• 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.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.123-139
• /
• 2019

The Korean NPL market was formed by the government and foreign capital shortly after the 1997 IMF crisis. However, this market is short-lived, as the bad debt has started to increase after the global financial crisis in 2009 due to the real economic recession. NPL has become a major investment in the market in recent years when the domestic capital market's investment capital began to enter the NPL market in earnest. Although the domestic NPL market has received considerable attention due to the overheating of the NPL market in recent years, research on the NPL market has been abrupt since the history of capital market investment in the domestic NPL market is short. In addition, decision-making through more scientific and systematic analysis is required due to the decline in profitability and the price fluctuation due to the fluctuation of the real estate business. In this study, we propose a prediction model that can determine the achievement of the benchmark yield by using the NPL market related data in accordance with the market demand. In order to build the model, we used Korean NPL data from December 2013 to December 2017 for about 4 years. The total number of things data was 2291. As independent variables, only the variables related to the dependent variable were selected for the 11 variables that indicate the characteristics of the real estate. In order to select the variables, one to one t-test and logistic regression stepwise and decision tree were performed. Seven independent variables (purchase year, SPC (Special Purpose Company), municipality, appraisal value, purchase cost, OPB (Outstanding Principle Balance), HP (Holding Period)). The dependent variable is a bivariate variable that indicates whether the benchmark rate is reached. This is because the accuracy of the model predicting the binomial variables is higher than the model predicting the continuous variables, and the accuracy of these models is directly related to the effectiveness of the model. In addition, in the case of a special purpose company, whether or not to purchase the property is the main concern. Therefore, whether or not to achieve a certain level of return is enough to make a decision. For the dependent variable, we constructed and compared the predictive model by calculating the dependent variable by adjusting the numerical value to ascertain whether 12%, which is the standard rate of return used in the industry, is a meaningful reference value. As a result, it was found that the hit ratio average of the predictive model constructed using the dependent variable calculated by the 12% standard rate of return was the best at 64.60%. In order to propose an optimal prediction model based on the determined dependent variables and 7 independent variables, we construct a prediction model by applying the five methodologies of discriminant analysis, logistic regression analysis, decision tree, artificial neural network, and genetic algorithm linear model we tried to compare them. To do this, 10 sets of training data and testing data were extracted using 10 fold validation method. After building the model using this data, the hit ratio of each set was averaged and the performance was compared. As a result, the hit ratio average of prediction models constructed by using discriminant analysis, logistic regression model, decision tree, artificial neural network, and genetic algorithm linear model were 64.40%, 65.12%, 63.54%, 67.40%, and 60.51%, respectively. It was confirmed that the model using the artificial neural network is the best. Through this study, it is proved that it is effective to utilize 7 independent variables and artificial neural network prediction model in the future NPL market. The proposed model predicts that the 12% return of new things will be achieved beforehand, which will help the special purpose companies make investment decisions. Furthermore, we anticipate that the NPL market will be liquidated as the transaction proceeds at an appropriate price.

• Korean Journal of Soil Science and Fertilizer
• /
• v.41 no.6
• /
• pp.393-398
• /
• 2008

Several researchers have proposed models or equations to predict soil $CO_2$ flux from more readily available biotic and abiotic measurement. Tree commonly used abiotic variables were N mineral and soil temperature and soil water content. This study was conducted to determine $CO_2$ emission to mineral N, soil water content and soil temperature with clay loam and sandy loam in pepper cultivation in 2004~2005. $CO_2$ flux in the upland with different levels of soil water potential was measured at least once in two weeks during the cropping period in the pepper cultivation plots. Soil water potential in the clay loam and sandy loam soils was established at -30kPa and -50kPa by measuring the soil gravimetric water content with two replications. $CO_2$ emission rate from the differently managed plots was highly correlation coefficient to between the mineral N ($R=0.830^{**}$, $0.876^{**}$) and soil temperature ($r^2=0.793^{**}$, $0.804^{**}$) in the clay loam and sandy loam, respectively. However, the relationships between $CO_2$ emission and soil water content were non-significant. $CO_2$ emissions at sandy loam soils was lower to 21~37% than at clay loam soils for both soil water conditions without differences in yield. At difference levels of soil water conditions, $CO_2$ emission at -50kPa decreased to 37.5% in comparison with that at -30kPa. From the path analysis as to contribution factors of GHGs, it appeared that contribution rate was in the order of soil temperature (54.9%), mineral N (32.7%), and soil moisture content (12.4%).

• Korea journal of population studies
• /
• v.9 no.1
• /
• pp.41-53
• /
• 1986

The purpose of this paper is two-fold. One is to investigate the determinants of the demand supply of labor, and another is to project long-term demand and supply of labor. The paper consists of three parts. In the first part, theoretical models and important hypotheses are discussed: for the case of a labor supply model, issues regarding discouraged worker model, permanent wage hypothesis, and relative wage hypothesis are examined and for the case of a demand model, issues regarding estimating an employment demand equation within the framework of an inverted short-run produc- tion function are inspected. Particularly, a theoretical justification for introducing a demographic cohort variable in a labor supply equation is also investigated. In the second part, empirical results of the estimated supply and demand equations are analyzed. Supply equations are specified differently between primary and secondary labor force. That is, for the case of primary labor force groups including males aged 25 and over, attempts are made to explain the variations in participation behavior within the framework of a neo-classical economics oriented permanent wage hypothesis. On the other hand, for the case of females and young male labor force, variations in participation rates are explained in terms of a relative wage hypothesis. In other words, the participation behavior of primary labor force is related to short-rum business fluctuations, while that of secondary labor force is associated with intermediate swings of business cycles and demographic changes in the age structure of population. Some major findings arc summarized as follows. (1) For the case of males aged 14~19 and 2O~24 groups and females aged 14∼19, the effect of schhool enrollment rate is dominant and thus it plays a key role in explaining the recent declining trend of participation rates of these groups. (2) Except for females aged 20∼24, a demographic cohort variable, which captures the impact of changes in the age structure on participation behavior, turns out to show positive and significant coefficients for secondary labor force groups. (3) A cyclical variable produce significant coefficients for prime-age males and females reflecting that as compared to other groups the labor supply behavior of these groups is more closely related to short-run cyclical variations (4) The wage variable, which represents a labor-leisure trade-off turns out to yield significant coefficients only for older age groups (6O and over) for both males and females. This result reveals that unlike the experiences of other higer-income nations, the participation decision of the labor force of our nation is not highly sensitive with respect to wage changes. (5)The estimated result of the employment demand equation displays that given that the level of GNP remains constant the ability of the economy to absord labor force has been declining;that is, the elasticity of GNP with respect to labor absorption decreasre over time. In the third part, the results of long-term projections (for the period of 1986 and 1995) for age-sex specific participation rates are discussed. The participation rate of total males is anticipated to increase slightly, which is contrary to the recent trend of declining participation rates of this group. For the groups aged 25 and below, the participation rates are forecast to decline although the magnitude of decrease is likely to shrink. On the other hand, the participation rate of prime- age males (25 to 59 years old) is predicted to increase slightly during 1985 and 1990. For the case of females, except for 20∼24 and 25∼34 age groups, the participation rates are projected to decrease: the participation rates of 25∼34 age group is likely to remain at its current level, while the participation rate of 20∼24 age group is expected to increase considerably in the future (specifi- cally, from 55% in 1985 to 61% in 1990 and to 69% in 1995). In conclusion, while the number of an excess supply of labor will increase in absolute magnitude, its size as a ratio of total labor force is not likely to increase. However, the age composition of labor force is predicted to change; that is, the proportion of prime-age male and female labor force is projected to increase.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.3 no.2
• /
• pp.1-15
• /
• 1983

This paper has concentrated on estimating the possibility and mathematical analysis for the application of BFB to the treatment of nightsoil with low dilution rate. The experiment for the study of this purpose was conducted by continuous type reactor at $20^{\circ}C$, varying F/M ratio from 0.12 to 0.37 and dilution ratio from 2 to 10, and in it provided matted reticulated polypropylene sheets for the solid supports. The obtained results showed that the application of BFB to the treatment of nightsoil would be more effective than any other biological treatment process. Also, it has observed that the optimum dilution ratio was about 5 times and the optimum HRT was about 17 hours, and then it was estimated that the reactor volume and the quantity of weak water could be reduced to the extent of 70 percent and 80 percent. The experimental results of BFB could be analysed by the mathematical models applied to complete mixing activated sludge process. The substrate removal rates which were obtained by McKinney's($K_m$) and EcKenfelder's($K_e$) equation was 1.784/hr and $2.0{\times}10l/mg{\cdot}day$, and substrate was removed very rapidly compared to those of conventional type biological treatment processes. The biomass yield coefficient($a_5$), the endogeneous respiration rate(b), the synthesis oxygen demand rate($a{_5}^{\prime}$), and the endogeneous respiration oxygen demand rate(b') were 0.349, 0.0237/day, 0.495 and 0.0336, respectively.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• Geophysics and Geophysical Exploration
• /
• v.16 no.1
• /
• pp.18-26
• /
• 2013

Shear-wave velocity ($v_s$) structures beneath two seismic stations, JJU and JJB on the flanks of the volcano Halla on Jeju island, Korea, were estimated by receiver-function inversion and H-${\kappa}$ stacking applied to 150 teleseismic events ($M_W{\geq}5.5$) recorded since 2007. $P_S$ waves converted at the Moho discontinuity does not appear clearly for northwesterly back-azimuths ($207{\sim}409^{\circ}$, average $308^{\circ}$) at station JJU and southeasterly back-azimuths ($119{\sim}207^{\circ}C$, average $163^{\circ}$) at station JJB. This may be due to a gradual velocity increase at Moho or heterogeneity within the crust. The $v_s$ models derived by inversion of receiver functions indicate a distinct low velocity layer ($v_s{\leq}3.5km/s$; LVL) within the crust and a gradual increase in $v_s$ in the depth interval of 30 to 40 km. Within the radius of 18 km beneath station JJB, the LVL occurs at depths of 14 ~ 26 km and the 'Moho' ($v_s{\geq}4.3km/s$) is at 34 km depth. Ten kilometers to the west, within the radius of 16 km beneath station JJU, both the LVL and the Moho are significantly shallower, at depths of 14 to 24 km and 30 km, respectively. H-${\kappa}$ analyses for stations JJU and JJB yield estimated crustal thickness of 29 and 33 km and $v_p/v_s$ ratios of 1.64 and 1.75, respectively. The lesser $v_p/v_s$ ratio was derived for rocks nearest to th peak of the volcano.

• Journal of agriculture & life science
• /
• v.46 no.1
• /
• pp.123-131
• /
• 2012

This study was conducted to estimate correlation structure between Hanwoo steer growth traits - body weights at 6 month, 12 month, 18 month and 24 month of age, average daily gain, carcass traits, body size traits at 18 months of age. Hanwoo progeny test data(body weight, body size traits) collected from 2004 to 2008 on a total of 1,838 steers at Hanwoo Improvement Main Center(NACF) were analyzed. Carcass traits were used to score the 24 months of age and slaughter. Correlation analyses were performed with observed scales of the traits and with residuals considering fixed effects in generalized linear models. The correlated coefficient estimated between live weight at slaughter(24 months of age) and cold carcass weight was high at 0.92. Correlation between beef yield index values and backfat thickness was estimated to be high and negative at -0.92. Hip height and wither height was found to be highly correlated(0.89). Chest width and chest depth also was found to be highly correlated at 0.73. Rump width was highly correlated with chest depth(0.75) and chest width(0.74). Correlation between pelvic width and rump width was estimated to be 0.74. Hipbone width was shown to be highly correlated with chest depth(0.73), chest width(0.70), rump width(0.75), or pelvic width(0.75). Correlation between wither height and carcass weight was 0.48 in observed scale. Chest girth was phenotyically (residual correlation) correlated with carcass weight (0.51), the estimates of which were some higher than than with the other carcass traits. This study will be utilized for Hanwoo Steers genetic evaluation.

• Journal of Life Science
• /
• v.29 no.2
• /
• pp.215-222
• /
• 2019

Muscle dysfunction may arise from skeletal muscle atrophy caused by aging, injury, oxidative stress, and hereditary disease. Powdered heat-killed Enterococcus faecalis (EF-2001) has anti-allergy, anti-inflammatory, and anti-tumor effects. However, its antioxidant and anti-atrophy effects are poorly characterized. In this study, we examined the effects of EF-2001 on muscle atrophy. To determine the protective effect of EF-2001 on oxidative stress, C2C12 myoblasts were treated with $H_2O_2$ to induce oxidative stress. This induced cell damage, which was reduced by treatment with EF-2001. The mechanism of EF-2001's effect was examined in response to oxidative stress. Treatment with EF-2001 reversed the expression of HSP70 and SOD1 proteins. Also, mRNA levels of Atrogin-1/MAFbx and MuRF1 increased under oxidative stress conditions but decreased following EF-2001 treatment. To evaluate muscle volume, two and three dimensional models of the muscles were analyzed using micro-CT. As expected, muscle volume decreased after sciatic denervation and recovered after oral administration of EF-2001. Therefore, EF-2001 is a candidate for the treatment of muscular atrophy, and future discovery of the additional effects of EF-2001 may yield further applications as a functional food with useful activities in various fields.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.1
• /
• pp.17-27
• /
• 2023

Weeds are one of the factors that reduce crop yield through nutrient and photosynthetic competition. Quantification of weed density are an important part of making accurate decisions for precision weeding. In this study, we tried to quantify the density of weeds in images of maize fields taken by unmanned aerial vehicle (UAV). UAV image data collection took place in maize fields from May 17 to June 4, 2021, when maize was in its early growth stage. UAV images were labeled with pixels from maize and those without and the cropped to be used as the input data of the semantic segmentation network for the maize detection model. We trained a model to separate maize from background using the deep learning segmentation networks DeepLabV3+, U-Net, Linknet, and FPN. All four models showed pixel accuracy of 0.97, and the mIOU score was 0.76 and 0.74 in DeepLabV3+ and U-Net, higher than 0.69 for Linknet and FPN. Weed density was calculated as the difference between the green area classified as ExGR (Excess green-Excess red) and the maize area predicted by the model. Each image evaluated for weed density was recombined to quantify and visualize the distribution and density of weeds in a wide range of maize fields. We propose a method to quantify weed density for accurate weeding by effectively separating weeds, maize, and background from UAV images of maize fields.