• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.345-348
• /
• 2004

플레이어의 상대 역할을 수행하는 NPC(Non-Player Character)의 구현은 게임에서 재미요소를 좌우하는 중요한 부분이다. 일반적인 NPC는 설정된 값에 따라, 동일한 조건에 대해 동일하게 반응하므로 플레이어로 하여금 예측 가능하게 하여 게임의 재미를 저하시키는 요인이 된다. 따라서 플레이어의 행동과 수준에 대하여 지능적으로 적절히 반응하는 NPC 기술이 필요하다. 본 논문은 퍼지 플러스터링을 이용한 플레이어의 게임 성향을 기반으로 NPC의 행동 반응을 조절함으로써 게임에 동적인 반응을 보이며 플레이어의 수준에 적절히 반응하도록 하는 NPC 기법을 제안한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.146.1-146
• /
• 2001

The researches of science and engineering need the latest information from internet resources. But searching and filtering processes of appropriate web documents from huge internet resources are very complex as well as having some repeated procedures. In this paper, I propose a Personalized Agent System(PAS), which can filter World Wide Web Documents that the user is interested, such as papers. To do this, PAS uses a modified spreading activation neural network which 1 propose here. PAS observes the user´s local paper database to analyze, adapt and learn the user interests, and the then constructs the user-specified neural network model by the analyzed interests ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.154.2-154
• /
• 2001

This paper presented a adaptation approach based on maximum model distance (MMD) method. This method shares the same framework as they are used for training speech recognizers with abundant training data. The MMD method could adapt to all the models with or without adaptation data. If large amount of adaptation data is available, these methods could gradually approximate the speaker-dependent ones. The approach is evaluated through the phoneme recognition task on the TIMIT corpus. On the speaker adaptation experiments, up to 65.55% phoneme error reduction is achieved. The MMD could reduce phoneme error by 16.91% even when ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.99.1-99
• /
• 2001

This paper presented an adaptation approach based on maximum model distance (MMD) method. This method shares the same framework as they are used for training speech recognizers with abundant training data. The MMD method could adapt to all the models with or without adaptation data. If large amount of adaptation data is available, these methods could gradually approximate the speaker-dependent ones. The approach is evaluated through the phoneme recognition task on the TIMIT corpus. On the speaker adaptation experiments, up to 65.55% phoneme error reduction is achieved. The MMD could reduce phoneme error by 16.91% even when only one adaptation utterance is used.

• Journal of the Korean Society of Costume
• /
• v.25
• /
• pp.63-69
• /
• 1995

The purpose of this study was to investigate to the costumes in a portrait of the Buddhist Monk of JUN-NAM's local Temple. The Kasa was used to base of the rule be-cause this was not our's own costumes. There-fore size, form, wearing-assistance ornament of Kasa were to similiar to the rule's Kasa. But in case of color were used to pink, yellow, chest-nut except the red color. A Buddhist monk's robe were putted on adapt to climate in our nation. Without special condition, a Buddhist monk's robe were used to varied color, that is grey, green, pink, blue,(light, navy) blue, chestnut etc.

• Research in Mathematical Education
• /
• v.5 no.2
• /
• pp.99-106
• /
• 2001

We have known that ethno-mathematics is a field of a study that emphasizes the socio-cultural environment in which a person "does" mathematics as stated by D'Ambrosio(Ethno mathematics and its Place in the History and Pedagogy of Mathematics, 1985). Measurement is an important mathematical topic, which leads students to relate math to the eal-world applications, particularly with socio-cultural aspects. The purpose of this article is to review the history of the measurement system in Korea briefly and to adapt the measurement system into real-world problems so that children acquire measurement knowledge in the most natural way.

• Journal of Agricultural Extension & Community Development
• /
• v.4 no.1
• /
• pp.195-199
• /
• 1997

Under the WTO, Bang-Wha country's agriculture is experiencing many difficulties and environmental changes. For overcoming this situation, some agricultural development strategy should be established in Bong-Wha county. First, special agricultural products adapt to local condition should be produced. Second, innovation technics should be developed in local agriculture. Third, marketing activities should be improved in local agricultural products. Finally, organic agricultural products' development should be activated.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.224-229
• /
• 1992

We investigate a neural network as a dynamic system controller when system characteristics are abruptly changing. The shape of sigmoid functions are determined by autotuing method for the optimum sigmoid function of the neural networks. By using information stored in the identifying network a novel algorithm that can adapt the control action of the controller has been developed. Robustness can be seen from its ability to adjust large variations of parameters. The potential of the proposed method is demonstrated by simulations.

• MALSORI
• /
• no.45
• /
• pp.93-105
• /
• 2003

In this paper, we present a single framework based on GMM for speaker recognition. The proposed framework can simultaneously minimize environmental variations on mismatched conditions and adapt the bias free and speaker-dependent characteristics of claimant utterances to the background GMM to create a speaker model. We compare the closed-set speaker identification for conventional method and the proposed method both on TIMIT and NTIMIT. In the several sets of experiments we show the improved recognition rates on a simulated channel and a telephone channel condition by 7.2% and 27.4% respectively.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.301-303
• /
• 2007

This paper presents user adaptation methods to overcome limitations of a user-independent model and a user-dependent model in a Korean sign language recognition system. To adapt model parameters for unobserved states in hidden Markov models, we introduce new methods based on motion similarity and prediction from adaptation history so that we can achieve faster adaption and higher recognition rates comparing with previous methods.