• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.269-272
• /
• 2011

일반적으로 지능형 에이전트에게 요구되는 가장 기초적인 상황 인식 기능 중의 하나가 불확실한 센서 데이터에 의존하여 자신의 현재 위치가 어디인지를 파악하는 일이다. 본 논문에서는 대표적인 확률기반의 측위 기법인 파티클 필터를 실제 로봇 측위에 적용한 실험을 수행하고, 이를 통해 측위 성능을 개선시킬 수 있는 방법들을 찾아본다. 특히 로봇 동작의 오차를 고려하지 않은 비-잡음 상태 전이 모델과 로봇 동작의 오차를 고려한 잡음 모델간의 비교 실험을 통해, 불확실성이 높은 실제 로봇 동작에 보다 근사한 상태 전이 모델이 파티클 필터 측위의 성능 개선에 도움이 될 수 있는지 분석해본다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.48-51
• /
• 2008

지능화된 국방 정보 시스템의 구축을 위해서는 정보를 수집하고, 수집된 정보를 분석하며, 이를 바탕으로 상황을 인지할 수 있는 시스템이 필요하다. 이러한 시스템의 개발을 위해서는, 단편적인 정보를 저장, 조회할 수 있는 데이터 베이스 구조보다는, 수집된 정보들간의 유기적인 관계를 설명할 수 있는 온톨로지 구조가 적합하다. 이를 위해 본 논문에서는 지능화된 국방 정보시스템 중 사람, 신호, 이미지로부터 획득한 정보를 통합·분석하기 위한 에이전트에서 사용될 온톨로지의 설계에 관하여 다룰 것이다. 본 온톨로지는 상위 온톨로지로는 SUMO를 사용하여 각 도메인 온톨로지로부터 들어온 정보를 통합할 수 있도록 하였고, 도메인 온톨로지로는 HUMINT, SIGINT, IMINT 를 사용하여 각 종류의 신호로부터 들어오는 정보를 분석할 수 있도록 하였다. 또한 각각의 온톨로지간의 유기적 관계를 구성하였다.

• Information Systems Review
• /
• v.8 no.1
• /
• pp.181-201
• /
• 2006

As the Internet spreads, many people have interests in e-CRM and product recommender systems, one of e-CRM applications. Among various approaches for recommendation, collaborative filtering and content-based approaches have been investigated and applied widely. Despite their popularity, traditional recommendation approaches have some limitations. They require at least one purchase transaction per user. In addition, they don't utilize much information such as demographic and specific personal profile information. This study suggests new hybrid recommendation model using two data mining techniques, association rule and classification, as well as intelligent agent to overcome these limitations. To validate the usefulness of the model, it was applied to the real case and the prototype web site was developed. We assessed the usefulness of the suggested recommendation model through online survey. The result of the survey showed that the information of the recommendation was generally useful to the survey participants.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.7
• /
• pp.49-58
• /
• 2011

Augmented Reality(AR) assists human's cognitive ability through the information visualization by substantiating information about virtual situation. This technology is studied in a variety of ways including education, design, industry, and so on, by various supply of information devices equipped with cameras and display monitors. Since the most of the AR system depends on limited interaction that responds to the order from user, it can not reflect diverse real world situation. In this study, we suggest a knowledge based augmented reality system, which is composed of context awareness agent that provides recognized context information, along with knowledge based component that provides intelligent capability by utilizing domain knowledges. With this capability, the augmented object can generate dynamic model intelligently by reflecting context information, and can make the interaction possible among the multiple objects. We developed rule based context awareness system along with 3D model generation, and tested interaction among the augmented objects. And we suggest a framework that can provide a convenient way of developing augmented reality system for user.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.2
• /
• pp.112-123
• /
• 2005

The latest E-commerce sites provide personalized services to maximize user satisfaction for Internet user The collaborative filtering is an algorithm for personalized item real-time recommendation. Various supplementary methods are provided for improving the accuracy of prediction and performance. It is important to consider these two things simultaneously to implement a useful recommendation system. However, established studies on collaborative filtering technique deal only with the matter of accuracy improvement and overlook the matter of performance. This study considers representative attribute-neighborhood, recommendation textile set, and similarity grouping that are expected to improve performance to the recommendation agent system. Ultimately, this paper suggests empirical applications to verify the adequacy and the validity on this system with the development of Fashion Design Recommendation Agent System (FDRAS ).

• Trans-
• /
• v.13
• /
• pp.141-169
• /
• 2022

Analysis of narrative texts has been regarded as academically and practically important, and has been made from various perspectives and methods. In this paper, the computational narrative analysis methodology from the perspective of information processing was examined. From the point of view of information processing, the creation and acceptance of narrative is a bidirectional coding process mediated by narrative text, and narrative text can be said to be a multi-layered structured code. In this paper, four methodologies that share this point of view - character network analysis, text mining and sentiment analysis, continuity analysis of event composition, and knowledge analysis of narrative agents - were examined together with cases. Through this, the mechanism and possibility of computational methodology in narrative analysis were confirmed. In conclusion, the significance and side effects of computational narrative analysis were examined, and the necessity of designing a human-computer collaboration model based on the consilience of the humanities and science/technology was discussed. Based on this model, it was argued that aesthetically creative, ethically good, politically progressive, and cognitively sophisticated narratives could be made more effectively.

• The KIPS Transactions:PartB
• /
• v.14B no.5
• /
• pp.383-390
• /
• 2007

Interactions between proteins and genes are often considered essential in the description of biomolecular phenomena and networks of interactions are considered as an entre for a Systems Biology approach. Recently, many works try to extract information by analyzing biomolecular text using natural language processing technology. Previous researches insist that linguistic information is useful to improve the performance in detecting gene interactions. However, previous systems do not show reasonable performance because of low recall. To improve recall without sacrificing precision, this paper proposes a new method for detection of gene interactions based on syntactic relations. Without biomolecular knowledge, our method shows reasonable performance using only small size of training data. Using the format of LLL05(ICML05 Workshop on Learning Language in Logic) data we detect the agent gene and its target gene that interact with each other. In the 1st phase, we detect encapsulation types for each agent and target candidate. In the 2nd phase, we construct verb lists that indicate the interaction information between two genes. In the last phase, to detect which of two genes is an agent or a target, we learn direction information. In the experimental results using LLL05 data, our proposed method showed F-measure of 88% for training data, and 70.4% for test data. This performance significantly outperformed previous methods. We also describe the contribution rate of each phase to the performance, and demonstrate that the first phase contributes to the improvement of recall and the second and last phases contribute to the improvement of precision.

• Journal of Korea Multimedia Society
• /
• v.9 no.5
• /
• pp.649-657
• /
• 2006

Reinforcement Learning is a computational approach to learning whereby an agent take an action which maximize the total amount of reward it receives among possible actions within current state when interacting with a uncertain environment. Q-learning, one of the most active algorithm in Reinforcement Learning, is consist of rewards which is obtained when an agent take an action. But it has the problem with mapping real world to discrete states. When state spaces are very large, Q-learning suffers from time for learning. In constant, when the state space is reduced, many state spaces map to single state space. Because an agent only learns single action within many states, an agent takes an action monotonously. In this paper, to reduce time for learning and complement simple action, we propose the Q-learning using influence map(QIM). By using influence map and adjacent state space's learning result, an agent could choose proper action within uncertain state where an agent does not learn. When this paper compares simulation results of QIM and Q-learning, we show that QIM effects as same as Q-learning even thought QIM uses 4.6% of the Q-learning's state spaces. This is because QIM learns faster than Q-learning about 2.77 times and the state spaces which is needed to learn is reduced, so the occurred problem is complemented by the influence map.

• Korean Journal of Cognitive Science
• /
• v.6 no.2
• /
• pp.47-79
• /
• 1995

Since the early age of computer graphics, facial animation has been applied to various fields, and nowadays it has found several novel applications such as virtual reality(for representing virtual agents), teleconference, and man-machine interface.When we want to apply facial animation to the system with multiple participants connected via network, it is hard to animate facial expression as we desire in real-time because of the size of information to maintain an efficient communication.This paper's major contribution is to adapt 'Level-of-Detail'to the facial animation in order to solve the above problem.Level-of-Detail has been studied in the field of computer graphics to reperesent the appearance of complicated objects in efficient and adaptive way, but until now no attempt has mode in the field of facial animation. In this paper, we present a systematic scheme which enables this kind of adaptive control using Level-of-Detail.The implemented system can generate speech synchronized facial expressions with various types of user input such as text, voice, GUI, head motion, etc.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.299-308
• /
• 2014

Various literatures related computing of information processing have been recently shown the researches inspired from the remarkably excellent human capabilities which recognize and categorize very complex visual patterns such as body motions and facial expressions. Applied from human's outstanding ability of perception, the classification function of visual sequences without context information is specially crucial task for computer vision to understand both the coding and the retrieval of spatio-temporal patterns. This paper presents a biological process based action recognition model of computer vision, which is inspired from visual information processing of human brain for action recognition of visual sequences. Proposed model employs the structure of neural fields of bio-inspired visual perception on detecting motion sequences and discriminating visual patterns in human brain. Experimental results show that proposed recognition model takes not only into account several biological properties of visual information processing, but also is tolerant of time-warping. Furthermore, the model allows robust temporal evolution of classification compared to researches of action recognition. Presented model contributes to implement bio-inspired visual processing system such as intelligent robot agent, etc.