• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.153-156
• /
• 2002

The image labeling and classification is one of the important tasks for a content-based image retrieval and an image understanding. This paper propose a new technique to label and classify natural images with a color-spatial histogram and production rules. We show that our proposed method is very efficient for a natural image composed of a few regions.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.10
• /
• pp.2041-2046
• /
• 2009

In this paper, we propose the feature points extraction method of hand region using vision. To do this, first, we find the HCbCr color model by using HSI and YCbCr color model. Second, we extract the hand region by using the HCbCr color model and the fuzzy color filter. Third, we extract the exact hand region by applying labeling algorithm to extracted hand region. Fourth, after finding the center of gravity of extracted hand region, we obtain the first feature points by using Canny edge, chain code, and DP method. And then, we obtain the feature points of hand region by applying the convex hull method to the extracted first feature points. Finally, we demonstrate the effectiveness and feasibility of the proposed method through some experiments.

• Journal of Korea Multimedia Society
• /
• v.4 no.4
• /
• pp.234-332
• /
• 2001

For a method improving fractal image segmentation which is a new application of fractal image coding, YST scheme have proposed an image segmentation scheme using labeling based on periodic points of pixel transformation and error-correction of labels by iterating fractal transformation. The scheme generates the high quality segmentation, however, it has the redundancy in the process of labeling and correction of labels. To solve this problem, we propose a labeling algorithm based on orbit of pixel transformation and restricted condition on iterating process of fractal transformation.

• Journal of environmental and Sanitary engineering
• /
• v.13 no.3
• /
• pp.37-42
• /
• 1998

2-Bromopropane has been implicated to be the reason for the mass intoxication of workers at an electronic company in Korea. 2-Bromopropane deposition and pattern of DNA replication in mouse fetuses were analyzed after intravenous injection of 2-bromopropane. Injections were administered to pregnant ICR mice in order to cytogenetically evaluate transplacental 2-bromopropane. The results are summarized as follows; 1. A dose-dependent effect on DNA replication was observed equally in the lung, liver and kideneys of fetuses has been exposed to 2-bromopropane transplacentally as reductions of the labeling index. 2. Deposition of transplacentally administred 2-bromopropane in the fetus was lower than placenta.

• Korean Journal of Digital Imaging in Medicine
• /
• v.15 no.1
• /
• pp.27-31
• /
• 2013

Perfusion MR imaging is how to use exogenous and endogenous contrast agent. Exogenous perfusion MRI methods which are dynamic susceptibility contrast using $T2^*$ effect and dynamic contrast-enhanced using T1 weighted image after injection contrast media. An endogenous perfusion MRI method which is arterial spin labeling using arterial blood flow in body. In order to exam perfusion MRI in human, technical access are very important according to disease conditions. For instance, dynamic susceptibility contrast is used in patients with acute stroke because of short exam time, while dynamic susceptibility contrast or dynamic contrast enhancement provides the various perfusion information for patients with tumor, vascular stenosis. Arterial spin labeling is useful for children, women who are expected to be pregnant. In this regard, perfusion MR imaging is required to understanding, and the author would like to share information with clinical users

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.5
• /
• pp.1-7
• /
• 2018

Reference string recognition is to extract individual reference strings from a reference section of an academic article, which consists of a sequence of reference lines. This task has been attacked by heuristic-based, clustering-based, classification-based approaches, exploiting lexical and layout characteristics of reference lines. Most classification-based methods have used sequence labeling to assign labels to either a sequence of tokens within reference lines, or a sequence of reference lines. Unlike the previous token-level sequence labeling approach, this study attempts to assign different labels to the beginning, intermediate and terminating tokens of a reference string. After that, post-processing is applied to identify reference strings by predicting their beginning and/or terminating tokens. Experimental evaluation using English and German reference string recognition datasets shows that the proposed method obtains above 94% in the macro-averaged F1.

• Bulletin of the Korean Chemical Society
• /
• v.31 no.6
• /
• pp.1474-1478
• /
• 2010

An efficient method for labeling individual proteins in live cells is required for investigations into biological mechanisms and cellular processes. Here we describe the preparation of small quantum dots (QDs) that target membrane surface proteins bearing a hexahistidine-tag ($His_6$-tag) via specific binding to an nitrilotriacetic acid complex of nickel(II) ($NTA{\cdot}Ni^{2+}$) on the QD surfaces. We showed that the $NTA{\cdot}Ni^{2+}$-QDs bound to His-tag functionalized beads as a cellular mimic with high specificity and that QDs successfully targeted $His_6$-tagged vesicle-associated membrane proteins (VMAP) on cell surfaces. This strategy provides an efficient approach to monitoring synaptic protein dynamics in spatially restricted and confined biological environments.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.121-125
• /
• 2020

With miniaturization of semiconductor, the manufacturing process become more complex, and undetected small changes in the state of the equipment have unexpectedly changed the process results. Fault detection classification (FDC) system that conducts more active data analysis is feasible to achieve more precise manufacturing process control with advanced machine learning method. However, applying machine learning, especially in supervised learning criteria, requires an arduous data labeling process for the construction of machine learning data. In this paper, we propose a semi-supervised learning to minimize the data labeling work for the data preprocessing. We employed equipment status variable identification (SVID) data and optical emission spectroscopy data (OES) in silicon etch with SF6/O2/Ar gas mixture, and the result shows as high as 95.2% of labeling accuracy with the suggested semi-supervised learning algorithm.

• ETRI Journal
• /
• v.36 no.3
• /
• pp.429-438
• /
• 2014

Semantic role labeling (SRL) is a task in natural-language processing with the aim of detecting predicates in the text, choosing their correct senses, identifying their associated arguments, and predicting the semantic roles of the arguments. Developing a high-performance SRL system for a domain requires manually annotated training data of large size in the same domain. However, such SRL training data of sufficient size is available only for a few domains. Constructing SRL training data for a new domain is very expensive. Therefore, domain adaptation in SRL can be regarded as an important problem. In this paper, we show that domain adaptation for SRL systems can achieve state-of-the-art performance when based on structural learning and exploiting a prior model approach. We provide experimental results with three different target domains showing that our method is effective even if training data of small size is available for the target domains. According to experimentations, our proposed method outperforms those of other research works by about 2% to 5% in F-score.

• Korean Journal of Community Nutrition
• /
• v.12 no.5
• /
• pp.519-533
• /
• 2007

This study was carried out to investigate the nutrition knowledge, dietary attitudes, and dietary habits of girl's high school students in Kunsan, and to investigate their recognition of food-nutrition labeling. The results are summarized as follows. General nutrition knowledge is relatively low, with an average of 0.57. It was shown that high school female students skipped breakfast rather than lunch or dinner, with a skipping rate of 28.9% for breakfast, 0.7% for lunch, and 8.6% for dinner. Regarding snacks, 35.5% of all the surveyed students had 1 snack per day, with 31.9% having them between lunch and dinner. The most popular snacks include biscuits (22.3%), noodles (18.3%) and bakery (13.3%). The most popular response was that students 'sometimes checked' the food label of processed domestic and imported processed food. The level of satisfaction with food labels is moderate, with an average of 2.96, out of 5. The most satisfactory title about food labels was 'helpful for food selection' with 3.19. On the other hand, the least satisfactory title was 'understands the label' with 2.78. Regarding the identification of the nutrition labeling, the highest response was 'sometimes watched, sometimes not' with 40.5%. Products which were most often checked were milk/milk products (3.44), snacks/bread (3.33), and soft drinks (3.07). Among nutrition labeling items, total calories was the most important, followed by fat, carbohydrate, cholesterol and calcium. The question regarding the knowledge of nutrition labeling rated an average of 0.58 (out of 1). There was a significant positive correlation between the degree of the nutrition label verification and the dietary attitude score, along with the nutrition labeling knowledge and the nutrition knowledge score of the subjects. On the other hand, the degree of the nutrition label verification and the knowledge on nutrition labeling had a significant negative correlation. Hence, it is of the opinion that education on properly reading nutrient information is necessary to enable adolescents to apply that in real life. Furthermore, labeling nutritional information on processed fred through a more comprehensive method is deemed necessary as a supporting measure.