• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.1236-1239
• /
• 2002

When we see an object, we usually can say what it is easily even for the case where the object isn't shown in the frontal view. However, it is difficult to believe that all views of every object we have ever seen are fully memorized in our brain. Possibly, when an object is shown, we have some typical views of the object in our brain through our past experience and reconstruct the view to recognize what the presented object is. Non-negative Matrix Factorization (NMF) is one of the methods to extract the basis images from sample data set. The prominent feature of this method is that the reconstructed image is obtained by only additions of the basis images with suitable positive weights. So NMF can be seen more biologically plausible method than any other feature extraction methods such as Vector Quantization (VQ) and principal Component Analysis (PCA). In this paper, we adopt NMF to extract the aspect features from the set of images, which consists of various views of a given object. Some experiments are shown how much well NMF can extract the aspect features than any other methods such as VQ and PCA.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 추계학술발표회 논문집
• /
• pp.281-286
• /
• 2003

Since National Geographic Information System was started, paper maps have been made with computer aided editing of digital map, instead of etching map-size negative film. Automated paper mapping system's necessity is growing more and more, because digital map has changed into Ver.2.0 which include attributes of feature. Therefore, in this study we try to analyze correlation of the digital map feature code and the 1/5,000 topographic map specifications which is necessary for paper mapping automatization using digital map Ver.2.0, and try to develop fundamental modules which will play a core role in automated paper mapping system.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 춘계학술발표회논문집
• /
• pp.321-328
• /
• 2004

Since National Geographic Information System was started, topographic maps have been made with computer aided editing of digital map, instead of etching map-size negative film. topographic mapping system's necessity is growing more and more, because digital map has changed into Ver.2.0 which include attributes of feature. On the basis of the previous study for analyzing correlation between the digital map feature code and the 1/5,000 topographic map specifications and trying to develop fundamental modules which will play a core role in topographic mapping system, in this study, we apply some 1/5,000 digital maps Ver.2.0 to topographic mapping system have implemented and try to analyze the result.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권1호
• /
• pp.168-182
• /
• 2020

Spoofing attacks, especially replay attacks, pose great security challenges to automatic speaker verification (ASV) systems. Current works on replay attacks detection primarily focused on either developing new features or improving classifier performance, ignoring the effects of feature variability, e.g., the channel variability. In this paper, we first establish a mathematical model for replay speech and introduce a method for eliminating the negative interference of the channel. Then a novel feature is proposed to detect the replay attacks. To further boost the detection performance, four post-processing methods using normalization techniques are investigated. We evaluate our proposed method on the ASVspoof 2017 dataset. The experimental results show that our approach outperforms the competing methods in terms of detection accuracy. More interestingly, we find that the proposed normalization strategy could also improve the performance of the existing algorithms.

• 한국정밀공학회지
• /
• 제28권5호
• /
• pp.578-584
• /
• 2011

In mechanical cutting process, burr was generated at workpiece by cutting tool generally. It is working disturbance during manufacturing process. Besides burr was taken shape relatively large size more micro scale machining than macro scale machining. Many researches have been studied to remove micro burr(de-burring), because it was negative effect for accuracy of machining shape. However, micro de-burring was constrained by burr height, micro feature and so on. In this paper, experimental research was carried out to compare de-burring characteristics of $Al_2O_3$ abrasive and polymer.

• ETRI Journal
• /
• 제33권2호
• /
• pp.240-250
• /
• 2011

To enable a relevance feedback paradigm to evolve itself by users' feedback, a reinforcement learning method is proposed. The feature space of the medical images is partitioned into positive and negative hypercubes by the system. Each hypercube constitutes an individual in a genetic algorithm infrastructure. The rules take recombination and mutation operators to make new rules for better exploring the feature space. The effectiveness of the rules is checked by a scoring method by which the ineffective rules will be omitted gradually and the effective ones survive. Our experiments on a set of 10,004 images from the IRMA database show that the proposed approach can better describe the semantic content of images for image retrieval with respect to other existing approaches in the literature.

• Journal of information and communication convergence engineering
• /
• 제21권4호
• /
• pp.294-299
• /
• 2023

Micro ribonucleic acids (miRNAs) can regulate the protein expression levels of genes in the human body and have recently been reported to be closely related to the cause of disease. Determining the genes related to miRNAs will aid in understanding the mechanisms underlying complex miRNAs. However, the identification of miRNA-related genes through wet experiments (in vivo, traditional methods are time- and cost-consuming). To overcome these problems, recent studies have investigated the prediction of miRNA relevance using deep learning models. This study presents a method for predicting the relationships between miRNAs and genes. First, we reconstruct a negative dataset using the proposed method. We then extracted the feature using an autoencoder, after which the feature vector was concatenated with the original data. Thereafter, the concatenated data were used to train a long short-term memory model. Our model exhibited an area under the curve of 0.9609, outperforming previously reported models trained using the same dataset.

• 대한전자공학회논문지SP
• /
• 제37권6호
• /
• pp.25-37
• /
• 2000

특징점의 궤적은 인접한 프레임에 존재하는 특정점 사이의 대응관계로 정의할 수 있다. 실제 영상열에서 존재할 수 있는 잘못된 특징점(false positive, false negative)들은 특징점의 대응관계를 결정할 때 많은 문제를 야기하기 때문에 특징점의 대응관계를 찾는 문제는 어려운 문제로 알려져 있다. 본 논문에서는 새로운 궤적의 나타남, 사라짐 등 불완전한 궤적을 갖는 특징점들을 고려하는 특징점 추적기법을 제안한다. 정합 척도로서 가중치가 부여된 유클리디언 거리를 사용하고 특징점의 운동특성을 잘 반영할 수 있도록 그 가중치를 자동으로 조정한다. 대응점 탐색과정에서 치명적인 영향을 줄 수 있는 애매한 특징점이 존재하는 경우를 고려하여 인접한 프레임 사이의 정합점 결정을 그래프에 의한 최적 대응점 탐색문제로 해결한다. 제안하는 대응점 탐색 알고리즘은 실제 영상열에서 나타날 수 있는 잘못된 특징점들이 대응관계를 결정할 때 주는 영향을 최소화하기 위하여 국부 최적(local optimal)을 찾게되며, 인접한 두 프레임에 m, n개의 특징점이 주어졌을 경우, 최선의 경우 O(mn), 최악의 경우 O($m^2n$)의 계산량을 필요로 한다. 제안하는 알고리즘은 정합과정에서 잘못된 특징점을 고려하고, 특징점의 운동특성을 잘 반영함으로써 대량의 특징점을 추적하는데도 충분히 적용할 수 있음을 실험을 통해 확인하였다.

• 한국컴퓨터정보학회논문지
• /
• 제17권9호
• /
• pp.39-47
• /
• 2012

일반적으로 사람들은 특정 상품에 관한 의견을 표현할 때 그 상품이 갖는 개별속성에 대해 긍부정 성향을 표시한다. 어떤 경우에는 상품이 갖는 동질의 개별 속성에 대해 포괄적으로 긍부정 성향을 표현하거나 상품 자체에 대해 표현하기도 한다. 따라서 의견검색 분야에서 추출 대상이 되는 의견 속성명에는 상품의 개별 속성명, 이 개별 속성들을 포함하는 전체어, 그리고 상품명이 존재한다. 그러나 의견 대상을 상품명이나 전체어로 표현할 때, 경우에 따라 의견문장 표면에 나타나는 속성명과 의견 작성자가 의도한 실제 대상이 일치하지 않을 수도 있다. 본 논문에서는 의견문장으로부터 의견 대상을 추출하는 방법을 제시한다. 무엇보다 우리는 의도한 대상과 일치하지 않는 속성명으로부터 의도한 대상을 추출하기 위한 새로운 방법을 제안한다. 제시하는 방법에서는 단어간 의존관계를 이용하여 의견속성 후보쌍을 추출하고, 추출된 후보쌍들 중 의견 대상과 일반적으로 빈번히 불일치하는 속성명을 선택한다. 선택된 속성명을 작성자가 의도한 개별속성으로 변경한 뒤, 이를 포함한 전체 의견속성 후보쌍들로부터 적합한 의견속성을 추출하기 위해 사람들이 관심 있어할만한 순으로 재배열하게 된다.

• 한국생활과학회지
• /
• 제8권2호
• /
• pp.255-273
• /
• 1999

The purpose of this study was to examine the relationship between characteristics of personality and respondent characteristics of Kinetic Family Drawing for young children. The subjects were 170 children(110 boys and 60 girls). The personal interview contained Personality Characteristic Test for young children(In-Sub Song, 1993) and Kinetic Family Drawing Test(Burns and Kaufman, 1982). Results of the test were analyzed by t-test and ANOVA by SAS program. Results are followings. First, chileren's sex and the general tendency of personal characteristic showed significant difference in the emotional personality among 4 personality characteristics. Girls show more positive tendency than boys in moral, physical, appearance and feature which expressed personal feeling and emotion. Also, girls showed more positive tendency than boys in personal characteristic which showed physical ability. Second, Children's sex and individual characteristic in Kinetic Family Drawing respondent characteristic showed significant difference in own's arm length. Also, Using a rare of paper and chapter 1 of the power among the family showed significant difference in styles and symbols. The boys drew lengther arms compared with their height than the girls. The girls were less complicative, anxious, comparative and aggressive for their family. Third, As a result of the study about the relationship between 4 personal characteristics of children and individual's behavior in Kinetic Family Drawing respondent characteristic, the significant difference is showed in academic personality and social personality had higher completion of their father's feature and drew bigger feet. In socal personality, negative behavior than positive children. Fourth, As a result of the study about the relationship between 4 personal characteristics of children and individual's characteristic, the significant difference were found in academic personality, social personality, family personality and emotional personality. Children with negative academic personality drew longer arms than children with positive academic personality, social personality and family personality. Also, Children with negative emotional personality drew more siblings than children with positive emotional personality. Fifth, The academic personality and the social personality had significant difference in the relationship between 4 personal characteristics of children and dynamics. In social personality, normal children were more tendencious to look at the important person with their mother's direction than positive children. Sixth, In terms of the relationship between 4 personal characteristics of children and mode, academic personality and family personality showed significant difference. Children with negative academic personality used more edge of papers than children with positive academic personality and children with positive academic personality and children with negative family personality fold more papers than children with positive family personality. At last, there were no significant difference between 4 personal characteristics of children and styles as well as symbols.