• Journal of KIISE:Software and Applications
• /
• v.32 no.10
• /
• pp.984-989
• /
• 2005

This study aims to identify grammatical relations (GRs) in Korean sentences. The key task is to find the GRs in sentences in terms of such GR categories as subject, object, and adverbial. To overcome this problem, we are fared with the many ambiguities. We propose a statistical model, which resolves the grammatical relational ambiguity first, and then finds correct noun phrases (NPs) arguments of given verb phrases (VP) by using the probabilities of the GRs given NPs and VPs in sentences. The proposed model uses the characteristics of the Korean language such as distance, no-crossing and case property. We attempt to estimate the probabilities of GR given an NP and a VP with Support Vector Machines (SVM) classifiers. Through an experiment with a tree and GR tagged corpus for training the model, we achieved an overall accuracy of $84.8\%,\;94.1\%,\;and\;84.8\%$ in identifying subject, object, and adverbial relations in sentences, respectively.

• Journal of KIISE:Software and Applications
• /
• v.34 no.10
• /
• pp.889-899
• /
• 2007

In proteomics, recent advancements In mass spectrometry technology and in protein extraction and separation technology made high-throughput analysis possible. This leads to thousands to hundreds of thousands of MS/MS spectra per single LC-MS/MS experiment. Such a large amount of data creates significant computational challenges and therefore effective data analysis methods that make efficient use of computational resources and, at the same time, provide more peptide identifications are in great need. Here, SIFTER system is designed to avoid inefficient processing of shotgun proteomic data. SIFTER provides software tools that can improve throughput of mass spectrometry-based peptide identification by filtering out poor-quality tandem mass spectra and estimating a Peptide charge state prior to applying analysis algorithms. SIFTER tools characterize and assess spectral features and thus significantly reduce the computation time and false positive rates by localizing spectra that lead to wrong identification prior to full-blown analysis. SIFTER enables fast and in-depth interpretation of tandem mass spectra.

• Journal of radiological science and technology
• /
• v.43 no.5
• /
• pp.397-404
• /
• 2020

Coronavirus disease(COVID-19) is highly infectious disease that directly affects the lungs. To observe the clinical findings from these lungs, the Chest Radiography(CXR) can be used in a fast manner. However, the diagnostic performance via CXR needs to be improved, since the identifying these findings are highly time-consuming and prone to human error. Therefore, Artificial Intelligence(AI) based tool may be useful to aid the diagnosis of COVID-19 via CXR. In this study, we explored various Deep learning(DL) approach to classify COVID-19, other viral pneumonia and normal. For the original dataset and lung-segmented dataset, the pre-trained AlexNet, SqueezeNet, ResNet18, DenseNet201 were transfer-trained and validated for 3 class - COVID-19, viral pneumonia, normal. In the results, AlexNet showed the highest mean accuracy of 99.15±2.69% and fastest training time of 1.61±0.56 min among 4 pre-trained neural networks. In this study, we demonstrated the performance of 4 pre-trained neural networks in COVID-19 diagnosis with CXR images. Further, we plotted the class activation map(CAM) of each network and demonstrated that the lung-segmentation pre-processing improve the performance of COVID-19 classifier with CXR images by excluding background features.

• Journal of Oriental Neuropsychiatry
• /
• v.24 no.2
• /
• pp.163-178
• /
• 2013

Objectives : The purpose of this study is to investigate the characteristics of Sasang constitutional types in the university students. Methods : One hundred fifty students of Woosuk University participated in this study and their majors were Korean medicine, nursing science and pharmacy. The Sasang constitutional types were determined by the results of Two Step Questionnaire for Sasang Constitution Diagnosis (TS-QSCD). The subjects were also tested by Academic Motivation Tests (AMT), Multi-dimensional Learning Strategy Tests (MLST) and Learning Style Questionnaire of Sasang Constitution (LSQ-SC). The subscale scores of AMT, MSLT and each questions of AMT, MLST, LSQ-SC were compared among the different Sasang constitutions using analysis of variances (ANOVA). Results : There were no significant differences in AMT results between Sasang constitutions. In subscales of AMT, Feeling scales (FTF) scores of Soyangin was significantly higher than Taeeumin. Other subscales of AMT were not different between Sasang constitutions. There were no significant differences in MLST results between Sasang constitutions. Subscales of MLST were not different between Sasang constitutions. There were many questions between Soyangin and other constitutions in the analysis of questions of AMT, MLST, and LSQ-SC, and less between Taeeumin and Soeumin. Conclusions : These results suggest that the characteristics of Soyangin is more prominent compared with other constitutions in the learning style, and there were a little differences between Soeumin and Taeeumin.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.3
• /
• pp.284-291
• /
• 2005

I propose a framework for detecting, recognizing and classifying facial features based on learned expression patterns. The framework recognizes facial expressions by using PCA and expression HMM(EHMM) which is Hidden Markov Model (HMM) approach to represent the spatial information and the temporal dynamics of the time varying visual expression patterns. Because the low level spatial feature extraction is fused with the temporal analysis, a unified spatio-temporal approach of HMM to common detection, tracking and classification problems is effective. The proposed recognition framework is accomplished by applying posterior probability between current visual observations and previous visual evidences. Consequently, the framework shows accurate and robust results of recognition on as well simple expressions as basic 6 facial feature patterns. The method allows us to perform a set of important tasks such as facial-expression recognition, HCI and key-frame extraction.

• Journal of The Korean Association of Information Education
• /
• v.22 no.1
• /
• pp.103-111
• /
• 2018

In order to examine the educational effects and future directions of unplugged activities, we conducted a systematic review of Korean journals and theses from 2007 to 2016. Three kinds of database were used for systematic review: RISS, KISS, and E-article, and were performed searches using options such as 'unplugged' and 'play-centered'. Based on the protocol selected in the framework of the systematic review, 37 articles were selected analyzed in terms of research status, research subjects, research methods, research hubs, study mechanisms, educational methods, and research effects. Unplugged activities were the most popular among elementary school students. Educational effects were found to have significant effects on academic achievement, problem solving ability, and logical thinking ability. In the affirmative domain, there was a significant effect on interest, curiosity, and motivation. Based on the results of the analysis, the characteristics and implications of Unplugged activities and present the direction of future education were discussed.

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.965-978
• /
• 2006

This paper implements an automatic Korean word-spacing system based on word-recognition using morpheme unigrams and the pattern that the categories of those morpheme unigrams share within a candidate word. Although previous work on Korean word-spacing models has produced the advantages of easy construction and time efficiency, there still remain problems, such as data sparseness and critical memory size, which arise from the morpho-typological characteristics of Korean. In order to cope with both problems, our implementation uses the stochastic information of morpheme unigrams, and their category patterns, instead of word unigrams. A word's probability in a sentence is obtained based on morpheme probability and the weight for the morpheme's category within the category pattern of the candidate word. The category weights are trained so as to minimize the error means between the observed probabilities of words and those estimated by words' individual-morphemes' probabilities weighted according to their categories' powers in a given word's category pattern.

• KIISE Transactions on Computing Practices
• /
• v.21 no.11
• /
• pp.706-712
• /
• 2015

These days, much information is provided as a list of summaries through mobile services. In this regard, users consume information in which they are interested by observing the list and not by expressing their interest explicitly or implicitly through rating content or clicking links. Therefore, to appropriately model a user's interest, it is necessary to detect latent interest content. In this study, we propose a method for reasoning latent interest of a user by analyzing mobile content consumption logs of the user. Specifically, since erroneous reasoning will drastically degrade service quality, a unanimity ensemble method is adopted to maximize precision. In this method, an item is determined as the subject of latent interest only when multiple classifiers considering various aspects of the log unanimously agree. Accurate reasoning of latent interest will contribute to enhancing the quality of personalized services such as interest-based recommendation systems.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.7
• /
• pp.891-900
• /
• 2019

In this paper, we investigate the relationship between IPR creation and export activity. And we try to examine the effects of IPR use as innovation on export performance. The dataset used in the empirical analysis are the annual "Survey of Business Activity(2006~2014)" panel data which include total of 6,144 samples of firms. Data set includes the sample characteristic such as employee, industry, export performance, possession/use/development of IPR. According to analysis results, this paper confirms that R&D and export activities of firms make positive effects on IPR creation. In addition, this paper finds that IPR use of firms make positive effects on firm's export performance. Exporting firms achieve higher export performance by developing new products and processes to enter and compete in overseas markets. In addition, exporting firms can achieve higher performance by using intellectual property rights to appropriate innovation outcomes in foreign markets and to exclude the possibility of patent disputes in advance.

• Journal of Convergence for Information Technology
• /
• v.9 no.8
• /
• pp.248-253
• /
• 2019

Early diagnosis of mild cognitive impairment (MCI) can reduce the incidence of dementia. This study developed the MCI prediction model for the elderly in Korea. The subjects of this study were 3,240 elderly (1,502 men, 1,738 women) aged 65 and over who participated in the Korean Longitudinal Survey of Aging (KLoSA) in 2012. Outcome variables were defined as MCI prevalence. Explanatory variables were age, marital status, education level, income level, smoking, drinking, regular exercise more than once a week, average participation time of social activities, subjective health, hypertension, diabetes Respectively. The prediction model was developed using Restricted Boltzmann Machine (RBM) neural network. As a result, age, sex, final education, subjective health, marital status, income level, smoking, drinking, regular exercise were significant predictors of MCI prediction model of rural elderly people in Korea using RBM neural network. Based on these results, it is required to develop a customized dementia prevention program considering the characteristics of high risk group of MCI.