• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.55-65
• /
• 2022

The purpose of this paper was to investigate the relationship between cybersickness symptoms and visual function and to determine whether visual perception training is effective in reducing symptoms of cybersickness. The study subjects were healthy adult males who experienced the same virtual reality program for 15 minutes. Afterwards, the VR satisfaction score and cybersickness level were measured and classified into a comfortable virtual reality program viewer group (CVR group, 20 people) and an uncomfortable virtual reality program viewer group (UVR group, 20 people). Visual function test was performed on all subjects, and the vision therapy training program was applied to the UVR group once a week for 40 minutes 12 times, and then the visual function and SSQ questionnaire were re-evaluated. Subjects with diplopia were 55% in the UVR group and 5% in the CVR group, which was significantly higher in the UVR group, there were differences in stereopsis, exophoria, near point convergence(p<.01) and vergence function(p<.001) between the two groups. After vision therapy, changes in SSQ, stereopsis, near point convergence, and vergence function of UVR user group were positively changed(p<.01). Therefore, cybersickness symptoms are related to visual function, it seems that the vision therapy can be used as a way to alleviate the symptoms of cybersickness.

• The Korean Journal of Emergency Medical Services
• /
• v.23 no.2
• /
• pp.139-151
• /
• 2019

Purpose: To discuss the records and legal standards of emergency medical technician training institutions in Korea and abroad, to identify the problems, and to provide the basic resources for improving the EMT-basic training institutions. Methods: We received advice through an advisory meeting of experts (professors of department of emergency medical technicians) and interested parties (Korean Association of Emergency Medical Technicians, officials of emergency medical technician training institutions) and referred to various reports published by governments, official institutions, and other trustworthy organizations. Also, we communicated with the related experts abroad (3 countries) on the phone or by email for surveys. Results: Compared to the abroad, it is necessary to categorize the standards and procedures of designating the emergency medical technician training institutions in Korea and improve the management of training institutions to train competent emergency medical technicians. Conclusion: It is necessary to designate and manage continuously the emergency medical technician-basic training programs for the systematic primary healthcare service.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1427-1434
• /
• 2021

In this paper, we propose a psychological state estimation process that computes children's attention and tension in response to training stimuli. Joint attention was adopted as the training stimulus required for behavioral intervention, and the Discrete trial training (DTT) technique was applied as the training protocol. Three types of training stimulation contents are composed to check the user's attention and tension level and provided mounted on a character-shaped tabletop robot. Then, the gaze response to the user's training stimulus is estimated with the vision-based head pose recognition and geometrical calculation model, and the nervous system response is analyzed using the PPG and GSR bio-signals using heart rate variability(HRV) and histogram techniques. Through experiments using robots, it was confirmed that the psychological response of users to training contents on joint attention could be quantified.

• Journal of the Korea Society for Simulation
• /
• v.28 no.2
• /
• pp.159-167
• /
• 2019

In the field of defense M&S, we are actively pursuing researches that interoperable multiple war game models to simulate various combat environments at the same time. Although the 'unit DB(Database)' for operating the war game models is originated from the identical data, it has been recognized that the method of expressing the attribute of the data is different and the cross reference is impossible. As a result, it makes unnecessary time and effort in establishing the same unit DB in the organizations that operate the war game model. In this study, a method of reusing the unit DB of the training war game model to the analysis war game model with similar resolution and simulated logic was applied to the actual field. For this purpose, we defined the procedure for converting the unit DB by analyzing metadata of the 'Chang-Jo21', a combat training model for corps and division, and the 'Vision21', an analysis model for corps and division operation plan. And we introduced an algorithm that can map different metadata of two unit DBs. This study was meaningful as the first attempt to map and integrate heterogeneous metadata semantically for the reuse of unit DB between different war game models in defense M&S field. Also, it provided implications for the necessity of paradigm shift that reuse of the unit DB between two different war game models is possible and the need for standardization of the unit DB metadata in the defense M&S filed.

• Journal of the Korea Convergence Society
• /
• v.11 no.9
• /
• pp.15-20
• /
• 2020

Software-related training can be considered essential in situations where software is an important factor in national innovation, growth and value creation. As one of the implementation methods for engineering education, various education through virtual simulations that can educate difficult situations in a similar environment are being conducted. Recently, the construction of smart factories at production and manufacturing sites is spreading, and product inspections using vision systems are being conducted. However, it has many difficulties due to lack of operation technology of vision system, but it requires a lot of cost to construct the system for education of vision system. In this paper, provide an educational virtual simulation model that integrates computer and physics engine camera functions and can extract and transmit video. It is possible to generate an image of 30Hz or more at an average of 35.4FPS of the experimental results of the proposed model, and it is possible to send and receive images in a time of 22.7ms, which can be utilized in an educational virtual simulation educational environment.

• Physical Therapy Rehabilitation Science
• /
• v.5 no.4
• /
• pp.193-197
• /
• 2016

Objective: In the present study, the effects of visual restriction and unstable base dual-task training (VUDT), stable base dual-task training (SDT), and on stroke patients' balance and concentration abilities were examined. Design: Two-group pretest-posttest design. Methods: Dual-task training was conducted for thirty persons with chronic stroke who were hospitalized or receiving physical therapy and were randomly assigned to either the VUDT group (n=15) or the SDT group (n=15). The subjects were divided into two groups of 15 participants each, the VUDT group and the SDT group. Dual-task training was administered for 30 minutes per session, three times a week for 8 weeks. The participants' balance was measured via the center of pressure migration distances, functional reach test (FRT), Berg Balance Scale (BBS), and attention was measured using the trail-making test and the Stroop test. Results: In comparisons within each group, the two groups showed significant differences before and after the training (p<0.05). In the comparisons between the groups, the VUDT group showed significant improvements in center of pressure (COP), FRT, and BBS, and TMT compared to the SDT group (p<0.05). Conclusions: It would be more effective to conduct dual-task training as a rehabilitation training program under vision restriction and unstable supporting surface conditions than to conduct the test under unstable supporting plane conditions to improve balance and attention in chronic stroke patients.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.33 no.6 s.113
• /
• pp.109-126
• /
• 2006

As the national interest in sports has been increased over time, sports facilities and sports complex are considered more than just physical environments for training athletes or watching games. Sports facilities now become symbolic spatial devices to represent the national and cultural pride of any countries. The existing national training camp located in Taenung, Seoul is gotting outdated and degraded. The polluted air in the city risks athletes' health condition. The government planned to construct the second training camp at Jincheon, Chungbuk at the area of $2,171,910m^2$. The Korea Sports Council called for proposals to envision the future training camp, and they held a design competition from August to November, 2005. The first phase was to present the masterplan for the entire site including training buildings, outdoor training facilities, dormitories, a visitor center, a research center, education and administration buildings. Considering the size of the site, the planning process required a strong relationship between landscape and architecture. This study tries to provide general explanations on the winning proposal focused on the landscape-related issues. It also attempts to have reference points for contemporary planning and design issues to situate the project in the stream of continuing design effort to avoid the dichotomy between nature and culture. The landscape proposal for the new national taming camp suggests four main strategies; 1) The camp has two intersecting and interweaving parks which represent the natural and urban order. 2) The entire site is organized and networked by the flow of landscape called landscape ribbon in terms of topography, vegetation, and water flow. 3) The landscape is choreographed through the time and process. 4) The ecological process and the digital contents are juxtaposed in the landscape. This winning proposal is the first step to portray the national vision for the sustainable environment coexisting with sports industry. Landscape in this proposal is an active agent to network various parts of the site which enables landscape to be infrastructure. Landscape design in this proposal should be considered open-ended strategies rather than determined concrete forms and its engaging further development will be tested in following Design-Build phase.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.217-228
• /
• 2022

The study aimed to build an electronic strategy in innovative learning situations for the role of education in combating intellectual currents. A total of 525 Saudi university faculty members and general education teachers were surveyed using two electronic questionnaires. Arithmetic averages and standard deviations, One-way ANOVA, Scheffé's test, Pearson's correlation coefficient, and Cronbach's alpha stability coefficient were used as statistical methods. The study statistically identifies the differences between the study sample at the level of significance (0.05). and the design of a digital application for individual learning to combat deviant intellectual currents to activate them in light of Saudi Vision 2030 by combining the theoretical academic material and turning it into a learning e-game called (crosswords). The game is equipped with hyper media that supports education with entertainment to direct ideas towards the promotion of identity, the development of values towards moderation and the consolidation of intellectual security. Additionally, the learning e-game represents awareness messages in three short films to activate the role of curricula and intellectual awareness centers to apply realistically, innovatively, and effectively.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.893-903
• /
• 2022

Recently, computer vision (CV)-based safety monitoring (i.e., object detection) system has been widely researched in the construction industry. Sufficient and high-quality data collection is required to detect objects accurately. Such data collection is significant for detecting small objects or images from different camera angles. Although several previous studies proposed novel data augmentation and synthetic data generation approaches, it is still not thoroughly addressed (i.e., limited accuracy) in the dynamic construction work environment. In this study, we proposed a game engine-driven synthetic data generation model to enhance the accuracy of the CV-based object detection model, mainly targeting small objects. In the virtual 3D environment, we generated synthetic data to complement training images by altering the virtual camera angles. The main contribution of this paper is to confirm whether synthetic data generated in the game engine can improve the accuracy of the CV-based object detection model.