• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.4
• /
• pp.337-343
• /
• 1996

In this paper, we investigate the defect detection by making use of pre-made reference image data and classify the defects by using the artificial neural network. The approach is composed of three main parts. The first step consists of a proper generation of two reference image data by using a low level morphological technique. The second step proceeds by performing three times logical bit operations between two ready-made reference images and just captured image to be tested. This results in defects image only. In the third step, by extracting four features from each detected defect, followed by assigning them into the input nodes of an already trained artificial neural network we can obtain a defect class corresponding to the features. All of the image data are formed in a bit level for the reduction of data size as well as time saving. Experimental results show that proposed algorithms are found to be effective for flexible defect detection, robust classification, and high speed process by adopting a simple logic operation.

• Journal of Korea Multimedia Society
• /
• v.17 no.2
• /
• pp.232-239
• /
• 2014

As online texts have been rapidly growing, their automatic classification gains more interest with machine learning methods. Nevertheless, comparatively few research could be found, aiming for Korean texts. Evaluating them with statistical methods are also rare. This study took a sample of tweets and used machine learning methods to classify emotions with features of morphemes and n-grams. As a result, about 76% of emotions contained in tweets was correctly classified. Of the two methods compared in this study, Support Vector Machines were found more accurate than Na$\ddot{i}$ve Bayes. The linear model of SVM was not inferior to the non-linear one. Morphological features did not contribute to accuracy more than did the n-grams.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.8
• /
• pp.1272-1277
• /
• 2017

To assist radiologists for the characterization of breast masses, Computer-aided Diagnosis(CADx) system has been studied. The CADx system can improve the diagnostic accuracy of radiologists by providing objective information about breast masses. Morphological and texture features were extracted from the breast ultrasound images. Based on extracted features, the CADx system retrieves masses that are similar to a query mass from a reference library using a k-nearest neighbor (k-NN) approach. Eight similarity measures of distance, Euclidean, Chebyshev(Minkowski family), Canberra, Lorentzian($F_2$ family), Wave Hedges, Motyka(Intersection family), and Cosine, Dice(Inner Product family) are evaluated by ROC(Receiver Operating Characteristic) analysis. The Inner Product family measure used with the k-NN classifier provided slightly higher performance for classification of malignant and benign masses than those with the Minkowski, $F_2$, and Intersection family measures.

• BMB Reports
• /
• v.31 no.2
• /
• pp.183-188
• /
• 1998

2-chloroethylethyl sulfide (CEES) is an alkylating agent that readily reacts with a wide variety of biological molecules causing metabolic abnormality. The mechanism of cell death during CEES injury is poorly understood. We have examined the effect of exposure of thymocytes with various concentrations of CEES to determine the pattern of cell death in thymocytes injury induced by CEES. In the present study, we show that two patterns of cell death occurred by either one of two mechanisms: apoptosis and necrosis. Exposure to low level of CEES (100 ${\mu}M$) for 5 h caused an induction of apoptosis on thymocytes, as identified by the following criteria: DNA fragmentation visualized by the characteristic "ladder" pattern was observed upon agarose gel electrophoresis and morphological features were revealed by microscopical observations. In contrast, exposure to high levels of CEES (500 ${\mu}M$) induce necrotic features such as cell lysis. Thus, depending on the concentrations, CEES can result in either apoptotic or necrotic cell damage. Our findings suggest that thymocytes which are not killed directly, but merely injured by low levels of CEES, are able to activate an internally-programmed cell death mechanism, whereas thymocytes receiving severe damages apparently can not.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.16 no.3
• /
• pp.602-608
• /
• 2002

To investigate whether Puerariae radix (PR) possesses protective effect against ethanol (EtOH)-inducecl apoptosis in the central nervous system, MTT (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide) assay, flow cytometric analysis, DNA fragmentation assay. and reverse transcription-polymerase chain reaction (RT-PCR) were performed on human neuroblastoma cell line SK-N-MC. Morphological and biochemical analyses demonstrated that SK-N-MC cells treated with EtOH exhibit classical apoptotic features. On the other hand, cells pre-treated with PR prior to EtOH exposure showed decreased occurrence of classical apoptotic features. In addition, it was shown that PR pre-treatment inhibits EtOH-induced increases in the levels of mRNA expression of bax and caspase-3, while it further enhances the level of bcl-2 expression. These results suggest that PR may exert protective effects against EtOH-induced apoptosis in human neuroblastoma cells.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.1
• /
• pp.13-20
• /
• 2006

In this paper, we constructed a spam-mail filtering system based on the lexical and conceptual information. There are two kinds of information that can distinguish the spam mail from the legitimate mil. The definite information is the mail sender's information, URL, a certain spam keyword list, and the less definite information is the word lists and concept codes extracted from the mail body. We first classified the spam mail by using the definite information, and then used the less definite information. We used the lexical information and concept codes contained in the email body for SVM learning. According to our results the spam precision was increased if more lexical information was used as features, and the spam recall was increased when the concept codes were included in features as well.

• Korean Journal of Environmental Biology
• /
• v.36 no.2
• /
• pp.150-155
• /
• 2018

Two siphonous green algae were collected from the eastern coast of Korea. These species share the typical features of Derbesia sporophytes, such as erect and prostrate siphonous filaments and the presence of basal septum in lateral branches. One is characterized by the combined features of a relatively small tufted sporophytic thalli arising from a rhizoidal base, subdichotomously branched filaments with a basal septum and one pyrenoid per subspherical to lenticular chloroplast. The other shows a larger sporophytic thallus, sparsely subdichotomously branched filaments with a basal septum and one pyrenoid per spherical chloroplast. In a phylogenetic tree based on rbcL sequence, the two above-mentioned Korean algae nest in the same clades as Derbesia minima and D. indica, respectively. The genetic distance between the sequences within the clades was 0.5-0.8%, which is considered to be included in the intra-specific range for the genus. These two siphonous Korean algae are identified as D. minima and D. indica, respectively, based on the morphological and molecular analyses. These species are newly recorded in the Korean marine algal flora herein.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.8
• /
• pp.65-72
• /
• 2020

Big data analysis is widely used in applications such as finance and communication, whose market size is growing rapidly every year. Nevertheless, it is rarely used by SMEs (small and medium-sized enterprises) since the existing services are not fully customized for them while being offered at high price. To resolve this, we develop and propose a new platform to provide big data analysis services specialized for SMEs in this paper. First, we compare existing work discussing social big data analysis, and extract service features necessary to help their marketing effectively. Then, we present a prototype system implementing the extracted features, and discuss technical issues needed to develop a complete system which are obtained from the prototype implementation.

• ETRI Journal
• /
• v.38 no.1
• /
• pp.174-184
• /
• 2016

Information identification with image data by means of low-level visual features has evolved as a challenging research domain. Conventional text-based mapping of image data has been gradually replaced by content-based techniques of image identification. Feature extraction from image content plays a crucial role in facilitating content-based detection processes. In this paper, the authors have proposed four different techniques for multiview feature extraction from images. The efficiency of extracted feature vectors for content-based image classification and retrieval is evaluated by means of fusion-based and data standardization-based techniques. It is observed that the latter surpasses the former. The proposed methods outclass state-of-the-art techniques for content-based image identification and show an average increase in precision of 17.71% and 22.78% for classification and retrieval, respectively. Three public datasets - Wang; Oliva and Torralba (OT-Scene); and Corel - are used for verification purposes. The research findings are statistically validated by conducting a paired t-test.

• Journal of architectural history
• /
• v.24 no.1
• /
• pp.41-50
• /
• 2015

This study aims to investigate the physical characteristics and architectural ornaments of the walls (DamJang) and their bordering area that defines the Rear Garden of Changdeok-gung, one of the Royal Palaces in Seoul. This area, centered on Buyong-ji(부용지) and Aeryeon-ji(애련지), features the morphological diversity of buildings, walls, gates and stone bases in the palace. The findings are summarized as follows: First, DamJang, as a basic architectural element for the space organization, takes a set of various forms featuring different construction materials while responding positively to the physiographic nature of the surroundings; Second, DamJang along with their gates, also features different types of ornamental expressions which also suggest the hierarchy of its building and space; Third, typical of the traditional garden design in Korea are a group of DamJang standing as independent structures mostly around Buyong-ji and Aeryeon-ji whose finishing conditions also differ based on the nature of the space; Fourth, among commonly observed examples of DamJang in the Rear Garden and Changdeok-gung palace-wide, is a 'T' shaped wall whose heights and materials function as a design element for the garden.