• 자동차안전학회지
• /
• 제14권3호
• /
• pp.60-64
• /
• 2022

In the automotive industry, the development of automobiles to meet safety requirements is becoming increasingly complex. This is because quality evaluation agencies in each country are continually strengthening new safety standards for vehicles. Among these various requirements, collision safety must be satisfied by controlling airbags, seat belts, etc., and can be defined as post-crash safety. Apart from this safety system, the Advanced Driver Assistance Systems (ADAS) use advanced detection sensors, GPS, communication, and video equipment to detect the hazard and notify driver before the collision. However, research to improve passenger safety in case of an accident by using the sensor of active safety represented by ADAS in the existing passive safety is limited to the level that utilizes the sudden braking level of the FCA (Forward Collision-avoidance Assist) system. Therefore, this study aims to develop logic that can improve passenger protection in case of an accident by using ADAS information and driving information secured before a collision. The proposed logic was constructed based on LSTM deep learning techniques and trained using crash test data.

• 한국전자통신학회논문지
• /
• 제16권6호
• /
• pp.1255-1262
• /
• 2021

학업을 중단하는 학생들의 비율이 해마다 증가하고 있어 대학은 학업중단을 막기 위하여 위험요소를 파악하고 이를 사전에 제거하기 위해 노력하고 있다. 그러나 특정 위험요소의 단변수 분석을 통해 위기학생을 관리하고 있어 예측이 부정확한 문제가 발생하고 있다. 본 연구에서는 이러한 문제점을 해결하기 위하여 학업중단 위험요소를 파악하고 학업중단 예측을 위해 머신러닝 방법을 통해 다변수 분석을 실시한다. 또한 다양한 예측방법별로 성능평가를 수행하여 최적화 방법을 도출하고 학업중단을 발생시키는 위험요소간의 연관성과 기여도를 평가한다.

• 정보교육학회논문지
• /
• 제6권1호
• /
• pp.42-52
• /
• 2002

효과적인 음악 감상 학습을 위해서는 음악 수업 시간의 감상뿐만 아니라 시간과 공간의 제약 없이 반복적인 음악 감상이 가능해야하며, 음악 감상 요소에 따른 다양한 멀티미디어 감상 학습 자료를 필요로 한다. 그러나 단위 시간에 개별화되고 반복적인 감상 학습이 어려울 뿐만 아니라 개별화된 감상 학습 자료도 부족한 실정이다. 이러한 문제를 해결하기 위해서 초등학교 음악 감상 학습에 필요한 학습 자료를 공유하고 음악 감상 학습 요소를 포함하는 초등학교 음악 감상 학습 시스템이 필요하다. 그러므로 본 논문에서는 초등학교 음악 감상 학습 요소를 분석하여 자기 주도적이고 능동적인 음악 감상학습이 가능하며, 또한, 온라인 상에서 학생이 올린 감상문을 교사가 평가함으로써 성취감과 자신감을 갖게 하여 즐거운 음악 활동을 경험할 수 있도록 초등학교 음악 감상 학습 시스템을 설계 및 개발하였다. 그리고 이를 초등학교에 적용해 보고 그 결과를 분석하였다.

• 한국콘텐츠학회논문지
• /
• 제7권7호
• /
• pp.104-113
• /
• 2007

본 연구는 사회복지분야에서의 효과적인 이러닝 구축과 개발을 위한 사례연구이다. K-이러닝센터에서 2006년도부터 1, 2학기 2007년도 1학기 운영된 [사회복지개론]과목과 관련된 전체 운영참여자(교수, 학생, 이러닝 전문가, 학습관리시스템운영자, 사례이러닝 운영자)가 자료수집에 참여하였다. 사회복지 영역에서의 e-Learning 커스터마이징화를 위하여 질적, 양적 실증연구를 진행하였다는데 본 연구의 의의가 있다. 분석결과, 사회복지개론 이러닝을 설계하기 위해서는 체계적 준비과정, 현장중심 학습내용, 시간 효율적인 학습관리, 학습자들 간의 상호작용을 통한 학습효과증진, 과제를 통한 과정평가 중심의 평가방법, 기술적 지원과 교육 등의 필요성이 제기되었다. 이를 위한 구체적인 전략으로 상호작용 학습모형 개발, 커스터마 이징화된 모형개발, 운영과정의 표준화와 체계화, 교수자들의 정보교환, 과제중심 과정평가체계구축, 운영 참여자의 협력적 작업시스템 기회의 정규화 등이 제시되었다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 춘계학술대회 학술발표 논문집
• /
• pp.267-270
• /
• 1997

In this paper, we proposed an optimazation method using Genetic Algorithm for nonlinear system modeling. Fuzzy Neural Network(FNNs) was used as basic model of nonlinear system. FNNs was fused of Fuzzy Inference which has linguistic property and Neural Network which has learning ability and high tolerence level. This paper, We used FNNs which was proposed by Yamakawa. The FNNs was composed Simple Inference and Error Back Propagation Algorithm. To obtain optimal model, parameter of membership function, learning rate and momentum coefficient of FNNs are tuned using genetic algorithm. And we used simplex algorithm additionaly to overcome limit of genetic algorithm. For the purpose of evaluation of proposed method, we applied proposed method to traffic choice process and waste water treatment process, and then obtained more precise model than other previous optimization methods and objective model.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1989년도 한국자동제어학술회의논문집; Seoul, Korea; 27-28 Oct. 1989
• /
• pp.407-412
• /
• 1989

Using the knowledge base which contains the patterns and data of the past experience of a plant, a learning control method is suggested. The knowledge for controlling a plant is stored to the knowledge base and continually modified after performance evaluation of an applied control input. The performance of the resultant knowledge based control system is examined by an application to process.

• 한국정보시스템학회지:정보시스템연구
• /
• 제30권3호
• /
• pp.93-112
• /
• 2021

Purpose Recently, many organizations are actively adopting enterprise architecture (EA) as a methodology to manage IT assets and build IT-based business system. This study intended to empirically examine how the role of EA operating unit and utilization capability of organizational members impact on system performance at the post-adoption stage. A balanced score card (BSC) is being used as a framework for a company's key performance indicator (KPI). Design/methodology/approach This study tried to investigate the causal relationship between the four perspectives of the balanced scorecard as an influencing factor of the introduction of the Enterprise Resource Planning (ERP) on the financial value. In particular, the mediating effect between the customer's point of view and the business process point of view was investigated between the learning growth point of view and the financial point of view, and the interaction effect (regulating effect) of strategic linkage in the system introduction process was investigated. Findings The results of the study were first, that the organizational learning and growth perspective had a positive effect on the customer perspective, business process, and financial perspective. In addition, the customer perspective and the process perspective also had a positive influence on the financial perspective. Second, between the learning growth and financial perspectives, the customer perspective and the process perspective showed a partial mediating effect. Third, as for strategic linkage, the interaction effect between the customer perspective, the learning growth perspective, and the process perspective and the financial perspective was not significant. The results of this study are expected to provide a framework for performance evaluation to organizations that have introduced ERP systems.

• 간호행정학회지
• /
• 제12권1호
• /
• pp.41-51
• /
• 2006

Purpose: The purposed of this study was to develop and evaluate a Web-based for medical terminology educational program. Method: For the development of this program, the NBISD model was applied as a basic model and WBI ID Process Action model was applied. It was executed for 15 weeks along with off-line lectures. After the operation of this program to 210 nursing students, learners' responses were analyzed twice(at 5th week and 15th week). Result: The satisfaction with this program was slightly above the center point. But the structure of system and composition of design were high score. The results of the final evaluation were more positive than those of the interim one. This program have the advantage of easy accessibility and easy understandability with picture and testing. Conclusions: This study proved the importance of the suitability of learning contents and learning form in developing WBI programs and showed possibility for applying WBI to medical terminology. In order to enhance the effects of Web-based medical terminology educational program for, it is necessary to perform analytic comparison with the effect of WBI based on self-directed learning.

• Journal of Platform Technology
• /
• 제9권1호
• /
• pp.23-31
• /
• 2021

최근 몇 년간 국내 산업에서 센서 오작동과 환경 모니터링의 부재로 인한 유해가스 방출 등으로 인명피해가 발생하고 이러한 유해 물질이 감지할 수 있는 환경 센서의 평가는 내구성 시험 및 위해성 검사 위주이기 때문에 센서의 측정 데이터에 대한 신뢰성 검증에는 한계가 있다. 본 플랫폼은 환경센서의 신뢰성을 검증하고 수집한 데이터를 통해 환경 분석을 위해 주요한 10종의 물질에 대해 측정하는 센서 보드와 각 센서의 성능 검증 체계를 설계하였다. 데이터를 수집하기 위해 센서 보드로 수집된 데이터를 LoRa 통신을 이용하여 데이터 신뢰성 평가 및 검증을 위한 서버로 전달되고 전달된 데이터를 모니터링 하기 위한 센서 데이터 플랫폼의 프로토타입을 제작하였다. 그리고 수집한 데이터를 이용하여 machine learning 기법을 통해 대기 환경을 분석하고 예측한다.

• 한국IT서비스학회지
• /
• 제21권4호
• /
• pp.75-90
• /
• 2022

From the past to the present, reviews have had much influence on consumers' purchasing decisions. Companies are making various efforts, such as introducing a review incentive system to increase the number of reviews. Recently, as various types of reviews can be left, reviews have begun to be recognized as interesting new content. This way, reviews have become essential in creating loyal customers. Therefore, research and utilization of reviews are being actively conducted. Some studies analyze reviews to discover customers' needs, studies that upgrade recommendation systems using reviews, and studies that analyze consumers' emotions and attitudes through reviews. However, research that predicts the future using reviews is insufficient. This study used a dataset consisting of two reviews written in pairs with differences in usage periods. In this study, the direction of consumer product evaluation is predicted using KoBERT, which shows excellent performance in Text Deep Learning. We used 7,233 reviews collected to demonstrate the excellence of the proposed model. As a result, the proposed model using the review text and the star rating showed excellent performance compared to the baseline that follows the majority voting.