• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.262-264
• /
• 2004

퍼지 클러스터링 방법은 일반적인 클러스터링 방법과는 달리 하나의 샘플이 다수의 집단에 속할 수 있으며 그 속하는 정도를 표현하여 보다 유연한 클러스터 분할의 분석을 가능하게 한다. 유전자 발현 데이터는 노이즈가 많고 공통된 기능을 가진 유전자들의 집단이 존재하기 때문에 퍼지 클러스터링을 사용하면 더욱 효율적으로 분석할 수 있다. 이러한 퍼지 클러스터링 방법에 있어서 중요한 것은 얼마나 분할이 정확하게 이루어졌으며 실제 데이터가 가지고 있는 분할과 결과가 얼마나 유사한가이다. 본 논문에서는 효과적인 유전자 클러스터의 평가를 위하여 베이지안 검증 방법을 제시하고, 결정트리로 생성된 규칙에 의하여 각 데이터의 특성에 따라 유연하게 검증하는 방법을 제안한다. 다양한 유전자 발현 데이터를 퍼지 c-means 알고리즘을 이용하여 클러스터링하고 제안하는 방법으로 검증한 결과, 그 유용성을 확인할 수 있었다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.185-185
• /
• 2018

광학우적계(PARSIVEL)는 강수 입자의 정확한 직경 및 분포 분석에 용이한 이유로 정밀 기상관측과 레이더 및 우량계 검보정을 위해 널리 사용되고 있다. 하지만 PARSIVEL S/W의 경우, 관측 순간의 각종 변수 및 분석 결과를 이해하기에 용이하나 강우 이벤트 전체를 분석하기 위해서는 별도의 후처리가 요구되는 번거로움이 있다. 본 연구에서는 소형레이더 및 전파강수계의 비교검증 효율성 향상을 위해 그림 1과 같이 PARSIVEL의 자료구조 및 포맷을 분석하여, 즉각적으로 원하는 강우 이벤트에 대해 다양한 분석도구를 적용할 수 있는 S/W를 개발하였다. 그림 2로부터 개발된 S/W로부터의 분석결과를 나타내었으며, 다양한 실험을 통해 제안한 S/W를 이용함으로써 각종 강우량계 비교검증 시 강수분석을 용이하게 함을 확인하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.375-384
• /
• 2021

Deep learning techniques have been proven to have high performance in image processing and are applied in various fields. The most widely used methods for validating a deep learning model include a holdout verification method, a k-fold cross verification method, and a bootstrap method. These legacy methods consider the balance of the ratio between classes in the process of dividing the data set, but do not consider the ratio of various features that exist within the same class. If these features are not considered, verification results may be biased toward some features. Therefore, we propose a deep learning model validation method based on data feature coverage for image classification by improving the legacy methods. The proposed technique proposes a data feature coverage that can be measured numerically how much the training data set for training and validation of the deep learning model and the evaluation data set reflects the features of the entire data set. In this method, the data set can be divided by ensuring coverage to include all features of the entire data set, and the evaluation result of the model can be analyzed in units of feature clusters. As a result, by providing feature cluster information for the evaluation result of the trained model, feature information of data that affects the trained model can be provided.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.5
• /
• pp.398-405
• /
• 2014

Recently the embedded software has been widely applied to the safety-critical systems in aviation and defense industries, therefore, the higher level of reliability, availability and fault tolerance has become a key factor for its implementation into the systems. The integrity of the software can be verified using the static analysis tools. And recent developed static analysis tool can evaluate code integrity through the mathematical analysis method. In this paper we detect the autocode error and violation of coding rules using the formal verification tool, Polyspace(R). And the fundamental errors on the flight control law model have been detected and corrected using the formal verification results. As a result of verification process, FBW helicopter control law autocode can ensure code integrity.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.10 no.3
• /
• pp.109-119
• /
• 1998

A horizontal tow-dimensional version of POM (Princeton Ocean Model) was modified in representing the bottom friction and the open boundary conditions. To simulate the flooding and drying of intertidal flats, a wetting-and-drying scheme was incorporated into the model. The model then was applied to the Chunsu Bay and its adjacent coastal water. Only the water movement due to tides, the dominant forcing in the study area, was considered. This presents the procedure and the results of model calibration and verification for the Chunsu Bay system. The model was calibrated, using the average tidal characteristics in Tide Tables, for the amplitudes and the phases of tidal waves throughout the modeling domain. Calibration results showed that the model gave a good reproduction of tidal waves. The calibrated model was verified using the time-series measurements of surface elevation and current velocity in the summer of 1995. The model reproduced the tides currents very well. calibration and verification results demonstrated that the model is capable of reproducing the tidal dynamics in the Chunsu Bay system.

• Journal of the Korean Applied Science and Technology
• /
• v.37 no.4
• /
• pp.1008-1019
• /
• 2020

The purpose of this study is to investigate the effects of social support of students majoring in physical education on their major satisfaction and intention to continue learning, and to prevent dropout of students majoring in physical education in the credit banking system and to find effective management methods. The research tools were verified by confirmatory factor analysis, concentration validity, discriminant validity, average variance extraction (AVE), concept reliability, and Cronbach's coefficient for validity and reliability verification of the research tools. The data processing method was conducted by using IBM SPSS Statistics 21 and IBM AMOS 21 to verify reliability analysis, correlation analysis, and structural equation model (SEM) through frequency analysis, confirmatory factor analysis, concentration validity, discriminant validity, Cronbach's coefficient calculation. The results are as follows. First, the study model was tested and the criteria were met for verifying the suitability of the relationship between social support, major satisfaction and learning persistence intention of the professors majoring in physical education in credit banking system. Second, as a result of the verification of Hypothesis 1, the social support of the professor of the physical education major in the credit banking system has a significant effect on the major satisfaction. The results of the verification of Hypothesis 2 showed that the social support of the professor of the physical education major in the credit banking system affects on the learning persistence. As a result of the verification of Hypothesis 3, it has been shown that major satisfaction has a significant effect on the learning persistence.

• The Journal of the Korea Contents Association
• /
• v.16 no.7
• /
• pp.100-111
• /
• 2016

This study analyzes targeting 584 senior citizens aged 65 and over in Gyeongsangnam-do to verify a mediated control effect of optimism and family support in stress and successful aging of the aged. Using SPSS Macro Way suggested by Preacher and Hayes. A study model is verified through a route model, and the verification of the study model is conducted in three stages. The first stage analyzes whether a control variable has a control effect in a relationship between predictor variable and standard variable, and the second stage confirms a relationship between predictor variable and mediated variable. In addition, the third stage confirms a mediated control effect. An analytical result is summarized as follows. First, as a result to verify a mediated effect between stress and successful aging, and optimism, it is confirmed that it supports a partially-mediated model. Second, as a result to verify a control effect of optimism and family support of successful aging, it is confirmed that everything has a control effect. Third, as a result to verify a mediated control effect of stress, optimism, successful aging, and family support, there is a mediated control effect. Based on these study results, practical undertone and future task are suggested, and a way to improve family support is presented for successful aging in advanced age.

• The Korean Journal of Financial Management
• /
• v.21 no.1
• /
• pp.183-204
• /
• 2004

This paper introduces an observable connection structure between stocks in Korean stock market and investigates the formation principles of the observed connection structure between stocks in economic views. Several recent studies have been attempting to explain that the connection structure between stocks is organized by Power-Law distribution, this implies that most stocks have a few links, but only a few stocks have very large number of links. Therefore, we want to investigate the reason about why the connection structure between stocks exhibited by Mantegna's approach is Power-Law distribution. As a result we found that the number of connection between stocks is determined by market factors and specific firm factors among many other factors. In addition, if a stock is more affected by common factors(market) than specific firm factors, the stock has large number of links with other stocks, otherwise more affected by specific firm factors, the stock has a few links.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.40 no.3
• /
• pp.201-208
• /
• 2012

In this paper, a series of experiment is performed for a scaled hovering rotor in a semi-anechoic chamber and the results are compared to the noise spectra predicted by using Lowson's loading noise equation and FW-H equation. It was founded that the sound directivity pattern for both experiments and predictions are similar in their trend. Meanwhile the FW-H equation showed better agreement with experiments in the near-field noise spectra, but at the far-field the Lowson's equation performed better. The discrete noise are known to be proportional to the loading on the blades, which can be controlled by collective pitch angle of the blades. It was founded that the predicted spectra with FW-H equation come close to the measured noise spectra in low collective pitch, but in high collective pitch angles the Lowson's equation be more reliable.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.43-43
• /
• 2022

유해 조류 대발생은 전국 각지의 인공호소나 하천에서 다발적으로 발생하며, 경관을 해치고 수질을 오염시키는 등 수자원에 부정적인 영향을 미친다. 본 연구에서는 인공호소에서 발생하는 유해 조류 대발생을 예측하기 위해 심층학습 기법을 이용하여 예측 모델을 개발하고자 하였다. 대상 지점은 대청호의 추동 지점으로 선정하였다. 대청호는 금강유역 중류에 위치한 댐으로, 약 150만명에 달하는 급수 인구수를 유지 중이기에 유해 남조 대발생 관리가 매우 중요한 장소이다. 학습용 데이터 구축은 대청호의 2011년 1월부터 2019년 12월까지 측정된 수질, 기상, 수문 자료를 입력 자료를 이용하였다. 수질 예측 모델의 구조는 다중 레이어 퍼셉트론(Multiple Layer Perceptron; MLP)으로, 입력과 한 개 이상의 은닉층, 그리고 출력층으로 구성된 인공신경망이다. 본 연구에서는 인공신경망의 은닉층 개수(1~3개)와 각각의 레이어에 적용되는 은닉 노드 개수(11~30개), 활성함수 5종(Linear, sigmoid, hyperbolic tangent, Rectified Linear Unit, Exponential Linear Unit)을 각각 하이퍼파라미터로 정하고, 모델의 성능을 최대로 발휘할 수 있는 조건을 찾고자 하였다. 하이퍼파라미터 최적화 도구는 Tensorflow에서 배포하는 Keras Tuner를 사용하였다. 모델은 총 3000 학습 epoch 가 진행되는 동안 최적의 가중치를 계산하도록 설계하였고, 이 결과를 매 반복마다 저장장치에 기록하였다. 모델 성능의 타당성은 예측과 실측 데이터 간의 상관관계를 R2, NSE, RMSE를 통해 산출하여 검증하였다. 모델 최적화 결과, 적합한 하이퍼파라미터는 최적화 횟수 총 300회에서 256 번째 반복 결과인 은닉층 개수 3개, 은닉 노드 수 각각 25개, 22개, 14개가 가장 적합하였고, 이에 따른 활성함수는 ELU, ReLU, Hyperbolic tangent, Linear 순서대로 사용되었다. 최적화된 하이퍼파라미터를 이용하여 모델 학습 및 검증을 수행한 결과, R2는 학습 0.68, 검증 0.61이었고 NSE는 학습 0.85, 검증 0.81, RMSE는 학습 0.82, 검증 0.92로 나타났다.