• 대한건축학회논문집:계획계
• /
• 제36권4호
• /
• pp.41-49
• /
• 2020

The purpose of this study was to investigate the use of the Deep Neural Networks(DNN) model to classify user's emotions, in particular Electroencephalography(EEG) toward Virtual-Reality(VR) based 3D design alternatives. Four different types of VR Space were constructed to measure a user's emotion and EEG was measured for each stimulus. In addition to the quantitative evaluation based on EEG data, a questionnaire was conducted to qualitatively check whether there is a difference between VR stimuli. As a result, there is a significant difference between plan types according to the normalized ranking method. Therefore, the value of the subjective questionnaire was used as labeling data and collected EEG data was used for a feature value in the DNN model. Google TensorFlow was used to build and train the model. The accuracy of the developed model was 98.9%, which is higher than in previous studies. This indicates that there is a possibility of VR and Fast Fourier Transform(FFT) processing would affect the accuracy of the model, which means that it is possible to classify a user's emotions toward VR based 3D design alternatives by measuring the EEG with this model.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.661-668
• /
• 2022

Various lean design and construction methods such as target value design, pull planning, value stream mapping have successfully transformed the commercial building construction industry into achieving improved productivity, higher design and construction quality, and meeting the target values of construction projects. Considering the significant advantages of lean, the accelerated dissemination and adoption of lean methods and tools for construction is highly desirable. Currently, the lean design and construction body of knowledge is imparted primarily through publications and conferences. However, one of the most effective ways to impart this soft knowledge is through getting students and trainees involved in hands-on participatory games, which can quickly help them truly understand the concept and apply it to real-world problems. The COVID-19 Pandemic has raised an urgent need of developing virtual games that can be played simultaneously from various locations over the Internet, but these virtual games should be as effective as in-person games. This research develops an online 3D simulation game for Target Value Design that is as effective as in-person games or possibly better in terms of knowledge capture and retention and enjoyable environment and experience. The virtual game is tested on volunteers using feedback from pre-and post- simulation surveys to evaluate its efficacy.

• 제어로봇시스템학회논문지
• /
• 제5권1호
• /
• pp.105-114
• /
• 1999

By using the conceptual impedance and the elasticity of a serial chain of spring-damper system, a real-time collision-free trajectory generation algorithm is proposed. The reference points on a trajectory connected by the spring-damper system have a mechanism for self-Position adjustment to avoid a collision by the impedance, and the local adjustment of each reference point is propagated through the elasticity to a real robot at the end of the spring-damper system. As a result, the overall trajectory consisting of the reference points becomes free of collision with environmental obstacles and efficient having the shortest distance as possible. In this process, the reference points connected by the spring-damper system take role of virtual robot as global guidance for a real robot, and a cooperative optimization is carried out by the system of virtual robots. A control algorithm is proposed to implement the impedance for a car-like mobile robot.

• 대한치과의사협회지
• /
• 제50권11호
• /
• pp.660-669
• /
• 2012

We describes the process of 3D virtual treatment planning and of CAD/CAM for surgical splint in orthognathic surgery. The potential benefits and disadvantages of 3D virtual approach and the use of CAD/CAM system for the treatment of the patient with a maxillofacial deformity are discussed. For the more convenient applications,3D software should be improved.

• 한국멀티미디어학회논문지
• /
• 제13권12호
• /
• pp.1820-1831
• /
• 2010

When interacting with unknown environments, an autonomous agent needs to decide which action or action order can result in a good state and determine the transition probability based on the current state and the action taken. The traditional multiple sequential learning model requires predefined probability of the states' transition. This paper proposes a multiple sequential learning and prediction system with definition of autonomous states to enhance the automatic performance of existing AI algorithms. In sequence learning process, the sensed states are classified into several group by a set of proposed motivation filters to reduce the learning computation. In prediction process, the learning agent makes a decision based on the estimation of each state's cost to get a high payoff from the given environment. The proposed learning and prediction algorithms heightens the automatic planning of the autonomous agent for interacting with the dynamic unknown environment. This model was tested in a virtual library.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1998년도 추계학술대회 논문집
• /
• pp.56-59
• /
• 1998

The rapid diffusion of the Internet and the World Wide Web is facilitating greater interaction - and potential opportunities for customization - between vendors and customers. For instance, virtual reality and multimedia technologies allow consumers to envision their designed products. The increasing pace of the business environment highlights the need to deploy intelligent systems in all stages of product design and production planning. This paper deals with a system to generate an appropriate product design by adapting customer preferences and constraints using the case based reasoning methodology. Moreover, intelligent agents are integrated with virtual reality technology to provide a friendly user interface.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.540-544
• /
• 2001

This paper addresses a hybrid control architecture for the hospital service robot, SmartHelper. In hybrid architecture, the deliberation takes place at planning layer while the reaction is dealt through the parallel execution of operations. Hence, the system presents both a hierarchical and an heterarchical decomposition, being able to show a predictable response while keeping rapid reactivity to the dynamic environment. The deliberative controller accomplishes four functions which are path generation, selection of navigation way, command and monitoring. The reactive controller uses fuzzy and potential field method for robot navigation. Through simulation under a virtual environment IGRIP, the effectiveness of the hybrid architecture is verified.

• Journal of International Society for Simulation Surgery
• /
• 제3권2호
• /
• pp.69-73
• /
• 2016

Traditionally 2D cephalometric analysis has been used for diagnosis and treatment of maxillofacial deformities. However, 2D has some limitations in diagnosis and treatment planning especially facial asymmetry cases. The most weakness of 2D is overlapping and unpredictability. Today 3D treatment tools are used by many maxillofacial surgeons. 3D treatment tools can show ungarbled facial anatomy and do virtual surgery. The aim of this report is to present usefulness of using 3D analysis and virtual orthognathic surgery for severe facial asymmetry patients.

• 동력기계공학회지
• /
• 제17권5호
• /
• pp.128-137
• /
• 2013

Modern transmission technologies such as automated manual transmission(AMT) and dual clutch transmission(DCT) are interested to all manufactures due to their fuel efficiency and driver's convenience, especially in a hybrid system. AMT has advantages in that they have a high efficiency of manual transmissions(MT) and offer operation convenience similar to automatic transmissions(AT), but it has some disadvantages in that they have torque gap during gear shift and shift time. To reduce disadvantages, it is necessary to evaluate errors and characteristics as a developing simulation model before experimental verification. The purpose of this study is to develop virtual components and simulate the transient response of AMT. A dynamic AMT model and a control logic for an integrated vehicle model have been developed using Matlab/Simulink as a simulation platform. In this paper, the clutch model to describe the stick-slip transition mode and the transmission model to describe the neutral gear shifting is introduced and compared with each other.

• 전자공학회논문지T
• /
• 제35T권3호
• /
• pp.67-75
• /
• 1998

이 논문은 이동 장애물 회피를 위한 새로운 로봇 동작 계획을 제안한다. 이동 장애물의 운동성을 고려하여, 로봇과 장애물 사이의 관계를 위해 가상거리 함수를 정의한다. 각각의 샘플링 시간에, 장애물의 움직임을 고려한 인공 전위계를 구성하기 위해 가상거리 함수를 이용한다. 로봇은 인공 전위 함수에 의해 유도된 인력과 척력 벡터에 따라 이동한다. 제안된 알고리즘은 실시간으로 이동 장애물을 회피할 수 있었다. 시뮬레이션 결과를 통해 제안된 알고리즘의 효율성을 입증한다.