• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.173-181
• /
• 2017

In this paper, we have studied tracking as a training stage of considering the position and the scale of a person given its previous position, scale, as well as next and forward image fraction. Unlike other learning methods, CNN is thereby learning combines both time and spatial features from the image for the two consecutive frames. We introduce multiple path ways in CNN to better fuse local and global information. A creative shift-variant CNN architecture is designed so as to alleviate the drift problem when the distracting objects are similar to the target in cluttered environment. Furthermore, we employ CNNs to estimate the scale through the accurate localization of some key points. These techniques are object-independent so that the proposed method can be applied to track other types of object. The capability of the tracker of handling complex situations is demonstrated in many testing sequences. The accuracy of the SVM classifier using the features learnt by the CNN is equivalent to the accuracy of the CNN. This fact confirms the importance of automatically optimized features. However, the computation time for the classification of a person using the convolutional neural network classifier is less than approximately 1/40 of the SVM computation time, regardless of the type of the used features.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.3
• /
• pp.567-578
• /
• 2014

PEAS (performance enhancement attitude scale) has been used to measure attitude and disposition toward doping in elite athlete. It is constructed of 17-item, 6-point scale. The purpose of this study was to verify validity of the PEAS for Korean elite player through Rasch model. The scale was administered to 438 Korean elite players. Principal component analysis was used to verify unidimensionality using SPSS program. Rasch measurement computer program, WISTEPS, was used to estimate goodness-of-fit of items and category structure. Differenctial item functioning by gender was also estimated by the WINSTEPS program. All alpha level was set at 0.05. First, principal component analysis showed that unidimensionality is satisfied as over 20.0% of variance of eigenvalue. Second, category probabilities curve showed 5-point scale was better than 6-point scaled statistically. Third, seven items (1, 9, 10, 12, 13, 14, 17) in the 17-item were not good model fit and three items (3, 12, 13) were estimated as the differential item functioning. This study showed that 9-item, 5-point scale is better PEAS to Korean elite player.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.59-66
• /
• 2016

This paper presents an empirical evaluation on dimensionality reduction strategies by which dissimilarity-based classifications (DBC) can be implemented efficiently. In DBC, classification is not based on feature measurements of individual objects (a set of attributes), but rather on a suitable dissimilarity measure among the individual objects (pair-wise object comparisons). One problem of DBC is the high dimensionality of the dissimilarity space when a lots of objects are treated. To address this issue, two kinds of solutions have been proposed in the literature: prototype selection (PS)-based methods and dimension reduction (DR)-based methods. In this paper, instead of utilizing the PS-based or DR-based methods, a way of performing DBC in Eigen spaces (ES) is considered and empirically compared. In ES-based DBC, classifications are performed as follows: first, a set of principal eigenvectors is extracted from the training data set using a principal component analysis; second, an Eigen space is expanded using a subset of the extracted and selected Eigen vectors; third, after measuring distances among the projected objects in the Eigen space using $l_p$-norms as the dissimilarity, classification is performed. The experimental results, which are obtained using the nearest neighbor rule with artificial and real-life benchmark data sets, demonstrate that when the dimensionality of the Eigen spaces has been selected appropriately, compared to the PS-based and DR-based methods, the performance of the ES-based DBC can be improved in terms of the classification accuracy.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.11-19
• /
• 2021

A software system is required to change during its life cycle due to various requirements such as adding functionalities, fixing bugs, and adjusting to new computing environments. Such program code modification should be considered as carefully as a new system development becase unexpected software errors could be introduced. In addition, when reusing open source programs, we can expect higher quality software if code changes of the open source program are predicted in advance. This paper proposes a Convolutional Neural Network (CNN)-based deep learning model to predict source code changes. In this paper, the prediction of code changes is considered as a kind of a binary classification problem in deep learning and labeled datasets are used for supervised learning. Java projects and code change logs are collected from GitHub for training and testing datasets. Software metrics are computed from the collected Java source code and they are used as input data for the proposed model to detect code changes. The performance of the proposed model has been measured by using evaluation metrics such as precision, recall, F1-score, and accuracy. The experimental results show the proposed CNN model has achieved 95% in terms of F1-Score and outperformed the multilayer percept-based DNN model whose F1-Score is 92%.

• Journal of Practical Engineering Education
• /
• v.13 no.2
• /
• pp.333-349
• /
• 2021

The fourth industrial revolution based on information and communication technology has increased the need for an environment where contents in new technologies can be learned for the development of lifelong vocational capabilities. To prepare for this, K University's online lifelong education center has established STEP, a smart learning platform. In this study, we conducted a study and other platform case analysis for STEP learner types, a survey of learners, and a comprehensive analysis based on these results to classify characteristics by learner types. It also intended to establish a plan to provide customized services to meet the needs of STEP learners in the future. The derived results are as follows. It is necessary to constantly manage learning content difficulty and learning motivation survey, and also needs to refine the operation of learning content in terms of learning composition. In addition, it is important to secure specialized content, to manage vulnerable learners, to actively introduce a learner support system and various educational methods.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.530-536
• /
• 2021

Recently, due to the development of deep learning, end-to-end speech recognition, which directly maps graphemes to speech signals, shows good performance. Especially, among the end-to-end models, conformer shows the best performance. However end-to-end models only focuses on the probability of which grapheme will appear at the time. The decoding process uses a greedy search or beam search. This decoding method is easily affected by the final probability output by the model. In addition, the end-to-end models cannot use external pronunciation and language information due to structual problem. Therefore, in this paper conformer with lexicon transducer is proposed. We compare phoneme-based model with lexicon transducer and grapheme-based model with beam search. Test set is consist of words that do not appear in training data. The grapheme-based conformer with beam search shows 3.8 % of CER. The phoneme-based conformer with lexicon transducer shows 3.4 % of CER.

• Journal of Korean Society of Forest Science
• /
• v.110 no.4
• /
• pp.610-621
• /
• 2021

The soil creep, primarily caused by earthquakes and torrential rainfall events, has widely occurred across the country. The Korea Forest Service attempted to quantify the soil creep susceptible areas using a discriminant value table to prevent or mitigate casualties and/or property damages in advance. With the advent of advanced computer technologies, machine learning-based classification models have been employed for managing mountainous disasters, such as landslides and debris flows. This study aims to quantify the soil creep susceptibility using several classifiers, namely the k-Nearest Neighbor (k-NN), Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM) models. To develop the classification models, we downscaled 292 data from 4,618 field survey data. About 70% of the selected data were used for training, with the remaining 30% used for model testing. The developed models have the classification accuracy of 0.727 for k-NN, 0.750 for NB, 0.807 for RF, and 0.750 for SVM against test datasets representing 30% of the total data. Furthermore, we estimated Cohen's Kappa index as 0.534, 0.580, 0.673, and 0.585, with AUC values of 0.872, 0.912, 0.943, and 0.834, respectively. The machine learning-based classifications for soil creep susceptibility were RF, NB, SVM, and k-NN in that order. Our findings indicate that the machine learning classifiers can provide valuable information in establishing and implementing natural disaster management plans in mountainous areas.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.8
• /
• pp.139-148
• /
• 2019

Fostering science-gifted individuals are very important for the future of the nation, and it is especially important to cultivate information-gifted individuals in the age of the fourth industry. There is no standardized curriculum for each gifted education center of the University. Therefore, in this study, we analyzed how effective the curriculum developed on the basis of computing thinking is to affect the characteristics of the information-gifted individuals. The curriculum developed on the components of computing thinking was applied to the information-gifted students of K University. In order to verify the effectiveness of the curriculum, we developed a creative personality test and an intrinsic motivation test, and conducted tests before and after the training. We compared pre-post test results by t-test with R program. The creative personality test consisted of 36 items with 6 factors: risk-taking, self - acceptance, curiosity, humor, dominance, and autonomy. The intrinsic motivation test consisted of 20 items with 5 items: curiosity and interest oriented tendency, challenging learning task preference orientation, independent judgment dependency propensity, independent mastery propensity, and internal criterion propensity. The effect of the curriculum on the creative personality of the experimental group was significant (0.009, 0.05). The significance level of the intrinsic motivation was 0.056 and was not significant at the 0.05 level of significance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.3
• /
• pp.9-15
• /
• 2019

Large global online shopping malls, such as Amazon, offer services in English or in the language of a country when their products are sold. Since many customers purchase products based on the product reviews, the shopping malls actively utilize the sentimental analysis technique in judging preference of each product using the large amount of review data that the customer has written. And the result of such analysis can be used for the marketing to look the potential shoppers. However, it is difficult to apply this English-based semantic analysis system to different languages used around the world. In this study, more than 500,000 data from Amazon fine food reviews was used for training a deep learning based system. First, sentiment analysis evaluation experiments were carried out with three models of English test data. Secondly, the same data was translated into seven languages (Korean, Japanese, Chinese, Vietnamese, French, German and English) and then the similar experiments were done. The result suggests that although the accuracy of the sentimental analysis was 2.77% lower than the average of the seven countries (91.59%) compared to the English (94.35%), it is believed that the results of the experiment can be used for practical applications.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.32 no.6
• /
• pp.370-374
• /
• 2018

Oriental Diagnosis System(ODS) is an artificial intelligence program that utilize entered diagnosis knowledge, determine patient's disease and decide right medicine. The purpose of this study is to find a correlation between pattern Identification in Korean medicine and each sasang types(Tae-Eum and So-Yang) by analyzing ODS diagnosis result. Eventually our study secure availability of using ODS program at clinical training or developing diagnosis program. Subject of this study is 50 patients who was performed Sasang constitution diagnosis (28 patients were Tae-Eum and 22 patients were So-Yang). We analyize patient's diagnosis records by using ODS program and obtained result about pattern Identification. We used SPSS statistics 23 in analyzing the differences of the scores of Eight Principle Pattern Identification, Qi-Blood Pattern Identification, and Bing-xie Pattern Identification in each Sasang types (Tae-Eum, So-Yang). The Heat and Heat-moisture scores were significantly different(p<0.05) and Qi-Blood Pattern Identification scores were not different in each Sasang types(p>0.05). And Weight was significantly different in each Sasang types(p<0.05). It is hard to generalize the result because subject of this study was not enough and had sample speciality(tinnitus patients). However, we explained correlation between pattern Identification in korean medicine and each sasang types based on quantifiable and objective evidence system. it can be used at education of korean medicine and evidence of practice diagnosis. Futhermore, there have been no studies about anaylizing correlation between pattern Identification in Korean medicine and each sasang types using ODS program. So it is worthy of being utilized at clinical evidence data of ODS program.