• 한국산업정보학회논문지
• /
• 제26권1호
• /
• pp.21-29
• /
• 2021

최근 다양한 애플리케이션 도메인을 위한 IoT 솔루션이 개발되고 있으며, 농업분야에서도 IoT 기술을 적용하여 농작물 생산량은 늘리는 반면에 손실은 줄임으로써 농업 생산성을 향상시키기 위한 데이터기반 정밀농업 연구가 진행되고 있다. 이에 본 논문은 미기상 데이터를 수집하여 서리 및 병해충 등 농업예측서비스를 제공하기 위한 스마트팜 플랫폼을 제안하고자 한다. 제안된 플랫폼에서는 실시간으로 수집한 미기상 데이터를 기반으로 서리 및 병해충을 예측하여, 농민들에게 서리 가능성과 병해충 예보 서비스를 제공한다. 실험을 통해 확인한 결과, 미기상기반 예측 플랫폼은 지역기상기반 데이터를 이용한 서리예측보다 더 높은 정밀도(Precision)값을 보임을 알 수 있었다. 정확한 실험을 위하여 시스템 설치 현장에서 실제 관측한 병해충 예찰 데이터를 수집 중에 있다. 본 플랫폼을 활용하여 서리와 병해충 발생 예측정보를 사전에 효과적으로 제공함으로써, 농민들이 작물 피해 및 불필요한 농약 사용을 줄일 수 있도록 하는 정밀농업 서비스를 제공할 수 있을 것으로 기대된다.

• Journal of Animal Science and Technology
• /
• 제63권6호
• /
• pp.1453-1463
• /
• 2021

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.

• Clinical Nutrition Research
• /
• 제12권2호
• /
• pp.138-153
• /
• 2023

The prevalence of metabolic syndrome (MetS) and its cost are increasing due to lifestyle changes and aging. This study aimed to develop a deep neural network model for prediction and classification of MetS according to nutrient intake and other MetS-related factors. This study included 17,848 individuals aged 40-69 years from the Korea National Health and Nutrition Examination Survey (2013-2018). We set MetS (3-5 risk factors present) as the dependent variable and 52 MetS-related factors and nutrient intake variables as independent variables in a regression analysis. The analysis compared and analyzed model accuracy, precision and recall by conventional logistic regression, machine learning-based logistic regression and deep learning. The accuracy of train data was 81.2089, and the accuracy of test data was 81.1485 in a MetS classification and prediction model developed in this study. These accuracies were higher than those obtained by conventional logistic regression or machine learning-based logistic regression. Precision, recall, and F1-score also showed the high accuracy in the deep learning model. Blood alanine aminotransferase (β = 12.2035) level showed the highest regression coefficient followed by blood aspartate aminotransferase (β = 11.771) level, waist circumference (β = 10.8555), body mass index (β = 10.3842), and blood glycated hemoglobin (β = 10.1802) level. Fats (cholesterol [β = -2.0545] and saturated fatty acid [β = -2.0483]) showed high regression coefficients among nutrient intakes. The deep learning model for classification and prediction on MetS showed a higher accuracy than conventional logistic regression or machine learning-based logistic regression.

• 한국버섯학회지
• /
• 제15권4호
• /
• pp.264-268
• /
• 2017

하이테크 산업은 이른바 스마트 농업의 융합에 장벽을 극복하기 위해 농업의 경관을 바꾸고있다. 정밀 농업의 핵심인 온도, 습도, 위치 정보 및 실시간 요약 정보 등의 중요한 ICT제어기술을 적용하여 버섯재배온도, 습도, 조명, 이산화탄소 등의 제어가 가능한 컨테이너형 버섯재배 시스템을 설계제작하였으며, 버섯 재배에 활용가능성을 표고버섯을 대상으로 시험을 수행하였다. 표고버섯의 초발이소요일수는 청색 LED광에서 5~6일, 적색 LED광, 청색-적색-흰색 혼합 LED광, 형광등에서 6~7일로 유사하였고 생체중은 청색 LED광에서 39.82 g으로 타처리구에 비해 우수하였다.

• 한국환경농학회지
• /
• 제35권1호
• /
• pp.6-14
• /
• 2016

BACKGROUND: Residual organochlorine pesticides (OCPs) are chemical substances that persist in the environment, bioaccumulate through the food web, and pose a risk of causing adverse effect to human health and the environment. They were designated as persistent organic pollutants (POPs) by Stockholm Convention. Greenhouse strawberry is economic crop in agriculture, and its cultivation area and yield has been increased. Therefore, we tried to investigate the POPs residue in greenhouse soil and strawberry.METHODS AND RESULTS: Extraction and clean-up method for the quantitative analysis of OCPs was developed and validated by gas chromatography (GC) with electron capture detector (ECD). The clean-up method was established using the modified quick, easy, cheap, effective, rugged, and safe(QuEChERS) method for OCPs in soil and strawberry. Limit of quantitation (LOQ) and recovery rates of OCPs in greenhouse soil and strawberry were 0.9-6.0 and 0.6-0.9 μg/kg, 74.4-115.6 and 75.6-88.4%, respectively. The precision was reliable sincerelative standard deviation (RSD) percentage (0.5-3.7 and 2.9-5.2%) was below 20, which was the normal percent value. The residue of OCPs in greenhouse soil was analyzed by the developed method, and dieldrin, β-endosulfan and endosulfan sulfate were detected at 1.6-23, 2.2-28.4 and 1.8-118.6 μg/kg, respectively. Those in strawberry were not detected in all samples.CONCLUSION: Dieldrin, β-endosulfan and endosulfan sulfate in a part of investigated greenhouse soil were detected. But those were not detected in investigated greenhouse strawberry. These results showed that the residue in greenhouse soil were lower level than bioaccumulation occurring.

• 적정기술학회지
• /
• 제6권2호
• /
• pp.136-145
• /
• 2020

개발도상국에 있어서 농업은 국가 경제의 중추임에도 불구하고, 대부분의 개도국에서는 장비와 지능형 시스템, 데이터 모니터링 등을 이용한 현상에 대한 통합적 판단 없이 인력에 의해 농업을 수행하고 있다. 농업의 중요한 요소인 관개는 작물 생산에 영향을 미치는 핵심적인 과정으로서, 연간 강우량의 변동에 대응하고자 대부분의 농장에서는 관개 시스템을 적용하고 있다. 그러나, 농장 관개 시스템의 모니터링과 제어 등에 대한 기술적 기반이 부족하여 생산성의 증대와 효율적인 농업용수 관리가 어려운 실정이다. 본 논문에서는 탄자니아 농촌 지역 관개 시스템의 스마트화를 위하여 433 MHz 무선 주파수 및 2G 기반 스마트 관개 측정 시스템과 농업용수 선불 시스템을 제안한다. 개발된 스마트 관개 시스템은 기상 데이터와 토양 수분 데이터를 하이브리드로 분석하도록 설계되었는데, 탄자니아 Arusha 지역의 Ngurudoto 마을로의 적용을 목적으로 한다. 제안된 시스템은 기상 측정 컨트롤러, 토양 수분 센서, 수류 센서, 솔레노이드 밸브 및 선불 시스템으로 구성되었는데, 센서를 통해 수집된 데이터는 433 MHz 무선 주파수 및 2G 기반 통신 아키텍처 모듈을 통해 서버로 전송된다. 본 시스템은 인터넷 운용이 제한되는 지역에 적합할 뿐만 아니라, 데이터 기반의 상태 판단과 실시간 예측이 가능하다. 개발된 시스템의 데이터 분석 알고리즘은 동적 회귀 알고리즘과 Naïve Bayes 알고리즘을 적용하여 선형 및 비선형분석 모두에 있어서 높은 정밀도를 보인다. 또한, 농장의 용수공급 시기와 용수의 양, 소요되는 전력에 대한 판단 뿐만 아니라 전체 시스템 하드웨어의 작동 및 오류에 대한 모니터링이 가능하다. 부가하여, 사용자가 농업용수를 공급받기 전에 선금을 지불하는 시스템을 적용하여 관리의 효율성을 도모하였으며, 농업의 전 과정에서 측정된 센서 데이터 및 용수 사용량은 사용자 인터페이스를 통하여 실시간으로 모니터링이 가능하도록 개발되었다. 본 연구를 통하여 개발된 RF(Radio Frequency) 및 2G 기반 스마트 관개 모니터링 시스템은 현장 적용의 편의성과 함께 사용자 중심의 모니터링 시스템을 통해 개발도상국의 경제, 사회 분야에 긍정적인 영향을 미칠 것으로 기대한다.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1251-1251
• /
• 2001

The routine analysis of milk chemical components is of major importance both for the management of animals in dairy farms and for quality control in dairy industries. NIRS technology is an analytical technique which greatly simplifies this routine. One of the most critical aspects in NIRS analysis of milk is sample preparation and analysis modes which should be fast and straightforward. An important difficulty when obtaining NIR spectra of milk is the high water content (80 to 90%) of this product, since water absorbs most of the infrared radiation, and, therefore, limits the accuracy of calibrating for other constituents. To avoid this problem, the DESIR system was set up. Other ways of radiation-sample interaction adapted for liquids or semi-liquids exist, which are practically instantaneous and with limited or null necessity of sample preparation: Transmission and Folded Transmission or Transflectance. The objective of the present work is to compare the precision and accuracy of milk calibration equations in two analysis modes: Reflectance (dry milk) and Folded Transmission (liquid milk). A FOSS-NIR Systems 6500 I spectrophotometer (400-2500 nm) provided with a spinning module was used. Two NIR spectroscopic methods for milk analysis were compared: a) folded transmission: liquid milk samples in a 0.1 pathlength sample cell (ref. IH-0345) and b) reflectance: dried milk samples in glass fibre filters placed in a standard ring cell. A set of 101 milk samples was used to develop the calibration equations, for the two NIR analysis modes, to predict casein, protein, fat and dry matter contents, and 48 milk samples to predict Somatic Cell Count (SCC). The calibrations obtained for protein, fat and dry matter have an excellent quantitative prediction power, since they present $r^2$ values higher than 0.9. The $r^2$ values are slightly lower for casein and SCC (0.88 and 0.89 respectively), but they still are sufficiently high. The accuracy of casein, protein and SCC equations is not affected by the analysis modes, since their ETVC values are very similar in reflectance and folded transmission (0.19% vs 0.21%; 0.16% vs 0.19% and 55.57% vs 53.11% respectively), Lower SECV values were obtained for the prediction of fat and dry matter with the folded transmission equations (0.14% and 0.25% respectively) compared to the results with the reflectance ones (0.43% and 0.34% respectively). In terms of accuracy and speed of analytical response, NIRS analysis of liquid milk is recommended (folded transmission), since the drying procedure takes 24 hours. However, both analysis modes offer satisfactory results.

• 융합정보논문지
• /
• 제7권3호
• /
• pp.27-36
• /
• 2017

최근 군수 산업, 해양수산업, 농업, 공업, 서비스 등의 거의 모든 산업 분야에서는 소형 무인항공기를 사람이 접근하기 힘들거나 CCTV가 설치되지 않은 영역에 대해 공중 촬영이나 근접 비행 등에 활용하고 있다. 또한 소형 무인기 촬영 정보를 토대로 감시나 통제, 또는 관리를 효율적으로 수행하기 위한 응용 연구가 활발하게 이루어지고 있다. 일련의 설정된 작업을 부여하고 자동으로 그 임무를 수행하도록 하는 임무 기반 형태의 작업을 수행하기 위해서는 소형 무인항공기가 안정적으로 비행해야 할 뿐만 아니라 일정시간마다 에너지를 충전할 수 있어야 하며, 또한 무인항공기가 임무 종료 후에는 특정 지점에 자동으로 그리고 정밀하게 착륙해야 할 필요가 있다. 이를 위해서는 소형 무인항공기 자체에서 촬영하는 동영상으로부터 착륙 지점에 설치되어 있는 마커를 탐지하고 인식하는 과정을 통해 착륙을 유도하는 자동 정밀 착륙 방법이 필요하며, 본 논문에서는 저가의 범용 소형 무인비행체를 사용함에 있어서 고 사양을 요구하는 다른 여러 가지 인식 기법들을 사용하지 않고 단순한 탬플릿 매칭 기법을 적용하여서도 정밀하고 안정된 자동 착륙이 가능함을 나타내고, 시뮬레이션과 실제 실험을 통해서 수 센티미터 이내의 오차를 보이는 정밀 착륙이 가능하며, 이는 산업 현장에 유용하게 활용될 수 있음을 보이고자 한다.

• Agricultural and Biosystems Engineering
• /
• 제7권1호
• /
• pp.18-26
• /
• 2006

In-field site-specific nitrogen (N) management increases crop yield, reduces N application to minimize the risk of nitrate contamination of ground water, and thus reduces farming cost. Real-time N sensing and fertilization is required for efficient N management. An 'on-the-go' site-specific N management system was developed and evaluated for the supplemental N application to com (Zea mays L.). This real-time N sensing and fertilization system monitored and assessed N fertilization needs using a vision-based spectral sensor and controlled the appropriate variable N rate according to N deficiency level estimated from spectral signature of crop canopies. Sensor inputs included ambient illumination, camera parameters, and image histogram of three spectral regions (red, green, and near-infrared). The real-time sensor-based supplemental N treatment improved crop N status and increased yield over most plots. The largest yield increase was achieved in plots with low initial N treatment combined with supplemental variable-rate application. Yield data for plots where N was applied the latest in the season resulted in a reduced impact on supplemental N. For plots with no supplemental N application, yield increased gradually with initial N treatment, but any N application more than 101 kg/ha had minimal impact on yield.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권4호
• /
• pp.226-231
• /
• 2020

In order to maximize the production of landscape plants in optimal condition while coexisting with the environment in terms of precision agriculture, quick and accurate information gathering of the internal environmental elements of the growing container is necessary. This may depend on the accuracy of the positioning of numerous sensors connected to landscape plants cultivating system (LPCS) in containers. Thus, this paper presents a method for estimating the location of the sensors related to cultivation environment connected to LPCS by measuring the received signal strength (RSS) or time of arrival TOA received between oneself and adjacent sensors. The Small sensors connected to the LPCS of container are known for their locations, but the remaining locations must be estimated. For this in the paper, Rao-Cramer limits and maximum likelihood estimators are derived from Gaussian models and lognormal models for TOA and RSS measurements, respectively. As a result, this study suggests that both RSS and TOA range measurements can produce estimates of the exact locations of the cultivation environment sensors within the wireless sensor network related to the LPCS.