• Computers and Concrete
• /
• 제31권5호
• /
• pp.405-417
• /
• 2023

The submerged floating tunnel (SFT) is tethered by mooring lines anchored to the seabed, therefore, the structural integrity of the anchor should be sensitively managed. Despite their importance, reaction forces cannot be simply measured by attaching sensors or load cells because of the structural and environmental characteristics of the submerged structure. Therefore, we propose an effective method for estimating the reaction forces at the seabed anchor of a submerged floating tunnel using a structural pattern model. First, a structural pattern model is established to use the correlation between tunnel motion and anchor reactions via a deep learning algorithm. Once the pattern model is established, it is directly used to estimate the reaction forces by inputting the tunnel motion data, which can be directly measured inside the tunnel. Because the sequential characteristics of responses in the time domain should be considered, the long short-term memory (LSTM) algorithm is mainly used to recognize structural behavioral patterns. Using hydrodynamics-based simulations, big data on the structural behavior of the SFT under various waves were generated, and the prepared datasets were used to validate the proposed method. The simulation-based validation results clearly show that the proposed method can precisely estimate time-series reactions using only acceleration data. In addition to real-time structural health monitoring, the proposed method can be useful for forensics when an unexpected accident or failure is related to the seabed anchors of the SFT.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.698-701
• /
• 2002

Subspace analysis (which includes PCA) seeks for feature subspace (which corresponds to the eigenspace), given multivariate input data and has been widely used in computer vision and pattern recognition. Typically data space belongs to very high dimension, but only a few principal components need to be extracted. In this paper I present a fast sequential algorithm for subspace analysis or tracking. Useful behavior of the algorithm is confirmed by numerical experiments.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1098-1101
• /
• 1993

The purpose of this work is to build a fuzzy model of a batch culture for a process control. The process is highly nonlinear system with large delay. This paper presents two methods of modeling the process behavior. One is a method of recognizing them by fuzzy rules that are contracted by the pattern analysis in consideration of skilled operators' way. The other is a method of predicting them by approximate linear models and fuzzy rules by statistic analysis.

• 융합경영연구
• /
• 제5권4호
• /
• pp.19-28
• /
• 2017

This study is aiming to suggest baseline date for the establishment of policy alternative to make healthy consumption life of the elderly through investigating and analyzing actual condition of consumption related with the awareness of health functional food such as purchase behavior and consumer's problems about health functional food. Under the assumption that the vitalization of health functional food market will become an important market in the present and in the future, the fundamental marketing information about elder consumers is more important than any other information that is essential for successful marketing to domestic corporations and senior policy experts. In addition, there was a fundamental significance to provide necessary basic data for health promotion of the elderly by offering information about rights and interests of elder consumers who are members of vulnerable social group or right choice of purchasing or intake. The limitations of this study are as follows. First, the subjects were selected who live in Gangwon-do with the age of 60 and over due to the limitation of sampling, and that might be shown local characteristics. Therefore, the study result could not be generalized on behalf of all elderly in Korea and it is difficult to apply the result to more segmented market. To solve this problem, studies containing sampling by regional groups might be needed.

• 한국산업융합학회 논문집
• /
• 제17권2호
• /
• pp.42-53
• /
• 2014

Robust voice recognition (RVR) is essential for a robot to communicate with people. One of the main problems with RVR for robots is that robots inevitably real environment noises. The noise is captured with strong power by the microphones, because the noise sources are closed to the microphones. The signal-to-noise ratio of input voice becomes quite low. However, it is possible to estimate the noise by using information on the robot's own motions and postures, because a type of motion/gesture produces almost the same pattern of noise every time it is performed. In this paper, we propose an RVR system which can robustly recognize voice by adults and children in noisy environments. We evaluate the RVR system in a communication robot placed in a real noisy environment. Voice is captured using a wireless microphone. Navigation Strategy is shown Obstacle detection and local map, Design of Goal-seeking Behavior and Avoidance Behavior, Fuzzy Decision Maker and Lower level controller. The final hypothesis is selected based on posterior probability. We then select the task in the motion task library. In the motion control, we also integrate the obstacle avoidance control using ultrasonic sensors. Those are powerful for detecting obstacle with simple algorithm.

• 대한간호학회지
• /
• 제27권4호
• /
• pp.843-856
• /
• 1997

The purpose of this study was to explore the subjective opinions related to of smoking behavior of university students with a history of smoking. The research period was from Feb, 1. 1996 to Sep. 10. 1997. The research method used was Q-methodology. The process of the research was as follows : 1. Collection of concourse : The statement of self-reference was derived from face to face interviews with 50 university students. Statement were categorized by researcher according to semantics. 2. Extraction of Q-sample : 38 of the self-reference statements from the 32 categories of the Q-population were selected. 3. Selection of P-sample : 30 of university students were selected by consideration of diversity in sociodemographic background. 4. Based on a 1 to 9 point scale, the selected university students were made to participate in Q-sorting. 5. Analysis of Q-type was obtained by use of the QUANAL program. The results of this study revealed as follows : There are three types of smoking behavior of Korean university students. 1. The first type focused on the right of the individual to smoke and the lack of recognition of smoking behavior as a health hazard. 2. The second type cared about smoking behavior as a hazard to health. 3. The third type was habitual smoker. They are bored and smoke habitually. It is suggested that the results of this study may contribute to the development of strategies for the purpose of decreasing the incidence of smoking of university students.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 춘계종합학술대회
• /
• pp.391-394
• /
• 2004

인터넷의 급속한 확장으로 인해 네트워크 공격기법의 패러다임의 변화가 시작되었으며 새로울 공격 형태가 나타나고 있으나 대부분의 침입 탐지 기술은 오용 탐지 기술을 기반으로 하는 시스템이주를 이루고 있어 알려진 공격 유형만을 탐지하고, 새로운 공격에 능동적인 대응이 어려운 실정이다. 이에 새로운 공격 유형에 대한 탐지력을 높이기 위해 인체 면역 메커니즘을 적용하려는 시도들이 나타나고 있다. 본 논문에서는 데이터 마이닝 기법을 이용하여 네트워크 패킷에 대한 정상 행위 프로파일을 생성하고 생성된 프로파일을 자기공간화 하여 인체면역계의 자기, 비자기 구분기능을 이용해 자기 인식 알고리즘을 구현하여 이상행위를 탐지하고자 한다. 자기인식 알고리즘의 하나인 Negative Selection Algorithm을 기반으로 anomaly detector를 생성하여 자기공간을 모니터하여 변화를 감지하고 이상행위를 검출한다. DARPA Network Dataset을 이용하여 시뮬레이션을 수행하여 침입 탐지율을 통해 알고리즘의 유효성을 검증한다.

• 품질경영학회지
• /
• 제20권2호
• /
• pp.94-108
• /
• 1992

This study involves an experiment for the cognitive experiment design and the human reliability in software engineering. Its overall objectives are to analyze common-cause human domain error and reliability in human-software interaction. A laboratory study was performed to analyze software engineers' task behavior in software production and to identify software design factors contributing to the effects in common cause failure redundancy. Common-cause model and its function were developed, then the main experiment using programming experts was conducted in order to define a new cognitive paradigm, in the aspects of identification, pattern recognition, and behavior domain for human reliability and quality control in software development. The results and analytical procedures developed in this research can be applied to reliability improvement and cost reduction in software development for many applications. Results are also expected to provide guidelines for software engineering quality control and for more effective design of human-software interface system.

• 대한예방한의학회지
• /
• 제20권1호
• /
• pp.1-10
• /
• 2016

Objectives : The purposes of this study were to investigate the recognition of Mibyeong, symptom, management plan and correlation between quality of life and health condition, and to suggest a plan for managing Mibyeong status. Methods : Participants were recruited based on the same sampling methods used on the previous study performed in 2013 based on area, gender and age. Questionnaires were collected by Gallup Korea professional surveyor through face-to-face interviews. The questionnaires contain questions about the recognition of Mibyeong, symptom, management plan and the quality of life in accordance with the relevant health conditions. Descriptive statistics were used for data analysis and the results were expressed as percentage ratios (%). Results : 1,100 of people were acquired in 2015. The responses for "First time to hear of Mibyeong" have shown that the percentage were reduced from 80% to 67% compared with 2013 data. The ratio of Mibyeong's symptoms in 2015 were similar to 2013. we suggested some ways to deal with the Mibyeong status including behavior adjustment (non smoking, non alcohol, control sleep pattern), herbal tea, health functional food, exercise, preventive health care (qi-gong, yoga), meditation, home health care medical device (hot-pack, seat device for fumigation, massager), and medical service (hospital, medical clinic oriental medical clinic). Almost people showed that positive opinion with them. There were significant correlation between quality of life with the health status rather than Mibyeong or disease group. Conclusions : This study was performed through scientific questionnaires collected in 2013 and 2015 to investigate people's understanding of Mibyeong as a present condition in Korean public. Some questions had significantly different responds between both years while others showed similar trends for both years. These results suggest that the concept of Mibyeong in oriental medicine could provide a management mechanisms that help people to manage the Mibyeong status.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권11호
• /
• pp.1147-1155
• /
• 2005

본 논문은 단순한 형태의 개인 착인 및 검증방법의 한계를 극복하여 절도나 누출에 의해 도용될 수 없고 변경되거나 분실할 위험성이 없는 새로운 형태의 인증 방법인 홍채인식을 연구하였다. 사람의 홍채는 태어날 때 한번 정해지면 평생 변화하지 않는 특성을 가지고 있으며, 개개인별로 모양이 모두 다른 것으로 알려져 있다. 이에, 본 논문에서는 홍채영상 취득 시 조명에 의한 동공의 크기 변화에 민감하지 않은 2차원의 홍채패턴을 취득하여, 2차 가버 웨이블릿과 퍼지 선형판별분석기법(LDA)을 이용하여 특징 벡터를 추출하고 인식한다. 인식과정에서는 상관관계 계수를 이용하여 다른 홍채의 특징간과 매칭값을 측정하고 유사도가 가장 큰 대상을 찾게 된다. 이때, 입력영상에 대하여 4개 방향의 가버 웨이블릿을 거쳐 얻어진 4개의 상관관계 계수 간 중 가장 큰 값을 갖는 대상자를 인식 대상자로 선정하므로 오인식될 확률을 최소화 할 수 있다. 제안한 알고리듬의 유용성을 확인하기 위해 대상자 50명에 대하여 각각 6회씩 촬영한 두 가지 데이타베이스(CASIA, CBNU)를 이용하였으며, 실험 결과 $90\%$ 이상의 인식률을 얻었다.