• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1350-1353
• /
• 2013

자동차의 안전성 향상에 대한 연구는 오랜 기간 다양한 분야에서 진행되고 있다. 이 시스템은 단일 카메라를 이용하여 차선을 감지함으로써 차선 침범을 방지한다. 시스템은 파티클 필터를 이용해 도로 모델 파라미터를 조정하고 두 개의 detector가 도로 모델의 일치도를 계산한다. Detector는 차선의 모양과 색이라는 대표적인 특징을 이용한다. 파티클 필터를 전 프레임에서 사용한 모델 파라미터를 이용하여 신속한 처리를 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.679-682
• /
• 2010

피부 영역 검출 기술은 생체 인식 기술의 하나로서 얼굴 자동 인식 혹은 손 모양 자동 인식 등을 위해 사용되고 있다. 일반적으로 색상을 이용하여 피부 영역을 검출하기 위해서는 다양한 피부색 샘플을 이용해 구해진 피부색 모델을 이용한다. 하지만 피부색은 사람마다 다르고, 조명과 같은 주변 환경의 영향도 받기 때문에 다양한 영상에 하나의 고정된 피부색 모델을 적용하여 피부 영역을 검출하기에는 한계가 있다. 이러한 문제점을 해결하기 위해 본 논문에서는 영상 피드백 방법을 이용하여 영상에 적응적인 피부색 모델을 구한 뒤 이를 적용하여 피부 영역을 추출하는 방법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.53-56
• /
• 2009

본 연구는 차세대 네트워크 환경에서 동적인 상황에 관련된 지식서비스를 제공하기 위해 서술논리와 SWRL 기반의 온톨로지 모델 프레임워크를 제공하여 추론과 상황 결정에 있어 온톨로지 기반의 지식베이스가 유용함을 제시한다. 기존 대부분의 온톨로지 모델은 단일 온톨로지나 정적인 온톨로지를 중심으로 모델링되었으나 본 연구에서 제시하는 온톨로지 모델은 서비스를 중심으로 동적인 상황에 능동적으로 대처할 수 있는 온톨로지 구조와 사용자를 중심으로 다양하게 변화하는 지식을 동적으로 처리할 수 있는 지식표현 패턴을 제안하여 공간과 시간에 따른 동적인 상황서비스가 적합함을 보여주었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.345-347
• /
• 2021

단일 이미지 초해상도는 딥러닝의 발전과 함께 놀라운 성능 향상이 이루어 졌다. 이러한 딥러닝 모델은 매우 많은 파라미터를 갖고 있어 많은 연산량과 메모리를 필요로 한다. 하지만 사용할 수 있는 리소스는 한정되어 있기 때문에 네트워크를 경량화 시키려는 연구도 지속되어 왔다. 본 논문에서는 Stochastic Weight Averaging (SWA) 알고리즘을 이용하여 상대적으로 적은 양의 메모리와 연산을 추가해 이미지 초해상도 모델의 성능을 높이고 안정적인 학습을 달성하였다. SWA 알고리즘을 적용한 모델은 그렇지 않은 모델에 비해 테스트셋에서 최대 0.13dB 의 성능 향상을 보였다.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.1-8
• /
• 2013

Data mining techniques are used to find important and meaningful information from huge databases, and pattern mining is one of the significant data mining techniques. Pattern mining is a method of discovering useful patterns from the huge databases. Frequent pattern mining which is one of the pattern mining extracts patterns having higher frequencies than a minimum support threshold from databases, and the patterns are called frequent patterns. Traditional frequent pattern mining is based on a single minimum support threshold for the whole database to perform mining frequent patterns. This single support model implicitly supposes that all of the items in the database have the same nature. In real world applications, however, each item in databases can have relative characteristics, and thus an appropriate pattern mining technique which reflects the characteristics is required. In the framework of frequent pattern mining, where the natures of items are not considered, it needs to set the single minimum support threshold to a too low value for mining patterns containing rare items. It leads to too many patterns including meaningless items though. In contrast, we cannot mine any pattern if a too high threshold is used. This dilemma is called the rare item problem. To solve this problem, the initial researches proposed approximate approaches which split data into several groups according to item frequencies or group related rare items. However, these methods cannot find all of the frequent patterns including rare frequent patterns due to being based on approximate techniques. Hence, pattern mining model with multiple minimum supports is proposed in order to solve the rare item problem. In the model, each item has a corresponding minimum support threshold, called MIS (Minimum Item Support), and it is calculated based on item frequencies in databases. The multiple minimum supports model finds all of the rare frequent patterns without generating meaningless patterns and losing significant patterns by applying the MIS. Meanwhile, candidate patterns are extracted during a process of mining frequent patterns, and the only single minimum support is compared with frequencies of the candidate patterns in the single minimum support model. Therefore, the characteristics of items consist of the candidate patterns are not reflected. In addition, the rare item problem occurs in the model. In order to address this issue in the multiple minimum supports model, the minimum MIS value among all of the values of items in a candidate pattern is used as a minimum support threshold with respect to the candidate pattern for considering its characteristics. For efficiently mining frequent patterns including rare frequent patterns by adopting the above concept, tree based algorithms of the multiple minimum supports model sort items in a tree according to MIS descending order in contrast to those of the single minimum support model, where the items are ordered in frequency descending order. In this paper, we study the characteristics of the frequent pattern mining based on multiple minimum supports and conduct performance evaluation with a general frequent pattern mining algorithm in terms of runtime, memory usage, and scalability. Experimental results show that the multiple minimum supports based algorithm outperforms the single minimum support based one and demands more memory usage for MIS information. Moreover, the compared algorithms have a good scalability in the results.

• Korean Chemical Engineering Research
• /
• v.50 no.3
• /
• pp.511-515
• /
• 2012

In this study, we used a commercial simulator to investigate the gasification characteristics of Roto coal in the partitioned fluidized-bed gasifier, which consists of 4 parts such as coal pyrolysis, char gasification, tar/oil gasification and char combustion. The heating medium was exchanged between the combustion part and the gasification part in order to supply the energy needed for pyrolysis and gasification. The correlation model from experimental data in relation to the reaction temperatures, the reaction gases and the coal feed rates was derived for the coal pyrolysis. The equilibrium model was used for the gasification and the combustion model for the char combustion. In order to compare the reaction behavior of the partitioned fluidized-bed gasifier, the single-bed gasifier was also simulated. The cold gas efficiency of both partitioned fluidized-bed gasifier and single-bed gasifier was almost the same. The $H_2$ and $CH_4$ contents of the syngas in the partitioned fluidized-bed gasifier slightly increased and the CO and $CO_2$ contents slightly decreased, compared with the singlebed gasifier. In order to verify the model, ten cases of the single-bed gasification experiment have been simulated. The contents of CO, $CO_2$, $CH_4$ in the syngas from the simulation corresponded with the experimental data while those of $H_2$ was slightly higher than experimental data, but the tendency of $H_2$ content in the syngas was similar to the experiments. In the coal conversion, the simulation results were higher than the experiments since equilibrium model was used for the gasification so that the residence time and contact time in the model is different from the experiments.

• Journal of KIISE:Software and Applications
• /
• v.33 no.1
• /
• pp.84-94
• /
• 2006

The color information in an image changes as the illuminant condition varies. The mechanism to find canonical color of an object by estimating illumination color in an image is generally referred as color constancy. In color constancy, computing robust and precise dichromatic line is most important to estimate illumination chromaticity. In this paper, a novel approach to estimate the color of a single illuminant for noisy and micro-textured images is introduced. An accurate dichromatic line is found by using Dichromatic Line Space (DLS), proposed in this paper. which has information about diffuse chromaticity and illumination chromaticity.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.3
• /
• pp.333-340
• /
• 2011

We evaluated the stress-reduction effect for different shapes of a composite adherend with or without a spew fillet. Six different single-lap joint specimens were modeled and assessed using nonlinear finite element analysis. Moreover, we investigated the effect of the stiffness ratio of the adherend and adhesive. The single-lap joint with normal tapering had the highest stress values, and the single-lap joint with reverse tapering and a spew fillet had the lowest stress values. The composite adherends with higher stiffness had lower stress values, and the adhesives with lower stiffness had lower stress values.

• Journal of the Korea Computer Graphics Society
• /
• v.3 no.1
• /
• pp.29-36
• /
• 1997

Most Virtual Reality Systems have been developed to support only a single user on a stand-alone system. With increasing availability of Internet, many people are taking strong interests in distributed Virtual Reality : the virtual environment is shared by many paticipants interacting over the network. To support sharing virtual environment and interactions on a network, we developed novel contributions to 3D world description and a network model. Interactive 3D world description is based on VRML, which is extended to support multi-user interactions. Then network model in our system consists of an architecture and a set of protocols for realizing a multi-user interactive shared 3D environment in IP multicast environment.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.498-500
• /
• 2012

비디오 해석 및 추적기술은 특정한 시스템에서만 적용되는 것이 아니다. 이것은 비디오 내에서 의미 있는 정보를 능동적으로 감시 대상을 정의, 해석, 모델화, 추정 및 추적 할 수 있는 기반 기술을 의미하다. 일반적으로 감시시스템에서 감시 대상은 사람이나 차량이며, 상황에 따라 출입통제 구역으로 설정하기도 한다. 이는 연속된 영상에서 객체의 형태, 모양, 행동 분석, 움직임, 색상정보를 가지고 데이터 정의, 검출, 모델화를 통하여 인식, 식별 그리고 추적한다. 본 논문에서는 비디오 영상분석을 통해 단일카메라기반의 감시시스템과 PTZ 카메라기반 감시시스템 제안한다. 이때 단일 카메라기반의 감시는 배경생성방법을 이용하여 연속된 영상내의 객체를 지속적으로 관리가 가능하도록 설계하였고, PTZ 카메라기반의 감시는 카메라의 이동에 따른 배경안정화 방법과 카메라의 절대좌표를 활용하여 카메라 이동을 제어함과 동시에 오검출 문제를 해결하였다. 실험 및 결과분석으로는 시나리오 환경에서 배경생성방법을 이용한 검출의 정확성과 PTZ카메라 위치 변화에도 강인한 검출 결과를 비교 분석하였다.