a naturally ventilated swine building containing animals with fewer input attributes.

실험돈사의 실내 공기 온도 예측을 위한 머신러닝 모델

( Elanchezhian Arulmozhi ),( Jayanta Kumar Basak ),( Byeong Eun Moon ),( Thavisack Sihalath ),( Hyeon Tae Kim ) 한국농업기계학회 2020 한국농업기계학회 학술발표논문집 Vol.25 No.1

Intensive swine production requires an environmental control system to guarantee the welfare and profitable. Indoor air temperature (IAT) is a highly influential variable of the indoor microclimate since that has a direct impact on animal growth, feed utilization, and wellbeing. The swine building environment is an uncertain nonlinear system in which classical modeling methods require several input variables to solve it. Therefore, the foremost goal of the current study is to develop a non-complex Machine Learning (ML) model to predict inside AT (IAT) in a naturally ventilated model swine building at Gyeongsang National University, Jinju, South Korea. Six group-housed Yorkshire x Duroc crossbred pigs were utilized for the present trial. A real-time sensor that collects IAT data was assigned as response data sets for the prediction model. A weather station comprising a data logger managed the acquisition of outdoor weather data for every 10 min interval. Three kinds of different input dataset named M1 (all outdoor parameters), M2 (all outdoor parameters including indoor humidity), and M3 (only the selected features) were used for the modeling. The performance of the model was evaluated with the coefficient of determination (R2), the root mean square error (RMSE), and the mean absolute error(MAE). Furthermore, the efficiency of the model was apprised by comparison with a traditional classical model. From the results the ML model along with M3 input performed better (R2 = 0.99; RMSE = 0.76; MAE = 0.61) than the classical model. The performance of the model was validated with a four-fold cross-validation method during the evaluation. The present study developed a simple and powerful ML model to predict the IAT of the swine building, which may integrate into livestock building controller devices through cloud technology in the future.

Mechanical Strength Analysis of Biodegradable Pots While Growing Cherry Tomato Plant in a Controlled Greenhouse

( Elanchezhian Arulmozhi ),( Qasim Waqas ),( Fawad Khan ),( Jayanta Kumar Basak ),( Jihoon Park ),( Frank Gyan Okyere ),( Yong Jin Lee ),( Hyeon Tae Kim ) 한국농업기계학회 2018 한국농업기계학회 학술발표논문집 Vol.23 No.2

In this decades we are using biodegradable pots for growing plants. Sometimes those pots create damaged in plant’s root due to environmental condition. It show unsuitable mechanical performances in the process of transplanting. The main objective of this study was to estimate the strength of biodegradable organic pots in the process of growing plants in controlled greenhouse. In this experiment, 100 bio-degradable paper pulp trays were used. Pots filled with commercial compost but 50 has cherry tomato plant seed whereas 50 has no seed. In the greenhouse “20-30” degree C temperature maintained which is the recommended for growing cherry tomato plant plants and water spray were supplied 5 min/day. We did analysis on weekly basis by taking 9 samples from each tray and checked the strength of biodegradable pots after removing the compost and plant. EZ 20 material testing machine was used for tension and compression test of individual pots and also for sides of each pot by cutting (3×2 mm) rectangular shape. The initial average maximum tension load (mean±SD) of pots was 70.06±2.5 N in 3.11 sec and average maximum compression load of pots was 77.4±1.5 N in 13.39 sec. For sides of pots, the initial average maximum tension load was 196.1±2.0 N in 4.47 sec and average maximum compression load was 58.1±1.0 N in 3.6 sec. From these result we can found water content and long roots of cherry tomato plant can have a significant effect on biodegradable pots. By this results we concluded that the water content and roots elongation have a significant effect on biodegradable organic pots so there is need to improve materials of biodegradable pots while using in transplanting machine.

Effects of Compost Amendment in Sandy Loam Soil Properties and Plant Moisture Level

( Elanchezhian Arulmozhi ),( Jayanta Kumar Basak ),( Ji-hoon Park ),( Fawad Khan ),( Frank Gyan Okyere ),( Yong-jin Lee ),( Jun-hyeon Lee ),( Deog-hyun Lee ),( Hyeon-tae Kim ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.1

Application of compost improves soil physical and chemical properties as well as increases crop yield. Soil moisture is one important characteristic of soil that helps to maintain sustainable plant productivity and it is influenced by the type of soil. Excessive soil moisture promotes root rot whereas insufficient soil moisture results in drought stress in plants particularly on heavy soils. The objective of this study is to analyse soil physical properties related to various compost types and its relationship to the moisture level of plants. The main medium used for this research was poultry manure and sawdust combination mixed with sandy loam soil. The compost was mixed in three proportion (15%, 30%, and 45% of poultry manure compost and sandy loam soil) where sandy loam soil (without compost) was used as the control. The 15%, 30%, and 45% compost and the sandy loam soil growing media were labelled as T1, T2, T3, and T4 respectively. The moisture content of the plant was also measured using the fresh-dry weight method. From the result analysis, T4 had the highest water retention rate (42%) followed by T3 (38%) and T2 (36.2%).T1 recorded the lowest water retention rate. Likewise the moisture level of plants, it was observed that strawberry plants in T4 had the highest water content (87.9%) followed by T3 (86.8%). It can be concluded that compost medium T4 has better soil properties that were suitable for strawberry plant growth and the strawberry plant which grown in T4 has the higher plant moisture level.

Water Drinking System Design in Pig Barns-Pig’s Neck Angle Based Approach

( Elanchezhian Arulmozhi ),( Jayanta Kumar Basak ),( Jihoon Park ),( Fawad Khan ),( Frank Gyan Okyere ),( Yongjin Lee ),( Junhyeon Lee ),( Deoghyun Lee ),( Hyeon Tae Kim ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.1

Drinking water is essential for the steady growth of pigs. Comparatively nipple drinker prompts more water intake while more water wastage as opposed to conventional drinking bowls. By fixing the nipple drinkers in right position can ready to diminish over half of water loss. The objective of this examination is to locate the right spot to fixing the nipple drinkers on the basis of neck movement angle of pigs. Three pig barns with group-housed environment which consists of six finishing pigs in every livestock test bed were used as model pig barns. The height to place the drinker calculated by the angle of pig. As indicated by the angle estimation, three treatments were directed with the name of T1 with 30.27⁰ angle, T2 with 86⁰ angle and T3 with 120.27⁰ angle where the angle created by pig. To understand the diurnal drinking pattern of pigs to provide adequate water in peak time, thus a CMOS camera placed on the top roof of a pig barn to monitor number of visits and duration of drinking, however camera additionally used to affirm each pig’s drinking routinely. All the treatment significantly not influence the water intake of pigs (P>0.60) but it emphatically influence the water wastage (P<0.05). The outcome shows that T3 has low dimension water wastage (32%) with higher average daily gain compared to T1 and T2. Additionally, the number of visits near to the drinker and time taken to drink water is affected by the treatments and there is correlation between the number of visits near to the drinker and water wastage (R²=0.785). T3 has low number of visits near to the drinker, consequently this treatment may create opportunity for all pigs to drink more in group- housed.

Design of a Programmable Greenhouse Environmental Data Collection System Using Raspberry Pi

( Anil Bhujel ),( Elanchezhian Arulmozhi ),( Byeong Eun Moon ),( Hyeon Tae Kim ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.1

Recently, greenhouse farming is gaining popularity because of the controlled environments due to which the quality and quantity production of crops improves significantly. To maintain a suitable environment for the plant, continuous monitoring of greenhouse inside environmental conditions is indispensable. However, manual monitoring of such parameters is impractical. A sensor-based data collection system is inherently implemented in the greenhouse monitoring system. In this experiment, a Raspberry Pi-based programmable data collection system was designed to collect the greenhouse indoor temperature and humidity using two DHT22 sensors. The DHT22 sensors spatially hung on two locations inside a greenhouse were connected to a Raspberry Pi via cables. A Python script is run in the Raspberry Pi to acquire the sensing digital data from the sensors and logged it into the micro SD card. Raspberry Pi is a miniature version of a computer, which offers a high-level language platform. Therefore, a user-interactive program written in Python language was implemented that allows configuring parameters like sensor numbers and sensing intervals in every time while restarting the program. The system was tested by installing it in a greenhouse with a user-defined logging interval. It concludes that a flexible data collection system can be designed by using Raspberry Pi.

Monitoring Predictive and Informative Indicators of Body Surface Temperature of Pig in the Context of Thermal Comfort Zone of Livestock Barn Using Infrared Sensor

( Jayanta Kumar Basak ),( Elanchezhian Arulmozhi ),( Ji-hoon Park ),( Fawad Khan ),( Frank Gyan Okyere ),( Yong-jin Lee ),( Deok-hyeon Lee ),( Hyeon-tae Kim ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.1

Temperature and relative humidity are the most pivotal parameters for life, and governs maximum factors of whole-animal performance and fitness. The aim of this experimental work was to examine and to prove the correlation between body surface temperature of pig and ambient environment in order to determine thermal comfort zone of livestock barn. The study evaluated the performance of four different models, including temperature model (T model), relative humidity model (H model), temperature-humidity model (TH model), and temperature-humidity index model (THI model) for monitoring and predicting body surface temperature. In total, six 10-week-old Hampshire species pigs with an initial body weight of 30.3±0.85 kg were obtained over a period of 92 days during two years (2017-2018) to develop and evaluate the four models. For this experiment, skin surface temperature was measured using infrared sensor (IR) from a fixed distance (20 cm) and position perpendicular to pig’ body at different locations: left side (LS), right side (RS), forehead (FH) and back side (BS). Livestock environment management systems (LEMS) data reception confirmation were installed to collect data of temperature and humidity, carbon dioxide, smoke and wind speed. The mean environmental temperature and humidity in livestock barn during the experimental period 2017 were 23.11±3.4°C and 64.33± 7.2% respectively and 21.95±3.3°C and 64.31±10.24% respectively in 2018. With respect to the regions analyzed by IR sensor, there were no significant difference (p>0.05) of temperatures in different body areas of the pigs. It was found that THI model was selected as the best model to make more accurate prediction in both training (R²=0.72, RMSE=0.80 ,RSE=0.26 and MAPE=2.08) and validation (R²=0.74, RMSE=1.10, RSE=0.40 and MAPE=2.80) stages. The applicability of the suggested equations to other animals, changing management conditions on different environmental condition should be tested.

Assessment of the Influence of Environmental Variables on Body Temperature of Pig Using ANN and MLR Models

( Jayanta Kumar Basak ),( Elanchezhian Arulmozhi ),( Fawad Khan ),( Frank Gyan Okyere ),( Jihoon Park ),( Dougheon Lee ),( Hyeon Tae Kim ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.2

The experiment was conducted to find out the most influential factors affecting pig’s body temperature (PBT). For this purpose, eight environmental parameters and three growth related factors were considered as variables. Two independent experiments were carried out over a period of 92 days in 2017 and 2018. Environmental parameters inside and outside the pig’s barn were recorded using livestock environment management systems (LEMS) and weather sensors, respectively. Infrared sensors were used for measuring PBT. Among these factors, seven environmental parameters, including temperature, CO2, temperature-humidity index inside and outside the pig’s barn and relative humidity inside the barn were taken as input variables for artificial neural networks (ANN) and multiple linear regression (MLR) models due to their good correlation (r≥0.5) with PBT. The performance of the models in predicting pig’s body temperature was determined using statistical quality parameters, including coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE). Result of the study showed that temperature-humidity index is the most and relative humidity inside the room is the least in fluential factors affecting PBT in MLR/ANN models.