• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.563-568
• /
• 2016

The word sense disambiguation problem is to find the correct sense of an ambiguous word having multiple senses in a dictionary in a sentence. We regard this problem as a multi-class classification problem and classify the ambiguous word by using Support Vector Machines. Context words of the ambiguous word, which are extracted from Sejong sense tagged corpus, are represented to two kinds of vector space. One vector space is composed of context words vectors having binary weights. The other vector space has vectors where the context words are mapped by word embedding model. After experiments, we acquired accuracy of 87.0% with context word vectors and 86.0% with word embedding model.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.643-648
• /
• 2005

In order to supply services necessary for users intelligently in the ubiquitous computing, effective filtering of context information is necessary. But studies of context information filtering have not been made much yet. In order for filtering of context information, we can use collaborative filtering being used much at electric commerce, etc. In order to use such collaborative filtering method in the filtering of ubiquitous computing environment, we must solve such problems as first rater problem, sparsity problem, stored data problem and etc. In this study, in order to solve such problems, the researcher proposes the collaborative filtering method using types of context information. And as the result of applying this filtering method to MAUCA, the P2P mobile agent system, the researcher could confirm the average result of 7.7% in the aspect of service supporting function.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.4
• /
• pp.590-597
• /
• 1990

To represent shape characteristics of digital closed curve, many algorithms, mainly based on local properties, have been proposed. In this paper, we propose a new algorithm for detecting local curvature maxima which reflects context, i.e., structural or surrounding regional characteristics. The algorithm does not require the value of k as an input parameter which is the major problem in k-curvature method in digital curve, but calculates it at each point depening on the context. The algorithm has been applied to two dimensional image boundaries. The efficiency of the algorithm is addressed by comparing the result of existing contest dependent algorithm.

• Journal of Information Technology Services
• /
• v.13 no.1
• /
• pp.197-207
• /
• 2014

With the recent advance in smartphones, users are allowed to use mobile applications anytime anywhere, and change their way to interact with smart environment and people. As a result, the need for developing context-aware applications on smartphones has a great attention from users and developers. This paper proposes a context-aware framework for supporting UI/UX of smartphones. The proposed framework collects a wide range of sensory data from smartphones and allows developers to analyze and model context models for their desired apps. In addition, it also supports real-time inference within the apps to make them to adapt to context. In order to show effectiveness of the proposed framework, we introduce two smartphone apps: context-aware home screen and automatic detection of smartphone problem use. Therefore, we expect that the proposed framework will help developers easily implement their apps with respect to context-awareness.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1378-1391
• /
• 2019

In recent years, automatic document summarization has been widely studied in the field of natural language processing thanks to the remarkable developments made using deep learning models. To decode a word, existing models for abstractive summarization usually represent the context of a document using the weighted hidden states of each input word when they decode it. Because the weights change at each decoding step, these weights reflect only the local context of a document. Therefore, it is difficult to generate a summary that reflects the overall context of a document. To solve this problem, we introduce the notion of a general context and propose a model for summarization based on it. The general context reflects overall context of the document that is independent of each decoding step. Experimental results using the CNN/Daily Mail dataset show that the proposed model outperforms existing models.

• Journal of the Korean Society of Earth Science Education
• /
• v.10 no.1
• /
• pp.1-16
• /
• 2017

This study presents an out-of-school problem-solving lesson we designed for American Indian students using a culturally relevant STEM topic. The lesson was titled "Shelter Design for Severe Weather Conditions." This shelter design lesson was developed based on an engineering design allowing us to integrate STEM topics within a traditional indigenous house-building context. This problem context was used to encourage students to apply their prior knowledge, experience, and community/cultural practice to solve problems. We implemented the lesson at a summer program on an American Indian reservation. Using the lesson, this study explores how American Indian students use cultural knowledge and experience to solve a STEM problem. We collected student data through pre- and post-STEM content knowledge tests, drawings and explanations of shelter models on the students' group worksheets, and classroom observations. We used interpretive and inductive methods to analyze the data. This study demonstrates that our culturally relevant, STEM problem-solving lesson helped the American Indian students solve a complex, real-world problem. This study examines how students' prior experiences and cultural knowledge affect their problem-solving strategies. Our findings have implications for further research on designing problem-solving lessons with culturally relevant STEM topics for students from historically marginalized populations.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.05a
• /
• pp.152-155
• /
• 2002

In recent years, with the spread of communication media, such as a cellular phone and E-mail, we are able to communicate with others without any restriction of position or time. However, complexity of communicative context has increased so that user has to guess a partner user's situation and status in order to use various medias efficiently. This problem will grow larger as new media are brought in the expanding communications network. To solve this problem, we propose the system that guesses the context in communication by a user's media from the position information on PHS (Personal Handy phone System) and schedule information from schedule application. In this system a user's agent guesses automatically the context that owner has set, and answers the demand of the context from a partner user. Moreover, the agent decides a suitable answer, when there is a demand of communication by the media, which cannot be used.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.13-19
• /
• 2001

Unlike that of most management science methodologies, the focus in systems thinking is not on \\\"solving\\\" problems or seeking an optimal solution. Conventional problem solving does not explicitly consider the context of the problem. This implies that the \\\"hospital financial management problem\\\" could be neatly isolated from its environmental and external factors. System thinking and system archetypes, in contrast, acknowledges the messiness of the world and views a problem in the context of its environment. This is one reason why qualitative variables play an important role in system thinking, as these variables represent conditions or phenomena that cannot be measured or accounted in a strictly quantitative approaches. In this paper we present specific healthcare system archetypes which consider such external influences in the healthcare industry in Australia and observe their behavior over time. behavior over time.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.887-892
• /
• 2005

Under pure P2P environments, collaborative filtering must be provided with only a few service items by real time information without accumulated data. However, in case of collaborative filtering with only a few service items collected locally, quality of recommended service becomes low. Therefore, it is necessary to research a method to improve quality of recommended service by users' context information. But because a great volume of users' context information can be recognized in a moment, there can be a scalability problem and there are limitations in supporting differentiated services according to fields and items. In this paper, we solved the scalability problem by clustering context information Per each service field and classifying il per each user, using SOM. In addition, we could recommend proper services for users by measuring the context information of the users belonging to the similar classification to the service requester among classified data and then using collaborative filtering.

• The Journal of Korea Robotics Society
• /
• v.1 no.2
• /
• pp.172-179
• /
• 2006

In this paper, we present a practical place and object recognition method for guiding visitors in building environments. Recognizing places or objects in real world can be a difficult problem due to motion blur and camera noise. In this work, we present a modeling method based on the bidirectional interaction between places and objects for simultaneous reinforcement for the robust recognition. The unification of visual context including scene context, object context, and temporal context is also. The proposed system has been tested to guide visitors in a large scale building environment (10 topological places, 80 3D objects).