• Journal of Microbiology and Biotechnology
• /
• v.14 no.6
• /
• pp.1150-1156
• /
• 2004

The GMO (Genetically Modified Organism) labeling system on raw materials has been in Korea since March 2001, and genetically modified organisms (GMOs)-derived foods since July 2001. Therefore, we designed a multiplex PCR method to ascertain the validity of the labeling system and to monitor the status of circulation for genetically modified maize (GM Maize). Five lines of GM Maize (GA21, TC1507, Mon810, NK603, and Bt176) were used, and specific primer pairs were designed to detect each line. Using this method, the different lines of GM Maize were monitored from raw products and processed foods in Korean market. Some of the maize processed foods and raw materials were shown to contain more than one foreign gene. This method was found to be effective for-detecting five different GM Maize in a single reaction.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.196-199
• /
• 2010

The human eyes are important facial landmarks for image normalization due to their relatively constant interocular distance. This paper introduces a novel approach for the eye detection task using optimal segmentation method for eye representation. The method consists of three steps: (1)edge extraction method that can be used to accurately extract eye region from the gray-scale face image, (2)extraction of eye region using labeling method, (3)eye localization based on intensity information. Experimental results show that a correct eye detection rate of 98.9% can be achieved on 2408 FERET images with variations in lighting condition and facial expressions.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.5
• /
• pp.841-849
• /
• 2001

The pixel information of the object was obtained sequentially and pixels were clustered to a label by the line labeling method. Feature points were determined by finding the slope for edge pixels after selecting the fixed number of edge pixels. The slope was estimated by the least square method to reduce the detection error. Once a matching point was determined by comparing the feature information of the object and the pattern, the parameters for translation, scaling and rotation were obtained by selecting the longer line of the two which passed through the matching point from left and right sides. Finally, modified Hausdorff Distance has been used to identify the similarity between the object and the given pattern. The multi-label method was developed for recognizing the patterns with more than one label, which performs the modified Hausdorff Distance twice. Experiments have been performed to verify the performance of the proposed algorithm and method for simple target image, complex target image, simple pattern, and complex pattern as well as the partially hidden object. It was proved via experiments that the proposed image matching algorithm for recognizing the object had a good performance of matching.

• ETRI Journal
• /
• v.37 no.3
• /
• pp.541-550
• /
• 2015

In this paper, we propose a classification-based approach for hybridizing statistical machine translation and rulebased machine translation. Both the training dataset used in the learning of our proposed classifier and our feature extraction method affect the hybridization quality. To create one such training dataset, a previous approach used auto-evaluation metrics to determine from a set of component machine translation (MT) systems which gave the more accurate translation (by a comparative method). Once this had been determined, the most accurate translation was then labelled in such a way so as to indicate the MT system from which it came. In this previous approach, when the metric evaluation scores were low, there existed a high level of uncertainty as to which of the component MT systems was actually producing the better translation. To relax such uncertainty or error in classification, we propose an alternative approach to such labeling; that is, a cut-off method. In our experiments, using the aforementioned cut-off method in our proposed classifier, we managed to achieve a translation accuracy of 81.5% - a 5.0% improvement over existing methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.796-799
• /
• 2006

This paper presents a new method for automatic detection of skew in a document image using mathematical morphology. To speed up processing, we use reduced image but it still requires long time to estimate the skew angle so the proposed method works with region of interest, not with whole image. Character strings are connected by using morphological closing operation and a component labeling is used to select region of interest. The method considers the lowermost pixels of characters in candidate regions in the binary image of original document image. Experimental results shows that the proposed method is extremely fast and robust as well as independent of script forms.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.8
• /
• pp.565-572
• /
• 2021

The role of the garment and textile industry is particularly important in the economies of many countries in the context of international goods trade. There is no denying that the garment and textile industry contributes significantly to the economic growth in the global economy. The study seeks to investigate the relationship between control variables and Vietnamese consumers' intention to buy Chinese garment products. While previous research has found some control variables influencing consumers' intention to buy products, little research has been done about the influence of control variables on consumers' intention to buy Chinese garment products, in developing countries like Vietnam. In particular, the textile industry plays an important role in export, but outsourcing is accounting for a high proportion of trade, hence, it is necessary to increase innovation to increase consumers' intention to buy domestic garment products. The data is collected from a survey of 406 Vietnamese consumers' in Hanoi city and Ho Chi Minh City. The methodology includes a mixed-method, i.e. qualitative method and quantitative method. The quantitative method applies SPSS analysis to measure the control variables' influence on Vietnamese consumers' intention to buy Chinese garment products. The results identify 1 control variable that impacts Vietnamese consumers' intention to buy Chinese garment products, which is domicile.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.5
• /
• pp.50-59
• /
• 1997

In this paper, we implement an automatic speech segmentation and labeling system which marks phone boundaries automatically for constructing the Korean speech database. We specify and implement the system based on conventional speech segmentation and labeling techniques, and also develop the graphic user interface(GUI) on Hangul $Motif^{TM}$ environment for the users to examine the automatic alignment boundaries and to refine them easily. The developed system is applied to 16kHz sampled speech, and the labeling unit is composed of 46 phoneme-like units(PLUs) and silence. The system uses both of the phonetic and orthographic transcription as input methods of linguistic information. For pattern-matching method, hidden Markov models(HMM) is employed. Each phoneme model is trained using the manually segmented 445 phonetically balanced word (PBW) database. In order to evaluate the performance of the system, we test it using another database consisting of sentence-type speech. According to our experiment, 74.7% of phoneme boundaries are within 20ms of the true boundary and 92.8% are within 40ms.

• Korean Journal of Clinical Laboratory Science
• /
• v.48 no.2
• /
• pp.114-117
• /
• 2016

In vivo labeling of bone with fluorochromes is a widely used method for assessment of bone formation and remodeling processes. In particular, calcein is used as a marker for identification of bone growth, which is indicated by a green color. Calcein green is a calcium chelator that adheres to regions of mineralizing bone thereby allowing localization of new bone. Bone formation and remodeling in vivo can be assessed by calcium-binding calcein labeling. In this study, changes in the femoral bone of a normal mouse model at both 4 and 8 weeks were evaluated using calcein labeling. Intense deposition of calcium in the bone was observed after application for 8 weeks. A mouse model is suitable for application in in vivo experiments using genetically modified mice, such as knock-out mice, however data regarding femoral cross sectional bone in young mice are limited. The current study confirmed calcein as a useful marker for identification of bone growth, which was indicated by a green color on photomicrographs. This methodological process may provide basic information for interpreting bone formation and regeneration to pharmacologic or genetic manipulation in mice.

• Journal of The Korean Association of Information Education
• /
• v.25 no.2
• /
• pp.327-335
• /
• 2021

This study verified the effectiveness of machine learning education programs focused on data labeling as an educational method for improving computational thinking of elementary school students. The education program was designed and developed based on the results of a preliminary demand analysis conducted on 100 elementary school teachers. In order to verify the effectiveness of the developed education program, 17 sixth-grade students attending K Elementary School were given 2 classes per day for a total of 6 weeks. In order to measure the effect of the training on improving computational thinking, the educational effects were analyzed by conducting pre-post-inspection using the "Beaver Challenge". According to the analysis, machine learning education focused on data labeling contributed to improving computational thinking of elementary school students.

• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1251-1258
• /
• 2019

Intelligent tutoring system enables users to effectively learn by utilizing various artificial intelligence techniques. For instance, it can recommend a proper curriculum or learning method to individual users based on their learning history. To do this effectively, user's characteristics need to be analyzed and classified based on various aspects such as interest, learning ability, and personality. Even though data labeled by the characteristics are required for more accurate classification, it is not easy to acquire enough amount of labeled data due to the labeling cost. On the other hand, unlabeled data should not need labeling process to make a large number of unlabeled data be collected and utilized. In this paper, we propose a semi-supervised learning method based on feedback variational auto-encoder(FVAE), which uses both labeled data and unlabeled data. FVAE is a variation of variational auto-encoder(VAE), where a multi-layer perceptron is added for giving feedback. Using unlabeled data, we train FVAE and fetch the encoder of FVAE. And then, we extract features from labeled data by using the encoder and train classifiers with the extracted features. In the experiments, we proved that FVAE-based semi-supervised learning was superior to VAE-based method in terms with accuracy and F1 score.