• Korean Journal of Clinical Pharmacy
• /
• v.31 no.4
• /
• pp.324-331
• /
• 2021

To investigate signals of adverse drug reactions of finasteride by using the Korea Adverse Events Reporting System (KAERS) database. This pharmacovigilance was based on the database of the drug-related adverse reactions reported spontaneously to the KAERS from 2013 to 2017. This study was conducted by disproportionality analysis. Data mining analysis was performed to detect signals of finasteride. The signal was defined by three criteria as proportional reporting ratio (PRR), reporting odds ratio (ROR), and information component (IC). The signals of finasteride were compared with those of the other drugs; dutasteride (similar mechanism of action), minoxidil (different mechanism but similar indications for alopecia), silodosin (different mechanism but similar indications for BPH). It was examined whether the detected signals exist in drug labels in Korea. The total number of adverse event-drug pairs was reported 2,665,429 from 2013 to 2017, of which 1,426 were associated with finasteride. The number of investigated signals of finasteride was 42. The signals that did not include in the drug label were 29 signals, including mouth dry, hypotension, dysuria etc. The signal of finasteride was similar to that of dutasteride and silodosin but was different to that of minoxidil. Early detection of signals through pharmacovigilance is important to patient safety. We investigated 29 signals of finasteride that do not exist in drug labels in Korea. Further pharmacoepidemiological studies should be needed to evaluate the signal causality with finasteride.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.1-9
• /
• 2022

Ship detection in synthetic aperture radar (SAR) images is an important application in marine monitoring for the military and civilian domains. Over the past decade, object detection has achieved significant progress with the development of convolutional neural networks (CNNs) and lot of labeled databases. However, due to difficulty in collecting and labeling SAR images, it is still a challenging task to solve SAR ship detection CNNs. To overcome the problem, some methods have employed conventional data augmentation techniques such as flipping, cropping, and affine transformation, but it is insufficient to achieve robust performance to handle a wide variety of types of ships. In this paper, we present a novel and effective approach for deep SAR ship detection, that exploits label-rich Electro-Optical (EO) images. The proposed method consists of two components: a data augmentation network and a ship detection network. First, we train the data augmentation network based on conditional generative adversarial network (cGAN), which aims to generate additional SAR images from EO images. Since it is trained using unpaired EO and SAR images, we impose the cycle-consistency loss to preserve the structural information while translating the characteristics of the images. After training the data augmentation network, we leverage the augmented dataset constituted with real and translated SAR images to train the ship detection network. The experimental results include qualitative evaluation of the translated SAR images and the comparison of detection performance of the networks, trained with non-augmented and augmented dataset, which demonstrates the effectiveness of the proposed framework.

• The Korean Journal of Applied Statistics
• /
• v.35 no.6
• /
• pp.739-754
• /
• 2022

Usually, text data consists of many variables, and some of them are closely correlated. Such multi-collinearity often results in inefficient or inaccurate statistical analysis. For supervised learning, one can select features by examining the relationship between target variables and explanatory variables. On the other hand, for unsupervised learning, since target variables are absent, one cannot use such a feature selection procedure as in supervised learning. In this study, we propose a word selection procedure that employs topic models to find latent topics. We substitute topics for the target variables and select terms which show high relevance for each topic. Applying the procedure to real data, we found that the proposed word selection procedure can give clear topic interpretation by removing high-frequency words prevalent in various topics. In addition, we observed that, by applying the selected variables to the classifiers such as naïve Bayes classifiers and support vector machines, the proposed feature selection procedure gives results comparable to those obtained by using class label information.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.204-205
• /
• 2023

This study studied a prediction model for sending collision alarms for small fishing boats based on semi-supervised learning(SSL). The supervised learning (SL) method requires a large number of labeled data, but the labeling process takes a lot of resources and time. This study used service data collected through a data pipeline linked to 'intelligent maritime traffic information service' and data collected from real-sea experiment. The model accuracy was improved as a result of learning not only real-sea experiment data with labeling determined based on actual user satisfaction but also service data without label determined together.

• Journal of Nutrition and Health
• /
• v.49 no.6
• /
• pp.459-470
• /
• 2016

Purpose: The purpose of the present study is to identify the relationship between practicing healthy diet and metabolic syndrome indicators in Koreans. Methods: This research is a cross-sectional study based on the 2013~2014 Korea National Health and Nutritional Examination Survey. This study investigated 6,748 adults aged 19 to 64 yr (19~49 yr: n = 4,230, 50~64 yr: n = 2,518) to examine practice of healthy diet and metabolic syndrome indicators. In this study, according to practicing healthy diet, we classified subjects into the "Practicing healthy diet (PHD)" group (19~49 yr: n = 1,782, 50~64 yr: n = 937) and "Non-practicing healthy diet (NPHD)" group (19~49 yr: n = 2,448, 50~64 yr: n = 1,581). PHD score was determined by adding the number of practicing factors: adequate fat intake, sodium intake ${\leq}2,000mg/day$, fruit & vegetable intake ${\geq}500g/day$, and using nutrition label information in food selection. Results: Female adults had a larger proportion of subjects who practiced a healthy diet compared to male adults (p < 0.001), and the percentages of 19~49 yr and 50~64 yr were 40.46% and 37.07%, respectively. The PHD group consumed significantly more calcium, vitamin $B_1$, $B_2$, and vitamin C density compared to the NPHD group. In 50~64 yr females, the subjects practicing healthy diet (PHD score ${\geq}2$) was inversely associated with risk of abdominal obesity (OR: 0.71, 95% CI: 0.54~0.93, p value = 0.0131) and metabolic syndrome (OR: 0.70, 95% CI: 0.52~0.94, p value = 0.0166) after adjustments for multiple confounding factors, compared with the lower PHD score (PHD score ${\leq}1$). Conclusion: Good dietary practice such as adequate fat intake, sodium intake ${\leq}2,000mg/day$, sufficient fruit & vegetable intake, and using nutrition label information in food selection could be useful in decreasing metabolic syndrome risk of Korean adults.

• Journal of Nutrition and Health
• /
• v.54 no.2
• /
• pp.199-210
• /
• 2021

Purpose: This study investigated the food consumption behaviors in Korean adults, according to the agrifood consumer competency index (ACCI). Methods: Data obtained from the 2019 Consumption Behaviors Survey for Food were analyzed. A total of 6,176 adults (2,783 males, 3,393 females) aged ≥ 19 years, were included in the study. Based on the score of agrifood consumer competency index, the subjects were classified into three groups. The dietary habits, eating-out and food-delivery/take-out behaviors, opinion of food labeling, and concerns for domestic products were compared among the 3 groups. Results: The ACCI scores of the male and female subjects were 63.6 and 64.8, respectively. Subjects of both genders in the highest tertile of the ACCI were more likely to have a higher education level and higher health concerns, as compared to subjects in the lowest tertile (p < 0.05). Male subjects having highest tertile of the ACCI reported significantly more exercise and alcohol consumption, as compared to subjects in the lowest tertile (p < 0.05). A higher score of the ACCI also portrayed a higher satisfaction in own diet and greater checking of the food label. Moreover, subjects with a higher score of the ACCI showed greater satisfaction and reliability in the food label, as well as increased concerns for domestic agrifoods, local foods, and eco-friendly foods. Subjects in the lowest tertile of the ACCI acquired their dietary information from acquaintances, whereas subjects in the highest tertile of the ACCI learnt the information from food labels themselves. Conclusion: These results are indicative of the food consumption and behaviors of Korean adults according to their ACCI scores, and provide basic data that will be useful for implementing an effective food policy.

• Journal of Food Hygiene and Safety
• /
• v.30 no.4
• /
• pp.329-342
• /
• 2015

The purpose of this study was to investigate consumers' perceptions of sodium saccharin in social media. Data was collected from Naver blogs and Naver web communities (Korean representative portal web-site), and media reports including comment sections on a Yonhap news website (Korean largest news agency). The results from Naver blogs and Naver web communities showed that it was primarily mentioned 'sodium saccharin-no added' products, properties of sodium saccharin, and methods of reducing sodium saccharin in food. When media reported the expansion of food categories permitted to use sodium saccharin, search volume for sodium saccharin has increased in both PC and mobile search engines. Also, it was mainly commented about distrust of government, criticism of food product price, and distrust of food companies below the news on the news site. The label of sodium saccharin-no added products in market emphasized "no added-sodium saccharin". These results suggest that consumers are interested in sodium saccharin and especially when media reported the expansion of food categories permitted to use it. Consumers were able to search various information on sodium saccharin except safety or acceptable daily intake through social media. Therefore media or competent authority should report item on sodium saccharin with information including safety or acceptable daily intake based on scientific background and reference or experts' interview for consumers to get reliable information.

• Journal of IKEEE
• /
• v.5 no.2 s.9
• /
• pp.136-145
• /
• 2001

As with appearing new applications that requires QoS guarantee such as VoIP, VPN in Internet, problems of IP QoS has been one of most important issues in next-generation Internet. IETF has proposed integrated services model(Int-Serv) and differentiated service(Diff-Serv) to supply IP QoS in Internet. Int-Serv model uses the state information of each IP flow, so satisfies QoS according to traffic characteristics, but increases the amount of flow state information with increasing flow number. Diff-Serv model uses PHP(Per Hop Behavior), and there are well-defined classes to provide differentiated traffics with different services according to delay and loss sensitivity. Diff-Serv model can provide diverse services in Internet because of having no the state and signal information of each flow. As MPLS uses the packet forwarding technique based-on label, it implements the traffic engineering in the networks easily. The MPLS can set up the path with different traffic parameters, and assign each path to particular Class of Services. Therefore it is possible to support the Diff-Serv model with well-defined classes. In this paper we investigate the performance improvement of Diff-Serv function in the MPLS network to guarantee class of services in Internet.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12B
• /
• pp.1450-1458
• /
• 2011

The HPcN (Hybrid & high Performance Convergence Network) in research networks means environment which can provide both computing resource such as supercomputer, cluster and network resource to application researchers in the field of medical, bio, aerospace and e-science. The most representative research network in Korea, KREONET has been developing following technologies through the HERO (Hybrid Networking project for research oriented infrastructure) from 200S. First, we have constructed and deployed a control plane technology which can provide a connection oriented network dynamically. Second, the integrated resource management system technology has been developing for reservation and allocation of both computing and network resources, whenever users want to utilize them. In this paper, a testbed network is presented, which is possible to reserve and allocate network resource using the integrated resource management system. We reserve network resource through GNSI (Grid Network Service Interface) messages between GRS (Global Resource Scheduler) and NRM (Network Resource Manager) and allocate network resource through GUNI (Grid User Network Interface) messages between the NRM (network resource manager) and routers, based on reservation information provided from a user on the web portal. It is confirmed that GUNI interface messages are delivered from the NRM to each router at the starting of reservation time and traffic is transmitted through LSP allocated by the NRM.