• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권4호
• /
• pp.254-259
• /
• 2008

Uncertainty of result of context awareness always exists in any context-awareness computing. This falling-off in accuracy of context awareness result is mostly caused by the imperfectness and incompleteness of sensed data, because of this reasons, we must improve the accuracy of context awareness. In this article, we propose a novel approach to model the uncertain context by using ontology and context reasoning method based on Bayesian Network. Our context aware processing is divided into two parts; context modeling and context reasoning. The context modeling is based on ontology for facilitating knowledge reuse and sharing. The ontology facilitates the share and reuse of information over similar domains of not only the logical knowledge but also the uncertain knowledge. Also the ontology can be used to structure learning for Bayesian network. The context reasoning is based on Bayesian Networks for probabilistic inference to solve the uncertain reasoning in context-aware processing problem in a flexible and adaptive situation.

• 정보처리학회논문지C
• /
• 제13C권6호
• /
• pp.691-700
• /
• 2006

유비쿼터스 컴퓨팅 환경에서 상황 인식 기반의 서비스를 제공하기 위해선 동적인 상황 관리 기술과 상황 추론 기술, 그리고 상황 모델링 기술이 필요하다. 기존 연구에서 상황 인식 서비스는 상황 인식 미들웨어에서 사용하는 상황 온톨로지를 이용해서 설계되기 때문에 서비스의 실행도중 상황 온톨로지를 동적으로 변경하기 어렵다. 본 논문에서는 유비쿼터스 컴퓨팅 환경에서 상황 변화에 대한 사용자의 요구사항을 능동적으로 반영하고, 동적인 응용 적응성을 지원하는 계층적 온톨로지 기반 상황 관리 모델을 제안하고 이를 기반으로 상황 인식 미들웨어를 설계한다 또한, 상황 인식 서비스 구현을 위해 다양한 컨텍스트 발견, 획득, 해석, 추론을 효과적으로 지원하며 사용자의 서비스 실행 시 발생할 수 있는 상황 충돌을 해결하기 위한 방법을 제시한다. 설계하는 미들웨어는 OSGi 프레임워크 위에서 구현함으로써 다양한 유비쿼터스 환경에 필요한 상황 인식 서비스의 개발 및 운용을 효과적으로 지원을 할 수 있다.

• 로봇학회논문지
• /
• 제2권1호
• /
• pp.80-92
• /
• 2007

For the pervasive computing in ubiquitous environment, it is very important to manage the context model to provide pertinent context knowledge to context-aware applications. The context model should be able to support efficiently the context knowledge reusing and sharing as well as reasoning. Previous works focus mainly on the context knowledge representation scheme for reasoning. This paper proposes a context knowledge modeling scheme especially for reusing and sharing. This scheme provides well-established principles and guides for 1) context knowledge modularization and hierarchization, and for 2) context knowledge identification and organization. Once the context models are built according to the scheme, the structure of the context model and the meanings of the context knowledge elements become clear and consistent, so that context-aware applications can share and reuse the context knowledge in easy and error-reduced manner. This paper also discusses the implementation of a context model and an application for Presentation Helper scenario running on a software middleware system (CAMUS) for ubiquitous service robots which is being developed by ETRI Korea.

• 한국HCI학회논문지
• /
• 제8권1호
• /
• pp.11-17
• /
• 2013

Context aware systems are those systems that are aware about the environment and perform productive functions automatically by reducing human computer interactions(HCI). In this paper, we present common architecture principles of context-aware systems to explain the important aspects of context aware systems. Our study focuses on identifying common concepts in pervasive computing approaches, which allows us to devise common architecture principles that may be shared by many systems. The principles consists of context sensing, context modeling, context reasoning, context processing, communication modelling and resource discovery. Such an architecture style can support high degree of reusability among systems and allows for design flexibility, extensibility and adaptability among components that are independent of each other. We also propose a new architecture based on broker-centric middleware and using ontology reasoning mechanism together with an effective behavior based context agent that would be suitable for the design of context-aware architectures in future systems. We have evaluated the proposed architecture based on the design principles and have done an analyses on the different elements in context aware computing based on the presented system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2881-2894
• /
• 2014

In complicated environment, context information plays an important role in image segmentation/labeling. The recently proposed auto-context algorithm is one of the effective context-based methods. However, the standard auto-context approach samples the context locations utilizing a fixed radius sequence, which is sensitive to large scale-change of objects. In this paper, we present a scale invariant auto-context (SIAC) algorithm which is an improved version of the auto-context algorithm. In order to achieve scale-invariance, we try to approximate the optimal scale for the image in an iterative way and adopt the corresponding optimal radius sequence for context location sampling, both in training and testing. In each iteration of the proposed SIAC algorithm, we use the current classification map to estimate the image scale, and the corresponding radius sequence is then used for choosing context locations. The algorithm iteratively updates the classification maps, as well as the image scales, until convergence. We demonstrate the SIAC algorithm on several image segmentation/labeling tasks. The results demonstrate improvement over the standard auto-context algorithm when large scale-change of objects exists.

• 한국컴퓨터정보학회논문지
• /
• 제21권2호
• /
• pp.25-32
• /
• 2016

In this paper, we design a middleware for context-awareness which provides compound contexts from diverse sensors on a mobile device. Until now, most of context-aware application developers have taken responsibility for context processing from sensing data. Such application-level context processing causes heavily redundant data processing and leads to significant resource waste in energy as well as computing. In the proposed scheme, we define primitive and compound context map which consists of relavant sensors and features. Based on the context definition, each application demands a context of interest to the middleware, and thus similar context-aware applications inherently share context information and procesing within the middleware. We show that the proposed scheme significantly reduces the resource amounts of cpu, memory, and battery, and that the performance gain gets much more when multiple applications which need similar contexts are running.

• 한국과학교육학회지
• /
• 제14권3호
• /
• pp.304-311
• /
• 1994

Four science concepts were selected from high school science textbook to investigate the differences in priorities of students knowledge activated during solving earth science problems in laboratory and earth science environmental contexts. Two items, one for laboratory context and the other for earth environmental context, were developed for earth selected concept The subjects were constituted of 192 students in 11th grade and 196 in 12th grade in one senior high school. Students' responses were categorized using graph models and analyzed in terms of 'Common Activated Knowledge'(CAK). and 'Specific Activated Knowledge'(SAK) across students' cognitive frames, grades, and sex. As contextual differences of the problems increased, context effects in priorities of CAK were reported in favor of laboratory context, on the contrary those of SAK in favor of earth environmental context. Context effects were reported across cognitive frames, especially students with laboratory cognitive frames showed more significant context effects than others. Lower graders and girls showed relatively large context effects. The results of this study showed that science concepts learned in a laboratory context are not easily transferred to earth environmental context. Therefore, special instructional strategies should be developed to overcome the context effect s according to activated knowledges with high priorities in laboratory and earth environmental context.

• 한국컴퓨터정보학회지
• /
• 제14권1호
• /
• pp.165-173
• /
• 2006

유비쿼터스 컴퓨팅 환경에서 상황 인식 기반의 서비스를 제공하기 위해선 동적인 상황 관리 기술과 상황 추론 기술, 그리고 상황 모델링 기술이 필요하다. 본 논문에서는 유비쿼터스 컴퓨팅 환경에서 상황 변화에 대한 사용자의 요구사항을 능동적으로 반영하고, 동적인 응용 적응성을 지원하는 계층적 온톨로지 기반 상황 관리 모델을 제안하고 이를 기반으로 상황 인식 미들웨어를 설계한다. 또한, 상황 인식 서비스 구현을 위해 다양한 컨텍스트 발견, 획득, 해석, 추론을 효과적으로 지원하며 사용자의 서비스 실행 시 발생할 수 있는 상황 충돌을 해결하기 위한 방법을 제시한다. 이 논문에서 제시한 계층적 온톨로지 기반 상황 인식 미들웨어는 유비쿼터스 환경에서 요구되는 다양한 상황 인식 서비스의 개발 및 운용을 효과적으로 지원 할 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제11권1호
• /
• pp.185-194
• /
• 2006

유비쿼터스 컴퓨팅 환경에서는 기존 컴퓨팅 환경에서의 사용자와 컴퓨터간의 대화형 상호작용이 아니라 물리적인 환경, 상황 등을 시스템이 인식하고 이에 따라서 사용자와의 상호 작용을 지원하는 상황 인식서비스가 중요한 요소로 자리잡고 있다. 상황 인식 서비스는 상황 인식 미들웨어로부터 전달된 상황 정보를 해석할 수 있어야 한다. 기존 연구에서 상황 인식 서비스는 상황 인식 미들웨어에서 사용하는 상황 온톨로지를 이용해서 설계되기 때문에 서비스의 실행도중 상황 온톨로지를 동적으로 변경하기 어렵다. 본 연구에서는 계층적 상황 온톨로지 관리 모델을 제안하고 이를 이용한 상황 인식 서비스 미들웨어를 설계한다. 제안한 모델은 상황 인식 서비스가 실행 중에 필요로 하는 상황 정보를 동적으로 추가할 수 있도록 함으로써 보다 유연하게 상황 인식 서비스를 운용할 수 있도록 지원한다. 또한 상황 온톨로지의 동적인 변화로 인해서 센서로부터 얻은 데이터를 상황 정보로 추론하는 과정에서 발생할 수 있는 상황 모호성(Context Uncertainty)을 해결하기 위해서 상황 충돌 해결 모델을 정의한다. 설계하는 미들웨어는 OSGi 프레임워크 위에서 구현함으로써 다양한 유비쿼터스 환경에 필요한 상황 인식 서비스의 개발 및 운용을 효과적으로 지원을 할 수 있다.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2006년도 학술대회 1부
• /
• pp.960-965
• /
• 2006

Privacy and security are latent problems in pervasive healthcare system. For the sake of protecting health monitoring information, it is necessary to classify and categorize the various contexts in terms of obfuscation. In this paper, we propose the physiological context categorization and specification methodology by exploiting data fusion network for automatic context alignment. In addition, we introduce the methodologies for making various level of physiological context on the context aware application model, which is wear-UCAM. This physiological context has several layers of context according to the level of abstraction such as user-friendly level or parametric level. This mechanism facilitates a user to restrict access to his/her monitoring results based on the level of details in context.