• 한국IT서비스학회:학술대회논문집
• /
• 한국IT서비스학회 2008년도 춘계학술대회
• /
• pp.572-577
• /
• 2008

정보보호 안전진단 제도는 정보보호 수준을 향상시키고 정보통신서비스의 안정성 및 신뢰성을 확보하기 위한 목적으로 2004년 7월부터 시행되었으나 일부의 안전진단 대상 사업자들은 본 제도에 대해 부정적이며, 대상 사업자 선정을 위해서 필요한 자료의 취득이 어려운 여건 등을 감안하여, 신뢰성있는 데이터에 기반하면서도 객관적이고 합리적으로 대상자를 선정하기 위한 기준이 필요하다. 본 연구에서는 관련 자료의 통계분석과 전문가의 의견을 취합하여 도출된 개선방안을 제안했는데, 주요내용은 정보통신서비스제공자와 집적시설사업자는 정보통신 매출액 50억 이상으로, 쇼핑몰 등 다중이용서비스 제공자는 개인정보 수집건수 200만명이상인 사업자를 안전진단 대상자로 선정하는 방안이다.

• 한국자동차공학회논문집
• /
• 제20권1호
• /
• pp.1-7
• /
• 2012

The brake-by-wire technology is a new automotive chassis system that allows standard braking operations by electronic components with lighter weights and faster response. The brake-by-wire units such as EMB (Electro-Mechanical Brake) are controlled by electronic sensors and actuators and, thus, the fault diagnosis is essential for implementation. In this study, a model-based fault diagnosis system is developed for the sensors based on the analytical redundancy method. The fault detection algorithm is verified in simulations for various faulty cases. A test bench is built including the EMB unit and the performance of the proposed fault diagnosis system is evaluated through the experiment.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권5호
• /
• pp.3281-3288
• /
• 2013

Background: Breast cancer is the leading cause of cancer-related deaths in women. Despite being associated with high morbidity and mortality, breast cancer is a disease that can be diagnosed and treated early. Materials and Methods: In this cross-sectional study of 321 women, data were collected by Questionnaire, Breast Cancer Risk Assessment Form and Champion's Health Belief Model Scale. Mann-Whitney U, Kruskal-Wallis, Chisquared tests and logistic regression were used in the statistical analysis. Results: It was found that only 2.2% of women have high and very high risk levels of breast cancer risk. There is a positive correlation between early diagnosis techniques and Health Belief Model Sub-Dimension scores which are sensibility, health motivation, BSE (Breast self-examination) self-efficient perception and negative correlation between mammography barrier score and BSE barrier score (p 0.05). When factors for not having BSE were examined, it was determined that the women who do not have information about breast cancer and the women who smoke have a higher risk of not having BSE. Conclusions: It is important to determine health beliefs and breast cancer risk levels of women to increase the frequency of early diagnosis. Women's health beliefs are thought to be a good guide for planning health education programs for nurses working in this area.

• 한국치위생학회지
• /
• 제13권3호
• /
• pp.525-534
• /
• 2013

Objectives : This study aimed to improve school health program by investigation of several variables through educational diagnostic factors which influence the level of subjective oral health perception and DMFT of students on the basis of PRECEDE model. Methods : A total of 286 high school students in Busan completed the self-reported questionnaire from September 3 to 28 in 2012. Results : 1. Social and epidemiologic diagnosis suggested that the level of subjective oral health perception of male students was not better than that of female students and DMFT number of the male was more than that of the female(p<0.001)(p<0.001). 2. Oral health diagnosis indicated that once a day tooth brushing group showed lower level of oral health perception(p<0.001) and high DMFT number(p<0.001). 3. Predisposing factor of educational diagnosis implied that more than 4 times a day snack intake group and sweet diet and soda friendly group showed lower level of oral health perception and high DMFT number(p<0.001). 4. Tooth brushing of the reinforcing factors had the most important effect on the level of oral health perception and the number of dental caries. Daily snack intake was the most important effect on DMFT number. Conclusions : The informed consent from each family was the important factor in implementing PRECEDE model. School health program improved oral health care. Oral health program can correct the risk oral health behavior in children and adolescents.

• 전기학회논문지
• /
• 제62권6호
• /
• pp.870-875
• /
• 2013

After introducing diagnosis equipment power failure prevention activities for distribution system have become more active. To do facility diagnosis and maintenance work more efficiently we need to evaluate reliability for the system and should determine the priority line with appropriate criteria. Thus, to calculate risk factor for the power distribution line that are composed of many component facilities its historical failure events for the last 5 years are collected and analysed. The failure statics show that more than 60% of various failures are related to environment factors randomly and about 20% of the failures are refer to the aging. As a strategic evaluation system reflecting these environmental influence is needed, a system on the basis of the probabilistic approach related statical variables in terms of failure rate and failure probability of electrical components is proposed. The figures for the evaluation are derived from the field failure DB. With adopting Bayesian rule we can calculate easily about conditional probability query. The proposed evaluation system is demonstrated with model system and the calculated indices representing the properties of the model line are discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• 한국전자통신학회논문지
• /
• 제17권5호
• /
• pp.809-814
• /
• 2022

주의력결핍장애는 산만함, 과잉행동을 보여주는 질환으로 소아청소년기에 진단 시 성인까지 증상이 지속되기 때문에 조기에 진단 및 치료를 시작하는 것이 중요하다. 그러나 소아는 정신적으로 미성숙하기 때문에 자가진단법 또는 측정 장비를 이용할 때 올바른 진단 데이터를 획득하기 어려운 문제가 있다. 이 논문에서는 ADHD 진단의 객관성과 정확도를 높이기 위하여 게임 콘텐츠를 이용하여 측정된 뇌전도 데이터에 대하여 CNN 모델링을 기반으로 분류하는 기법을 제시하고 실험하였다. 실험을 위하여 3D 네트워크 모델을 구성하였으며 평균적으로 97%의 정확도를 보여주었다.

• 한국인공지능학회지
• /
• 제11권1호
• /
• pp.1-7
• /
• 2023

In this paper, a study was conducted to compare the prediction model of cardiovascular disease occurrence. It is the No.1 disease that accounts for 1/3 of the world's causes of death, and it is also the No. 2 cause of death in Korea. Primary prevention is the most important factor in preventing cardiovascular diseases before they occur. Early diagnosis and treatment are also more important, as they play a role in reducing mortality and morbidity. The Results of an experiment using Azure ML, Logistic Regression showed 88.6% accuracy, Decision Tree showed 86.4% accuracy, and Support Vector Machine (SVM) showed 83.7% accuracy. In addition to the accuracy of the ROC curve, AUC is 94.5%, 93%, and 92.4%, indicating that the performance of the machine learning algorithm model is suitable, and among them, the results of applying the logistic regression algorithm model are the most accurate. Through this paper, visualization by comparing the algorithms can serve as an objective assistant for diagnosis and guide the direction of diagnosis made by doctors in the actual medical field.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2013년도 춘계학술대회 논문집
• /
• pp.500-501
• /
• 2013

• 한국가정과교육학회지
• /
• 제32권4호
• /
• pp.125-148
• /
• 2020

본 연구의 목적은 '가정과 초임교사의 역량모델'을 개발하는 데 있다. 이에 역량모델 개발 준비, 구체화, 타당성 검증, 역량진단의 4단계에 걸쳐 연구를 실시하였으며, 연구 결과는 다음과 같다. 첫째, 문헌연구를 통해 1차 역량모델(안)을 도출하고, FGI를 통해 2차 역량모델(안)을 도출하였다. 도출된 2차 역량모델(안)의 타당성을 검증한 결과, 본 연구에서 도출한 역량군과 역량, 역량의 정의는 내용타당도를 확보하고 있는 것으로 나타났다. 둘째, 가정과 초임교사에게 가장 우선적으로 요구되는 '최우선 역량'으로는 총 7개의 역량('수업설계역량', '수업실행역량', '학습지원역량', '교육과정운영역량', '학생평가역량', '자료개발 및 활용역량', '자기관리역량')이 도출되었다. 이상의 연구 결과를 종합하여 최종적으로 개발한 '가정과 초임교사 역량모델'은 총 4개의 역량군과 22개의 역량 및 역량 정의로 구성되었으며, 각 역량군별 역량은 가정과 초임교사들이 중요하다고 생각하는 역량일수록 상위에 제시하였다. 본 연구는 FGI와 역량진단을 통해 가정과 초임교사들의 역량에 대한 인식과 요구를 파악하고, 이를 반영하여 역량모델을 개발하였다는 데 의의가 있다.