• Korean Journal of Agricultural and Forest Meteorology
• /
• v.14 no.1
• /
• pp.1-10
• /
• 2012

Digital Forecast of the Korea Meteorological Administration (KMA) represents 5 km gridded weather forecast over the Korean Peninsula and the surrounding oceanic regions in Korean territory. Digital Forecast provides 12 weather forecast elements such as three-hour interval temperature, sky condition, wind direction, wind speed, relative humidity, wave height, probability of precipitation, 12 hour accumulated rain and snow, as well as daily minimum and maximum temperatures. These forecast elements are updated every three-hour for the next 48 hours regularly. The objective of this study was to construct Forest Fire Danger Rating Systems on the Korean Peninsula (FFDRS_KORP) based on the daily weather index (DWI) and to improve the accuracy using the digital forecast data. We produced the thematic maps of temperature, humidity, and wind speed over the Korean Peninsula to analyze DWI. To calculate DWI of the Korean Peninsula it was applied forest fire occurrence probability model by logistic regression analysis, i.e. $[1+{\exp}\{-(2.494+(0.004{\times}T_{max})-(0.008{\times}EF))\}]^{-1}$. The result of verification test among the real-time observatory data, digital forecast and RDAPS data showed that predicting values of the digital forecast advanced more than those of RDAPS data. The results of the comparison with the average forest fire danger rating index (sampled at 233 administrative districts) and those with the digital weather showed higher relative accuracy than those with the RDAPS data. The coefficient of determination of forest fire danger rating was shown as $R^2$=0.854. There was a difference of 0.5 between the national mean fire danger rating index (70) with the application of the real-time observatory data and that with the digital forecast (70.5).

• Korean Journal of Animal Reproduction
• /
• v.9 no.1
• /
• pp.9-30
• /
• 1985

The study was carried out to find out the changes of the sex hormone levels in the milk of Holstein cows during the reproductive stages such as the estrous cycle, pregnancy and periparturient period. The FSH, LH, estradiol-17$\beta$ and progesterone from the milk samples were assayed by radioimmunoassay methods. The results of this study were summarized as follows: 1. The levels of progesterone and estradiol-17$\beta$ were similar among inter-quarters, but they were higher in after milking than before milking times, with no statistical significance. 2. The milk progesterone levels during the estrous cycles reached a peak mean level of 3.55$\pm$0.26ng/$m\ell$ at 15 days after estrus and they did not show any differences among the length of estrous cycles. The estradiol-17$\beta$ levels during the estrous cycles showed a peak level of 36.40$\pm$2.38pg/$m\ell$ at estrus, and decreased(17.20$\pm$0.46 pg/$m\ell$ to 18.65$\pm$1.26pg/$m\ell$) at luteal phase. 3. The FSH levels during the estrous cycles ranged from 2.25$\pm$0.23mIU/$m\ell$ to 4.35$\pm$0.24mIU/$m\ell$ showing significant changes. The LH levels during the estrous cycles gradually increased and remained a peak level of 10.90$\pm$0.36mIU/$m\ell$ from 20 to 25 days after estrus. 4. The progesterone levels during the pregnancy were decreased from 30 to 60 days after artificial insemination, and therafter continuously increased until 240 days. The estradiol-17$\beta$ levels during the pregnancy were 24.56$\pm$1.19pg/$m\ell$ at day 30 after artificial inseminaton, and increased rapidly until 180 days. The levles were agagin decreased by 26.17$\pm$3.03pg/$m\ell$ until 210 days and markedly increased by 68.00$\pm$8.70pg/$m\ell$ until 240 days. 5. The prolactin levels during the pregnancy were 31.27$\pm$2.31ng/$m\ell$ and 42.60$\pm$2.37ng/$m\ell$ at day 150 and 240 after artificial insemination respectively. The LH levels during the pregnancy reached a peak of 27.47$\pm$7.90mIU/$m\ell$ at day 30 after artificial insemination, and thereafter gradually decreased. 6. The progesterone levels during the periparturient period reached a peak of 4.61$\pm$0.34ng/$m\ell$ at day 3 prepartum, and thereafter gradually decreased, and showed 2.05$\pm$0.60ng/$m\ell$ at day 7 postpartum. The estradiol-17$\beta$ levels during the periparturient period showed high level from 207.23$\pm$6.04pg/$m\ell$ at day 1 prepartum to 239.90$\pm$13.90pg/$m\ell$ at day 2 prepartum, and thereafter began to decline and reached 51.87$\pm$1.72pg/$m\ell$ at by 7 postpartum. 7. The prolactin levels during the periparturient period showed relatively higher level at the time of parturition. The LH levels during the periparturient period rnage from 6.32$\pm$0.32mIU/$m\ell$ to 13.90$\pm$1.37mIU/$m\ell$ showing significant changes. 8. The progesterone levels(4.6$\pm$0.8ng/$m\ell$) of the pregnant cows were significantly higher than those (1.84$\pm$1.4ng/$m\ell$) of nonpregnant cows. The cows of artificial insemination from 61 to 90 days after parturition showed higher progesterone levels. 9. During 20 to 25 days after artificial insemination, the accuracy of pregnancy diagnosis from milk progesterone levels were 94.4% for nonpregnant cows(<2.3ng/$m\ell$), and 75.0% for pregnant cows( 3.2ng/$m\ell$). The average overall accuracy of pregnancy prediction for nonpregnant and pregnant cows 83.3% 10. The results obtained this study suggest that the understanding of the endocrinological mechanisms by means of milk hormone analysis during the estrous cycle, pregnancy and parturition would give the basic information needed for increasing efficiency of reproduction. This study would not only provide an accurate method of the early pregnancy diagnosis by milk progesterone levels but also contribute to the research of providing the method of detecting of FSH levels in milk, which was difficult in blood serum.

• Tuberculosis and Respiratory Diseases
• /
• v.46 no.4
• /
• pp.542-547
• /
• 1999

Background: Decision in mediastinal lymph node involvement of lung cancer by CT scan is very important and valuable for the treatment planning and prognosis prediction. In general, long diameter of mediastinal lymph node more than 15mm is used as criterion of lung cancer involvement. Adenocarci-noma has a tendency of early distant metastasis and micrometastasis, so adenocarcinoma may involve lymph node earlier and cannot be detected before lymph nodes are enlarged enough. The authors tried to determine the difference between two size criteria(15mm, 10mm) in adenocarcinoma for the detection of cancer involvement. Methods: Numbers of sample are 60 cases(male 46, female 14, median age: 61.5 years). According to pathology, squamous cancer 41, large cell cancer 2, adenocarcinoma 17. According to TNM stage, I 23, III 24, IIIA 13. Results : Mean long diameter of lymph node involvement is 16.0($\pm8.0$) mm in non-adenocarcinoma group, and that of adenocarcinoma group is 12.0($\pm3.2$) mm(p<0.05). If long diameter of lymph node larger than 15mm as involvement criterion is applied, sensitivity, specificity, positive predictive index, negative predictive index, accuracy of nonadenocarcinoma group are 54%, 100%, 100%, 83%, 86%, and those of adenocarcinoma group are 43%, 90%, 75%, 69%, 71%. If long diameter of lymph node larger than 10mm as involvement criterion is applied, sensitivity, specificity, positive predictive index. negative predictive index. accuracy of nonadenocarcinoma group are 65%, 77%, 61%, 92%, 79%, and those of adenocarcinoma group are 100%, 80%, 78%, 100%, 88%. Conclusion: Long diameter of lymph node larger than 10mm is more valuable criterion as lymph node involvement in adenocarcinoma of lungs.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.32 no.3
• /
• pp.301-308
• /
• 2012

Near infrared reflectance spectroscopy (NIRS) has become increasingly used as a rapid and accurate method of evaluating some chemical compositions in forages. This study was carried out to explore the accuracy of near infrared spectroscopy (NIRS) for the prediction of chemical parameters of Italian ryegrass silages. A population of 267 Italian ryegrass silages representing a wide range in chemical parameters and fermentative characteristics was used in this investigation. Samples of silage were scanned at 2 nm intervals over the wavelength range 680~2,500 nm and the optical data recorded as log 1/Reflectance (log 1/R) and scanned in intact fresh condition. The spectral data were regressed against a range of chemical parameters using partial least squares (PLS) multivariate analysis in conjunction with spectral math treatments to reduced the effect of extraneous noise. The optimum calibrations were selected on the basis of the highest coefficients of determination in cross validation ($R^2$) and the lowest standard error of cross validation (SECV). The results of this study showed that NIRS predicted the chemical parameters with very high degree of accuracy. The $R^2$ and SECV were 0.98 (SECV 1.27%) for moisture, 0.88 (SECV 1.26%) for ADF, 0.84 (SECV 2.0%), 0.93 (SECV 0.96%) for CP and 0.78 (SECV 0.56), 0.81 (SECV 0.31%), 0.88 (SECV 1.26%) and 0.82 (SECV 4.46) for pH, lactic acid, TDN and RFV on a dry matter (%), respectively. Results of this experiment showed the possibility of NIRS method to predict the chemical composition and fermentation quality of Italian ryegrass silages as routine analysis method in feeding value evaluation and for farmer advice.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.143-159
• /
• 2015

Predicting IT trends has been a long and important subject for information systems research. IT trend prediction makes it possible to acknowledge emerging eras of innovation and allocate budgets to prepare against rapidly changing technological trends. Towards the end of each year, various domestic and global organizations predict and announce IT trends for the following year. For example, Gartner Predicts 10 top IT trend during the next year, and these predictions affect IT and industry leaders and organization's basic assumptions about technology and the future of IT, but the accuracy of these reports are difficult to verify. Social media data can be useful tool to verify the accuracy. As social media services have gained in popularity, it is used in a variety of ways, from posting about personal daily life to keeping up to date with news and trends. In the recent years, rates of social media activity in Korea have reached unprecedented levels. Hundreds of millions of users now participate in online social networks and communicate with colleague and friends their opinions and thoughts. In particular, Twitter is currently the major micro blog service, it has an important function named 'tweets' which is to report their current thoughts and actions, comments on news and engage in discussions. For an analysis on IT trends, we chose Tweet data because not only it produces massive unstructured textual data in real time but also it serves as an influential channel for opinion leading on technology. Previous studies found that the tweet data provides useful information and detects the trend of society effectively, these studies also identifies that Twitter can track the issue faster than the other media, newspapers. Therefore, this study investigates how frequently the predicted IT trends for the following year announced by public organizations are mentioned on social network services like Twitter. IT trend predictions for 2013, announced near the end of 2012 from two domestic organizations, the National IT Industry Promotion Agency (NIPA) and the National Information Society Agency (NIA), were used as a basis for this research. The present study analyzes the Twitter data generated from Seoul (Korea) compared with the predictions of the two organizations to analyze the differences. Thus, Twitter data analysis requires various natural language processing techniques, including the removal of stop words, and noun extraction for processing various unrefined forms of unstructured data. To overcome these challenges, we used SAS IRS (Information Retrieval Studio) developed by SAS to capture the trend in real-time processing big stream datasets of Twitter. The system offers a framework for crawling, normalizing, analyzing, indexing and searching tweet data. As a result, we have crawled the entire Twitter sphere in Seoul area and obtained 21,589 tweets in 2013 to review how frequently the IT trend topics announced by the two organizations were mentioned by the people in Seoul. The results shows that most IT trend predicted by NIPA and NIA were all frequently mentioned in Twitter except some topics such as 'new types of security threat', 'green IT', 'next generation semiconductor' since these topics non generalized compound words so they can be mentioned in Twitter with other words. To answer whether the IT trend tweets from Korea is related to the following year's IT trends in real world, we compared Twitter's trending topics with those in Nara Market, Korea's online e-Procurement system which is a nationwide web-based procurement system, dealing with whole procurement process of all public organizations in Korea. The correlation analysis show that Tweet frequencies on IT trending topics predicted by NIPA and NIA are significantly correlated with frequencies on IT topics mentioned in project announcements by Nara market in 2012 and 2013. The main contribution of our research can be found in the following aspects: i) the IT topic predictions announced by NIPA and NIA can provide an effective guideline to IT professionals and researchers in Korea who are looking for verified IT topic trends in the following topic, ii) researchers can use Twitter to get some useful ideas to detect and predict dynamic trends of technological and social issues.

• Journal of Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.795-805
• /
• 2021

In this study, after developing an LSTM-based deep learning model for estimating daily runoff in the Soyang River Dam basin, the accuracy of the model for various combinations of model structure and input data was investigated. A model was built based on the database consisting of average daily precipitation, average daily temperature, average daily wind speed (input up to here), and daily average flow rate (output) during the first 12 years (1997.1.1-2008.12.31). The Nash-Sutcliffe Model Efficiency Coefficient (NSE) and RMSE were examined for validation using the flow discharge data of the later 12 years (2009.1.1-2020.12.31). The combination that showed the highest accuracy was the case in which all possible input data (12 years of daily precipitation, weather temperature, wind speed) were used on the LSTM model structure with 64 hidden units. The NSE and RMSE of the verification period were 0.862 and 76.8 m³/s, respectively. When the number of hidden units of LSTM exceeds 500, the performance degradation of the model due to overfitting begins to appear, and when the number of hidden units exceeds 1000, the overfitting problem becomes prominent. A model with very high performance (NSE=0.8~0.84) could be obtained when only 12 years of daily precipitation was used for model training. A model with reasonably high performance (NSE=0.63-0.85) when only one year of input data was used for model training. In particular, an accurate model (NSE=0.85) could be obtained if the one year of training data contains a wide magnitude of flow events such as extreme flow and droughts as well as normal events. If the training data includes both the normal and extreme flow rates, input data that is longer than 5 years did not significantly improve the model performance.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.39 no.2
• /
• pp.114-120
• /
• 2019

This study was carried out to explore the accuracy of near infrared spectroscopy(NIRS) for the prediction of moisture content and chemical parameters on winter annual forage crops. A population of 2454 winter annual forages representing a wide range in chemical parameters was used in this study. Samples of forage were scanned at 1nm intervals over the wavelength range 680-2500nm and the optical data was recorded as log 1/Reflectance(log 1/R), which scanned in intact fresh condition. The spectral data were regressed against a range of chemical parameters using partial least squares(PLS) multivariate analysis in conjunction with spectral math treatments to reduced the effect of extraneous noise. The optimum calibrations were selected based on the highest coefficients of determination in cross validation($R^2$) and the lowest standard error of cross-validation(SECV). The results of this study showed that NIRS calibration model to predict the moisture contents and chemical parameters had very high degree of accuracy except for barely. The $R^2$ and SECV for integrated winter annual forages calibration were 0.99(SECV 1.59%) for moisture, 0.89(SECV 1.15%) for acid detergent fiber, 0.86(SECV 1.43%) for neutral detergent fiber, 0.93(SECV 0.61%) for crude protein, 0.90(SECV 0.45%) for crude ash, and 0.82(SECV 3.76%) for relative feed value on a dry matter(%), respectively. Results of this experiment showed the possibility of NIRS method to predict the moisture and chemical composition of winter annual forage for routine analysis method to evaluate the feed value.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.

• Korean Journal of Environment and Ecology
• /
• v.34 no.6
• /
• pp.589-600
• /
• 2020

Effective conservation and management of protected areas require monitoring the settlement of invasive alien species and reducing their dispersion capacity. We simulated the potential distribution of invasive alien plant species (IAPS) using three representative species distribution models (Bioclim, GLM, and MaxEnt) based on the IAPS distribution in the forest genetic resource reserve (2,274ha) in Uljin-gun, Korea. We then selected the realistic and suitable species distribution model that reflects the local region and ecological management characteristics based on the simulation results. The simulation predicted the tendency of the IAPS distributed along the linear landscape elements, such as roads, and including some forest harvested area. The statistical comparison of the prediction and accuracy of each model tested in this study showed that the GLM and MaxEnt models generally had high performance and accuracy compared to the Bioclim model. The Bioclim model calculated the largest potential distribution area, followed by GLM and MaxEnt in that order. The Phenomenological review of the simulation results showed that the sample size more significantly affected the GLM and Bioclim models, while the MaxEnt model was the most consistent regardless of the sample size. The optimal model overall for predicting the distribution of IAPS among the three models was the MaxEnt model. The model selection approach based on detailed flora distribution data presented in this study is expected to be useful for efficiently managing the conservation areas and identifying the realistic and precise species distribution model reflecting local characteristics.