• Korean Journal of Breeding Science
• /
• v.41 no.2
• /
• pp.177-181
• /
• 2009

'Pyeongwon' is a new japonica rice cultivar which is developed from a cross between Jinbu19 and Samjiyeon4 from North Korea by the rice breeding team of National Institute of Crop Science, RDA. Pyeongwon has about 107 days duration from seeding to heading in mid-northen plain, alpine, north-eastern coastal and southern alpine areas. It has about 67 cm culm length and tolerance to lodging. Pyeongwon has 13 tillers per hill and 82 spikelets per panicle. It showed tolerance to heading delay and spikelet sterility due to cold treatment similar to Odaebyeo. It also showed slow leaf senescence and moderate tolerance to viviparous germination during the ripening stage. Pyeongwon has resistance to blast disease but susceptible to stripe virus and brown planthopper. Milled rice of Pyeongwon has translucent kernels, relatively clear non-glutinous endosperm and medium short grain. It is characterized as a low gelatinization temperature and slightly lower amylose content (17.1%) variety compared to Odaebyeo (19.5%) and has good palatability of cooked rice. The milled rice yield performance of this cultivar was about 5.28 MT/ha by ordinary culture in local adaptability test for three years. This cultivar may be highly adaptable to the mid-northen plain, alpine, north-eastern coastal and southern alpine areas of Korea.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.27 no.2
• /
• pp.19-30
• /
• 2019

Objective of this study was to develop an organic fertilizer utilizing domestic livestock horn meal and to investigate the application effect of rice and eggplant. The possibility of utilization of livestock horn meal as an organic resource to replace imported expeller cake fertilizer was examined. In order to select domestic organic resources with high nitrogen content, 8 kinds of organic matter such as chicken manure, fish meal, soybean meal, sesame meal, perilla meal, blood meal, livestock horn meal, and beer sludge were analyzed and organic resources with high nitrogen content were selected. In addition, the conditions for the production of organic fertilizers that can be used in organic agriculture were established by mixing of the rice husk biochar and the rice bran as the supplements with the raw materials for mixing ratios. The content of total nitrogen (T-N) in the livestock horn meal was 12.0 %, which was the next low in 13.5 % blood meal. The content of total nitrogen was 5.9 ~ 7.9 % in fish meal and oil cakes. Total nitrogen content of non-antibiotic chicken manure for organic farming was 3 % and nitrogen content in beer sludge was 3.5 %. Organic fertilizer was produced by using biochar, rice bran as a main ingredient of non-antibiotic chicken manure, livestock horn meal and beer sludge. Compared to nitrogen content (4.0 to 4.2 %) of imported expeller cake fertilizer (ECF), the nitrogen content of organic fertilizer utilizing domestic livestock horn meal is as high as 7.5 %. The developed organic fertilizer is met as Zn 400 mg/kg, Cu 120 mg/kg the quality of organic agricultural materials such as or less. To investigate the effect of fertilizer application on the crops, prototypes of developed organic fertilizer were used for the experiment under selected conditions. As a result of application the developed organic livestock horn meal fertilizer (LHMF) for cultivation of the rice and eggplant, the application quantity of the developed organic LHMF 100 % was decreased by 40 % compared to that of the mixed expeller cake fertilizer (MECF). The application of LHMF, which refers to the application rate corresponding to the nitrogen fertilization recommended by the soil test, was reduced by 40% compared to the application rate of MECF, but the same results were obtained in crop growth and yield. The selection of a new high concentration nitrogen source utilizing domestic organic resources and the development of organic fertilizer is the starting point of the research for substitution of imported ECF using domestic local resources at the present time that the spread of eco-friendly agriculture is becoming increasingly important. If it is expanded in the future, it is expected to contribute to the stable production of eco-friendly agricultural products.

• Journal of Bio-Environment Control
• /
• v.28 no.2
• /
• pp.95-103
• /
• 2019

Temperature and relative humidity are important factors in crop cultivation and should be properly controlled for improving crop yield and quality. In order to control the environment accurately, we need to predict how the environment will change in the future. The objective of this study was to predict air temperature and relative humidity at a future time by using a multilayer perceptron (MLP). The data required to train MLP was collected every 10 min from Oct. 1, 2016 to Feb. 28, 2018 in an eight-span greenhouse ($1,032m^2$) cultivating mango (Mangifera indica cv. Irwin). The inputs for the MLP were greenhouse inside and outside environment data, and set-up and operating values of environment control devices. By using these data, the MLP was trained to predict the air temperature and relative humidity at a future time of 10 to 120 min. Considering typical four seasons in Korea, three-day data of the each season were compared as test data. The MLP was optimized with four hidden layers and 128 nodes for air temperature ($R^2=0.988$) and with four hidden layers and 64 nodes for relative humidity ($R^2=0.990$). Due to the characteristics of MLP, the accuracy decreased as the prediction time became longer. However, air temperature and relative humidity were properly predicted regardless of the environmental changes varied from season to season. For specific data such as spray irrigation, however, the numbers of trained data were too small, resulting in poor predictive accuracy. In this study, air temperature and relative humidity were appropriately predicted through optimization of MLP, but were limited to the experimental greenhouse. Therefore, it is necessary to collect more data from greenhouses at various places and modify the structure of neural network for generalization.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.41 no.1
• /
• pp.23-28
• /
• 2021

This experiment was conducted to compare the seed productivity of Spring sown Italian ryegrass(Lolium multiflorum Lam.) depending on the seeding rates(20kg/ha, 30kg/ha, 40kg/ha) in Gangwon region. The experiment was a randomized block design with three replications. The test plots were located in alpine areas of about 600 m above sea level in Gangwon province. The tested Italian ryegrass variety was 'Greencall' developed by the National Institute of Animal Science, RDA. Italian Ryegrass was sown on March 26, 2020, and the seed harvesting was on the 60th day(2 July) from heading date. The heading date was May 8 with no difference, There were no significant differences in the agronomic characteristics including plant height. 30kg/ha seed rate was the highest at 146.8 seed/spike and 40kg/ha seed rate was the lowest at 114.7 seed/spike for the number of seeds per spike. The number of spikes per unit area was the highest in 40kg/ha at 886/㎡ and the lowest in 20kg/ha at 750/㎡. The yield of seed and straw was the highest in 40kg/ha at 1,288kg/ha and 2,970kg/ha respectively, but there was no difference. From the above results, the production of Italian ryegrass seeds through spring sowing in the Gangwon region is not much than autumn seeding, requiring the input of various technologies to increase productivity in the future, and it is desirable to determine the production cost through economic analysis was evaluated.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.295-304
• /
• 2022

The purpose of this study is to detect the sorghum panicle using YOLOv5 based on RGB images acquired by a unmanned aerial vehicle (UAV) system. The high-resolution images acquired using the RGB camera mounted in the UAV on September 2, 2022 were split into 512×512 size for YOLOv5 analysis. Sorghum panicles were labeled as bounding boxes in the split image. 2,000images of 512×512 size were divided at a ratio of 6:2:2 and used to train, validate, and test the YOLOv5 model, respectively. When learning with YOLOv5s, which has the fewest parameters among YOLOv5 models, sorghum panicles were detected with mAP@50=0.845. In YOLOv5m with more parameters, sorghum panicles could be detected with mAP@50=0.844. Although the performance of the two models is similar, YOLOv5s ( 4 hours 35 minutes) has a faster training time than YOLOv5m (5 hours 15 minutes). Therefore, in terms of time cost, developing the YOLOv5s model was considered more efficient for detecting sorghum panicles. As an important step in predicting sorghum yield, a technique for detecting sorghum panicles using high-resolution RGB images and the YOLOv5 model was presented.

• Korean Journal of Breeding Science
• /
• v.51 no.3
• /
• pp.190-200
• /
• 2019

It is reported that the absence of lipoxygenase-3 (LOX-3) may contribute to a reduction in stale flavor after the storage of rice. To improve the quality of stored rice of the Korean japonica rice cultivar, we conducted a breeding program to develop near-isogenic rice without LOX-3 in the genetic background of Saenuri, a mega variety of Korea. In the first step of the breeding program, we used a donor parent of LOX-3 null, Daw Dam, and a recurrent japonica parent, Sindongjin, to develop HR27873-AC12 by backcross (BC₁), color test for introgression of lox-3, and anther culture for rapid fixation. In the second step, we used the donor parent, HR27873-AC12, and the recurrent parent, Saenuri, to develop HR28896-31-3-1-1 by backcross (BC₁), marker-assisted selection (MAS) for lox-3, and phenotypic selection (PS) for agronomic traits. Finally, in the third step, we developed HR30960-186-2-1-2-1 (Jeonju624), derived from a cross between Saenuri and HR28896-31-3-1-1, by MAS for lox-3 and PS with high selection pressure for agronomic characteristics. Jeonju624 was confirmed with the introgression of lox-3 by molecular marker. Jeonju624 was a mid-late maturing rice with similar agronomic characteristics to Saenuri, lodging tolerance with short culm, erect plant architecture, and resistance to bacterial blight and rice stripe virus. The yield components of Jeonju624 were mostly similar to Saenuri, except for the 1,000-grain weight of brown rice. The appearance of the grain of Jeonju624 was better than that of Saenuri, and the characteristics of cooked rice were similar to those of Saenuri. In the genetic background analysis using 406 KASP (Kompetitive Allele-Specific PCR) markers, Jeonju624 was confirmed to be the near-isogenic line (NIL) of Saenuri with a 95.8% recovery rate. Jeonju624 is the NIL of Saenuri without LOX-3, and overcomes the linkage drag of Daw Dam with similar agronomic characteristics and genetic background to Saenuri. Jeonju624 can be utilized as a practical cultivar to improve the quality of stored rice, breeding material for the introgression of lox-3, and genetic material to elucidate the effect of introgressed genes.

• Journal of Bio-Environment Control
• /
• v.32 no.4
• /
• pp.366-376
• /
• 2023

This study was conducted to develop a model for predicting the growth of kimchi cabbage using image data and environmental data. Kimchi cabbages of the 'Cheongmyeong Gaual' variety were planted three times on July 11th, July 19th, and July 27th at a test field located at Pyeongchang-gun, Gangwon-do (37°37' N 128°32' E, 510 elevation), and data on growth, images, and environmental conditions were collected until September 12th. To select key factors for the kimchi cabbage growth prediction model, a correlation analysis was conducted using the collected growth data and meteorological data. The correlation coefficient between fresh weight and growth degree days (GDD) and between fresh weight and integrated solar radiation showed a high correlation coefficient of 0.88. Additionally, fresh weight had significant correlations with height and leaf area of kimchi cabbages, with correlation coefficients of 0.78 and 0.79, respectively. Canopy coverage was selected from the image data and GDD was selected from the environmental data based on references from previous researches. A prediction model for kimchi cabbage of biomass, leaf count, and leaf area was developed by combining GDD, canopy coverage and growth data. Single-factor models, including quadratic, sigmoid, and logistic models, were created and the sigmoid prediction model showed the best explanatory power according to the evaluation results. Developing a multi-factor growth prediction model by combining GDD and canopy coverage resulted in improved determination coefficients of 0.9, 0.95, and 0.89 for biomass, leaf count, and leaf area, respectively, compared to single-factor prediction models. To validate the developed model, validation was conducted and the determination coefficient between measured and predicted fresh weight was 0.91, with an RMSE of 134.2 g, indicating high prediction accuracy. In the past, kimchi cabbage growth prediction was often based on meteorological or image data, which resulted in low predictive accuracy due to the inability to reflect on-site conditions or the heading up of kimchi cabbage. Combining these two prediction methods is expected to enhance the accuracy of crop yield predictions by compensating for the weaknesses of each observation method.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.17
• /
• pp.1-44
• /
• 1974

These studies were made at Suwon in 1972 and at Suwon, Iri, and Kwangju in 1973 to investigate grain filling process and variation of grain quality of NB 68513 and Caprock as hard red winter wheat, Suke ＃169 as soft red winter wheat variety and Yungkwang as semi-hard winter variety, grown under-three different fertilizer levels and seeding dates. Other experiments were conducted to find the effects of temperature, humidity and light intensity on the grain filling process and grain quality of Yungkwang and NB 68513 wheat varieties. These, experiments were conducted at Suwon in 1973 and 1974. 1. Grain filling process of wheat cultivars: 1) The frequency distribution of a grain weight shows that wider distribution of grain weight was associated with large grain groups rather than small grain group. In the large grain groups, the frequency was mostly concentrated near mean value, while the frequency was dispersed over the values in the small grain group. 2) The grain weight was more affected by the grain thickness and width than by grain length. 3) The grain weight during the ripening period was rapidly increased from 14 days after flowering to 35 days in Yungkwang and from 14 days after flowering to 28 days in NB 68513. The large grain group, Yungkwang was rather slowly increased and took a longer period in increase of endosperm ratio of grain than the small grain group, NB 68513. 4) In general, the 1, 000 grain weight was reduced under high temperature, low humidity, while it was increased under low temperature and high humidity condition, and under high temperature and humidity condition. The effect of shading on grain weight was greater in high temperature than in low temperature condition and no definite tendency was found in high humidity condition. 5) The effects of temperature, humidity and shading on 1, 000 grain weight were greater in large-grain group, Yungkwang than in small grain group, NB 68513. Highly significant positive correlation was found between 1, 000 grain weight and days to ripening. 6) The 1, 000 grain weight and test weight were increased more or less as the fertilizer levels applied were increased. However, the rate of increasing 1, 000 grain weight was low when fertilizer levels were increased from standard to double. The 1, 000 grain weight was high when planted early. Such tendency was greater in Suwon than in Kwangju or Iri area. 2. Milling quality: 7) The milling rate in a same group of varieties was higher under the condition of low temperature, high humidity and early maturing culture which were responsible for increasing 1, 000 grain weight. No definite relations were found along with locations. 8) In the varieties tested, the higher milling rate was found in large grain variety, Yungkwang, and the lowest milling rate was obtained from Suke ＃ 169, the small grain variety. But the small grained hard wheat variety such as Caprock and NB 68513 showed higher milling rate compared with the soft wheat variety, Suke ＃ 169. 9) There were no great differences of ash content due to location, fertilizer level and seeding date while remarkable differences due to variety were found. The ash content was high in the hard wheat varieties such as NB 68513, Caprock and low in soft wheat varieties such as Yungkwang and Suke ＃ 169. 3. Protein content: 10) The protein content was increased under the condition of high temperature, low humidity and shading, which were responsible for reduction of 1, 000 grain weight. The varietal differences of protein content due to high temperature, low humidity and shading conditions were greater in Yungkwang than in NB 68513. 11) The high content of protein in grain within one to two weeks after flowering might be due to the high ratio of pericarp and embryo to endosperm. As grains ripen, the effects of embryo and pericarp on protein content were decreased, reducing protein content. However, the protein content was getting increased from three or four weeks after flowering, and maximized at seven weeks after flowering. The protein content of grain at three to four weeks after flowering increased as the increase of 1, 000 grain weight. But the protein content of matured grain appeared to be affected by daily temperature on calender rather than by duration of ripening period. 12) Highly significant positive correlation value was found between the grain protein content and flour protein content. 13) The protein content was increased under the high level of fertilizers and late seeding. The local differences of protein content were greater in Suwon than in Kwangju and Iri. 14) Protein content in the varieties tested were high in Yungkwang, NB 68513 and Caprock, and low in Suke ＃ 169. However, variation in protein content due to the cultural methods was low in Suke ＃ 169. 15) Protein yield per unit area was increased in accordance with increase of fertilizer levels and early maturing culture. However, nitrogen fertilizer was utilized rather effectively in early maturing culture and Yungkwang was the highest in protein yield per unit area. 4. Physio-chemical properties of wheat flour: 16) Sedimentation value was higher under the conditions of high temperature, low humidity and high levels of fertilizers than under the conditions of low temperature, high moisture and low levels of fertilizers. Such differences of sedimentation values were more apparent in NB 68513 and Caprock than Yungkwang and Suke ＃ 169. The local difference of sedimentation value was greater in Suwon than in Kwangju and Iri. Even though the sedimentation value was highly correlated with protein content of grain, the high humidity was considered one of the factors affecting sedimentation value. 17) Changes of Pelshenke values due to the differences of cultural practices and locations were generally coincident with sedimentation values. 18) The mixing time required for mixogram was four to six minutes in NB 68513, five to seven minutes in Cap rock. The great variation of mixing time for Yungkwang and Suke ＃ 169 due to location and planting conditions was found. The mixing height and area were high in hard wheat than in soft wheat. Variation of protein content due to cultural methods were inconsistent. However, the pattern of mixogram were very much same regardless the treatments applied. With this regard, it could be concluded that the mixogram is a kind of method expressing the specific character of the variety. 19) Even though the milling property of NB 68513 and Caprock was deteriorated under either high temperature and low humidity of high fertilizer levels and late seeding conditions, baking quality was better due to improved physio-chemical properties of flour. In contrast, early maturing culture deteriorated physio-chemical properties, milling property of grain and grain protein yield per unit area was increased. However, it might be concluded that the hard wheat production of NB 68513 and Caprock for baking purpose could be done better in Suwon than in Iri or Kwangju area. 5. Interrelationships between the physio-chemical characters of wheat flour: 20) Physio-chemical properties of flour didn't have direct relationship with milling rate and ash content. Low grain weight produced high protein content and better physio-chemical flour properties. 21) In hard wheat varieties like NB 68513 and Caprock, protein content was significantly correlated with sedimentation value, Pelshenke value and mixing height. However, gluten strength and baking quality were improved by the increased protein content. In Yungkwang and Suk ＃ 169, protein content was correlated with sedimentation value, but no correlations were found with Pelshenke value and mixing height. Consequently, increase of protein content didn't improve the gluten strength in soft wheat. 22) The highly significant relationships between protein content and gluten strength and sedimentation . value, and between Pelshenke value, mixogram and gluten strength indicated that the determination of mixogram and Pelshenke value are useful for de terming soft and hard type of varieties. Determination of sedimentation value is considered useful method for quality evaluation of wheat grain under different cultural practices.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• Journal of Animal Science and Technology
• /
• v.55 no.5
• /
• pp.451-460
• /
• 2013

The feed value of sesame meal, a main agricultural by-product from the northern area of Gyeongsangbuk-do province, was assessed in Hanwoo steers. A total of twelve Hanwoo steers (average BW = 412.08 kg) were allocated into a Control (fed no sesame meal) or Treatment (fed sesame meal from 14.6 months of age) group, considering BW and ages, and the animals were fed for a total of 480 days. The final BW, total gain and ADG for the Control and Treatment groups were 741.17 kg and 762.67 kg, 331.84 kg and 347.84 kg, and 0.69 kg and 0.72 kg, respectively, showing better performances in sesame meal-fed animals. Feed requirements during the whole experimental period improved by feeding sesame meal (15.31 and 14.87 for Control and Treatment group, respectively). Hanwoo steers fed sesame meal also showed a 22.83 kg heavier cold carcass weight (424.17 kg and 447.00 kg in the Control and Treatment group, respectively), and 2.41% improved dressing percentages (58.60% and 57.22% for the Control and Treatment group, respectively). The area of the M. longissimus dorsi was $91.83cm^2$ and $88.33cm^2$ in the Control and Treatment group, respectively. The final yield of A and B grade meat were 50 : 50% and 33.3 : 66.7% from the Control and Treatment group, respectively. The average marbling score was 4.83 and 5.50, and the numeric values for quality grade was 2.17 and 2.67 for the Control and Treatment group, respectively, showing better beef quality in sesame meal-fed Hanwoo steers. In fact, there were two animals with beef quality $1^{{+}{+}}$ in the sesame meal-fed group. The melting point of lipid extracted from the M. longissimus dorsi of Hanwoo steers was significantly (p<0.05) lower in the Treatment group ($28.28^{\circ}C$) compared to the Control group ($30.65^{\circ}C$). The composition of saturated fatty acids, $C_{14:0}$ (myristic acid) and $C_{16:0}$ (palmitic acid), were significantly lower in sesame meal-fed animals, 4.70% and 2.20% for myristic acid, and 30.55% and 27.12% for palmitic acid, in the Control and Treatment group, respectively. In contrast, there were no significant differences in C18:0 (stearic acid) composition between the groups. The composition of a representative unsaturated fatty acid, $C_{18:1}$ (oleic acid), was significantly higher in Treatment animals (49.89%) than Control animals (44.29%) (p<0.05). The ratio of total monounsaturated fatty acids / saturated fatty acids; M/S) was 1.10 and 1.36 for the Control and Treatment groups, respectively, showing remarkably higher ratios in sesame meal-fed group. The content of glutamic acid, related to beef flavor, was significantly higher in the Treatment group (3.35 mg/100 g) compared to the Control group (1.88 mg/100g) (p<0.05). The tenderness score, evaluated by an eight-point scale in the panel test, and overall palatability (based on juiciness, flavor, oiliness, and umami) were significantly higher in the Treatment group (5.67 and 5.23, respectively) than the Control group (3.83 and 4.60, respectively) (p<0.05). In conclusion, the current results imply that sesame meal could serve as a good supplement for Hanwoo steers for producing high quality beef.