• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.832-834
• /
• 2005

본 논문에서는 여러 가지 표정으로 입력되어지는 얼굴 이미지를 효율적으로 인식시키는 작업을 수행하는 방법에 대한 내용을 소개하고 있다. 각 얼굴 이미지들은 상황에 따라 많은 표정에 영향 성분을 포함하고 있다. 이런 각기 특성이 다른 얼굴 이미지들의 효율적인 인식을 위하여, 특징 점을 선정을 한 후 실험 진행을 하면 표정에 영향을 많이 받는 이미지를 구분할 수 있다. 여기서 제안하는 방법은 표정이 많이 포함된 이미지에 대하여 표정에 영향을 많이 미치는 특징 점과 그 특징 점영역에 와핑 기법을 처리함으로써 표정이 있는 이미지를 인식하는 방법을 제안한다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.221-226
• /
• 2009

Not many years ago, people found the contemporary technology expensive and difficult to use in collaborative type of meetings. Today, with the technology advanced to high standards and accessible at cheaper price, its adaption is becoming more and more ubiquitous with wide range of applications. Today's meeting rooms are not just plain old telephone systems with microphones and speakers. Today's meeting rooms are smart and intelligent. They can identify the participants; they can provide natural view of remote participants; they can proactively manage resources for collaboration and so on. More effective collaboration is possible with deployment of devices like high-definition cameras, advanced displays, sensors, gigabit networks, trackers, pointers, and high-end audio devices. Devices alone are not enough in the meeting rooms. We need software infrastructure to manage the devices and meeting contexts. One such software infrastructure is SMeet, a Smart Meeting space, which we have developed to provide an effective multi-party remote collaboration environment. Networked display systems are used in such advanced collaboration environment for better visualization. In this paper we discuss a novel approach to control and manage networked display systems in SMeet environment.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.253-255
• /
• 2003

We address an integrated multimedia framework based on a software agent platform for context-aware multimedia computing. We adopt the FIPA (Foundation for Intelligent Physical Agents) platform which provides agent communications and management mechanisms. In order to express context information, we use MPEG-21 metadata for describing user characteristics and usage environment. We encapsulate such context information as a FIPA message to be delivered between agents. Based on context information, appropriate multimedia content delivery becomes possible. We present our system implementation with a use case scenario and show that our proposed framework is effective for context-aware multimedia computing so that personalization of multimedia consumption can be possible.

• Journal of the Korea Safety Management & Science
• /
• v.12 no.4
• /
• pp.175-181
• /
• 2010

The government have plans to improve the railway transport capacity and transport hub for the sustainable national transport and logistics system. Specially, there are much efforts to improve transportation capacity such as high speed transportation of rail freight, enlargement of BT train, development of double stack train, etc. between railway transport hubs. If the transport capacity between railway logistics hubs is increased as planned, we must increase the handling capacity of railway hub terminals. But there are limits to enlarge the terminal infrastructure because of investment scale, location circumstances and urban development plans. To ensure the capacity, with the minimum required enlargement of infrastructure, it is necessary to extremely increase the efficiency of terminal operations. For improving the efficiency, we have to introduce the efficient terminal operation systems based on u-IT and operation optimize technologies. In this paper, we analyse the issues and problems of railway terminals(including ICD) and suggest the concept of intelligent railway terminal and the construction components of technology.

• Food Science of Animal Resources
• /
• v.32 no.4
• /
• pp.448-457
• /
• 2012

The predictive ability for off-flavor development and quality change of ground beef was evaluated using a microbial time temperature indicator (TTI). Quality indices such as off-flavor detection (OFD) time, color, pH, volatile basic nitrogen (VBN), aerobic mesophilic bacteria (AMB) counts, and lactic acid bacteria (LAB) counts were measured during storage at 5, 10, 15, and $25^{\circ}C$, respectively. Arrhenius activation energies (Ea) were estimated for temperature dependence. The Ea values for TTI response (changes in titratable acidity (TA)), VBN, AMB counts, LAB counts, and freshness, which is defined based on OFD time for quality indices of ground beef, were 106.22 kJ/mol, 58.98 kJ/mol, 110.35 kJ/mol, 116.65 kJ/mol, and 92.73 kJ/mol, respectively. The Ea of microbial TTI was found to be closer to those of the AMB counts, LAB counts, and freshness. Therefore, AMB counts, LAB counts, and freshness could be predicted accurately by the microbial TTI response due to their Ea similarity. The microbial TTI exhibited consistent relationships between its TA change and corresponding quality indices, such as AMB counts, LAB counts, and freshness, regardless of storage temperature. Conclusively, the results established that the developed microbial TTI can be used in intelligent packaging technology for representing some selected quality indices of ground beef.

• Proceedings of the KIPE Conference
• /
• 2012.07a
• /
• pp.576-577
• /
• 2012

본 연구에서는 자동차 납축전지를 위한 지능형 배터리 센서(Intelligent Battery Sensor; IBS) 모듈 기능검사장비를 개발한다. 이를 위해 IBS 모듈에 대한 기능 및 특성평가를 위한 기능 검사 시스템을 구축하고 LABVIEW를 이용한 기능검사 프로그램을 개발한다. IBS를 이용한 감시 제어 시스템은 배터리의 상태를 모니터링하여 최적의 조건을 유지하고 문제 발생 시에 미리 조치할 수 있다. 배터리의 상태 파라미터로는 전압, 전류, 온도를 사용한다. 감시 제어 시스템은 PC를 이용하여 환경을 구축하였으며 LabView를 이용한 GUI(Graphic User Interface)를 구축하여 배터리 데이터를 모니터링하고 저장, 관리가 편리한 장점을 가진다.

• Advances in nano research
• /
• v.12 no.5
• /
• pp.489-499
• /
• 2022

Nanofluids have recently triggered a substantial scientific interest as cooling media. However, their stability is challenging for successful engagement in industrial applications. Different factors, including temperature, nanoparticles and base fluids characteristics, pH, ultrasonic power and frequency, agitation time, and surfactant type and concentration, determine the nanofluid stability regime. Indeed, it is often too complicated and even impossible to accurately find the conditions resulting in a stabilized nanofluid. Furthermore, there are no empirical, semi-empirical, and even intelligent scenarios for anticipating the stability of nanofluids. Therefore, this study introduces a straightforward and reliable intelligent classifier for discriminating among the stability regimes of alumina-water nanofluids based on the Zeta potential margins. In this regard, various intelligent classifiers (i.e., deep learning and multilayer perceptron neural network, decision tree, GoogleNet, and multi-output least squares support vector regression) have been designed, and their classification accuracy was compared. This comparison approved that the multilayer perceptron neural network (MLPNN) with the SoftMax activation function trained by the Bayesian regularization algorithm is the best classifier for the considered task. This intelligent classifier accurately detects the stability regimes of more than 90% of 345 different nanofluid samples. The overall classification accuracy and misclassification percent of 90.1% and 9.9% have been achieved by this model. This research is the first try toward anticipting the stability of water-alumin nanofluids from some easily measured independent variables.

• 한국IT서비스학회:학술대회논문집
• /
• 2007.05a
• /
• pp.488-493
• /
• 2007

최근 정보통신 기술의 발전으로 인하여 어느 장소에서든 컴퓨터 또는 무선장치를 사용하여 집안의 지능형 가전기기들을 점검하고 제어 할 수 있는 수준까지 이르렀다. 이와 같은 서비스를 제공하기 위한 요소기술 중에 마이크로소프트사에서 발표한 UPnP(Universal Plug & Play)는 TCP/IP 프로토콜을 기반으로 하여 각 지능형 가전기기에 IP주소를 할당하여 어느 곳에서나 누구나 편리하게 지능형 가전기기의 서비스를 이용할 수 있도록 해준다. 본 논문에서는 UPnP 미들웨어 기반의 홈 네트워크에서 웹 기반의 인터페이스를 통해 지능형 가전기기를 쉽게 관리할 수 있는 홈 게이트웨이와 지능형 가전기기 간 연동 시스템을 설계하고 구현한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.477-481
• /
• 2007

A background is a part where do not vary too much or frequently change in an image sequence. Using this assumption, it is presented a background acquisition algorithm for not only static but also dynamic view in this paper. For generating background, we detect a region, where has high correlation rate compared within selected region in the prior pyramid image, from the searching region in the current image. Between a detected region in the current image and a selected region in the prior image, we calculate movement vector for each regions in time sequence. After we calculate whole movement vectors for two successive images, vector histogram is used to determine the camera movement. The vector which has the highest density in the histogram is determined a camera movement. Using determined camera movement, we classify clusters based on pixel intensities which pixels are matched with prior pixels following camera movement. Finally we eliminate clusters which have lower weight than threshold, and combine remained clusters for each pixel to generate multiple background clusters. Experimental results show that we can automatically detect background whether camera move or not.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.76-79
• /
• 2001

This paper is concerned with a stability analysis of Madam Type fuzzy systems. It Introduces the canonical form of an unforced fuzzy system and its stability theorem suggested in the previous study. Then it gives new simplified stability conditions based on the Lyapunov function method. A common positive definite matrix in the stability conditions is searched by the LMI method.