• Journal of radiological science and technology
• /
• v.45 no.1
• /
• pp.41-47
• /
• 2022

The purpose of this study is to apply a deep learning model that can distinguish lung perfusion and lung ventilation images in nuclear medicine, and to evaluate the image classification ability. Image data pre-processing was performed in the following order: image matrix size adjustment, min-max normalization, image center position adjustment, train/validation/test data set classification, and data augmentation. The convolutional neural network(CNN) structures of VGG-16, ResNet-18, Inception-ResNet-v2, and SE-ResNeXt-101 were used. For classification model evaluation, performance evaluation index of classification model, class activation map(CAM), and statistical image evaluation method were applied. As for the performance evaluation index of the classification model, SE-ResNeXt-101 and Inception-ResNet-v2 showed the highest performance with the same results. As a result of CAM, cardiac and right lung regions were highly activated in lung perfusion, and upper lung and neck regions were highly activated in lung ventilation. Statistical image evaluation showed a meaningful difference between SE-ResNeXt-101 and Inception-ResNet-v2. As a result of the study, the applicability of the CNN model for lung scintigraphy classification was confirmed. In the future, it is expected that it will be used as basic data for research on new artificial intelligence models and will help stable image management in clinical practice.

• Geomechanics and Engineering
• /
• v.12 no.1
• /
• pp.35-52
• /
• 2017

In order to evaluate the grouting effects of water-rich fault in tunnels systematically, a feasible and scientific method is introduced based on the extension theory. First, eight main influencing factors are chosen as evaluation indexes by analyzing the changes of permeability, mechanical properties and deformation of surrounding rocks. The model of evaluating grouting effects based on the extension theory is established following this. According to four quality grades of grouting effects, normalization of evaluation indexes is carried out, aiming to meet the requirement of extension theory on data format. The index weight is allocated by adopting the entropy method. Finally, the model is applied to the grouting effects evaluation in water-rich fault F4-4 of Qingdao Jiaozhou Bay Subsea Tunnel, China. The evaluation results are in good agreement with the test results on the site, which shows that the evaluation model is feasible in this field, providing a powerful tool for systematically evaluating the grouting effects of water-rich fault in tunnels.

• The Korean Journal of Physiology and Pharmacology
• /
• v.9 no.3
• /
• pp.159-164
• /
• 2005

Effects of antioxidants on the established nephropathy were investigated. The experimental nephropathy was induced in rats by intravenous injection of adriamycin (2 mg/kg). Six weeks later, when proteinuria was apparent, the rats were supplemented with N-acetylcysteine (NAC, 1 g/kg/day) in drinking water for additional 6 weeks. Glomerulosclerosis score and tubulointerstitial injury index were determined by light microscopy. Expression of transforming growth factor (TGF) ${\beta}1$ and laminin ${\beta}1$ was determined in the renal cortex by reverse transcription-polymerase chain reaction, Western blotting, immunohistochemistry, and immunogold electron microscopy. The adriamycin-induced proteinuria as well as the glomerulosclerosis and tubulointerstitial injury was ameliorated by the treatment with NAC. Adriamycin increased the expression of TGF ${\beta}1$ mRNA and protein, which was ameliorated by NAC. Although the expression of laminin ${\beta}1$ mRNA was increased, adriamycin did not significantly alter that of its protein. These results indicate that antioxidants ameliorate the established nephropathy in association with normalization of overexpressed TGF ${\beta}1$.

• International Journal of Highway Engineering
• /
• v.17 no.6
• /
• pp.117-126
• /
• 2015

PURPOSES : This study prioritizes potential technology for establishing a safe work zone environment on roadways. We consider almost all conceivable technologies that enable mitigation of unexpected accidents for both road workers and drivers. METHODS : This study suggests a methodology to set the priority of potential technology for establishing a safe work zone environment by using the analytical hierarchy process (AHP). For this purpose, the AHP structure was first developed. Thereafter, a web-based survey was conducted to collect experts' opinions. Based on the survey results, weights associated with the relevant criteria of the developed structure were estimated. With the consistency index (CI) and consistency ratio (CR), we verified the estimated weights. In addition, a sensitivity analysis was performed to confirm whether the estimated weights were reliable. We finally proposed the priority for potential technology for establishing a safe work zone environment on roadways. RESULTS : In the first level, safety technology has the highest priority, and real-time information delivery for work zone, hazard warning for drivers, and temporal automated operation for traffic facilities were selected in the second level of hierarchy. CONCLUSIONS : The results imply that establishing the priority will be useful to establish a future road map for improving the work environment for road workers and drivers by employing appropriate protection facilities and developing safety systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.10
• /
• pp.2102-2111
• /
• 1997

Hand written numeral is projected on the 3D space after pre-processing of inputs and it makes a index by tracking of numerals. It computes the distance between extracted every features. It is used by input part of recognition process from the statistical historgram of the normalization of data in order to adaptation from variation. One hundred unmeral patterns have used for making a standard feature map and 100 pattern for the recogintion experiment. The result of it, we have the recoginition rete is 93.5% based on thresholding is 0.20 and 97.5% based on 0.25.

• Journal of Information Technology Services
• /
• v.11 no.sup
• /
• pp.61-74
• /
• 2012

As the retail industry has been challenged by stiff competition, the retailer becomes more interested in better understanding consumers' in-store behavior to gain and sustain competitive advantage. Consumers' shopping paths provide valuable clues to understanding customers' in-store behavior, which has been a long standing research issue in business. This study is to explore the shopping path patterns in a grocery using RFID technology and clustering method. To this end, we designed the RFID systems, affixing active RFID tags to the bottom of grocery carts. The tag emit signal that is received by receptors installed at various location throughout the store. The RFID systems provide the time and location of the cart while consumers shop around the store. The point of sale data are matched with the cart movement records to provide a complete picture of each shopping path. To find the distinctive patterns of consumers' shopping paths, we proposed the distance-index matrix using dijkstra method and normalization method to conduct the clustering in order to handle the problem in measuring the similarity among shopping paths, which is raised by the spatial nature of consumer movement in a grocery. After analyzing the RFID data obtained in one of the groceries in a major Korean retailer, we could successfully identify several distinctive patterns of shopping paths, which prove to provide the valuable implications for store management.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.53.1-53.1
• /
• 2011

We analyze the halo and galaxy catalogs from the Millennium simulations at redshifts z=0, 0.5, 1 to determine the alignment profiles of cluster galaxies in terms of the matter density correlation coefficient and discuss a cosmological implication our result has for breaking parameter degeneracies. For each selected cluster, we measure the alignment between the major axes of the pseudo inertia tensors from all satellites within cluster's virial radius and from only those satellites within some smaller radius. Then we average the measured values over the similar-mass sample to determine the cluster galaxy alignment profile as a function of top-hat scale difference at each redshift. It is shown that the alignment profile of cluster galaxies is well approximated by a power-law of the nonlinear density correlation coefficient that is independent of the power spectrum normalization and bias factor. The alignment profile of cluster galaxies is found to have higher amplitude and lower power-law index when averaged over the larger-mass sample and to have rather weak redshift-dependence. This result is consistent with the picture that the satellite galaxies retain the memory of the external tidal fields right after merging and infalling into the clusters but they gradually lose the initial alignment tendency as the cluster's relaxation proceeds. Demonstrating that the nonlinear density correlation coefficient varies sensitively with the density parameter and neutrino mass fraction, we discuss a potential power of the cluster galaxy alignment profile as an independent probe of cosmology.

• Journal of the Korean Applied Science and Technology
• /
• v.37 no.3
• /
• pp.604-612
• /
• 2020

The purpose of this study is to analyze the level of obesity and sarcopenia among chronic obstructive pulmonary disease(COPD) patients in Korea. The current study recruited 75 patients with COPD who visited the department of respiratory medicine at J University Hospital in J-do. Height, body weight, waist circumference, and hip circumference were measured, and body composition, muscle strength, and flexibility were assessed. The levels of obesity were classified with body mass index(BMI), waist-hip circumference ratio(WHR) and percent body fat, and sarcopenia was classified with the value of skeletal muscle mass and muscle strength by Asian Working Group for Sarcopenia. In results, it was found that the level of obesity was very high as 43% by BMI, 88% by WHR, and 64% by percent body fat. The lower level of muscle strength was 15.50% in males and 23.50% in females. The lower level of muscle mass was 24.10% in males and .00% in females. Males who had one sarcopenia factors were 22.40%, and females were 23.50%, respectively. Males with sarcopenia were 6.90%, and females were .00%. In conclusion, regular resistance exercise is essential not only for the development of motor skills, but also for the normalization of skeletal muscle function and prevention of muscle dystrophy among COPD patients.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.1
• /
• pp.1-9
• /
• 2019

In this paper, we propose a method of generating a 2D gray image from LiDAR 3D reflection intensity. The proposed method uses the Fully Convolutional Network (FCN) to generate the gray image from 2D reflection intensity which is projected from LiDAR 3D intensity. Both encoder and decoder of FCN are configured with several convolution blocks in the symmetric fashion. Each convolution block consists of a convolution layer with $3{\times}3$ filter, batch normalization layer and activation function. The performance of the proposed method architecture is empirically evaluated by varying depths of convolution blocks. The well-known KITTI data set for various scenarios is used for training and performance evaluation. The simulation results show that the proposed method produces the improvements of 8.56 dB in peak signal-to-noise ratio and 0.33 in structural similarity index measure compared with conventional interpolation methods such as inverse distance weighted and nearest neighbor. The proposed method can be possibly used as an assistance tool in the night-time driving system for autonomous vehicles.

• Journal of Distribution Science
• /
• v.20 no.2
• /
• pp.55-64
• /
• 2022

Purpose: This research is aimed to study the level of the intellectual potential distribution, as well as the correlation between economic growth and key indicators of intellectual potential in each region of Kazakhstan. A review of the conceptual framework shows that there is a large body of research evaluating the level of intellectual potential in different ways based on different factors. Research design, data, and methodology: The research methodology is divided into two groups the integral index method using the normalization of indicators, weighting, and ranking; the method of correlation analysis. By the proposed methodological approaches, were calculated a set of factors affect the distribution of the intellectual potential. Statistics are taken for indicators of development of the intellectual potential for 2011-2020 from the Bureau of National Statistics. Results: Ranking results showed gaps between regions in Kazakhstan by the level of intellectual potential. Correlation analysis results revealed a statistically significant relationship on expenditures on R&D, computer literacy, innovative products, number of PhD students, and cultural and leisure indicators. Conclusions: Based on the obtained results of the intellectual potential level development there were given recommendations for the reproduction and regulation of the intellectual potential in the future.