• 한국인터넷방송통신학회논문지
• /
• 제21권6호
• /
• pp.77-82
• /
• 2021

요검사는 물리적 성상 검사, 화학적 검사, 현미경 검사 세 가지가 있다. 이 중에서 화학적 요검사는 일반인이 쉽게 접근하는 방법으로 요검사지의 화학반응을 눈으로 표준비색표와 비교하거나 휴대용 요검사기를 별도로 구매하여 검사를 진행한다. 현재는 스마트폰의 보급이 대중화되어 스마트폰을 활용한 요검사 서비스 연구가 높아지고 있다. 요검사 스크리닝 애플리케이션은 스마트폰을 활용한 요검사 서비스 중 하나이다. 그러나 요검사 스크리닝 애플리케이션으로 촬영한 요검사 패드 RGB 값은 조명영향으로 인해 큰 편차가 발생한다. 요검사 패드 RGB 값의 편차는 요검사 판별의 정확도를 떨어뜨린다. 따라서 본 논문에서는 스마트폰 기반 요검사 스크리닝 애플리케이션으로 촬영한 요검사지를 검사 항목별 요검사 패드로 분류한 후 CNN을 통해 요검사 패드 이미지 판별의 정확도를 높인다. 요검사지는 다양한 배경에서 촬영하여 CNN 이미지를 생성하였으며 ResNet-50 CNN 모델을 사용하여 요검사 판별을 분석하였다.

• Journal of the Korean Statistical Society
• /
• 제30권2호
• /
• pp.247-263
• /
• 2001

This paper concerns a problem of classification based on training dta. A framework of information geometry is given to elucidate the characteristics of discriminant functions including logistic discrimination and AdaBoost. We discuss a class of loss functions from a unified viewpoint.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2826-2840
• /
• 2018

Traditional methods based active contours or region merging are powerless in processing images with blurring border or hair occlusion. In this paper, a structure based convolutional neural networks is proposed to solve segmentation of skin lesion image. The structure mainly consists of two networks which are segmentation net and discrimination net. The segmentation net is designed based U-net that used to generate the mask of lesion, while the discrimination net is designed with only convolutional layers that used to determine whether input image is from ground truth labels or generated images. Images were obtained from "Skin Lesion Analysis Toward Melanoma Detection" challenge which was hosted by ISBI 2016 conference. We achieved segmentation average accuracy of 0.97, dice coefficient of 0.94 and Jaccard index of 0.89 which outperform the other existed state-of-the-art segmentation networks, including winner of ISBI 2016 challenge for skin melanoma segmentation.

• 한국컴퓨터정보학회논문지
• /
• 제21권5호
• /
• pp.167-175
• /
• 2016

The volatile component analysis of 82 commercialized liquors(44 samples of single malt whisky, 20 samples of blended whisky and 18 samples of brandy) was carried out by gas chromatography after liquid-liquid extraction with dichloromethane. Pattern recognition techniques such as principle component analysis(PCA), cluster analysis(CA), linear discriminant analysis(LDA) and partial least square discriminant analysis(PLSDA) were applied for the discrimination of different liquor categories. Classification rules were validated by considering sensitivity and specificity of each class. Both techniques, LDA and PLSDA, gave 100% sensitivity and specificity for all of the categories. These results suggested that the common characteristics and identities as typification of whiskies and brandys was founded by using multivariate data analysis method.

• International Journal of Safety
• /
• 제1권1호
• /
• pp.28-35
• /
• 2002

Kullback Discrimination Information (KDI) is one of the pattern recognition methods. KDI defined as a measure of the mutual dissimilarity computed between two time series was studied for detection and classification of bearing flaking on outer-race and inner-races. To model the damages, the bearings in normal condition, outer-race flaking condition and inner-races flaking condition were provided. The vibration sensor was attached by the bearing housing. This produced the total 25 pieces of data each condition, and we chose the standard data and measure of distance between standard and tested data. It is difficult to detect the flaking because similar pulses come out when balls pass the defection point. The detection and classification method for inner and outer races are defected by KDI and nearest neighbor classification rule is proposed and its high performance is also shown.

• 경영과정보연구
• /
• 제13권
• /
• pp.141-162
• /
• 2003

This article discusses the issues of the estimated size and characteristics of irregular employment work force in Korea after IMF economic crisis in 1997. The issues of the estimated size of irregular employment work force originated from different concepts and its operationalizations among the labor economists, despite their utilization of the same labor force data, 'Economically Active Population Survey(EAPA)' collected from Korea National Statistical Office(KNSO). And the issues contribute toward the understandings of the irregular employment and the limits of the EAPA, despite its various usefulness. This article also describes the summary characteristics of irregular employment work force from both sides of labor supply and its demand. The major characteristics of irregular employment work force on the labor supply side appears in the concentration of social minorities, i.e. woman, the aged, lower educated and skilled populations. On the labor demand of irregular employment work force, the majority of it concentrated on the establishments under 10 employees, and probably the important incentives for irregular employment work force of the firms is labor cost efficiency. Finally, this article propose an alternative against the discrimination between the regular and irregular work force.

• BMB Reports
• /
• 제31권6호
• /
• pp.525-535
• /
• 1998

A critical step in the faithful translation of genetic information is specific tRNA recognition by aminoacyl-tRNA synthetases. These enzymes catalyze the covalent attachment of particular amino acids to the terminal adenosine of cognate tRNA substrates. In general, there is one synthetase for each of the twenty amino acids and each enzyme must discriminate against all of the cellular tRNAs that are specific for the nineteen noncognate amino acids. Primary sequence information combined with structural data have resulted in the division of the twenty synthetases into two classes. In recent years, several high-resolution co-crystal structures along with biochemical data have led to an increased understanding of tRNA recognition by synthetases of both classes. The anticodon sequence and the amino acid acceptor stem are the most common locations for critical recognition elements. This review will focus on acceptor stem discrimination by class II synthetases. In particular, the results of in vitro aminoacylation assays and site-directed and atomic group mutagenesis studies will be discussed. These studies have revealed that even subtle atomic determinants can provide signals for specific tRNA aminoacylation.

• 음성과학
• /
• 제9권4호
• /
• pp.253-263
• /
• 2002

In this paper, we propose new algorithm of speaker recognition which identifies the speaker using the information obtained by the intensive speech feature analysis such as pitch, intensity, duration, and formant, which are crucial parameters of individual voice, for candidates of high percentage of wrong recognition in the existing speaker recognition algorithm. For testing the power of discrimination of individual parameter, DTW (Dynamic Time Warping) is used. We newly set the range of threshold which affects the power of discrimination in speech verification such that the candidates in the new range of threshold are finally discriminated in the next stage of sound parameter analysis. In the speaker verification test by using voice DB which consists of secret words of 25 males and 25 females of 8 kHz 16 bit, the algorithm we propose shows about 1% of performance improvement to the existing algorithm.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2017년도 제56차 하계학술대회논문집 25권2호
• /
• pp.79-82
• /
• 2017

게임 산업이 발달하고 유저가 증가하면서, MOBA 장르의 게임들이 큰 인기를 끌고 있다. 하지만 팀원의 협동을 필요로 하는 게임에서 성으로 인한 차별적 대우를 받는 유저들이 급증하고 있고, 사회적으로도 이슈가 되고 있다. 본 연구에서는 MOBA 게임에서 유저들이 받고 있는 성차별 피해 사례를 수집하여 차별의 이유를 분석하고, 이런 성차별 피해를 없애기 위해 어떤 시스템을 도입하면 좋을지에 대해 방향을 제시한다.

• 산업경영시스템학회지
• /
• 제29권2호
• /
• pp.1-6
• /
• 2006

This study proposes a new approach which combines Data Envelopment Analysis(DEA) and the Analytic Hierarchy Process(AHP) techniques to effectively evaluate Decision Making Units(DMUs). While DEA evaluates a quantitative data set, employs linear programming to obtain input and output weights and ranks the performance of DMUs, AHP evaluates the qualitative data retrieved from expert opinions and other managerial information in specifying weights. The objective of this research is to design a decision support process for managers to incorporate positive aspects of DEA's absolute numerical evaluations and AHP's human preference structure values. It is believed that a pragmatic manager will be more receptive to the results that include subjective opinions incorporated into the evaluation of the efficiency of each DMU efficiency. The WPDEA method provides better discrimination than the DEA method by reducing the number of efficient units.