• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.672-680
• /
• 2019

This paper proposes "A Smart Farm Environment Optimization and Yield Prediction Platform based on IoT and Deep Learning" which gathers bio-sensor data from farms, diagnoses the diseases of growing crops, and predicts the year's harvest. The platform collects all the information currently available such as weather and soil microbes, optimizes the farm environment so that the crops can grow well, diagnoses the crop's diseases by using the leaves of the crops being grown on the farm, and predicts this year's harvest by using all the information on the farm. The result shows that the average accuracy of the AEOM is about 15% higher than that of the RF and about 8% higher than the GBD. Although data increases, the accuracy is reduced less than that of the RF or GBD. The linear regression shows that the slope of accuracy is -3.641E-4 for the ReLU, -4.0710E-4 for the Sigmoid, and -7.4534E-4 for the step function. Therefore, as the amount of test data increases, the ReLU is more accurate than the other two activation functions. This paper is a platform for managing the entire farm and, if introduced to actual farms, will greatly contribute to the development of smart farms in Korea.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.62 no.2
• /
• pp.149-155
• /
• 2017

To establish cultivation areas for the stable production of yacon, this study investigated the productivity and functional component contents of yacon in eight regions of Korea from 2011 to 2013. The results of principal component analysis using these data were as follows. A survey of 16 agricultural traits and meteorological data in the eight yacon cultivation areas showed that five factors (average temperature, maximum temperature, minimum temperature, frost-free days, and fructooligosaccharide content) were highly significant at the p < 0.001 level. Among the 16 agricultural traits and meteorological data used in the main component analysis of yacon cultivation areas, approximately eight contributed to the first principal component, and approximately four contributed to each of the second and third principal components. In particular, factors related to productivity, fructooligosaccharide content, and temperature change were considered important criteria for the classification of cultivation areas. The cultivation areas were divided into three groups by principal component analysis. In Group I, containing the Jinbu and Bonghwa areas in the mid-highland region at 500-560 m above sea level, the product yield was the highest at 2,622-3,196 kg/10a, the fructooligosaccharide content was also the highest at 9.04-9.62%, and the mean temperature was $17.3-18.5^{\circ}C$. In Group II, the areas Suncheon, Okcheon, Yeoju, and Gangneung, at 20-180 m above sea level, had the lowest yield, relatively lower fructooligosaccharide content, and the highest temperature. The areas in Group III showed values intermediate between those of Group I and Group II. For the different yacon cultivation areas, the product quantity and fructooligosaccharide content differed according to the environmental temperature, and the temperature conditions and number of frost-free days are considered important indicators for cultivation sites. Therefore, in terms of producing yacon with high quality, cultivation at 500-560 m is considered to give a higher yield and functional fructooligosaccharide content.

• Korean Journal of Environmental Biology
• /
• v.34 no.4
• /
• pp.257-263
• /
• 2016

Objective of this study was to evaluate the carbon budget on 40 years old pear orchard at Naju. For carbon budget assessment, we measured the soil respiration, net ecosystem productivity of herbs, pear biomass and net ecosystem exchange. In 2015, pear orchard released about $25.6ton\;CO_2\;ha^{-1}$ by soil respiration. And $27.9ton\;CO_2\;ha^{-1}$ was sequestrated by biomass growth. Also about $12.6ton\;CO_2\;ha^{-1}$ was stored at pruning branches and about $5.2ton\;CO_2\;ha^{-1}$ for photosynthesis of herbs. As a result, 25.6 ton of $CO_2$ per ha is annually released to atmosphere. At the same time about 45.7 ton of $CO_2$ was sequestrated from atmosphere. When it sum up the amount of $CO_2$ release and sequestration, approximately $20.1ton\;CO_2\;ha^{-1}$ was sequestrated by pear orchard in 2015, and it showed no significant differences with net ecosystem exchanges ($17.8ton\;CO_2\;ha^{-1}\;yr^{-1}$) by eddy covariance method with the same period. Continuous research using various techniques will help the understanding of $CO_2$ dynamics in agroecosystem and it can be able to present a new methodology for assessment of carbon budget in woody crop field. Futhermore, it is expected that the this study can be used as the basic data to be recognized as a carbon sink.

• Korean Journal of Remote Sensing
• /
• v.31 no.5
• /
• pp.491-499
• /
• 2015

In developed countries such as USA and Europe, agricultural monitoring system is developed and utilized in various fields in order to predict crop yield, observe weather conditions and anomaly, categorize crop fields, and calculate areas for each crop. These system is Web Map Service(WMS) which utilizes open source and commercial softwares, and various information collected from remote sensing data are provided. This study will utilize tools such as GeoServer, ArcGIS Server, which are widely used to monitor agricultural production, to publish Map Server and Web Application Server. This enables performance test study for future agricultural production monitoring system by making use of response time and data transfer test. When tested in identical condition GeoServer showed a better result in response time and data transfer for performance test.

• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.2933-2940
• /
• 2018

It is known that fruit is more affected by the weather than other crops. Therefore, in order to create high value for farmers, it is necessary to develop a wholesale price model considering the weather. Peaches produced under relatively limited conditions were chosen as subjects of study. The data were collected from 2015 to 2017 provided by okdab 4.0. The meteorological data used for the analysis were generated by weighting the cultivation area and the variables with high correlation among the weather data were selected from the day before to 7 days before. Randomforest, gradient boosting machine, and XGboost were used for the analysis. As a result of analysis, XGboost showed the best performance in the sense of RMSE and correlation, and price prediction was comparatively well predicted, but the accuracy of the trading volume prediction was not so good enough. The top three weather variables affecting to the peach were minimum temperature, average maximum temperature, and precipitation.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.13 no.3
• /
• pp.82-88
• /
• 2005

This study was carried out to investigate on the change of NaCl content during the food waste composting and on the safety of food waste compost(FWC) manufactured by the non-stirrer sealed fermenter. Plant culture test with pepper crop was also performed to see the effect of FWC, which was produced by the G co. ltd., on the growth of peper and migration of NaCl in soil. The culture test was performed at the farmland in Chungnam National University. The results were as follows; the NaCl content was gradually accumulated during food waste composting process, probably through water evaporation. Sodium concentration was, however, remarkably decreased at the final stage due to the desalting effect by water which was concentrated on the ceil of the fermentor. The analysis of chemical properties and humidity parameters on the food waste compost revealed that the product is quite a good qualified one. More than 0.5 tons of FWC application on red pepper cultivation caused diminished effect on the yield and the accumulation of salts on soil.

• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.53-60
• /
• 2018

Smart farm dissemination by continuously developing IoT is one of the best solution for decreasing labor in Korea farming area because of ageing. For this reason, the number of Smart farm in Korea is being increased. The Smart farm can control farming environment such as temperature for human. Specially, The important thing is controlling proper temperature for farming. In order to control the temperature, legacy smart farms are usually using pans or air conditioners which can control the temperature. However, those devices result in increasing production cost because the electric power consumption is high. For this reason, we propose a smart farm which can predict the proper temperature after an hour by using Deep learning to minimize the electric power consumption by controlling window instead of pans or air conditioners. We can see the 83% of electric power saving by means of the proposed smart farm.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.311-311
• /
• 2022

자색옥수수 색소 1호와색소 5호는 강원도농업기술원에서 육성한 옥수수 품종으로 색소 1호는2014년에 품종 등록되었고 색소 5호는 2021 년 품종 출원되었다. 색소 1호와 색소 5호는 알곡은 노란색, 포엽과 속대에 짙은 자색을 띄는 색소 옥수수이며 포엽과 속대에는 안토시아닌이 고함량으로 집적되는 특징이 있다. 색소 1호 및 5호 종실용 옥수수는 포엽과 속대의 안토시아닌 함량이 알곡보다 풍부하고 영양성분이 적어 유효성분을 활용하는데 효과적이며 건강기능성식품 소재로 활용 가능성이 높다. 현재 포엽과 속대 추출물은 식약처의 고시형 식품원료로 등재가 완료되었으며 간 보호 인체적용시험을 진행하고 있다. 추후, 식품원료 및 건강기능식품으로의 사용처 확대에 따른 원료의 효율적 인 생산 및 관리를 위하여 농가를 대상으로 시범재배를 수행하고 있다. 본 연구에서는 자색옥수수 추출물의 품질관리를 위하여 원재료인 속대를 대상으로 제웅과 무제웅 재배 시 속대의 안토시아닌 함량을 비교하였다. 제웅한 옥수수의 속대는 알곡이 맺히지 않았으며 수확 후 건조하여 분석 시료로 사용하였다. 반면, 제웅하지 않은 옥수수의 속대는 수확 후 건조하여 알곡을 제거한 후 분석 시료로 사용하였다. 두 형태의 건조 속대의 안토시아닌 함량 비교를 위하여 UV와 HPLC를 사용하여 총안토시아닌 및 지표성분 cyanidin3-o-glucoside(C3G)를 각각 분석하였다. 분석결과, 제웅한 속대의 총안토시아닌 및 C3G의 함량은 각각 2.45, 0.19 g/100g이었고 제웅하지 않은 속대의 함량은 0.87, 0.11 g/100g이었다. 이러한 분석결과는 향후 자색옥수수의 고품질 원료 관리를 위한 기초데이터로 활용할 예정이다.

• Journal of Plant Biotechnology
• /
• v.39 no.3
• /
• pp.121-126
• /
• 2012

To determine whether FT-IR spectroscopy combined with multivariate analysis for whole cell extracts can be used to discriminate major leguminous plant at metabolic level, seed extracts of six leguminous plants were subjected to Fourier transform infrared spectroscopy (FT-IR). FT-IR spectral data from seed extracts were analyzed by principal component analysis (PCA), partial least square discriminant analysis (PLS-DA) and hierarchical clustering analysis (HCA). The PCA could not fully discriminate six leguminous plants, however PLS-DA could successfully discriminate six leguminous plants. The hierarchical dendrogram based on PLS-DA separated the six leguminous plants into four branches. The first branch was consisted of all three Vigna species including Vigna radiata var. radiate, Vigna angularis var. angularis and Vigna unguiculata subsp. Unguiculata. Whereas Pisum sativum var. sativum, Glycine max L and Phaseolus vulgaris var. vulgaris were clustered into a separate branch respectively. The overall results showed that metabolic discrimination system were in accordance with known phylogenic taxonomy. Thus we suggested that the hierarchical dendrogram based on PLS-DA of FT-IR spectral data from seed extracts represented the most probable chemotaxonomical relationship between six leguminous plants.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.59 no.1
• /
• pp.89-96
• /
• 2014

We aimed to evaluate the effects of climatic elements on potato yield and create a model with climatic elements for estimating the potato yield, using the results of the regional adjustment tests of potato. We used 86 data of the yield data of a potato variety, Sumi, from 17 regions over 11 years. According to the results, the climatic elements showed significant level of correlation coefficient with marketable yield appeared to be almost every climatic elements except wind velocity, which was daily average air temperature (Tave), daily minimum air temperature (Tmin), daily maximum air temperature(Tmax), daily range of air temperature (Tm-m), precipitation (Prec.), relative humidity (R.H.), sunshine hours (S.H.) and days of rain over 0.1 mm (D.R.) depending on the periods of days after planting or before harvest. The correlations between these climatic elements and marketable yield of potato were stepwised using SAS, statistical program, and we selected a model to predict the yield of marketable potato, which was $y=7.820{\times}Tmax_-1-6.315{\times}Prec_-4+128.214{\times}DR_-8+91.762{\times}DR_-3+643.965$. The correlation coefficient between the yield derived from the model and the real yield of marketable yield was 0.588 (DF 85).