• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2006.06a
• /
• pp.122-129
• /
• 2006

The context-awareness has become the one of core technologies and the indispensable function. for application services in ubiquitous computing environment. In this research, we incorporated the capability of context-awareness in a music recommendation system. Our proposed system consists of such components as Intention Module, Mood Module and Recommendation Module. Among these modules, the Intention Module infers whether a user wants to listen to the music or not from the environmental context information. We built the Intention Module using data mining techniques such as decision tree, support vector machine and case-based reasoning. The results showed that the case-based reasoning model outperformed the other models and its accuracy was 84.1%.

• Journal of Information Processing Systems
• /
• v.17 no.5
• /
• pp.867-878
• /
• 2021

In context awareness and user intention tasks, dataset construction is expensive because specific domain data are required. Although pretraining with a large corpus can effectively resolve the issue of lack of data, it ignores domain knowledge. Herein, we concentrate on data domain knowledge while addressing data scarcity and accordingly propose a multi-channel long short-term memory (LSTM). Because multi-channel LSTM integrates pretrained vectors such as task and general knowledge, it effectively prevents catastrophic forgetting between vectors of task and general knowledge to represent the context as a set of features. To evaluate the proposed model with reference to the baseline model, which is a single-channel LSTM, we performed two tasks: voice phishing with context awareness and movie review sentiment classification. The results verified that multi-channel LSTM outperforms single-channel LSTM in both tasks. We further experimented on different multi-channel LSTMs depending on the domain and data size of general knowledge in the model and confirmed that the effect of multi-channel LSTM integrating the two types of knowledge from downstream task data and raw data to overcome the lack of data.

• Journal of Intelligence and Information Systems
• /
• v.12 no.3
• /
• pp.111-126
• /
• 2006

The context-awareness is one of the core technologies in ubiquitous computing environment. In this research, we incorporated the capability of context-awareness in a case-based music recommendation system. Our proposed system consists of Intention Module and Recommendation Module. The Intention Module infers whether a user wants to listen to the music or not from the environmental context information. Then, the Recommendation Module selects songs from the songs that are listened by similar users in similar context, and recommends them to the user. The results showed that our proposed system outperformed the traditional case-based music recommendation system in accuracy by about 9% point.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.333-336
• /
• 2005

The advance of wireless telecommunication and observation technologies leads developing sensor and sensor network for serving the context information continuously. Besides, in order to understand and cope with the context awareness based on the sensor network, it is becoming important issue to deal with plentiful data transmitted from various sensors. Therefore, we propose a context awareness system to deal with the plentiful sensor data in a vast area such as the prevention of a forest fire, the warning system for detecting environmental pollution, and the analysis of the traffic information, etc. The proposed system consists of the context acquisition to collect and store various sensor data, the knowledge base to keep context information and context log, the rule manager to process context information depending on user defined rules, and the situation information manager to analysis and recognize the context, etc. The proposed system is implemented for managing renewable energy data management transmitted from a large scale area.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.2
• /
• pp.221-226
• /
• 2010

Ubiquitous computing is technology that provides services appropriate for the user. At places where environmental and situational context are relevant in making the determination of what services are appropriate, there are sensor nodes installed, which automatically collect, manage and control environmental information. In this computing environment, in order to meet the requirements of services provided to users, a context awareness system is needed for context awareness processing. In this thesis, using RFID/USN sensors, the context of a user entering and leaving an area was produced, and the user's identification information was received via the RFID reader and antenna. At the same time, to decide whether or not to allow access for the user, a distance sensor node was installed to collect context data. Based on this, a system that provides practical services needed in real life for users was designed and implemented. The context of a user entering an area was produced, which the system recognized and provided appropriate services for the user.

• Journal of Internet Computing and Services
• /
• v.14 no.4
• /
• pp.1-12
• /
• 2013

Context-awareness is a computing technology that automatically delivers useful services to users based on their situation. Most previous studies on context-awareness adopted the view that the user simply is a consumer of what the developer creates. Few studies addressed catering to the need of personalized services for the user. They are either too complex for the user to grasp or unable to express many useful services due to their weak expressive power. To address these issues, we propose Dobby as a new model and architecture for user-driven context-aware service development. Dobby enables the user to create services that are more suited to his personal preferences. We argue that Dobby offers an enhanced method for defining personalized context-aware services over existing methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.169-172
• /
• 2013

In this paper, we develop an application service of user authentication system using context awareness technology. The proposed security printer system service is applying 'NFC(Near Field Communication) technology', 'authentication system using communication with server, according to context awareness to application system. Our system extracts several context-awareness elements that happen through the user's printing with server communication. The proposed system property elements contain as print time, number of printing and name of document, etc. based on working memory operation as DB. This proposed system provide with context-awareness weight algorithm and analyzes the service which decides success or failure of user's printing. The develop app service is formed and applied when approved user who gets request. Approved user according to these context awareness tech will be provided with final service after authenticating again for the certain NFC card to reader. This results cab be contributed an authentication service based on context awareness weight algorithm and improved performance of management service in secure service applications.

• Korean Institute of Interior Design Journal
• /
• v.19 no.3
• /
• pp.251-259
• /
• 2010

The purpose of this study is to show the characteristics of integrated welfare center space by applying Context-Awareness technology in order to provide user-friendly services for efficient use of integrated welfare centers as more and more people are interested in using welfare integrated welfare centers which have increasingly been supplied. For this study, we propose the spaces which provide users of integrated welfare centers with proper services by applying Context-Awareness after reviewing the theory of Context-Awareness through literature study as well as case analysis and choosing the reasonable Context-Awareness technology for integrated welfare centers. As it is possible to efficiently provide users with safety service, information service and convenient service by the analysis of space, users' movement in lobby where Context-Awareness is applied and the lobbies of integrated welfare centers in Munsan area, Paju-si out of domestic cases about integrated welfare centers, the different type of spaces from the existing one is expected.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.4 no.3
• /
• pp.139-147
• /
• 2009

This paper proposed the context awareness reasoning system to provide the personalized services dynamically in a ubiquitous mobile environments. The proposed system is designed to provide the personalized services to mobile users and consists of the context aggregator and the knowledge manager. The context aggregator can collect information from networks through Open API Gateway as well as sensors in a various ubiquitous environment. And it can also extract the place types through the geocoding and the social address domain ontology. The knowledge manager is the core component to provide the personalized services, and consists of activity reasoner, user pattern learner and service recommender to provide the services predict by extracting the optimized service from user situations. Activity reasoner uses the ontology reasoning and user pattern learner learns with previous service usage history and contexts. And to design service recommender easy to flexibly apply in dynamic environments, service recommender recommends service in the only use of current accessible contexts. Finally, we evaluate the learner and recommender of proposed system by simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.655-660
• /
• 2009

The context prediction algorithms are not suitable to provide real-time personalized service for users in context-awareness environment. The algorithms have problems like time delay in training data processing and the difficulties of implementation in real-time environment. In this paper, we propose a prediction algorithm with user modeling to shorten of processing time and to improve the prediction accuracy in the context prediction algorithm. The algorithm uses moving path of user contexts for context prediction and generates user model by time-series analysis of user's moving path. And that predicts the user context with the user model by sequence matching method. We compared our algorithms with the prediction algorithms by processing time and prediction accuracy. As the result, the prediction accuracy of our algorithm is similar to the prediction algorithms, and processing time is reduced by 40% in real time service environment.