• Korean Journal of Computational Design and Engineering
• /
• v.16 no.4
• /
• pp.249-259
• /
• 2011

In this paper we present our work on the parameterized construction of virtual drivers' reach motion to seat belt, by using motion capture data. A user can generate a new reach motion by controlling a number of parameters. We approach the problem by using multiple sets of example reach motions and learning the relation between the labeling parameters and the motion data. The work is composed of three tasks. First, we construct a motion database using multiple sets of labeled motion clips obtained by using a motion capture device. This involves removing the redundancy of each motion clip by using PCA (Principal Component Analysis), and establishing temporal correspondence among different motion clips by automatic segmentation and piecewise time warping of each clip. Next, we compute motion blending functions by learning the relation between labeling parameters (age, hip base point (HBP), and height) and the motion parameters as represented by a set of PC coefficients. During runtime, on-line motion synthesis is accomplished by evaluating the motion blending function from the user-supplied control parameters.

• Korean Journal of Community Nutrition
• /
• v.1 no.1
• /
• pp.28-40
• /
• 1996

This study was conducted to evaluate the nutrition quality of the commercial infant formulas and to seek the solution to the establishment of the standard of nutrient requirements for infant formula in Korea. Nutrition informations were obtained from the labels of nineteen commercial infant formulas manufactured by 3 different companies, and the actual amounts of some nutrients were analyzed and compared to the labeled amounts. In addition, the nutrient composition of the commercial infant formulas was compared to the composition of breast milk, RDA for infants, and Codex standard for infant formula. The kind of minerals, vitamins and special components added to the commercial infant formulas were the major differences among 3 manufacturers. For some nutrients, the analyzed amounts were lower than the labeled amounts. In addition when different batches of the same kind of infant formula were analyzed, the large variations in the amounts of certain nutrients were noted. These data suggest that the nutrition labeling informations need to be validated, and nutrients added to the formulas are to be homogenized thoroughly. In order to solve these problems, therefore, like other countries, we need to establish the standard of nutrient requirements for infant formulas. Considering the available data on breast milk composition, RDA for infants and coordination with the international standard, we suggest the adoption of the Codex standard for infant formula may be the best way to manage the nutrition quality of commercial infant formulas at the present time.

• Journal of the Korean Society of Food Culture
• /
• v.32 no.1
• /
• pp.39-51
• /
• 2017

The purpose of this study was to analyze the current status relating to food packaging and design for status of small and medium food enterprises. A company survey was conducted from June to October, 2015 and targeted 1300 small and medium domestic food enterprises. Finally, a total of 1300 (recovery rate 100%) useable data were selected. Statistical analyses were performed on the data utilizing the SPSS PASW Statistics 18.0 for Windows, such as descriptive statistics and frequency analysis. According to the results, awareness and importance of food labeling were high, but performance of English inscription of product name was relatively low. The most important reason for food labeling was 'providing correct information on food' 910 (72.8%). Accordingly, a system which can provide the latest information by continuously monitoring mandatory disclosure requirements for types of foods in individual countries is needed.

• Journal of Biomedical Engineering Research
• /
• v.28 no.4
• /
• pp.549-555
• /
• 2007

In order to study cortical properties in human, it is necessary to obtain an accurate and explicit representation of the cortical surface in individual subjects. Among many approaches, surface-based method that reconstructs a 3-D model from contour lines on cross-section images is widely used. In general, however, medical brain imaging has some problems such as the complexity of the images, non-linear gain artifacts and so on. Due these limitations, therefore, extracting anatomical structures from imaging data is very a complicated and time-consuming task. In this paper, we present an improved method for extracting contour lines of cortical surface from magnetic resonance images that simplifies procedures of a conventional method. The conventional method obtains contour lines through thinning and chain code process. On the other hand, the proposed method can extract contour lines from comparison between boundary data and labeling image without supplementary processes. The usefulness of the proposed method has been verified using brain image.

• Journal of the Korean Society of Costume
• /
• v.54 no.6
• /
• pp.77-90
• /
• 2004

The purpose of this study was to provide basic information requisite in the new sizing system for gloves. KS glove standards' size dimensions, size designation and labeling systems were analyzed. Also, KS glove standards' control sizes were compared to the anthropometric data of 824 Korean adults taken in the previous study. As well, the ISO hand size system was also compared to the anthropometric data of the previous study according to frequency tables of hand length and hand circumference. The size dimensions showed differences among KS standards and there was no size designation and labeling systems existed in KS standards. Among KS glove size systems, protective rubber gloves for radioactive contamination and surgical rubber gloves' size which followed ISO system were accurately indicate the hand size of the person a glove is intended to fit. ISO glove sizing system comprised the control dimensions of hand length and hand circumference. The coverage of ISO size A was 84.8% which was highest among ISO size A. B, C. And in hand circumference 178, 191, 203, 216mm showed the frequencies above 3% and in hand length 167, 175. 183, 191, 199mm showed the frequencies above 3%.

• Journal of Computing Science and Engineering
• /
• v.3 no.3
• /
• pp.165-180
• /
• 2009

The HKIB, or Hankookilbo, test collections are two archives of Korean newswire stories manually categorized with semi-hierarchical or hierarchical category taxonomies. The base newswire stories were made available by the Hankook Ilbo (The Korea Daily) for research purposes. At first, Chungnam National University and KISTI collaborated to manually tag 40,075 news stories with categories by semi-hierarchical and balanced three-level classification scheme, where each news story has only one level-3 category (single-labeling). We refer to this original data set as HKIB-40075 test collection. And then Yonsei University and KISTI collaborated to select 20,000 newswire stories from the HKIB-40075 test collection, to rearrange the classification scheme to be fully hierarchical but unbalanced, and to assign one or more categories to each news story (multi-labeling). We refer to this modified data set as HKIB-20000 test collection. We benchmark a k-NN categorization algorithm both on HKIB-20000 and on HKIB-40075, illustrating properties of the collections, providing baseline results for future studies, and suggesting new directions for further research on Korean text categorization problem.

• Preventive Nutrition and Food Science
• /
• v.18 no.4
• /
• pp.242-248
• /
• 2013

In recent years, manufacturers of animal-based foods with health claims have encountered difficulties in the labeling of their products because of a lack of regulation on defining the functionality of animal-based foods. Therefore, this study was conducted to establish the basic requirements for the development of a definition for functional animal-based foods by investigating consumer and industry awareness. Survey data were collected from 114 industry representatives and 1,100 consumers. The questions of the survey included items on production status and future production plans, functionality labeling, promotion plans, establishment of definition, the role of the government, consumer perception, and selection of products. The results show that both industry representatives and consumers believe that legislation and the provision of scientific evidence should be improved for the development of a functional animal-based foods market. The results obtained from this study will contribute to consumer trust by supplying correct information and can be utilized in the industry as basic data for the development of functional animal-based food products.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.79-87
• /
• 2021

In this paper, we analysis the semi-supervised learning (SSL), which is adopted in order to train a deep learning-based classification model using the small number of labeled data. The conventional SSL techniques can be categorized into consistency regularization, entropy-based, and pseudo labeling. First, we describe the algorithm of each SSL technique. In the experimental results, we evaluate the classification accuracy of each SSL technique varying the number of labeled data. Finally, based on the experimental results, we describe the limitations of SSL technique, and suggest the research direction to improve the classification performance of SSL.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.132-137
• /
• 2019

The amount of data generated from medical images is increasingly exceeding the limits of professional visual analysis, and the need for automated medical image analysis is increasing. For this reason, this study evaluated the classification and accuracy according to the presence or absence of tumor using Inception V3 deep learning model, using MRI medical images showing normal and tumor findings. As a result, the accuracy of the deep learning model was 90% for the training data set and 86% for the validation data set. The loss rate was 0.56 for the training data set and 1.28 for the validation data set. In future studies, it is necessary to secure the data of publicly available medical images to improve the performance of the deep learning model and to ensure the reliability of the evaluation, and to implement modeling by improving the accuracy of labeling through labeling classification.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.555-562
• /
• 2016

Semantic Role Labeling (SRL) is to determine the semantic relation of a predicate and its argu-ments in a sentence. But Korean semantic role labeling has faced on difficulty due to its different language structure compared to English, which makes it very hard to use appropriate approaches developed so far. That means that methods proposed so far could not show a satisfied perfor-mance, compared to English and Chinese. To complement these problems, we focus on suffix information analysis, such as josa (case suffix) and eomi (verbal ending) analysis. Korean lan-guage is one of the agglutinative languages, such as Japanese, which have well defined suffix structure in their words. The agglutinative languages could have free word order due to its de-veloped suffix structure. Also arguments with a single morpheme are then labeled with statistics. In addition, machine learning algorithms such as Support Vector Machine (SVM) and Condi-tional Random Fields (CRF) are used to model SRL problem on arguments that are not labeled at the suffix analysis phase. The proposed method is intended to reduce the range of argument instances to which machine learning approaches should be applied, resulting in uncertain and inaccurate role labeling. In experiments, we use 15,224 arguments and we are able to obtain approximately 83.24% f1-score, increased about 4.85% points compared to the state-of-the-art Korean SRL research.