• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.276-281
• /
• 2019

Food printers must use food ink cartridges approved by the Ministry of Food and Drug Safety (MFDS). A 2D bar code is used to read whether the ink cartridge is authentic. However, since the dye is diverged by heat pressure and printed, the barcode is contaminated. In this paper, we propose a pre-processing algorithm to solve the problem of barcode contamination by food coloring dust in a latte art printer. The algorithm is based on various morphological operations. We apply this algorithm before reading contaminated barcode images with a general QR code reader. It has been confirmed that, as compared with the existing QR code reader, the contamination rate that can be perceived is increased from 25% to 40% and even at a contamination rate of 45%, the recognition rate reaches 50%.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.36 no.3
• /
• pp.113-120
• /
• 2020

The purpose of this study is to compare the models of Deep Learning-based Convolution Neural Network(CNN) for concrete crack detection. The comparison models are AlexNet, GoogLeNet, VGG16, VGG19, ResNet-18, ResNet-50, ResNet-101, and SqueezeNet which won ImageNet Large Scale Visual Recognition Challenge(ILSVRC). To train, validate and test these models, we constructed 3000 training data and 12000 validation data with 256×256 pixel resolution consisting of cracked and non-cracked images, and constructed 5 test data with 4160×3120 pixel resolution consisting of concrete images with crack. In order to increase the efficiency of the training, transfer learning was performed by taking the weight from the pre-trained network supported by MATLAB. From the trained network, the validation data is classified into crack image and non-crack image, yielding True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), and 6 performance indicators, False Negative Rate (FNR), False Positive Rate (FPR), Error Rate, Recall, Precision, Accuracy were calculated. The test image was scanned twice with a sliding window of 256×256 pixel resolution to classify the cracks, resulting in a crack map. From the comparison of the performance indicators and the crack map, it was concluded that VGG16 and VGG19 were the most suitable for detecting concrete cracks.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.17-22
• /
• 2021

In this paper, a machine learning-based automatic infographic recommendation system is proposed to improve the existing infographic production method. This system consists of a part that machine learning multiple infographic images and a part that automatically recommends infographics with artificial intelligence only by inputting basic data from the user. The recommended infographics are provided in the form of a library, and additional data can be input by drag & drop method. In addition, the infographic image is designed to be dynamically adjusted according to the size of the input data. As a result of analyzing the machine learning-based automatic infographic recommendation process, the matching success rate for layout and keyword was very high, and the matching success rate for type was rather low. In the future, a study to improve the matching success rate for the image type for each part of the infographic will be needed.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.529-536
• /
• 2022

In the past two years, Severe Acute Respiratory Syndrome Coronavirus-2(SARS-CoV-2) has been hitting more and more to people. This paper proposes a novel U-Net Convolutional Neural Network to classify and segment COVID-19 lung CT images, which contains Sub Coding Block (SCB), Atrous Spatial Pyramid Pooling(ASPP) and Attention Gate(AG). Three different models such as FCN, U-Net and U-Net-SCB are designed to compare the proposed model and the best optimizer and atrous rate are chosen for the proposed model. The simulation results show that the proposed U-Net-MMFE has the best Dice segmentation coefficient of 94.79% for the COVID-19 CT scan digital image dataset compared with other segmentation models when atrous rate is 12 and the optimizer is Adam.

• Journal of Chest Surgery
• /
• v.57 no.3
• /
• pp.272-280
• /
• 2024

Background: The phenomenon known as the "weekend effect" impacts various medical disciplines. We compared outcomes between regular hours and off hours to investigate the presence of the weekend effect in extracorporeal cardiopulmonary resuscitation (ECPR). Methods: Between January 2018 and December 2020, 159 patients at our center were treated with veno-arterial extracorporeal membrane oxygenation (ECMO) for cardiac arrest. We assessed the time required for ECMO preparation, the rate of successful weaning, and the rate of in-hospital mortality. These factors were compared among regular hours ("daytime": weekdays from 7:00 AM-7:00 PM), off hours on weekdays ("nighttime": weekdays from 7:00 PM-7:00 AM), and off hours on weekends and holidays ("weekend": Fridays at 7:00 PM to Mondays at 7:00 AM). Results: The time from the recognition of cardiac arrest to the arrival of the ECMO team was shortest for the daytime group and longest for those treated over the weekend (daytime, 10.0 minutes; nighttime, 12.5 minutes; weekend, 15.0 minutes; p=0.064). The time from the ECMO team's arrival to ECMO initiation was shortest for the daytime and longest for the nighttime group (daytime, 13.0 minutes; nighttime, 18.5 minutes; weekend, 14.0 minutes; p=0.028). No significant difference was observed in the rate of successful ECMO weaning (daytime, 48.3%; nighttime, 39.5%; weekend, 36.1%; p=0.375). Conclusion: In situations involving CPR, the time to arrival of the ECMO team was longer during off hours. Furthermore, ECMO insertion required more time at night than during the other periods. These findings warrant specific training in decision-making and emergent ECMO insertion.

• Journal of Science Education
• /
• v.36 no.1
• /
• pp.69-83
• /
• 2012

The purpose of this study was to analyze the reading materials in 7th curriculum and 2009 revised high school chemistry I textbook for identifying the problems of reading material presented in science textbooks and to investigate science teachers' recognition about utilization reading materials in science textbook. For this purpose, each four 7th curriculum and 2009 revised high school chemistry I textbook were analyzed according to the number of reading materials, the type of contents and the type of students' activities. In addition, the secondary school science teachers' recognition about utilization reading materials in science textbook was investigated. The results were as follows: First, anylizing reading materials in chemistry I textbooks showed that and the rate of reading materials were presented from 7.9 to 17.1% in 7th curriculum and from 20.6 to 28.2% in 2009 revised curriculum textbook. It implies that the rate of reading materials in 2009 revised textbooks increases more than those in 7th curriculum textbook. The result of analyzing the type of contents, 'life sciences' was the largest proportion with 34.3 % in the 7th curriculum chemistry I, but 'enrichment and supplement of knowledge' was the largest proportion with 23.7% in 2009 revised curriculum. Analyzing the type of student activities, only 13% of the reading materials in 7th National Curriculum textbook was found to be inquiry type, but 35% of the reading materials in the 2009 revised curriculum. appears to be inquiry type. It suggested that the curriculum objectives was reflected in the textbook. Second, investigating recognition of teachers' perceptions of utilization science textbooks, 67% teachers responded that they used the reading materials in their science class, but teachers who didn't use the reading materials was almost 33%. A large number of teachers responded that the reading materials associated with the real-life needed for integrated education and thought that the reading materials about 'life and science' should be included in the science textbooks.

• The Journal of the Korea Contents Association
• /
• v.14 no.12
• /
• pp.959-972
• /
• 2014

This study aims to describe childlessness trends and examine the factors impacting on the childlessness of married couples among Korean provinces between 1990 and 2010. The results are as follows: There have been differences in childlessness rates among provinces and over time as well. Furthermore, social development, transportation, women's status, and economic development have statistically significant positive impacts on ASMCR. It turns out that age-specific marital childlessness rate is rather accurate measurement than general marital childlessness rate in terms of exploring the factors influencing on the childlessness among Korean provinces. Korea's government policy to aid the married couples who are suffering from in-fecundity is strongly recommended to maintain its policy and extend its subjects in order to increase married couples' fertility rate. Furthermore, campaigns to change married couples' recognition and attitudes from unfavorable against childbearing to favorable toward childbearing so that the married couples would be willing to have childbearing in terms of fertility rate increase.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2010

With the widespread use of vision-based surveillance systems, the capability for person identification is now an essential component. However, the CCTV cameras used in surveillance systems tend to produce relatively low-resolution images, making it difficult to use face recognition techniques for person identification. Therefore, an algorithm is proposed for person identification in CCTV camera images based on the clothing. Whenever a person is authenticated at the main entrance of a building, the clothing feature of that person is extracted and added to the database. Using a given image, the clothing area is detected using background subtraction and skin color detection techniques. The clothing feature vector is then composed of textural and color features of the clothing region, where the textural feature is extracted based on a local edge histogram, while the color feature is extracted using octree-based quantization of a color map. When given a query image, the person can then be identified by finding the most similar clothing feature from the database, where the Euclidean distance is used as the similarity measure. Experimental results show an 80% success rate for person identification with the proposed algorithm, and only a 43% success rate when using face recognition.

• Journal of the East Asian Society of Dietary Life
• /
• v.25 no.6
• /
• pp.979-989
• /
• 2015

The purpose of this study was to investigate the usage and perception jochung Self-administered questionnaires were collected from 445 living residents in the Daegu and Gyeongbuk areas. When purchasing jochung, respondents answered that they considered both health and taste. Recognition rate scores for jochung were in the order of 'brown rice', 'balloon flower', 'plum', and 'corn'. On the other hand, recognition rate scores for 'purple radish', 'sword bean', and 'sasa quelpaertensis' were very low. Preference and intake levels of jochung were in the order of 'plum', 'corn', 'sorghum', 'strawberry' and 'balloon flower'. On the other hand, preferences for 'purple radish', 'sword bean', and 'Hovenia dulcis' were very low. Reasons for eating jochung as a sweetener were identified as due to 'family, friend, or neighbor' (40.1%) and 'for health' (39.2%), and 54.6% ate it once or twice per week. Consumers showed low preference for different jochung used as sweeteners, and did not exactly recognize the characteristics of various jochung. Furthermore, 70.8% replied "increasing" prospects for jochung consumption. To increase consumption of jochung, there is a need for greater hygiene and safety with regards to jochung products as well as variations and improvements in quality.

• Journal of radiological science and technology
• /
• v.35 no.3
• /
• pp.227-235
• /
• 2012

Digital Mammography makes it possible to reproduce the entire breast image. And it is used to detect microcalcification and mass which are the most important point of view of nonpalpable early breast cancer, so it has been used as the primary screening test of breast disease. It is reported that microcalcification of breast lesion is important in diagnosis of early breast cancer. In this study, six types of texture features algorithms are used to detect microcalcification on breast US images and the study has analyzed recognition rate of lesion between normal US images and other US images which microcalification is seen. As a result of the experiment, Computer aided diagnosis recognition rate that distinguishes mammography and breast US disease was considerably high 70~98%. The average contrast and entropy parameters were low in ROC analysis, but sensitivity and specificity of four types parameters were over 90%. Therefore it is possible to detect microcalcification on US images. If not only six types of texture features algorithms but also the research of additional parameter algorithm is being continually proceeded and basis of practical use on CAD is being prepared, it can be a important meaning as pre-reading. Also, it is considered very useful things for early diagnosis of breast cancer.