• Journal of Animal Science and Technology
• /
• v.48 no.4
• /
• pp.521-532
• /
• 2006

An in vitro study was conducted to examine the effect of addition level of carbohydrates on fermentation characteristics, and bio-hydrogenation of unsaturated fatty acids by mixed rumen bacteria when incubated with soybean oil or flaxseed oil. Four levels(0%, 0.3%, 0.6% and 0.9%, w/v) of the mixed carbohydrates(glucose, cellobiose, soluble starch, 1:1:1, in weight basis) and oil sources(soybean or flaxseed oil, 60mg in 150ml culture solution) were added to the mixed solution of strained rumen fluid with artificial saliva(1:4, v/v), and incubated anaerobically for 12 hours at 39℃. pH and ammonia-N concentration were lower by increasing the substrate levels at all incubation periods(P<0.05～P<0.001). The propionate proportion increased(P<0.001), but acetic acid and butyric acid decreased(P<0.001) with the substrate level at 6 and 12 h incubations. Oil sources did not influence the proportions of individual VFA. At the end of incubation, the proportions of C18:0(P<0.01), C18:1(P<0.001) and trans-11C-18:1(P<0.01) were reduced but those of C18:2(P<0.001) and C18:3(P<0.01) were enhanced by the addition of flaxseed oil compared to addition of soybean oil. The proportions of C18:0 and total CLA were reduced(P<0.01) but those of trans-11-C18: (P<0.05) and C18:2(P<0.01) were increased with the substrate level when incubated with soybean oil or flaxseed oil. There were interactions(P<0.05) in the proportions of C18:1, C18:2 and C18:3(P<0.01) between oil source and substrate level. The proportions of cis-9, trans-11-CLA and trans-10, cis-12-CLA tended to reduce with substrate level, although there was no significant difference between treatments.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.303-308
• /
• 2020

The ReLU(Rectified Linear Unit) function has been dominantly used as a standard activation function in most deep artificial neural network models since it was proposed. Later, Leaky ReLU, Swish, and Mish activation functions were presented to replace ReLU, which showed improved performance over existing ReLU function in image classification task. Therefore, we recognized the need to experiment with whether performance improvements could be achieved by replacing the RELU with other activation functions in the super resolution task. In this paper, the performance was compared by changing the activation functions in EDSR model, which showed stable performance in the super resolution task. As a result, in experiments conducted with changing the activation function of EDSR, when the resolution was converted to double, the existing activation function, ReLU, showed similar or higher performance than the other activation functions used in the experiment. When the resolution was converted to four times, Leaky ReLU and Swish function showed slightly improved performance over ReLU. PSNR and SSIM, which can quantitatively evaluate the quality of images, were able to identify average performance improvements of 0.06%, 0.05% when using Leaky ReLU, and average performance improvements of 0.06% and 0.03% when using Swish. When the resolution is converted to eight times, the Mish function shows a slight average performance improvement over the ReLU. Using Mish, PSNR and SSIM were able to identify an average of 0.06% and 0.02% performance improvement over the RELU. In conclusion, Leaky ReLU and Swish showed improved performance compared to ReLU for super resolution that converts resolution four times and Mish showed improved performance compared to ReLU for super resolution that converts resolution eight times. In future study, we should conduct comparative experiments to replace activation functions with Leaky ReLU, Swish and Mish to improve performance in other super resolution models.

• Journal of fish pathology
• /
• v.23 no.2
• /
• pp.199-209
• /
• 2010

This study was aimed to investigate the effects in different immersion doses of garlic, Allium sativum, juice to modulate on the nonspecific immune responses of the olive flounder, Paralichthys olivaceus, artificially prechallenged with Streptococcus iniae BS10 and Edwardsiella tarda KE-1, respectively. The nonspecific immune responses of the tested fish were assessed in term of skin mucus lysozyme activity, the change of bacterial cell counts in organs, the number of lymphocytes and neutrophils in blood, and SOD activity. Almost groups of the prechallenged with either S. iniae BS10 or E. tarda KE-1 fish which had been immersed in garlic juice showed the enhanced skin mucus lysozyme activity, the number of lymphocytes and neutrophils in blood, and SOD activity in the kidney but the decreased the number of bacterial cell in surveyed organs. RPS in the group immersed in 0.25 g/L of garlic juice was much higher than in other immersed test groups. These results suggested that the garlic juice immersion can be effective on enhancement of the nonspecific immune responses and the protective ability of olive flounder to the artificial challenge with S. iniae BS10 and E. tarda KE-1.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.171-187
• /
• 2023

When a person's face is recognized through a recording device such as a low-pixel surveillance camera, it is difficult to capture the face due to low image quality. In situations where it is difficult to recognize a person's face, problems such as not being able to identify a criminal suspect or a missing person may occur. Existing studies on face recognition used refined datasets, so the performance could not be measured in various environments. Therefore, to solve the problem of poor face recognition performance in low-quality images, this paper proposes a method to generate high-quality images by performing image quality improvement on low-quality facial images considering various environments, and then improve the performance of facial feature point detection. To confirm the practical applicability of the proposed architecture, an experiment was conducted by selecting a data set in which people appear relatively small in the entire image. In addition, by choosing a facial image dataset considering the mask-wearing situation, the possibility of expanding to real problems was explored. As a result of measuring the performance of the feature point detection model by improving the image quality of the face image, it was confirmed that the face detection after improvement was enhanced by an average of 3.47 times in the case of images without a mask and 9.92 times in the case of wearing a mask. It was confirmed that the RMSE for facial feature points decreased by an average of 8.49 times when wearing a mask and by an average of 2.02 times when not wearing a mask. Therefore, it was possible to verify the applicability of the proposed method by increasing the recognition rate for facial images captured in low quality through image quality improvement.

• The Mathematical Education
• /
• v.63 no.2
• /
• pp.255-272
• /
• 2024

This study aims to design mathematics-integrated classes that cultivate artificial intelligence (AI) thinking and to analyze students' AI thinking within these classes. To do this, four classes were designed through the integration of the AI4K12 Initiative's AI Big Ideas with the 2015 revised elementary mathematics curriculum. Implementation of three classes took place with 5th and 6th grade elementary school students. Leveraging the computational thinking taxonomy and the AI thinking components, a comprehensive framework for analyzing of AI thinking was established. Using this framework, analysis of students' AI thinking during these classes was conducted based on classroom discourse and supplementary worksheets. The results of the analysis were peer-reviewed by two researchers. The research findings affirm the potential of mathematics-integrated classes in nurturing students' AI thinking and underscore the viability of AI education for elementary school students. The classes, based on AI Big Ideas, facilitated elementary students' understanding of AI concepts and principles, enhanced their grasp of mathematical content elements, and reinforced mathematical process aspects. Furthermore, through activities that maintain structural consistency with previous problem-solving methods while applying them to new problems, the potential for the transfer of AI thinking was evidenced.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.187-201
• /
• 2024

Osteoporosis is a major health issue globally, often remaining undetected until a fracture occurs. To facilitate early detection, deep learning (DL) models were developed to classify osteoporosis using abdominal computed tomography (CT) scans. This study was conducted using retrospectively collected data from 3,012 contrast-enhanced abdominal CT scans. The DL models developed in this study were constructed for using image data, demographic/clinical information, and multi-modality data, respectively. Patients were categorized into the normal, osteopenia, and osteoporosis groups based on their T-scores, obtained from dual-energy X-ray absorptiometry, into normal, osteopenia, and osteoporosis groups. The models showed high accuracy and effectiveness, with the combined data model performing the best, achieving an area under the receiver operating characteristic curve of 0.94 and an accuracy of 0.80. The image-based model also performed well, while the demographic data model had lower accuracy and effectiveness. In addition, the DL model was interpreted by gradient-weighted class activation mapping (Grad-CAM) to highlight clinically relevant features in the images, revealing the femoral neck as a common site for fractures. The study shows that DL can accurately identify osteoporosis stages from clinical data, indicating the potential of abdominal CT scans in early osteoporosis detection and reducing fracture risks with prompt treatment.