• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.733-735
• /
• 2014

Example based Super Resolution(SR) is using the correspondence between the low and high resolution image from a database. This method uses only one image to estimate a high resolution image and can get the larger image than 2 times. Example based SR is proposed to solve the problem of classical SR. Neighbor embedding(NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the poor generalization of NE decreases the performance of such algorithm. The sizes of local training sets are always too small to improve the performance of NE. We propose the advanced NE baesd on SVR having an excellent generalization ability to solve this problem. Given a low resolution image, we estimate a pixel in its high resolution version by using SVR based NE. Through experimental results, we quantitatively and qualitatively confirm the improved results of the proposed algorithm when comparing with conventional interpolation methods and NE.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.626-631
• /
• 2019

The policy-making and technological development for the supply expansion of eco-friendly automobiles has been continuing, but the internal combustion engines still accounts for about 95%. Also, in order to meet the stricter emission regulations of internal combustion engines based on fossil fuels, the proportion of after-treatments for vehicles and (ocean going) vessels is gradually increasing. This study is a basic study for the post-Euro-VI exhaust response of CNG buses, and it is to investigate the basic characteristics according to Pd substitution transition metal effect, catalyst volume effect and space velocity. A catalysts was prepared and tested using a model gas reactor. The NGOC catalyst with 3Pd exhibited the highest catalytic activity with 22% at $300^{\circ}C$, 48% at $350^{\circ}C$ and about 75% at $500^{\circ}C$. 3Co NGOC containing 3wt% of transition metal was excellent in oxidation ability, and it was small in size of 2nm, and the degree of catalyst dispersion was improved and de-NO/CO conversion was high. The volume of the NGOC-LNT-SCR catalyst system was optimal in the combination of 1.5+0.5+0.5 with a total score of 165, considering $de-CH_4/NOx$ performance and catalyst cost. For SV $14,000h^{-1}$, the $CH_4$ reduction performance was the highest at about 20%, while the SV $56,000h^{-1}$ was the lowest at about 5%. If the space velocity is small, the flow velocity decreases and the time remaining in the catalyst volume become long, so that the harmful gas was reduced.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.479-488
• /
• 2019

The flight test operational procedure artifact includes mission planning, execution methods, and safety measures for each step of test progress. As the development of guided missiles has become more advanced and strategic, flight test has become increasingly complex and broadened. Therefore, increased reliability of the flight test operation procedures was required to ensure test safety. Particularly, the design of the flight test operational procedures required verification through M&S to predict and prepare for the uncertainty in a new test. The relevant studies have published the optimal framework development for flight tests and the model-based improvements of flight test processes, but they lacked the specificity to be applied directly to the flight test operational procedures. In addition, the flight test operational procedures, which consist of document bases, have caused problems such as limitations of analysis capabilities, insensitive expressions, and lack of scalability for the behavior and performance analysis of test resources. To improve these problems, this paper proposes how to design operational procedure of guided missile flight test system by applying MBSE(Model-based Systems Engineering). This research has improved reliability by increasing the ability to analyze the behavior and performance of test resources, and increased efficiency with the scalability applicable to multiple flight tests. That can be also used continuously for the guided missile flight tests that will be developed in the future.

• Journal of Animal Science and Technology
• /
• v.63 no.2
• /
• pp.367-379
• /
• 2021

The objectives of this study were to evaluate convolutional neural network models and computer vision techniques for the classification of swine posture with high accuracy and to use the derived result in the investigation of the effect of dietary fiber level on the behavioral characteristics of the pregnant sow under low and high ambient temperatures during the last stage of gestation. A total of 27 crossbred sows (Yorkshire × Landrace; average body weight, 192.2 ± 4.8 kg) were assigned to three treatments in a randomized complete block design during the last stage of gestation (days 90 to 114). The sows in group 1 were fed a 3% fiber diet under neutral ambient temperature; the sows in group 2 were fed a diet with 3% fiber under high ambient temperature (HT); the sows in group 3 were fed a 6% fiber diet under HT. Eight popular deep learning-based feature extraction frameworks (DenseNet121, DenseNet201, InceptionResNetV2, InceptionV3, MobileNet, VGG16, VGG19, and Xception) used for automatic swine posture classification were selected and compared using the swine posture image dataset that was constructed under real swine farm conditions. The neural network models showed excellent performance on previously unseen data (ability to generalize). The DenseNet121 feature extractor achieved the best performance with 99.83% accuracy, and both DenseNet201 and MobileNet showed an accuracy of 99.77% for the classification of the image dataset. The behavior of sows classified by the DenseNet121 feature extractor showed that the HT in our study reduced (p < 0.05) the standing behavior of sows and also has a tendency to increase (p = 0.082) lying behavior. High dietary fiber treatment tended to increase (p = 0.064) lying and decrease (p < 0.05) the standing behavior of sows, but there was no change in sitting under HT conditions.

• Journal of dental hygiene science
• /
• v.21 no.4
• /
• pp.233-242
• /
• 2021

Background: The importance of infection with COVID-19 is being emphasized in dentistry with high risks such as aerosols. The purpose of this study is to investigate the knowledge and practice of infection control, stress and coping, and turnover of dental hygienists. Methods: Questionnaire was conducted knowledge and practice of infection control, occupational stress and coping, turnover. Survey data was investigated about 149 dental hygienists from February to March 2021 Data were analyzed t-test, ANOVA, Pearson's correlation using statistical programs of PASW Statistics ver. 21.0. Results: Regarding occupational stress, relationship conflict was higher in the group with less than 2 years of experience (p<0.05). Job anxiety, organizational system, inadequate compensation, and workplace culture were highly surveyed in the 3 to 5 year of experience. The group with more than 6 years of experience had the highest perception of lack of job autonomy (p<0.05). The group with higher knowledge of infection control had lower mean inappropriate rewards and stress (p<0.05). The group with high infection control performance had a lower average in items such as job instability, organizational system, inadequate compensation, workplace culture, and stress. And problem-focused coping ability was found to be high (p<0.05). Infection control knowledge and performance were positively correlated (r=0.251, p<0.01), infection control practice and stress were negatively correlated (r=-0.264, p<0.01), and stress and emotional coping were positively correlated (r=0.367, p<0.01). Stress was positively correlated with turnover rate (r=0.549, p<0.01). Conclusion: Infection control training was required to reduce occupational stress. Occupational stress was highly correlated with turnover, a holistic and systemic organizational operation and improvement of the quality of medical care were required to reduce stress.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.309-315
• /
• 2022

The purpose of this study is to analyze the correlation between importance and satisfaction of beauty contest using IPA(Importance-Performance Analysis) by deriving the quality factors of contest for revitalize beauty contest. For the study, a survey was conducted on participants with experience participating in beauty contest, and the collected data were analyzed using a response sample t-test and a PIA matrix. The results are as follows. First, there was a difference in importance and satisfaction as the average of importance was high. Second, in the first quadrant of the IPA matrix, contents related to contest assignment were mainly shown. This was analyzed as an effective factor that can improve the quality of the competition. Third, in the second quadrant, factors related to contest review were distributed. Accordingly, measures are required to increase the expertise and transparency of review. Fourth, in the third quadrant, the contents of the contest operation are mainly shown, and the satisfaction level is low, but supplementing it will have an improvement effect. Fifth, in the fourth quadrant, the satisfaction of the ability improvement item was high, which is analyzed that the contest experience affects the improvement of individual skills. Through this, it is significant to be used as basic data to establish a plan for revitalizing beauty contest.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.378-390
• /
• 2022

With the recent development of deep composite multiplication neural network learning, deep learning techniques applied to single-image super-resolution have shown good results, and the strong expression ability of deep networks has enabled complex nonlinear mapping between low-resolution and high-resolution images. However, there are limitations in applying it to real-time or low-power devices with increasing parameters and computational amounts due to excessive use of composite multiplication neural networks. This paper uses blocks that extract hierarchical characteristics little by little using information distillation and suggests the Recursive Distillation Super Resolution Network (RDSRN), a lightweight network that improves performance by making more accurate high frequency components through high frequency residual purification blocks. It was confirmed that the proposed network restores images of similar quality compared to RDN, restores images 3.5 times faster with about 32 times fewer parameters and about 10 times less computation, and produces 0.16 dB better performance with about 2.2 times less parameters and 1.8 times faster processing time than the existing lightweight network CARN.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.2
• /
• pp.123-135
• /
• 2021

The data processing of this study is focused on keywords related to 'Corona 19 and professional baseball' and 'Corona 19 and professional baseball no spectators', using text mining and social network analysis of textom program to identify problems and view quality. It was used to set the variable of For quantitative analysis, a questionnaire on viewing quality was constructed, and out of 270 survey respondents, 250 questionnaires were used for the final study. As a tool for securing the validity and reliability of the questionnaire, exploratory factor analysis and reliability analysis were conducted, and IPA analysis (importance-satisfaction) was conducted based on the questionnaire that secured validity and reliability, and the results and strategies were presented. As a result of IPA analysis, factors related to the image (image composition, image coloration, image clarity, image enlargement and composition, high-quality image) were found in the first quadrant, and the second quadrant was the game situation (support team game level, support player game level, star). Player discovery, competition with rival teams), game information (match schedule information, player information check, team performance and player performance, game information), interaction (consensus with the supporting team), and some factors appeared. The factors of commentator (baseball-related knowledge, communication ability, pronunciation and voice, use of standard language, introduction of game-related information) and interaction (real-time communication with the front desk, sympathy with viewers, information exchange such as chatting) appeared.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.10-21
• /
• 2022

In order to improve formal presentation attitudes such as presentation of job interviews and presentation of project results at the company, there are few automated methods other than observation by colleagues or professors. In previous studies, it was reported that the speaker's stable speech and gaze processing affect the delivery power in the presentation. Also, there are studies that show that proper feedback on one's presentation has the effect of increasing the presenter's ability to present. In this paper, considering the positive aspects of correction, we developed a program that intelligently corrects the wrong presentation habits and attitudes of college students through facial analysis of videos and analyzed the proposed program's performance. The proposed program was developed through web-based verification of the use of redundant words and facial recognition and textualization of the presentation contents. To this end, an artificial intelligence model for classification was developed, and after extracting the video object, facial feature points were recognized based on the coordinates. Then, using 4000 facial data, the performance of the algorithm in this paper was compared and analyzed with the case of facial recognition using a Teachable Machine. Use the program to help presenters by correcting their presentation attitude.

• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.513-518
• /
• 2022

Electron beam quality assurance (QA) should be done regularly for accurate radiation therapy. However, QA tools used in clinical practice are designed mainly for X-rays. So, a dosimeter for electron beam QA is required. Therefore, in this study, the electron beam detection performance was measured by using a thorium bromide material as an electron beam sensor. In addition, it was evaluated whether it could be applied with an electron beam QA dosimeter. Reproducibility, linearity, and dose rate dependence were evaluated at 6 MeV and 9 MeV energies. As a result of reproducibility, it showed a maximum output change of 0.92% at 6 MeV and 1.15% at 9 MeV. The linearity result evaluation and determination coefficient were presented as 0.9998. As a result of dose rate dependence evaluation, relative standard deviation 0.51% at 6 MeV and relative standard deviation 1.07% at 9 MeV were presented. The manufactured TlBr sensor shows the ability to detect radiation that meets the criteria for evaluation of reproducibility, linearity, and dose rate dependence. These results mean that the TlBr dosimeter is applicable as an electron beam QA dosimeter.