• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1998년도 추계학술대회
• /
• pp.201-202
• /
• 1998

In this paper we suggested an automated method for detecting and counting rapid eye movement(REM) using EOG during sleep. This method is formulated by two step fuzzy logic. At first step, the velocity and the distance of single channel eye movement are used for the fuzzy input to get the possibility of being REM at each EOG. At second step, the two possibility values of both EOG from the first step and the correlation coefficient of both eye movements are used for the fuzzy logic input, and the output is the final possibility of being Rapid Eye Movement. We applied this algorithm to the normal and narcoleptic sleep data and compared the difference. We found the possibility that the count of REM can be a parameter that has significant physiological meanings.

• 한국물환경학회지
• /
• 제18권3호
• /
• pp.283-290
• /
• 2002

In this study, home-made detection system by means of noble FIA is introduced on the measurement of toxic nitrite in the water samples collected from the area of Kwangju. As the standard calibration between 30 to 1000 ppb, the linearity has been shown more than 0.9999 as the correlation coefficient($R^2$) with the detection limit 1.5 ppb(S/N>2). The distribution of sample concentration was monitored as N.D. - 123 ppb which is wide span of concentrations in field water samples. The low level of nitrite is hardly detectable with other expensive sophisticated instruments including ion chromatography. Whereas the result of high concentration brings forth the necessity monitoring constantly our precious water resources. Successfully, the FIA system has played a very important role detecting wide span of nitrite in water sample. This technique can be adopted for controlling our environment in the near future.

• 인터넷정보학회논문지
• /
• 제8권1호
• /
• pp.125-132
• /
• 2007

본 논문은 가중 퍼지소속함수 기반 신경망(neural network with weighted fuzzy membership functions, NEWFM)을 이용하여 심전도(ECG) 신호로부터 조기심실수축(premature vedtricular contractions, PVC)을 자동 탐지하는 방안을 제시하고 있다. NEWFM은 MIT-BIH 데이터베이스의 부정맥 심전도를 웨이블릿 변환(wavelet transform, WT)한 계수로부터 학습하여 정상 파형과 PVC 파형을 구분한다. 비중복면적 분산 측정법을 적용하여 중요도가 가장 높은 웨이블릿 변환의 d3과 d4의 8개 계수를 추출하였다. 이들 특징입력을 3개의 실험군에 사용하여 각각 99.80%, 99.21%, 98.78%의 신뢰성 있는 전체분류율을 나타내었고, 이는 각 실험군에 대한 특징입력의 종속성이 적음을 보여준다. 추출된 8개 계수의 ECG 신호 구간과 퍼지소속함수를 제시함으로써 특징입력에 대한 명시적인 해석을 가능하게 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.2948-2963
• /
• 2015

In the field of computer vision, visual surveillance systems have recently become an important research topic. Growth in this area is being driven by both the increase in the availability of inexpensive computing devices and image sensors as well as the general inefficiency of manual surveillance and monitoring. In particular, the ultimate goal for many visual surveillance systems is to provide automatic activity recognition for events at a given site. A higher level of understanding of these activities requires certain lower-level computer vision tasks to be performed. So in this paper, we propose an intelligent activity recognition model that uses a structure learning method and a classification method. The structure learning method is provided as a K2-learning algorithm that generates Bayesian networks of causal relationships between sensors for a given activity. The statistical characteristics of the sensor values and the topological characteristics of the generated graphs are learned for each activity, and then a neural network is designed to classify the current activity according to the features extracted from the multiple sensor values that have been collected. Finally, the proposed method is implemented and tested by using PETS2013 benchmark data.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제33권10호
• /
• pp.877-885
• /
• 2006

최근에 대화형 에이전트에서 사용자 질의의 주제 추론을 위하여 베이지안 네트워크가 효과임이 발표되었다. 하지만 베이지안 네트워크는 설계에 있어서 많은 시간이 소요되며, 스크립트(대화를 위한 데이타베이스)의 추가 변경시에는 베이지안 네트워크도 같이 수정해야 하는 번거로움이 있어 대화형 에이전트의 확장성을 저해하고 있다. 본 논문에서는 스크림트로부터 베이지안 네트워크를 자동으로 생성함으로써 베이지안 네트워크를 이용한 대화형 에이전트의 확장성을 높이는 방법을 제안한다. 제안한 방법은 베이지안 네트워크의 구성노드를 계층적으로 설계하고, Noisy-OR gate를 사용하여 베이지안 네트워크의 조건부 확률 테이블을 구성한다. 피험자 10명이 대화형 에이전트를 위한 베이지안 네트워크를 수동 설계한 것과 비교한 결과 제안하는 방법이 효과적임을 알 수 있었다.

• 한국산학기술학회논문지
• /
• 제11권5호
• /
• pp.1873-1880
• /
• 2010

최근 인간 중심의 정보화 사회가 USN 기술의 발전과 더불어 유비쿼터스 컴퓨팅 사회로 급격히 변모하고 있다. USN 응용 웹 서비스는 USN 기술을 이용하여 환경과 상황의 자동 인지를 통해 편리함을 제공하며 실시간 관리를 통해 최적의 서비스를 제공함으로써 인간 생활의 편리성과 안전성을 향상시킨다. 따라서 이러한 기술을 이용한 USN 응용 웹 서비스는 생활 전반에 다양하게 적용된다. 본 논문에서는 USN을 기반으로 수집된 메타 데이터와 센싱 데이터에 대하여 사용자들의 요구사항을 분석하여 시나리오를 구현하고 각 시나리오에 가장 효과적으로 대응 할 수 있는 시각화를 구현하였다.

• 한국태양에너지학회 논문집
• /
• 제28권3호
• /
• pp.45-52
• /
• 2008

In order to clarify characteristics of variation in wind energy over a long-term period, an investigation was carried out at Seoguang site on Jeju island. The wind data for 10 years from Automatic Weather System (AWS) were analyzed for each year. The variation in the annual energy production (AEP) for the 2 MW wind turbine was estimated through statistical work. The result shows that the range of the yearly average wind speed at 15 m above ground level for 10 years was from -22.6% to +13.7%, which is wider range than that in Japan. The coefficient of variation for the AEP was 22.7%, which is about twice of that for the yearly average wind speed. Therefore, for estimating the wind energy potential accurately at a given site, the wind data should be analyzed over a long-term period based on the data from the meteorological station.

• 대한안전경영과학회지
• /
• 제10권4호
• /
• pp.189-198
• /
• 2008

At present, companies write daily work record or use bar-code in order to collect distribution flow data in real time. However, it needs additional works to check the record or read the bar-code with a scanner. In this case, human error could decrease accuracy of data and it would cause problems in reliability. To solve this problem, RFID (Radio Frequency Identification) is introduced in many automatic recognition sector recently. RFID is a technology that identification data is inserted into micro-mini IC chip and recognize, trace, and manage object, animal, or person using wireless frequency. This is being emerged as the core technology in future ubiquitous environment. This study is intended to suggest RFID application method in franchise business. Traceability and visibility of individual product are supplied based on EPCglobal network. It includes DW system which supplies various assessment data about product in supply chain, financial transaction system which is based on product transaction and position information, and RFID middleware which refines and divides product data from RFID tag. With the suggested application methods, individual product's profile data are supplied in real time and it would boost reliability to customer and make effective cooperation with existing operation systems (SCM, CRM, and e-Business) possible.

• 제어로봇시스템학회논문지
• /
• 제21권11호
• /
• pp.989-995
• /
• 2015

Due to the recent increase of the importance and demand of security services, the importance of a surveillance monitor system that makes an automatic security system possible is increasing. As the market for surveillance monitor systems is growing, price competitiveness is becoming important. As a result of this trend, surveillance monitor systems based on an embedded system are widely used. In this paper, an object detection algorithm based on an embedded system for a surveillance monitor system is introduced. To apply the object detection algorithm to the embedded system, the most important issue is the efficient use of resources, such as memory and processors. Therefore, designing an appropriate algorithm considering the limit of resources is required. The proposed algorithm uses two background models; therefore, the embedded system is designed to have two independent processors. One processor checks the sub-background models for if there are any changes with high update frequency, and another processor makes the main background model, which is used for object detection. In this way, a background model will be made with images that have no objects to detect and improve the object detection performance. The object detection algorithm utilizes one-dimensional histogram distribution, which makes the detection faster. The proposed object detection algorithm works fast and accurately even in a low-priced embedded system.

• 전자공학회논문지 IE
• /
• 제45권4호
• /
• pp.60-67
• /
• 2008

피부색은 자동화된 얼굴 인식을 위한 매우 중요한 정보 중의 하나이다. 본 논문에서는 컬러 정보와 피부색 모델을 이용한 피부 영역 검출 기법을 제안하였다. 제안된 방법은 적응적 조명 보정 기법을 통해 피부색 영역의 검출 성능을 개선하였고 전처리 필터를 적용하여 피부색이 아닌 영역을 먼저 제거시킴으로써 처리 속도를 향상시켰다. 또한 피부색 검출 성능이 우수한 ST 컬러 공간을 수정하여, 보다 정확한 피부색 영역을 추출할 수 있도록 하였다. 제안된 방법의 실험 결과 기존의 방법과 비교하여 보다 우수한 검출 결과를 나타냈으며, 처리 속도 또한 약 $33{\sim}48%$ 향상시킬 수 있었다.