• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.571-573
• /
• 2000

기존 분산 가상환경 시스템에서는 참여자들 사이의 언어 외적인 의사교환을 지원하기 위해 참여자의 아바타에 몸짓이나 얼굴 표정 등을 표현할 수 있도록 애니메이션 가능한 아바타를 사용한다. 하지만 아바타 애니메이션으로 참여자의 의사 및 감정 표현을 표현하는데는 한계가 있다. 따라서, 이 논문에서는 가상 환경 내의 다중 사용자들의 의사 교환 및 감정 표현을 극대화할 수 있는 방법으로 실시간 화상 대화 가상 환경 학습.훈련 시스템을 설계하였다. 설계한 시스템은 학습 참여자의 화상 및 음성 스트림을 전달함으로써 기존 응용들에 비해 풍부한 의사 교환을 지원하고, 가상 공간에서 학습에 필요한 다양한 모듈들을 포함하고 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1689-1691
• /
• 2015

인체 장기의 내부 구조를 학습하기 위해 많은 3 차원 인체영상관련 콘텐츠들이 소개되어 왔다. 하지만, 이러한 학습 콘텐츠들은 사실적인 색상을 표현하기 어려울 뿐만 아니라 사용자가 조작할 때 현실감이 떨어지기 때문에 해부도감과 같은 2 차원 학습 콘텐츠와 차별성이 적다. 본 논문에서는 사실적인 인체 색 정보를 가지고 있는 컬러 인체 데이터와 사용자의 동작을 인식하는 센서를 활용하여 몰입감 높은 체험형 가상 내시경 모의 훈련 시스템을 제안한다. 컬러 인체 데이터를 양안시 볼륨렌더링 하여 입체감을 높이고 동작인식 센서를 이용하여 사용자의 손동작으로 직접 가상 내시경 카메라를 조작하여 항행하도록 하였다. 제안한 시스템을 이용하여 다양한 인체 장기의 내부 구조를 사실적으로 표현할 수 있으며 이를 통해 의학정보 학습에 도움을 줄 수 있다.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1996.05a
• /
• pp.608-613
• /
• 1996

본 논문에서는 고온, 고압, 그리고 방사능 준위가 높은 원자력발전소 구조물의 극한환경(Hazardous Environments)에서의 점검 및 보수에 대한 작업자의 훈련을 위해 지능형 상호협조 훈련시스템 (COINS-I: COoperative INtelligent training System-I)의 개념모델을 제안하였다. 비교적 방사능준위가 높은 격납용시 구조물과 보조(Auxiliary) 빌딩을 일차적 극한작업환경으로 설정하였다. 격납용기 구조물과 보조빌딩에 대한 가상발전소 환경(Virtual Plant Environments)을 모델링하여, 극한환경에서의 점검 및 보수훈련 Pilot 연구를 COINS-I의 개발목적으로 하였다. COINS-I은 점검, 보수훈련을 위한 가상발전소 환경을 갖는 극한작업 시뮬레이터, 지능형 Tutoring 기능을 갖는 극한작업 훈련프로그램, 3차원 가상인터페이스 등의 훈련장비를 갖는 훈련설비로 구성된다. COINS-I을 통한 교육 및 훈련 궁극적으로 작업자가 경험치 못한 극한작업(예를들면, 원자로해체, 중대사고, Life-extension 등)의 가상 시뮬레이션을 통한 훈련이 가능하여 방사능 피폭량을 저감하며, 극한작업 자동화를 위한 연구에의 활용이라 하겠다.

• International journal of advanced smart convergence
• /
• v.11 no.3
• /
• pp.49-55
• /
• 2022

Hair styling has a significant influence on human social perception. An increasing number of people are learning hair styling and obtaining hair designer licenses. However, it takes a considerable amount of money and time to learn professional hairstyle and beauty techniques for hair styling. Since COVID-19, there has been a growing need for offline and video lectures due to the decline in onsite training opportunities. This study provides a field practice environment in which real hair beauty is performed in a virtual space. Further, the hairstyle that is most similar to the user's hair taken with a webcam or mobile phone is determined through an image matching system using the speeded up robust features (SURF) method. The matching hairstyle was created into a three-dimensional (3D) hair model. The created 3D hair model uses a head-mounted display (HMD) and a controller that enables finger tracking through mapping to reproduce the haircutting scissors' motion while providing a feeling of real hair beauty.

• Korean Chemical Engineering Research
• /
• v.61 no.3
• /
• pp.388-393
• /
• 2023

The analysis of engineering data using neural network based on supervised learning has been utilized in various engineering fields such as optimization of chemical engineering process, concentration prediction of particulate matter pollution, prediction of thermodynamic phase equilibria, and prediction of physical properties for transport phenomena system. The supervised learning requires training data, and the performance of the supervised learning is affected by the composition and the configurations of the given training data. Among the frequently observed engineering data, the data is given in log-scale such as length of DNA, concentration of analytes, etc. In this study, for widely distributed log-scaled training data of virtual 100×100 images, available loss functions were quantitatively evaluated in terms of (i) confusion matrix, (ii) maximum relative error and (iii) mean relative error. As a result, the loss functions of mean-absolute-percentage-error and mean-squared-logarithmic-error were the optimal functions for the log-scaled training data. Furthermore, we figured out that uniformly selected training data lead to the best prediction performance. The optimal loss functions and method for how to compose training data studied in this work would be applied to engineering problems such as evaluating DNA length, analyzing biomolecules, predicting concentration of colloidal suspension.

• Journal of the Ergonomics Society of Korea
• /
• v.33 no.1
• /
• pp.15-25
• /
• 2014

Objective: This study aims to analyze the factors that affect the ability to maintain dynamic sitting balance (DSB), biomechanical characteristics, and physical characteristics in spinal cord injuries (SCI) patients. Background: Virtual ski training systems, ski equipment, and training protocols for disabled skiers are being studied to spread awareness. However, few studies have been reported on the sitting balance ability associated with chair mono skiing. Method: A dynamic sitting balance border system was built to investigate the ability to maintain dynamic sitting balance in SCI patients. Trunk muscle activity was evaluated by electromyogram while conducting dynamic sitting balance tests. The trunk muscle strength was tested with a portable handheld dynamometer. Physical activity scores were measured with the physical activity recall assessment. Results: There were high levels of correlation between the ability to maintain DSB and trunk flexor strength, extensor strength, rotator strength, and physical activity score. However, height, weight, and injury level in SCI patients were not correlated with the ability to maintain DSB. Additionally, strong negative correlations were found between muscle activities of the external oblique and lumbar erector spinae muscles and the ability to perform the backward tilt test. Trunk extensor muscle activity during the ball lifting test was significantly higher than in other tests. Conclusion: The results indicate that improving trunk muscle strength and physical activity can increase the ability to maintain DSB. Application: The findings of a close relationship between trunk strength, physical activity, and the ability to maintain DSB need to be reflected in the chair mono ski training program.

• Science of Emotion and Sensibility
• /
• v.5 no.4
• /
• pp.45-49
• /
• 2002

Recently, virtual environment systems are used in various application fields such as industry, medicine, and training and education. However, the negative effect, cybersickness including nausea, visual fatigue, and disorientation, could be happened while using VR systems. It prevents VR system from spreading much more. To control the cybersickness, first of all, the objective measurement method should be established. As one of alternative methods, the postural instability could be a measure of cybersickness. In this study, 45 participants' postural sway before and after experiencing a H driving simulator was measured by using a force platform. Especially, we examined if two factors, motion and feedback, could affect on the postural instability The results showed the postural instability slightly increased after experiencing the VR driving simulator. For the factors, the providing of motion synchronized to visual display showed statistical significant decrease in postural sway along lateral side. To check the effectiveness of postural instability as a cybersickness measure, further studies are needed.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.681-687
• /
• 2007

Face recognition technique is very popular for a personal information security and user identification in recent years. However, the face recognition system is very hard to be implemented due to the difficulty where change in illumination, pose and facial expression. In this paper, we consider that an illumination change causing the variety of face appearance, virtual image data is generated and added to the D-LDA which was selected as the most suitable feature extractor. A less sensitive recognition system in illumination is represented in this paper. This way that consider nature of several illumination directions generate the virtual training image data that considered an illumination effect of the directions and the change of illumination density. As result of experiences, D-LDA has a less sensitive property in an illumination through ORL, Yale University and Pohang University face database.

• International Journal of Internet, Broadcasting and Communication
• /
• v.9 no.3
• /
• pp.70-77
• /
• 2017

Dynamic visual acuity is used as an important factor to measure athletic performance in sports field. A study on visual acuity testing system using non-see head mounted display (NST-HMD) was conducted recently. However, the NST-HMD has a problem that the sense of space felt by the subject differs from the actual environment. This is because the view is blocked so that it is only implemented in a virtual space. This paper proposes a dynamic visual acuity testing system using optical see through head mounted display (OST-HMD). To do this, OST-HMD and NST-HMD comparative tests were conducted using existing K-D (King-Devick) charts. Experiments were performed on 30 subjects and their visual acuity was measured and analyzed by parametric statistics and one-sample T-test. The results of the study demonstrate the effectiveness of the proposed OST-HMD. This study is expected to use the visual inspection and training equipment of OST-HMD.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1509-1516
• /
• 2017

In first-person perspective training system, the users needs realistic experience. For providing this experience, the system should offer the users virtual and real images at the same time. We propose an automatic a persons's arm segmentation and image composition method. It consists of arm segmentation part and image composition part. Arm segmentation uses an arbitrary image as input and outputs arm segment or alpha matte. It enables end-to-end learning because we make use of FCN in this part. Image composition part conducts image combination between the result of arm segmentation and other image like road, building, etc. To train the network in arm segmentation, we used arm images through dividing the videos that we took ourselves for the training data.