• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.2
• /
• pp.80-98
• /
• 2023

This study explores the effectiveness of various data preprocessing algorithms for improving subseasonal to seasonal (S2S) climate predictions from six climate forecast models and their Multi-Model Ensemble (MME) using a deep learning-based postprocessing model. A pipeline of data transformation algorithms was constructed to convert raw S2S prediction data into the training data processed with several statistical distribution. A dimensionality reduction algorithm for selecting features through rankings of correlation coefficients between the observed and the input data. The training model in the study was designed with TimeDistributed wrapper applied to all convolutional layers of U-Net: The TimeDistributed wrapper allows a U-Net convolutional layer to be directly applied to 5-dimensional time series data while maintaining the time axis of data, but every input should be at least 3D in U-Net. We found that Robust and Standard transformation algorithms are most suitable for improving S2S predictions. The dimensionality reduction based on feature selections did not significantly improve predictions of daily precipitation for six climate models and even worsened predictions of daily maximum and minimum temperatures. While deep learning-based postprocessing was also improved MME S2S precipitation predictions, it did not have a significant effect on temperature predictions, particularly for the lead time of weeks 1 and 2. Further research is needed to develop an optimal deep learning model for improving S2S temperature predictions by testing various models and parameters.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.2
• /
• pp.15-31
• /
• 2022

This study was conducted to suggest a start-up policy that includes start-up education and support for active seniors with various careers who try to change their careers before and after retirement. From this point of view, this study divided the factors affecting the entrepreneurial will of active seniors into entrepreneurship organizational and functional competency and identified the effect of these competencies on entrepreneurial efficacy and entrepreneurial intention. In the proposed model, start-up competency is divided into organizational competency (leadership, creativity problem-solving, communication, decision-making) and functional competency (management strategy, marketing, business plan). And this study examined the mediating role of entrepreneurial efficacy in the relationship between entrepreneurial competency factors and entrepreneurial intention. Meanwhile, PLS-POS analysis was performed to uncover the heterogeneity and pattern in the proposed structural model. The survey was conducted with the help of an online survey company from November 27 to December 15, 2020 for the active senior age group from 40 to under 65 years old. Data were collected from a total of 433 panelists and analyzed using SPSS 22.0 and SmartPLS 3.3.7 programs. The findings are as follows. First, the finding shows that the entrepreneurial organizational and functional competencies of active seniors had significant positive(+) effects on entrepreneurial efficacy. Second, the result shows that entrepreneurial organizational and functional competencies of active seniors had significant positive(+) effects on entrepreneurial intention. Third, the findings show that entrepreneurship efficacy had a significantly positive(+) effect on entrepreneurial intention. The findings of PLS-POS show that entrepreneurship education needs to be carried out by identifying the needs that require entrepreneurial organizational and functional competency when training for entrepreneurship competency. In summary, the findings of the current study are to determine what the competency factors are for the government (local government) to increase the policy direction necessary for establishing and implementing entrepreneurship education and training programs to develop policies to enhance the economic activity participation rate of active seniors.

• Journal of Korean Orthopaedic Sports Medicine
• /
• v.5 no.1
• /
• pp.69-74
• /
• 2006

Purpose: To perform the retrospective analysis of the sports injuries sustained by the college Taekwondo athletes in the respect of the injury patterns, mechanism of injury and clinical outcome Materials and Methods: This study is based on 47 out of 49 college Takwondo athletes, who had experienced the Takwondo related musculoskeletal injuries severe enough to visit the clinic for medical treatment. The mean age at the time of injury was 18.8 years and 39 were males and 8 females. The Taekwondo career was average 9.6 years and the injuries were sustained at average 6.7 years of their career. The injuries were analyzed by the detailed interview with thorough physical examination. Results: Forty-seven Taekwondo athletes in the study experienced average 1.8 injury/person (total 85 cases) with 26 persons of one time experience(55.3%), 11 persons of 2 times(23.4%),4 persons of 3 times (8.5%),5 persons of 4 times (10.6%) and 1 person of 5 times (2.2%). Injuries occurred during training in 50 cases (58.8%), while during match in 35 cases (41.2%). Injuries occurred during the attack phase of the match are 26 cases (31.7%) while 49 cases (57.6%) during the defense phase. As for the pattern of injury, fracture was the most common with 49 cases (57.6%), followed by ligament injury with 21 cases (24.7%). The upper extremity injuries were 32 cases (37.7%) while the lower extremity injuries were 44 cases (51.8%) Mode of medical treatment were operation in 15cases(17.7%), cast in 21 cases(24.7%), splint in 33 cases (38.8%), physical therapy in 15cases(17.7%) and acupuncture in 1 case(1.1%) Conclusion: Almost all the college Taekwondo athletes (96%) experienced sports injuries severe enough to receive medical treatments with the fracture being the most common injury pattern. The injuries occurred more commonly during the defense phase of the competition.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.1-12
• /
• 2019

As Artificial Intelligence (AI) technology develops, it is applied to various fields such as image, voice, and text. AI has shown fine results in certain areas. Researchers have tried to predict the stock market by utilizing artificial intelligence as well. Predicting the stock market is known as one of the difficult problems since the stock market is affected by various factors such as economy and politics. In the field of AI, there are attempts to predict the ups and downs of stock price by studying stock price patterns using various machine learning techniques. This study suggest a way of predicting stock price patterns based on the Convolutional Neural Network(CNN) among machine learning techniques. CNN uses neural networks to classify images by extracting features from images through convolutional layers. Therefore, this study tries to classify candlestick images made by stock data in order to predict patterns. This study has two objectives. The first one referred as Case 1 is to predict the patterns with the images made by the same-day stock price data. The second one referred as Case 2 is to predict the next day stock price patterns with the images produced by the daily stock price data. In Case 1, data augmentation methods - random modification and Gaussian noise - are applied to generate more training data, and the generated images are put into the model to fit. Given that deep learning requires a large amount of data, this study suggests a method of data augmentation for candlestick images. Also, this study compares the accuracies of the images with Gaussian noise and different classification problems. All data in this study is collected through OpenAPI provided by DaiShin Securities. Case 1 has five different labels depending on patterns. The patterns are up with up closing, up with down closing, down with up closing, down with down closing, and staying. The images in Case 1 are created by removing the last candle(-1candle), the last two candles(-2candles), and the last three candles(-3candles) from 60 minutes, 30 minutes, 10 minutes, and 5 minutes candle charts. 60 minutes candle chart means one candle in the image has 60 minutes of information containing an open price, high price, low price, close price. Case 2 has two labels that are up and down. This study for Case 2 has generated for 60 minutes, 30 minutes, 10 minutes, and 5minutes candle charts without removing any candle. Considering the stock data, moving the candles in the images is suggested, instead of existing data augmentation techniques. How much the candles are moved is defined as the modified value. The average difference of closing prices between candles was 0.0029. Therefore, in this study, 0.003, 0.002, 0.001, 0.00025 are used for the modified value. The number of images was doubled after data augmentation. When it comes to Gaussian Noise, the mean value was 0, and the value of variance was 0.01. For both Case 1 and Case 2, the model is based on VGG-Net16 that has 16 layers. As a result, 10 minutes -1candle showed the best accuracy among 60 minutes, 30 minutes, 10 minutes, 5minutes candle charts. Thus, 10 minutes images were utilized for the rest of the experiment in Case 1. The three candles removed from the images were selected for data augmentation and application of Gaussian noise. 10 minutes -3candle resulted in 79.72% accuracy. The accuracy of the images with 0.00025 modified value and 100% changed candles was 79.92%. Applying Gaussian noise helped the accuracy to be 80.98%. According to the outcomes of Case 2, 60minutes candle charts could predict patterns of tomorrow by 82.60%. To sum up, this study is expected to contribute to further studies on the prediction of stock price patterns using images. This research provides a possible method for data augmentation of stock data.

• Radiation Oncology Journal
• /
• v.22 no.3
• /
• pp.184-191
• /
• 2004

Purpose: In order to improve the proper use of radiotherapy and breast-conserving treatment (BCT) in the management of breast cancer, current status of breast cancer treatment in Korea was surveyed nationwide and the use of BCT were evaluated. Materials and Methods: Patients characteristics and treatment pattern of 1048 breast cancer patients from 27 institutions diagnosed between January, 1998 and June, 1998 were analyzed. The incidence of receiving BCT was analyzed according to the stage, age, geography, type of hospital, and the availability of radiotherapy facility. Results: Radical mastectomy was peformed in 64.8$\%$ of total patients and 26$\%$ of patients received breast- conserving surgery (BCS). The proportions of patients receiving BCT were 47.5$\%$ in stage 0, 54.4$\%$ in stage I, and 20.3$\%$ in stage II, Some of the patients (6.6$\%$ of stage I, 10.1$\%$ of stage II and 66.7$\%$ of stage III) not received radiotherapy after BCS. Only 45$\%$ of stage III patients received post-operative radiotherapy after radical mastectomy. The proportion of patients receiving BCT was different according to the geography and availability of radiotherapy facilities. Conclusion: Radiotherapy was not fully used in the management of breast cancer, even in the patients received breast-conserving surgery. The proportion of the patients who received BCT was lower than the report of western countries. To improve the application of proper management of breast cancer, every efforts such as a training of physicians, public education, and improving accessibility of radiotherapy facilities should be done. The factors predicting receipt of BCT were accessibility of radiotherapy facility and geography. Also, periodic survey like current research is warranted.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.43 no.4
• /
• pp.75-86
• /
• 2015

The survey was taken from July to August 2012 by users who visited Gyeongju National Park to compare the perceived gap of users regarding management policy by characteristic of Gyeongju National Park district type in this study. Gyeongju National Park users' characteristic, use pattern and perception regarding park management policy were created as survey items. First, district type was classified based on use pattern of the visitor and the key resources of 8 districts in Gyeongju National Park. Tohamsan District, which has many visitors for the purpose of scenery appreciation and recreation with Bulguksa and Seokguram Grotto, is classified as tourism type, Namsan and Daebon District, which bring in many visitors seeking to learn about historical culture and environmental education, could be classified as historical culture education types, and Hwarang, Seoak, Sogeum River, Gumisan District are places residents use for physical training, hiking and walking to improve health, thus classifying them as neighborhood park types. People perceived that the tourism type is where users for historical artifact tours are concentrated, thus consideration for plans that can improve visitors' satisfaction from a user limit policy is required, and a manager's right to control use behavior must be reinforced in historical culture education types. On the other hand, users of neighborhood parks found the lowest necessity for most of the policy, and this showed that users of each of Gyeongju National Park's districts felt differently about the need for policies. This result is expected to be utilized as a database for introducing policy that reflects the perception of users in each districts of Gyeongju National Park in the future.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.77-97
• /
• 2010

Market timing is an investment strategy which is used for obtaining excessive return from financial market. In general, detection of market timing means determining when to buy and sell to get excess return from trading. In many market timing systems, trading rules have been used as an engine to generate signals for trade. On the other hand, some researchers proposed the rough set analysis as a proper tool for market timing because it does not generate a signal for trade when the pattern of the market is uncertain by using the control function. The data for the rough set analysis should be discretized of numeric value because the rough set only accepts categorical data for analysis. Discretization searches for proper "cuts" for numeric data that determine intervals. All values that lie within each interval are transformed into same value. In general, there are four methods for data discretization in rough set analysis including equal frequency scaling, expert's knowledge-based discretization, minimum entropy scaling, and na$\ddot{i}$ve and Boolean reasoning-based discretization. Equal frequency scaling fixes a number of intervals and examines the histogram of each variable, then determines cuts so that approximately the same number of samples fall into each of the intervals. Expert's knowledge-based discretization determines cuts according to knowledge of domain experts through literature review or interview with experts. Minimum entropy scaling implements the algorithm based on recursively partitioning the value set of each variable so that a local measure of entropy is optimized. Na$\ddot{i}$ve and Booleanreasoning-based discretization searches categorical values by using Na$\ddot{i}$ve scaling the data, then finds the optimized dicretization thresholds through Boolean reasoning. Although the rough set analysis is promising for market timing, there is little research on the impact of the various data discretization methods on performance from trading using the rough set analysis. In this study, we compare stock market timing models using rough set analysis with various data discretization methods. The research data used in this study are the KOSPI 200 from May 1996 to October 1998. KOSPI 200 is the underlying index of the KOSPI 200 futures which is the first derivative instrument in the Korean stock market. The KOSPI 200 is a market value weighted index which consists of 200 stocks selected by criteria on liquidity and their status in corresponding industry including manufacturing, construction, communication, electricity and gas, distribution and services, and financing. The total number of samples is 660 trading days. In addition, this study uses popular technical indicators as independent variables. The experimental results show that the most profitable method for the training sample is the na$\ddot{i}$ve and Boolean reasoning but the expert's knowledge-based discretization is the most profitable method for the validation sample. In addition, the expert's knowledge-based discretization produced robust performance for both of training and validation sample. We also compared rough set analysis and decision tree. This study experimented C4.5 for the comparison purpose. The results show that rough set analysis with expert's knowledge-based discretization produced more profitable rules than C4.5.

• Journal of Korean Society of Forest Science
• /
• v.98 no.4
• /
• pp.370-378
• /
• 2009

This study tries to provide the basic direction to form the arboretum with the distinct features by providing the basic data to help the differentiated strategy for each arboretum. For this purpose, the users' pattern, importance of the indicator by the function, and the stimulation and specialization importance were examined for Daegu Arboretum, Gyeongbuk Arboretum and Gyeongnam Arboretum in Gyeongsang Province. The result says, looking into the functions of arboretum, the collection function showed the highest importance in the preservation of the endangered crisis species; the display function showed the highest in the use as the nature experiencing spaces through the plant exhibition; the research function showed the highest in the study on Plant Systematics; the education function showed the highest in the protection of the native plants; and the recreational function showed the highest in the healthy recreational space. In the plan for the promotion of the arboretum showed the highest in the public education program operation such as the narration from arboretum and education for plant. Therefore, it is considered to need the system setup such as the education program, material development and specialist training in terms of the arboretum. For the specialization plan for arboretum in this study, it seem desirable to concentrate on the research and education related to the natural resources renewal, for Daegu Arboretum; to concentrate on the resort site for the protection and display of the species and the disabled visitors by utilizing the geographical traits in the mountains, for Gyeongbuk Arboretum; to create the specialization plan mainly for the tree species suitable for the warm weather and for the children.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.157-173
• /
• 2011

As the Internet use explodes recently, the malicious attacks and hacking for a system connected to network occur frequently. This means the fatal damage can be caused by these intrusions in the government agency, public office, and company operating various systems. For such reasons, there are growing interests and demand about the intrusion detection systems (IDS)-the security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. The intrusion detection models that have been applied in conventional IDS are generally designed by modeling the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. These kinds of intrusion detection models perform well under the normal situations. However, they show poor performance when they meet a new or unknown pattern of the network attacks. For this reason, several recent studies try to adopt various artificial intelligence techniques, which can proactively respond to the unknown threats. Especially, artificial neural networks (ANNs) have popularly been applied in the prior studies because of its superior prediction accuracy. However, ANNs have some intrinsic limitations such as the risk of overfitting, the requirement of the large sample size, and the lack of understanding the prediction process (i.e. black box theory). As a result, the most recent studies on IDS have started to adopt support vector machine (SVM), the classification technique that is more stable and powerful compared to ANNs. SVM is known as a relatively high predictive power and generalization capability. Under this background, this study proposes a novel intelligent intrusion detection model that uses SVM as the classification model in order to improve the predictive ability of IDS. Also, our model is designed to consider the asymmetric error cost by optimizing the classification threshold. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, when considering total cost of misclassification in IDS, it is more reasonable to assign heavier weights on FNE rather than FPE. Therefore, we designed our proposed intrusion detection model to optimize the classification threshold in order to minimize the total misclassification cost. In this case, conventional SVM cannot be applied because it is designed to generate discrete output (i.e. a class). To resolve this problem, we used the revised SVM technique proposed by Platt(2000), which is able to generate the probability estimate. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 1,000 samples from them by using random sampling method. In addition, the SVM model was compared with the logistic regression (LOGIT), decision trees (DT), and ANN to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell 4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on SVM outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that our model reduced the total misclassification cost compared to the ANN-based intrusion detection model. As a result, it is expected that the intrusion detection model proposed in this paper would not only enhance the performance of IDS, but also lead to better management of FNE.

• Journal of agricultural medicine and community health
• /
• v.26 no.2
• /
• pp.79-96
• /
• 2001

In order to ascertain the utilization patterns and Perception and attitudes of Primary Health Post(PHP) by rural residents in farm areas, a survey was conducted of 753 households(1,803 persons) in 24 PHPs in Sangju-si, Gyeongsangbuk- do, from December 10, 2000 to January 15, 2001. The morbidly rate of acute illnesses for last two weeks for all households was 29.6%, and the rate of use of medical facilities to treat acute illness was 98.3%. The morbidly rate was highest between the ages of 60 and 69, with a rate of 35.4%. The higher their ages and the lower their educational levels were, the higher the morbidly rate was. The morbidly rate of chronic illnesses for one year for all households was 19.2%, and the rate of use of medical facilities to treat chronic illness was 92.8%. The elderly over 70 years old had the highest morbidly rate of 37.2%. The higher their ages and the lower their educational levels were, the higher the chronic illnesses rate was. For the rate of use of medical facilities to treat acute diseases, the use of PHPs was 89.5%, accounting for the majority of the time. However, for chronic diseases, hospitals and clinics were used more often, with a rate of 48.9%, compared to the use of PHPs, 40.2%. Their previous experiences on the use of PHPs one year before the survey showed that 94.8% used PHPs, 72.2% just visited them, not for the purpose of getting any medical assistance, and 73.3% received health education from PHPs. 98.5% remembered the locations of PHPs, 98.6% thought that PHPs were helpful for their health management, and 84.3% said that PHPs were playing great roles in development of their communities. 97.4% said that they found PHPs necessary. They understood the main job of PHPs as in the order of disease treatment, vaccination and health counseling. The work that they mostly wanted PHPs to do was health counseling and health management, which 31.6% answered. 88.9% said the examination fee was not expensive, 98.4% said CHPs were kind, and 97.0% said they were satisfied with the services at PHPs. Complaints about PHPs included a lack of a variety of medications, said by 42.9%, and poor facilities, by 15.8%. According to the above results, it is concluded that local residents on survey were frequently using PHPs due to their geographical and economical conditions. Also, the residents appeared to be satisfied with the services at PHPs, and they had a high demand for public health service as well as disease treatment. Considering the complaints about medications and medical facilities and equipment, active supports are required to manage PHPs in a way it can provide desirable services to the residents in remote villages through the readjustment of PHPs' functions, reinforcement of facilities and equipment and enhancement of CHPs ' training.