• Journal of Physiology & Pathology in Korean Medicine
• /
• v.17 no.4
• /
• pp.845-851
• /
• 2003

The objective is to establish the standard of criteria for differential diagnosis of signs and symptoms. This study selected signs and symptoms related to heart which stands for Fire(火) as a kind of five phase(五行). Eleven experts was asked to evaluate the adequateness of criteria which was developed by Korea Institute of Oriental Medicine(KIOM) and to suggest the amendment of them. To implement the study, we used the questionnaire which asks about the diagnosis criteria for an insufficiency of the heart-qi(心氣虛證), deficiency of the heart blood(心血氣證), deficiency of the heart-yin(心陰虛證), insufficiency of the heart-yang(心陽虛證), exuberant fire due to hyperactivity of the heart(心火亢盛證), stagnation of the heart blood(心血瘀阻證), heart disturbed by phlegm-fire(痰火擾心證), attack of the heart by retainedfluid(水氣凌心證). Every criteria consists of primary symptoms, secondary symptoms, tongue findings. and pulse findings. In perspectives of the classification of patterns for signs and symptoms and criteria for diagnosis, the result shows that the previous standard doesn't have so many problem. So many of experts were agree with the criteria which was suggested but the trend is that they use, in their actual practice, less than the criteria. Additionally, they pointed that every element in a criterion should have the different weight value, criteria for the overlapped pattern should be added, and, in future, criteria which are based on clinical investigation should be established.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.7
• /
• pp.213-220
• /
• 2020

The convolutional neural network is composed of convolutional layers and fully connected layers. The nonlinear activation function is used in each layer of the convolutional layer and the fully connected layer. The activation function being used in a neural network is a function that simulates the method of transmitting information in a neuron that can transmit a signal and not send a signal if the input signal is above a certain criterion when transmitting a signal between neurons. The conventional activation function does not have a relationship with the loss function, so the process of finding the optimal solution is slow. In order to improve this, an agile activation function that generalizes the activation function is proposed. The agile activation function can improve the performance of the deep neural network in a way that selects the optimal agile parameter through the learning process using the primary differential coefficient of the loss function for the agile parameter in the backpropagation process. Through the MNIST classification problem, we have identified that agile activation functions have superior performance over conventional activation functions.

• Journal of agriculture & life science
• /
• v.46 no.4
• /
• pp.31-39
• /
• 2012

In this study, biodiversity was classified as 4 sectors (genes, species, ecosystems, and cultures) and overall 14 indicators were subdivided by the classification criterion of 4 sectors. Among those 14 indicators, monetary evaluation was conducted for 11 indicators that can be quantified in economic perspectives. Results show that negative economy effects (forest degradation, forest fire, forest damage caused by diseases and insects, deforestation, and cost under the assumption with the adoption of the Nagoya Protocol to be compensated for traditional knowledge) by reducing forest biodiversity were evaluated as 254.5 billion won annually. Also, Bioindustry, indigenous species, forest production, protection area, and income associated with mountain village were considered as positive economy effects and their annual economic value was 6.72 trillion won. Net annual benefit by maintaining forest biodiversity was about 6.5 trillion won.

• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.427-441
• /
• 2021

Purpose: This study proposes a method for developing a model that predicts the probability of traffic accidents in advance to prevent the most frequent traffic accidents in the military. Method: For this purpose, CRISP-DM (Cross Industry Standard Process for Data Mining) was applied in this study. The CRISP-DM process consists of 6 stages, and each stage is not unidirectional like the Waterfall Model, but improves the level of completeness through feedback between stages. Results: As a result of modeling the same data set as the previously constructed accident investigation data for the entire group, when the classification criterion was 0.5, Significant results were derived from the accuracy, specificity, sensitivity, and AUC of the model for predicting traffic accidents. Conclusion: In the process of designing the prediction model, it was confirmed that it was difficult to obtain a meaningful prediction value due to the lack of data. The methodology for designing a predictive model using the data set was proposed by reorganizing and expanding a data set capable of rational inference to solve the data shortage.

• Journal of Digital Convergence
• /
• v.19 no.4
• /
• pp.339-347
• /
• 2021

The purpose was to analyze the trend of sport pedagogy in secondary teacher certification examination based on the secondary teacher qualification criterion in Korea Institute for Curriculum and Evaluation since abolition of multiple-choice questions from 2014 to 2020. The result showed the questions for sport pedagogy were 48 question since 2014, and found 83 sub-questions. The implications are as follows. First, the frequency of sub-questions in sport pedagogy has increased, causing an integrated question. Second, the serious unbalanced issue of questions for examination was presented. Third, dependence on specific domains was excessively high. Fourth, the confusion caused by the overlapped domains with the content knowledge of physical education subject was intensified. Therefore, evaluation factors based on 2016 KICE classification table should be clear and field application questions should be developed.

• Journal of Korea Planning Association
• /
• v.53 no.7
• /
• pp.109-126
• /
• 2018

The purpose of this study is to identify the spatial types for thermal environment improvement considering heat flux and its spatial context through empirical orthodox formulas. First, k-means clustering was used to classify values of three kinds of heat flux - latent, sensible and storage heat. Next, from the k-means clustering, we defined a type of thermal environment (type LHL) where improvement is needed for more comfortable and pleasant thermal environment in the city, among the eight types. Lastly, we compared and analyzed the characteristics of each classified thermal environmental types based on land cover types. From the study, we found that the ratio of impervious surfaces, roads, and buildings of the type LHL is higher than those of the type HLH (relatively thermal comfort environment). In order to improve the thermal environment, the following contents are proposed to urban planners and designers depending on the results of the study. a) Increase the green zone rate by 10% to reduce sensible heat; b) Reduce the percentage of impermeable surfaces and roads by 10% ; c) Latent heat increases when water and green spaces are expanded. This study will help to establish a minimum criterion for a land cover rate for the improvement of the urban thermal environment and a standard index for the thermal environmental improvement can be derived.

• Journal of Oriental Neuropsychiatry
• /
• v.29 no.4
• /
• pp.281-290
• /
• 2018

Objectives: The objective of this study was to review the research trends in the treatment of acupuncture on schizophrenia in traditional Chinese medicine. Methods: Articles in the China National Knowledge Infrastructure (CNKI) from September 2008 to August 2018 were reviewed. The selected articles were evaluated by the Jadad Scale. Results: 11 articles were selected from a total of 33 articles. 1 study was single group before-and-after study while the other 10 studies were randomized controlled trial studies. Chinese Classification of Mental Disorders-3 was most frequently used as a diagnostic criterion. Brief Psychiatric Rating Scale was most commonly used as an outcome measurement. From Jadad Quality Assessment Scale of the 11 articles, the quality of the studies generally was low. Conclusions: BaekHoi (GV20) and YinDang (EX-HN3) are most commonly used in acupuncture treatment. According to this study, acupuncture treatment in addition to western medication on schizophrenia is more effective as compared to the controls. In future, this study could be primary data for development of more clinical research on the treatment of schizophrenia in Korean medicine.

• Genomics & Informatics
• /
• v.16 no.4
• /
• pp.31.1-31.7
• /
• 2018

The prevalence of metabolic syndrome (MS) in the nonobese population is not low. However, the identification and risk mitigation of MS are not easy in this population. We aimed to develop an MS prediction model using genetic and clinical factors of nonobese Koreans through machine learning methods. A prediction model for MS was designed for a nonobese population using clinical and genetic polymorphism information with five machine learning algorithms, including naïve Bayes classification (NB). The analysis was performed in two stages (training and test sets). Model A was designed with only clinical information (age, sex, body mass index, smoking status, alcohol consumption status, and exercise status), and for model B, genetic information (for 10 polymorphisms) was added to model A. Of the 7,502 nonobese participants, 647 (8.6%) had MS. In the test set analysis, for the maximum sensitivity criterion, NB showed the highest sensitivity: 0.38 for model A and 0.42 for model B. The specificity of NB was 0.79 for model A and 0.80 for model B. In a comparison of the performances of models A and B by NB, model B (area under the receiver operating characteristic curve [AUC] = 0.69, clinical and genetic information input) showed better performance than model A (AUC = 0.65, clinical information only input). We designed a prediction model for MS in a nonobese population using clinical and genetic information. With this model, we might convince nonobese MS individuals to undergo health checks and adopt behaviors associated with a preventive lifestyle.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.1088-1097
• /
• 2021

Vibration data of mechanical equipment inevitably have noise. This noise adversely af ects the maintenance of mechanical equipment. Accordingly, the performance of a learning model depends on how effectively the noise of the data is removed. In this study, the noise of the data was removed using the Denoising Auto Encoder (DAE) technique which does not include the characteristic extraction process in preprocessing time series data. In addition, the performance was compared with that of the Wavelet Transform, which is widely used for machine signal processing. The performance comparison was conducted by calculating the failure detection rate. For a more accurate comparison, a classification performance evaluation criterion, the F-1 Score, was calculated. Failure data were detected using the One-Class SVM technique. The performance comparison, revealed that the DAE technique performed better than the Wavelet Transform technique in terms of failure diagnosis and error rate.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.33 no.s01
• /
• pp.39-47
• /
• 1988

Soybean grain is most widely used and soybean crop produces most high protein per area among crops. To meet rapid increase of human population and supply protein in safety. soybean has considered more and more important crop. And it has been emphasizing that high quality and high protein soybean breeding must be made efforts in future. Many papers related to soybean breeding for high quality and protein and soybean protein composition have suggested the problems to do in future. Soybean germplasm collection. classification and conservation should be continuously performed, and it is emphasized that wild type of soybeans (G. soja) be considered to use in breeding for high protein varieties. Selections would be better emphasized in first yield and therefore high yield of protein per area. Selection for high protein would be secondary criterion. High protein lines with high yielding potential could be selection from certain populations, and breeders should consider this phenomenon in procedure of selection. Heritability of protein percent is relatively high and genetic gain of increment of protein percent is large. Soybean protein which is comprised 70 to 90% of globulin is constituted mostly 11S and 7S proteins. Sulfur-containing amino acids, methionine and cysteine, are identified to contain more in 11S protein than 7S protein. High 11S germplasm should be desirable to use in crossing plan, and selection of high ratio of 11S/7S lines be better in development of high quality varieties.