• 감성과학
• /
• 제20권3호
• /
• pp.119-130
• /
• 2017

본 연구는 증강현실 홈 트레이닝 시스템을 통해 가상 참여자의 존자개 사용자에게 미치는 영향을 살펴보고자 한다. 구체적으로, 가상의 참여자가 제공되는 경우와 아닌 경우의 몰입, 인지된 경쟁, 그리고 정보 습득의 욕구의 차이에 대해 살펴보았다. 자동으로 실험 참여자들의 자세에 따른 정확도와 피드백을 제공하는 홈 트레이닝 시스템을 직접 개발하였고, 이를 활용하여 다음의 세 가지 가설을 실증하였다. 첫째, 가상의 참여자를 보며 트레이닝 시스템을 사용하면 그렇지 않은 경우보다 몰입이 더욱 높을 것이다. 둘째, 가상의 참여자를 보며 트레이닝 시스템을 사용하면 그렇지 않은 경우보다 인지된 경쟁이 더욱 높을 것이다. 셋째, 가상의 참여자를 보며 트레이닝 시스템을 사용하면 그렇지 않은 경우보다 정보 습득의 욕구가 더욱 높을 것이다. 실험을 통해 세 가지 가설이 모두 지지되었으며, 가상의 참여자가 이용자에 영향을 미침을 확인할 수 있었다. 기존 연구가 가상 트레이닝 시스템 그 자체에 대한 효과를 보는 것에 반해, 본 연구가 가상 트레이닝 시스템을 이용할 때 다른 운동 참여자가 나오는 영상을 보는 것이 유의한가에 대한 답을 하고 있다는 점에서 시사점을 제공한다.

• 로봇학회논문지
• /
• 제14권2호
• /
• pp.122-130
• /
• 2019

Collecting a rich but meaningful training data plays a key role in machine learning and deep learning researches for a self-driving vehicle. This paper introduces a detailed overview of existing open-source simulators which could be used for training self-driving vehicles. After reviewing the simulators, we propose a new effective approach to make a synthetic autonomous vehicle simulation platform suitable for learning and training artificial intelligence algorithms. Specially, we develop a synthetic simulator with various realistic situations and weather conditions which make the autonomous shuttle to learn more realistic situations and handle some unexpected events. The virtual environment is the mimics of the activity of a genuine shuttle vehicle on a physical world. Instead of doing the whole experiment of training in the real physical world, scenarios in 3D virtual worlds are made to calculate the parameters and training the model. From the simulator, the user can obtain data for the various situation and utilize it for the training purpose. Flexible options are available to choose sensors, monitor the output and implement any autonomous driving algorithm. Finally, we verify the effectiveness of the developed simulator by implementing an end-to-end CNN algorithm for training a self-driving shuttle.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2002년도 추계학술대회 논문집
• /
• pp.193-196
• /
• 2002

Successful rehabilitation with respect to the activities of daily living (ADL) requires accurate and effective assessment and training. A number of studies have emphasized the requirement for rehabilitation methods that are both relevant to the patients real world environment, and that can also be transferred to other daily living tasks. Virtual reality (VR) has a many advantage over other ADL rehabilitation techniques, and offers the potential to develop a human performance testing and training environment. Therefore, in this study, the virtual supermarket was developed and the possibility of using a VR system to assess and train cognitive ability in ADL investigated. This study demonstrates that, VR technology offers great promise in the field of ADL training.

• 디지털융복합연구
• /
• 제14권11호
• /
• pp.357-367
• /
• 2016

본 연구에서는 가상현실 기반 신경근 자세조절 융합 훈련을 이용하여 기능적 발목 불안정성을 가진 축구선수들의 균형 능력과 점프 수행력에 미치는 효과에 대하여 알아보고자 하였다. 축구선수는 가상현실 기반 신경근 자세조절 융합 훈련군 15명과 일반적인 트레드밀 훈련군 15명으로 나누어 8주간 주 3회, 30분간 시행하였고, 균형 능력을 평가하기 위해 Biorescue를 이용하여 신체 중심 이동면적, 총 궤적길이, 안정성 한계를 측정하였다. 점프 수행력을 측정하기 위해 Counter movement jump with arm swing과 제자리 멀리 뛰기를 측정하였다. 균형 능력 비교에서는 신체 중심 이동면적과 총 궤적 길이 및 안정선한계에서 통계적으로 유의한 차이를 보였고, 점프 수행력 비교에서는 Counter movement jump with arm swing과 제자리 멀리 뛰기에서 통계적으로 유의한 차이를 보였다. 이에 따라 가상현실 기반 신경근 자세조절 융합 훈련이 일반적인 트레드밀 훈련 보다 균형 능력과 점프 수행력을 향상시키는데 효과적임을 알 수 있었다.

• The Journal of Korean Physical Therapy
• /
• 제26권6호
• /
• pp.430-435
• /
• 2014

Purpose: The objective of this study was a virtual reality-based balance training program effective for improvement in physical function, examined the balance ability and fall efficacy of elderly women with experienced falls, intending to examine the program's usefulness as an exercise program to prevent the recurrence of a fall. Methods: The participants were 30 elderly women aged 65 or older who met the conditions. The participants were randomly assigned to either a balance training group (BT) or a virtual reality-based balance training group (VT) and received the training three times per week, 30 minutes per day, for six weeks. To measure static balance, the Tetrax Portable Multiple System (Tetrax Ltd, Israel) were used. To measure dynamic balance, the Berg Balance Scale (BBS) and functional reach test (FRT) was used, and regarding fall efficacy, the Korean Fall Efficacy Scale (K-FES) was used. Results: Tetrax significantly improved after the intervention in both the BT group and the VT group (p<0.05). The comparison between the two groups was not significantly. BBS and FRT result significantly improved after the intervention in both the BT and VT groups (p<0.001), while K-FES was significantly ameliorated in the VT group only (p<.05). Comparing the groups, there were more significant changes in the BBS (p<0.05) and FRT (p<0.01) result of the VT group than the BT group. Conclusion: A virtual reality-based balance training program is considered to be usable as an exercise program to prevent recurrence of falls in elderly women.

• The Journal of Korean Physical Therapy
• /
• 제21권2호
• /
• pp.31-38
• /
• 2009

Purpose: This study was examined the effect of training using a Virtual Reality System on the sitting balance and Activities of Daily Living for patients with a spinal cord injury. Methods: The subjects were divided into an experimental (6 persons) and control group (5 persons). The experimental group trained the 5 programs, three times per week for 6 weeks using the Virtual Reality System and five days for week using conventional physical therapy. The control group trained five days for a week using conventional physical therapy. Results: The difference in the mean Spinal Cord Independence Measurement (SCIM) score in the experimental and control groups was increased to 8.33 and 6.60 (p=0.79), respectively. The difference in the mean functional reaching test in experimental and control group increased to 4.21 and 1.09 (p=0.25), respectively. The difference in the mean sitting time in experimental and control group increased to 41.05 and 10.33 (p=0.66), respectively. There was a difference in the mean of all variances but these differences were not statistically significant. Conclusion: These results suggest that training using the Virtual Reality System increased the SCIM, functional reaching test and sitting time in people with a spinal cord injury.

• ETRI Journal
• /
• 제44권2호
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• 한국CDE학회논문집
• /
• 제19권4호
• /
• pp.423-433
• /
• 2014

For the proper decision making and responsibility enhancement for an unexpected accident in large-scale facilities, it is important to train operators or first responders to minimize potential human errors and consequences resulted from them. Simulation technologies, including human-computer interaction and virtual reality, enables personnel to participate in simulated hazardous situations with a safe, interactive, repetitive way to perform these training activities. For the development of accident response training simulator, it is necessary to define components comprising the simulator and to integrate them for the given training purpose. In this paper, we analyze requirements of the training simulator, derive key components, and design the training simulator. Based on the design, we developed a prototype training simulator and verified the simulator through experiments.

• 한국컴퓨터그래픽스학회논문지
• /
• 제26권3호
• /
• pp.111-121
• /
• 2020

가상현실의 높은 몰입감을 활용한 실감형 훈련 콘텐츠가 산업, 교육, 의료 등 다양한 분야에서 활용되고 있다. 특히 현실에서 실시하기 힘든 고위험, 고비용이 발생하는 교육훈련을 최신 가상현실 기술을 적용하여 현실과 비슷한 환경에서 효율적이고 안전하게 체험하여 교육효과를 높일 수 있다. 본 논문은 실감형 가상훈련 콘텐츠를 체계적으로 관리하고 정의된 평가요소를 기반으로 훈련 결과를 도식화된 그림으로 가시화하는 관리 시스템을 소개한다. 관리 시스템은 콘텐츠에서 생성되는 정보를 데이터베이스에 저장하여 각 훈련생의 훈련 기록을 실용적으로 관리할 수 있다. 또한 콘텐츠 기반 시나리오 생성 방법으로 훈련 목표, 참여인원, 평가요소 등을 설정하여 하나의 콘텐츠를 여러 시나리오로 생성할 수 있다. 본 논문은 관리 시스템의 제작 방법과 그 결과를 적용 사례인 가상현실 훈련 콘텐츠 기반으로 설명한다.

• 대한안전경영과학회지
• /
• 제2권2호
• /
• pp.21-28
• /
• 2000

In the real environment, it is not easy to get the effective training or to simulate several hazard situations for safety because of the direct exposure to the hazards of the actual system. But the virtual environment(VE) can help the users to get the effective training or to simulate all kind of possible situations without the exposure to the harzards of the actual system. Therefore, the number of virtual reality(VR) application for safety will be increased dramatically in the future. This paper proposes a category of VR applications and also the steps to develope the VE for emergency management.