• Journal of The Korean Society of Clinical Toxicology
• /
• v.16 no.2
• /
• pp.61-67
• /
• 2018

Purpose: To evaluate the association between neutrophil-to-lymphocyte ratio (NLR) and occurrence of aspiration pneumonia in drug intoxication (DI) patients in the emergency department (ED) and to evaluate the relationship between NLR and length of hospital admission/intensive care unit (ICU) admission Methods: A total of 466 patients diagnosed with DI in the ED from January 2016 to December 2017 were included in the analysis. The clinical and laboratory results, including NLR, were evaluated as variables. NLR was calculated as the absolute neutrophil count/absolute lymphocyte count. To evaluate the prognosis of DI, data on the development of aspiration pneumonia were obtained. Also, we evaluated the relationship between NLR and length of hospital admission and between NLR and length of ICU admission. Statistically, multivariate logistic regression analyses, receiver-operating characteristic (ROC) curve analysis, and Pearson's correlation (${\rho}$) were performed. Results: Among the 466 DI patients, 86 (18.5%) developed aspiration pneumonia. Multivariate logistic regression analysis revealed NLR as an independent factor in predicting aspiration pneumonia (odds ratio, 1.7; p=0.001). NLR showed excellent predictive performance for aspiration pneumonia (areas under the ROC curves, 0.815; cut-off value, 3.47; p<0.001) with a sensitivity of 86.0% and a specificity of 72.6%. No correlations between NLR and length of hospital admission (${\rho}=0.195$) and between NLR and length of ICU admission (${\rho}=0.092$) were observed. Conclusion: The NLR is a simple and effective marker for predicting the occurrence of aspiration pneumonia in DI patients. Emergency physicians should be alert for aspiration pneumonia in DI patients with high NLR value (>3.47).

• Clinical and Experimental Pediatrics
• /
• v.63 no.11
• /
• pp.438-446
• /
• 2020

Background: Most developmental screening tools in Korea are adopted from foreign tests. To ensure efficient screening of infants and children in Korea, a nationwide screening tool with high reliability and validity is needed. Purpose: This study aimed to independently develop, standardize, and validate the Korean Developmental Screening Test for Infants and Children (K-DST) for screening infants and children for neurodevelopmental disorders in Korea. Methods: The standardization and validation conducted in 2012-2014 of 3,284 subjects (4-71 months of age) resulted in the first edition of the K-DST. The restandardization and revalidation performed in 2015-2016 of 3.06 million attendees of the National Health Screening Program for Infants and Children resulted in the revised K-DST. We analyzed inter-item consistency and test-retest reliability for the reliability analysis. Regarding the validation of K-DST, we examined the construct validity, sensitivity and specificity, receiver operating characteristic curve analysis, and a criterion-related validity analysis. Results: We ultimately selected 8 questions in 6 developmental domains. For most age groups and each domain, internal consistency was 0.73-0.93 and test-retest reliability was 0.77-0.88. The revised K-DST had high discriminatory ability with a sensitivity of 0.833 and specificity of 0.979. The test supported construct validity by distinguishing between normal and neurodevelopmentally delayed groups. The language and cognition domain of the revised K-DST was highly correlated with the K-Bayley Scales of Infant Development-II's Mental Age Quotient (r=0.766, 0.739), while the gross and fine motor domains were highly correlated with Motor Age Quotient (r=0.695, 0.668), respectively. The Verbal Intelligence Quotient of Korean Wechsler Preschool and Primary Scales of Intelligence was highly correlated with the K-DST cognition and language domains (r=0.701, 0.770), as was the performance intelligence quotient with the fine motor domain (r=0.700). Conclusion: The K-DST is reliable and valid, suggesting its good potential as an effective screening tool for infants and children with neurodevelopmental disorders in Korea.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.1-9
• /
• 2021

Traditionally, most malicious codes have been analyzed using feature information extracted by domain experts. However, this feature-based analysis method depends on the analyst's capabilities and has limitations in detecting variant malicious codes that have modified existing malicious codes. In this study, we propose a ResNet-Variational AutoEncder-based variant malware classification method that can classify a family of variant malware without domain expert intervention. The Variational AutoEncoder network has the characteristics of creating new data within a normal distribution and understanding the characteristics of the data well in the learning process of training data provided as input values. In this study, important features of malicious code could be extracted by extracting latent variables in the learning process of Variational AutoEncoder. In addition, transfer learning was performed to better learn the characteristics of the training data and increase the efficiency of learning. The learning parameters of the ResNet-152 model pre-trained with the ImageNet Dataset were transferred to the learning parameters of the Encoder Network. The ResNet-Variational AutoEncoder that performed transfer learning showed higher performance than the existing Variational AutoEncoder and provided learning efficiency. Meanwhile, an ensemble model, Stacking Classifier, was used as a method for classifying variant malicious codes. As a result of learning the Stacking Classifier based on the characteristic data of the variant malware extracted by the Encoder Network of the ResNet-VAE model, an accuracy of 98.66% and an F1-Score of 98.68 were obtained.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.5
• /
• pp.59-69
• /
• 2011

Since power analysis attack which uses a characteristic that power consumed by crypto device depends on processed data has been proposed, many logics that can block these correlation originally have been developed. DRP logic has been adopted by most of logics maintains power consumption balanced and reduces correlation between processed data and power consumption. However, semi-custom design is necessary because recently design circuits become more complex than before. This design method causes unbalanced design pattern that makes DRP logic consumes unbalanced power consumption which is vulnerable to power analysis attack. In this paper, we have developed new logic style which adds another discharge phase to discharge two output nodes at the same time based on DyCML to remove this unbalanced power consumption. Also, we simulated 1bit fulladder to compare proposed logic with other logics to prove improved performance. As a result, proposed logic is improved NED and NSD to 60% and power consumption reduces about 55% than any other logics.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.16-24
• /
• 2021

The exiting word embedding methodology such as word2vec represents words, which only occur in the raw training corpus, as a fixed-length vector into a continuous vector space, so when mapping the words incorporated in the raw training corpus into a fixed-length vector in morphologically rich language, out-of-vocabulary (OOV) problem often happens. Even for sentence embedding, when representing the meaning of a sentence as a fixed-length vector by synthesizing word vectors constituting a sentence, OOV words make it challenging to meaningfully represent a sentence into a fixed-length vector. In particular, since the agglutinative language, the Korean has a morphological characteristic to integrate lexical morpheme and grammatical morpheme, handling OOV words is an important factor in improving performance. In this paper, we propose parallel Tri-LSTM sentence embedding that is robust to the OOV problem by extending utilizing the morphological information of words into sentence-level. As a result of the sentiment analysis task with corpus in Korean, we empirically found that the character unit is better than the morpheme unit as an embedding unit for Korean sentence embedding. We achieved 86.17% accuracy on the sentiment analysis task with the parallel bidirectional Tri-LSTM sentence encoder.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.39-60
• /
• 2021

In the field of deep learning, there are many algorithms mainly after GAN in research related to generation, but in terms of generation, there are similarities and differences with art. If the generation in the engineering aspect is mainly to judge the presence or absence of a quantitative indicator or the correct answer and the incorrect answer, the creation in the artistic aspect creates a creation that interprets the world and human life by cross-validating and doubting the correct answer and incorrect answer from various perspectives. In this paper, the video generation ability of deep learning was interpreted from the perspective of collage and compared with the results made by the artist. The characteristic of the experiment is to compare and analyze how much GAN reproduces the result of the creator made with the collage technique and the difference between the creative part, and investigate the satisfaction level by making performance evaluation items for the reproducibility of GAN. In order to experiment on how much the creator's statement and purpose of expression were reproduced, a deep learning algorithm corresponding to the statement keyword was found and its similarity was compared. As a result of the experiment, GAN did not meet much expectations to express the collage technique. Nevertheless, the image association showed higher satisfaction than human ability, which is a positive discovery that GAN can show comparable ability to humans in terms of abstract creation.

• Journal of Gastric Cancer
• /
• v.21 no.4
• /
• pp.368-378
• /
• 2021

Purpose: When patients with early gastric cancer (EGC) undergo non-curative endoscopic submucosal dissection requiring gastrectomy (NC-ESD-RG), additional medical resources and expenses are required for surgery. To reduce this burden, predictive model for NC-ESD-RG is required. Materials and Methods: Data from 2,997 patients undergoing ESD for 3,127 forceps biopsy-proven differentiated-type EGCs (2,345 and 782 in training and validation sets, respectively) were reviewed. Using the training set, the logistic stepwise regression analysis determined the independent predictors of NC-ESD-RG (NC-ESD other than cases with lateral resection margin involvement or piecemeal resection as the only non-curative factor). Using these predictors, a risk-scoring system for predicting NC-ESD-RG was developed. Performance of the predictive model was examined internally with the validation set. Results: Rate of NC-ESD-RG was 17.3%. Independent pre-ESD predictors for NC-ESD-RG included moderately differentiated or papillary EGC, large tumor size, proximal tumor location, lesion at greater curvature, elevated or depressed morphology, and presence of ulcers. A risk-score was assigned to each predictor of NC-ESD-RG. The area under the receiver operating characteristic curve for predicting NC-ESD-RG was 0.672 in both training and validation sets. A risk-score of 5 points was the optimal cut-off value for predicting NC-ESD-RG, and the overall accuracy was 72.7%. As the total risk score increased, the predicted risk for NC-ESD-RG increased from 3.8% to 72.6%. Conclusions: We developed and validated a risk-scoring system for predicting NC-ESD-RG based on pre-ESD variables. Our risk-scoring system can facilitate informed consent and decision-making for preoperative treatment selection between ESD and surgery in patients with EGC.

• The korean journal of orthodontics
• /
• v.52 no.1
• /
• pp.3-19
• /
• 2022

Objective: The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals. Methods: Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradient-weighted class activation mapping (Grad-CAM). Results: In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis. Conclusions: Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.89-100
• /
• 2021

Comedy has been popular since ancient Greece. In order to visualize comedy more effectively, the actor's acting acts as an important factor. Then active discussion is needed on how actors can actually shape their comedic performance. I would like to approach comedic acting methods, focusing on the character of Kim Seo-young in the play . This researcher played the character of Kim Mi-young, and the characteristics of comedic acting include exaggeration, repetition, fast tempo, changing tone, and exaggerated physical behavior. Comedic acting comes from a dissonance of reactions. This is because unexpected reactions to stimuli can cause audience laughter. Comedic acting is also important in exaggeration and repetition, which must be based on true acting. The fast tempo of the act and the changing tone of the words also affect comedic acting expressions, and the embodiments of 'slapstick' and 'group dance', which are characteristics of farce acting, play an important role in causing audience laughter. In order for these characteristic elements to show comic effects, the actor's true acting must be the basis. What is important in comedic acting is understanding the narrative flow and features of the text and expressing it accurately. Comedic effects can be sufficiently represented if an actor truly expresses his means and faithfully demonstrates what the text requires. It is hoped that such research will help explore various acting arts, the acting education field, and the theater creation process.

• Structural Engineering and Mechanics
• /
• v.83 no.3
• /
• pp.305-326
• /
• 2022

To realize the recycling utilization of waste concrete and alleviate the shortage of resources, 11 specimens of steel reinforced recycled concrete (SRRC) filled circular steel tube columns were designed and manufactured in this study, and the cyclic loading tests on the specimens of columns were also carried out respectively. The hysteretic curves, skeleton curves and performance indicators of columns were obtained and analysed in detail. Besides, the finite element model of columns was established through OpenSees software, which considered the adverse effect of recycled coarse aggregate (RA) replacement rates and the constraint effect of circular steel tube on internal RAC. The numerical calculation curves of columns are in good agreement with the experimental curves, which shows that the numerical model is relatively reasonable. On this basis, a series of nonlinear parameters analysis on the hysteretic behaviors of columns were also investigated. The results are as follows: When the replacement rates of RA increases from 0 to 100%, the peak loads of columns decreases by 7.78% and the ductility decreases slightly. With the increase of axial compression ratio, the bearing capacity of columns increases first and then decreases, but the ductility of columns decreases rapidly. Increasing the wall thickness of circular steel tube is very profitable to improve the bearing capacity and ductility of columns. When the section steel ratio increases from 5.54% to 9.99%, although the bearing capacity of columns is improved, it has no obvious contribution to improve the ductility of columns. With the decrease of shear span ratio, the bearing capacity of columns increases obviously, but the ductility decreases, and the failure mode of columns develops into brittle shear failure. Therefore, in the engineering design of columns, the situation of small shear span ratio (i.e., short columns) should be avoided as far as possible. Based on this, the calculation model on the skeleton curves of columns was established by the theoretical analysis and fitting method, so as to determine the main characteristic points in the model. The effectiveness of skeleton curve model is verified by comparing with the test skeleton curves.