• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.540-546
• /
• 2008

In the near future, robots should be able to understand human's emotional states and exhibit appropriate behaviors accordingly. In Human-Human Interaction, the 93% consist of the speaker's nonverbal communicative behavior. Bodily movements provide information of the quantity of emotion. Latest personal robots can interact with human using multi-modality such as facial expression, gesture, LED, sound, sensors and so on. However, a posture needs a position and an orientation only and in facial expression or gesture, movements are involved. Verbal, vocal, musical, color expressions need time information. Because synchronization among multi-modalities is a key problem, emotion expression needs a systematic approach. On the other hand, at low intensity of surprise, the face could be expressed but the gesture could not be expressed because a gesture is not linear. It is need to decide the emotional boundaries for effective robot behavior generation and synchronization with another expressible method. If it is so, how can we define emotional boundaries? And how can multi-modality be synchronized each other?

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.1-10
• /
• 2021

In the past, designers relied primarily on past experience and reference to industry standard thresholds to design spaces. Such design often results in spaces that do not meet the needs of users. The purpose of this paper is to investigate the process and way of generating design parameters by constructing a BP neural network algorithm for spatial design. From the perspective. This paper adopts an experimental research method to take a kindergarten with a large number of complex needs in space as the object of study, and through the BP neural network algorithm in machine learning, the correlation between environmental behavior parameters and spatial design parameters is imprinted. The way of generating spatial design parameters is studied. In the future, the corresponding spatial design parameters can be derived by replacing specific environmental behavior influence factors, which can be applied to a wider range of scenarios and improve the efficiency of designers.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.6
• /
• pp.777-784
• /
• 2017

In the architectural space, the user's behavior is the most important factor in evaluating the quality of architecture. Normally, the evaluation of user behavioral performance was carried out after a building was completed. Recently, interest in and efforts at pre-simulation based on information technology are accelerating. However, since existing user simulation technology is concerned mainly with simply escaping from a large space, it is impossible to simulate the behavior of multiple users in an architectural space. The present study strives to develop a human-figured intelligent agent for advanced user simulation based on ontology. The main purpose of the study is to employ the intelligent behaviors of a NPC(Non-player Character) to infer the ontology of both spatial and user information. In this paper, we intend to integrate ontology inference technology into the virtual space. And also, this study suggest the ontology visualization technology which illustrate the ontology-based information and their change in the spatial information.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.399-408
• /
• 2002

다중 에이전트 학습이란 다중 에이전트 환경에서 에이전트간의 조정을 위한 행동전략을 학습하는 것을 말한다. 본 논문에서는 에이전트간의 통신이 불가능한 다중 에이전트 환경에서 각 에이전트들이 서로 독립적으로 대표적인 강화학습법인 Q학습을 전개함으로써 서로 효과적으로 협조할 수 있는 행동전략을 학습하려고 한다. 하지만 단일 에이전트 경우에 비해 보다 큰 상태-행동 공간을 갖는 다중 에이전트환경에서는 강화학습을 통해 효과적으로 최적의 행동 전략에 도달하기 어렵다는 문제점이 있다. 이 문제에 대한 기존의 접근방법은 크게 모듈화 방법과 일반화 방법이 제안되었으나 모두 나름의 제한을 가지고 있다. 본 논문에서는 대표적인 다중 에이전트 학습 문제의 예로서 먹이와 사냥꾼 문제(Prey and Hunters Problem)를 소개하고 이 문제영역을 통해 이와 같은 강화학습의 문제점을 살펴보고, 해결책으로 신경망 SOM을 이용한 일반화 방법인 QSOM 학습법을 제안한다. 이 방법은 기존의 일반화 방법과는 달리 군집화 기능을 제공하는 신경망 SOM을 이용함으로써 명확한 다수의 훈련 예가 없어도 효과적으로 이전에 경험하지 못했던 상태-행동들에 대한 Q값을 예측하고 이용할 수 있다는 장점이 있다. 또한 본 논문에서는 실험을 통해 QSOM 학습법의 일반화 효과와 성능을 평가하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.369-372
• /
• 2002

다양한 특성들을 가지고 있는 멀티에이전트 시스템의 행동학습은 에이전트 설계에 많은 부담을 덜어준다. 특성들로부터 나오는 다양한 행동의 효과적인 학습은 에이전트들이 환경에 대한 자율성과 반응성을 높여준 수 있다. 행동학습은 model-based learning과 같은 교사학습보다는 각 상태를 바로 지각하여 학습하는 강화학습과 같은 비교사 학습이 효과적이다. 본 논문은 로봇축구환경에 에이전트들의 행동을 개선된 강화학습법인 Modular Q-learning을 적용하여 복잡한 상태공간을 효과적으로 나누어 에이전트들의 자율성과 반응성을 높일 수 있는 강화학습구조를 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.550-552
• /
• 2004

가상공간에는 PC(Playerable Character), NPC(Non-Playerable Character)등의 동적 객체와 건물, 지형 등의 정적 객체들이 존재하게 된다. 동적 객체들의 경우, 현실감을 위해 인공지능이 자주 이용된다 현재까지 인공지능에 대한 연구는 유한상태기계(Finite State Machine. FSM). 학습 알고리즘, 유전자 알고리즘, 신경망 알고리즘 등을 중심으로 진행되어 왔다. 이중 유한상태기계는 비교적 알고리즘이 간단하고, 시스템의 부담이 적어 간단한 객체의 인공지능으로 가장 널리 사용되고 있다. 본 논문은 유찬상태기계를 확장하여 모드변경(Mode Change)과 그룹행동을 보여줄 수 있는 XML을 활용한 FSM 시스템을 제안한다. 여기서 모드변경이란 하나의 행동 패턴에서 다른 행동 패턴으로 변경하는 것을, 그룹행동은 여러 객체가 함께 행동하는 Flocking기법을 지칭한파. 이러한 XML을 활용한 FSM 시스템은 다양한 패턴의 정의는 물론, 객체의 상태 정의 및 수정, 확장이 용이하여, 다양한 응용 분야에서 활용될 수 있다.

• Proceedings of the Zoological Society Korea Conference
• /
• 2001.10a
• /
• pp.134.2-134
• /
• 2001

• Proceedings of the KHMA Conference
• /
• 2009.05a
• /
• pp.374-374
• /
• 2009

• Journal of Environmental Impact Assessment
• /
• v.29 no.3
• /
• pp.182-197
• /
• 2020

This study investigated the home range and characteristics of activities to contribute to the improvement of management techniques and the successful promotion of management policies of invasive nutria, which is a representative invasive species of South Korea. Six individuals were captivated for the study. Remote radio tracking on three of them was carried out followed by the analysis of the results. The average home range of the follow-up individuals were confirmed to be 0.043 ㎢ at MCP 95%, 0.085 ㎢ at K 95%. It was 0.018 ㎢ at K 50%, which is the core space. In 95% MCP, males exhibited the home range with 0.058 ㎢, showed wider home range 0.046 ㎢ than females who showed 0.012 ㎢, and showed a wider home range 0.015 ㎢ more at night than during the day. As a result of comparing the results of this study with the case studies of overseas studies, it is determined that the magnitude of the derived home range is the result of a stable habitat in which the procurement of food resources is smooth and human interference is limited. The daily moved distance of males was larger than that of females, with a maximum moved distance of 1,278 m per day. Activity at the study site is high from around sunset to around 6 A.M., 10 P.M., 7 P.M., 1 A.M., and 5 A.M., and high around sunrise and low during the daytime such as 2 P.M., which reflected the propensity of nocturnal animals to act. The results of this study on the home range and activity in nutria can be used as useful data forimproving the management of invasive alien species for the installation and operation of traps, the spatial setting of controlled areas, and the calculation of the amount ofresources together with a basic understanding of nutria's behaviors in South Korea.

• Journal of Korean Society of Transportation
• /
• v.30 no.6
• /
• pp.13-26
• /
• 2012

In this study, factors influencing the parking policy compliance (i.e. levying a garage option on car buyers) were identified, and then, were applied to the theory of planned behavior. To find out the influence of factors and their path, the study built a parking policy compliance model using structural equation modeling. The independent variables such as attitude, subjective norm, perceived behavioral control had positive effects on the parameter describing the efforts to secure his garage, but the parameter impact on the dependent variable was not significant. In the end, the independent variables affected the dependent variable was not significant. The perceived behavioral control utilizing regulations had positive effects on the parking policy compliance behavior, but past behavior such as street parking and prowling to find a free parking space had a negative effect on parking policy compliance behavior.