• Korean Journal of Remote Sensing
• /
• v.22 no.2
• /
• pp.111-121
• /
• 2006

The classification using spectral angle is a new approach based on the fact that the spectra of the same type of surface objects in RS data are approximately linearly scaled variations of one another due to atmospheric and topographic effects. There are many researches on the unsupervised classification using spectral angle recently. Nevertheless, there are only a few which consider the characteristics of Hyperspectral data. On this study, we propose the ISOMUSAC(Iterative Self-Organizing Modified Unsupervised Spectral Angle Classification) which can supplement the defects of previous unsupervised spectral angle classification. ISOMUSAC uses the Angle Division for the selection of seed points and calculates the center of clusters using spectral angle. In addition, ISOMUSAC perform the iterative merging and splitting clusters. As a result, the proposed algorithm can reduce the time of processing and generate better classification result than previous unsupervised classification algorithms by visual and quantitative analysis. For the comparison with previous unsupervised spectral angle classification by quantitative analysis, we propose Validity Index using spectral angle.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.343-353
• /
• 2021

Historical dramas are changing in response to the public who wants more dramatic development, and historical costumes are also expressed in a modern sense. The purpose of this study is to examine the modernization of historical costumes in historical dramas and how the modernization of historical costumes in historical dramas is fostered from the learner's point of view with suggesting implications. As a result of this study, first, the essential problem with the modernization of historical costumes was the excessive modern transformation that undermines historical facts in historical dramas. Second, the negative perceptions of the modernization of historical costumes in historical dramas included the loss of the unique Korean identity, decreased immersion in drama, and the educational influence of media. Positive perceptions focused on the increased interest through raising awareness of traditional culture, compromises on changes in the times, and increased visual play of the public. Third, the implications of the modernization of historical costumes in historical dramas require the awareness improvement of participants in historical drama and a thorough preliminary investigation by the costume designer on the historical costume, an in-depth study of traditional costumes, a systematic educational approach, viewers' attention, and government effort.

• Asian Spine Journal
• /
• v.12 no.6
• /
• pp.1106-1116
• /
• 2018

Study Design: Prospective observational study. Purpose: To evaluate the disability domains relevant to Indian patients with low backache and propose a modified disability questionnaire for such patients. Overview of Literature: The Oswestry Disability Index (ODI) is a self-reported measurement tool that measures both pain and functional status and is used for evaluating disability caused by lower backache. Although ODI remains a good tool for disability assessment, from the Indian perspective questions related to weight lifting and sexual activity of ODI are questioned in some of the earlier studies. Activities of daily living in Indian patients vary substantially from those in other populations and include activities like bending forwards, sitting in floor and squatting which are not represented in the ODI. Methods: In this prospective observational study, a seven-step approach was used for the development of a questionnaire. Thirty patients were interviewed to identify the most challenging issue they faced while performing their daily activities (by free listing) and understand how important the questionnaire items were in terms of the standard ODI. Thus, a comprehensive disability questionnaire comprising 14 questions was developed and administered to 88 patients. Both qualitative (interviews) and quantitative methods (to establish the validity, reliability, and correlation with the Visual Analog Scale [VAS] and Rolland Morris disability questionnaire) were used to identify the 10 questions that best addressed the disability domains relevant to Indian patients. Results: According to free listing, four new questions pertaining to bending forward, sitting on the floor, walking on uneven surfaces, and work-related disabilities were included. In the second phase, wherein the questionnaire with 14 items was used, 56.8% patients did not answer the questions related to sexual activity, whereas 23.8% did not answer those related to walking on uneven surfaces. The modified questionnaire demonstrated good internal consistency (Cronbach's alpha=0.892) and correlation with the Rolland Morris questionnaire (Cronbach's alpha=0.850, p>0.05), as well as with the VAS score for disability (Cronbach's alpha=0.712, p>0.05) and pain (Cronbach's alpha=0.625, p>0.05). Conclusions: A modified disability questionnaire that was designed by adding two questions related to bending forward and work status and removing questions related to sexual activity and weight lifting or traveling (depending on the occupation) can help evaluate disability caused by back pain in Indian population.

• 재활복지
• /
• v.21 no.3
• /
• pp.129-146
• /
• 2017

In an event of an emergency, such as fire in a building, visually impaired and blind people are prone to exposed to a level of danger that is greater than that of normal people, for they cannot be aware of it quickly. Current fire detection methods such as smoke detector is very slow and unreliable because it usually uses chemical sensor based technology to detect fire particles. But by using vision sensor instead, fire can be proven to be detected much faster as we show in our experiments. Previous studies have applied various image processing and machine learning techniques to detect fire, but they usually don't work very well because these techniques require hand-crafted features that do not generalize well to various scenarios. But with the help of recent advancement in the field of deep learning, this research can be conducted to help solve this problem by using deep learning-based object detector that can detect fire using images from security camera. Deep learning based approach can learn features automatically so they can usually generalize well to various scenes. In order to ensure maximum capacity, we applied the latest technologies in the field of computer vision such as YOLO detector in order to solve this task. Considering the trade-off between recall vs. complexity, we introduced two convolutional neural networks with slightly different model's complexity to detect fire at different recall rate. Both models can detect fire at 99% average precision, but one model has 76% recall at 30 FPS while another has 61% recall at 50 FPS. We also compare our model memory consumption with each other and show our models robustness by testing on various real-world scenarios.

• Anxiety and mood
• /
• v.15 no.1
• /
• pp.45-52
• /
• 2019

Objective : The objective of this study is to determine the effects of fear of Middle East respiratory syndrome (MERS) on socio-psychological health during an outbreak of MERS and the post-traumatic stress as a mediator on the relationship between stress and socio-psychological health. Methods : Visual Analog Scale, Impact of Event Scale -Revised, Psychosocial well-being index short form was implemented for 150 medical persons who worked at the hospital in which exposure to MERS cases had been confirmed and 96 ordinary people. A Pearson correlation coefficient and a hierarchical multiple regression was carried out to confirm the effect of fear of MERS and the mediating effect of post-traumatic stress between fear and socio-psychological health. Results : The higher the fear, the lower the socio-psychological health in both healthcare workers and the public (r=0.32, p<0.01) and the higher post-traumatic stress (r=0.32, p<0.01). But, the research results showed that only healthcare workers had a partially mediating effect of post-traumatic stress in the relationship between fear and socio-psychological health (${\beta}=0.45$, t=6.33 p<0.001), (${\beta}$ value : 0.39>0.26). Conclusion : This study demonstrated that the post-traumatic stress can indirectly lead to a negative effect on the socio-psychological health of healthcare workers when under the fear of MERS and shows adverse effects on psycho-social wellbeing. This suggests that clinical intervention and psycho-social approach aiming at reducing post-traumatic stress is important to maintain mental health during crisis development.

• Journal of the HCI Society of Korea
• /
• v.14 no.2
• /
• pp.49-60
• /
• 2019

With the appearance of self-driving cars and electric cars, the automobile industry is rapidly changing. In the midst of these changes, HMI studies are becoming more important as to how the driver obtains safety and convenience with controlling the vehicle. This study sought to understand how automobile manufacturers understand the driving situation, and how they define and limit driver interaction. For this, prior studies about HMI were reviewed and 15 participants performed an on-road study to drive vehicles from five manufacturers with using their interfaces. The results of the study confirmed that buttons and switches that are easily controlled by the user while driving were different from manufacturer to manufacturer. And there are some buttons that are more intensively controlled and others that are difficult to control while driving. It was able to derive 'selection and concentration' from Audi's vehicle, 'optimization of the driving ' from BMW's, 'simple and minimize' from Benz's vehicle, 'remove the manual distraction' from the vehicle of Lexus, and 'visual stability' from KIA's vehicle as the distinctive keywords for the HMI. This shows that each manufacturer has a different definition and interpretation of the driver's driving control area. This study has a distinct value in that it has identified the characteristics of vehicle-specific HMI in actual driving conditions, which is not apparent in appearance. It is expected that this research approach can be useful to see differences in interaction through actual driving despite changes in driving environment such as vehicle platooning and self-driving technology.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.3
• /
• pp.197-202
• /
• 2019

In the era of the fourth revolution, interest in content production using proven engines in the broadcasting sector, such as Vizrt, is growing. The new visual effects required in the 5G era are critical to content production training. Vizrt has a good production time utility and affordability for broadcast and media content. In this paper, we are going to use this to present a practical case of the theorem and application of the basic training course in the production of virtual content, and to present the basic training direction. In the introduction, the graphic algorithm analyzed and studied the characteristics and environmental factors of the Vizrt engine. In this paper, the production process was studied separately, and the work carried out through engine implementation was presented. The VS Studio Foundation was provided as a practical production case at each stage. The Vizrt engine operator process is important in graphic approach and application, and through the results of the lecture, the method of understanding and implementing algorithms for virtual reality perspective suitable for basic learning was studied. Based on practice, the research method of main theory was to create Vizrt contents specialized in 5G contents work in each sector and to implement graphic production in new areas from contents image. Through this study, we came to the conclusion of the basic training method through virtual reality content work based on Vizrt by practicing content creation according to the subject. It also proposes the effect of creating Vizrt content and the direction of building Vizrt basic training courses.

• Journal of Korean Neurosurgical Society
• /
• v.62 no.4
• /
• pp.422-431
• /
• 2019

Objective : In an aging society, the number of patients with symptomatic degenerative spondylolisthesis (DS) is increasing and there is an emerging need for fusion surgery. However, few studies have compared transforaminal lumbar interbody fusion (TLIF) and lateral lumbar interbody fusion (LLIF) for the treatment of patients with DS. The purpose of this study was to investigate the clinical and radiological outcomes between TLIF and LLIF in DS. Methods : We enrolled patients with symptomatic DS at L4-5 who underwent TLIF with open pedicle screw fixation (TLIF group, n=41) or minimally invasive LLIF with percutaneous pedicle screw fixation (LLIF group, n=39) and were followed-up for more than one year. Clinical (visual analog scale and Oswestry disability index) and radiological outcomes (spondylolisthesis rate, segmental sagittal angle [SSA], mean disc height [MDH], intervertebral foramen height [FH], cage subsidence, and fusion rate) were assessed. And we assessed the changes in radiological parameters between the postoperative and the last follow-up periods. Results : Preoperative radiological parameters were not significantly different between the two groups. LLIF was significantly superior to TLIF in immediate postoperative radiological results, including reduction of spondylolisthesis rate (3.8% and 7.2%), increase in MDH (13.9 mm and 10.3 mm) and FH (21.9 mm and 19.4 mm), and correction of SSA ($18.9^{\circ}$ and $15.6^{\circ}$) (p<0.01), and the changes were more stable from the postoperative period to the last follow-up (p<0.01). Cage subsidence was observed significantly less in LLIF (n=6) than TLIF (n=21). Fusion rate was not different between the two groups. The clinical outcomes did not differ significantly at any time point between the two groups. Complications were not statistically significant. However, TLIF showed chronic mechanical problems with screw loosening in four patients and LLIF showed temporary symptoms associated with the surgical approach, such as psoas and ileus muscle symptoms in three and two cases, respectively. Conclusion : LLIF was more effective than TLIF for spondylolisthesis reduction, likely due to the higher profile cage and ligamentotactic effect. In addition, LLIF showed mechanical stability of the reduction level by using a cage with a larger footprint. Therefore, LLIF should be considered a surgical option before TLIF for patients with unstable DS.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.3
• /
• pp.303-310
• /
• 2021

Cracks in bridges are important factors that indicate the condition of bridges and should be monitored periodically. However, a visual inspection conducted by a human expert has problems in cost, time, and reliability. Therefore, in recent years, researches to apply a deep learning model are started to be conducted. Deep learning requires sufficient data on the situations to be predicted, but bridge crack data is relatively difficult to obtain. In particular, it is difficult to collect a large amount of crack data in a specific situation because the shape of bridge cracks may vary depending on the bridge's design, location, and construction method. This study developed a crack detection model that generates and trains insufficient crack data through a Generative Adversarial Network. GAN successfully generated data statistically similar to the given crack data, and accordingly, crack detection was possible with about 3% higher accuracy when using the generated image than when the generated image was not used. This approach is expected to effectively improve the performance of the detection model as it is applied when crack detection on bridges is required, though there is not enough data, also when there is relatively little or much data f or one class.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.6
• /
• pp.751-760
• /
• 2021

Most bridges in Korea are over 20 years old, and many problems linked to their deterioration are being reported. The current practice for bridge inspection mainly depends on expert evaluation, which can be subjective. Recent studies have introduced data-driven methods using building information modeling, which can be more efficient and objective, but these methods require manual procedures that consume time and money. To overcome this, this study developed an image-based automaticbridge component classification network to reduce the time and cost required for converting the visual information of bridges to a digital model. The proposed method comprises two convolutional neural networks. The first network estimates the type of the bridge based on the superstructure, and the second network classifies the bridge components. In avalidation test, the proposed system automatically classified the components of 461 bridge images with 96.6 % of accuracy. The proposed approach is expected to contribute toward current bridge maintenance practice.