• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.8
• /
• pp.1899-1907
• /
• 2013

This paper presents an efficient defect detection and classification system based on reference image for COF (Chip-on-Film) which encounters fatal defects after ultra fine pattern fabrication. These defects include typical ones such as open, mouse bite (near open), hard short and soft short. In order to detect these defects, conventionally it needs visual examination or electric circuits. However, these methods requires huge amount of time and money. In this paper, based on reference image, the proposed system detects fatal defect and efficiently classifies it to one of 4 types. The proposed system includes the preprocessing of the test image, the extraction of ROI, the analysis of local binary pattern and classification. Through simulations with lots of sample images, it is shown that the proposed system is very efficient in reducing huge amount of time and money for detecting the defects of ultra fine pattern COF.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.3
• /
• pp.106-113
• /
• 2009

Various statistical classification methods have been used to establish prediction model of underground cultural assets in our country. Among them, linear discriminant analysis, logistic regression, decision tree, neural network, and support vector machines are used in this paper. We introduced the basic concepts of above-mentioned classification methods and applied these to the analyses of real data of I city. As a results, five different prediction models are suggested. And also model comparisons are executed by suggesting correct classification rates of the fitted models. To see the applicability of the suggested models for a new data set, simulations are carried out. R packages and programs are used in real data analyses and simulations. Especially, the detailed executing processes by R are provided for the other analyser of related area.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.117-123
• /
• 2023

To detect advanced ransomware attacks with machine learning-based models, the classification model must train learning data with high-dimensional feature space. And in this case, a 'curse of dimension' phenomenon is likely to occur. Therefore, dimensionality reduction of features must be preceded in order to increase the accuracy of the learning model and improve the execution speed while avoiding the 'curse of dimension' phenomenon. In this paper, we conducted classification of ransomware by applying three machine learning models and two feature extraction techniques to two datasets with extremely different dimensions of feature space. As a result of the experiment, the feature dimensionality reduction techniques did not significantly affect the performance improvement in binary classification, and it was the same even when the dimension of featurespace was small in multi-class clasification. However, when the dataset had high-dimensional feature space, LDA(Linear Discriminant Analysis) showed quite excellent performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.8C
• /
• pp.1159-1174
• /
• 2004

In this paper, we present an efficient algorithm for region analysis of business card images acquired in a PDA by using DCT and information pixel density. The proposed method consists of three parts: region segmentation, information region classification, and text region classification. In the region segmentation, an input business card image is partitioned into 8 f8 blocks and the blocks are classified into information and background blocks using the normalized DCT energy in their low frequency bands. The input image is then segmented into information and background regions by region labeling on the classified blocks. In the information region classification, each information region is classified into picture region or text region by using a ratio of the DCT energy of horizontal and vertical edge components to that in low frequency band and a density of information pixels, that are black pixels in its binarized region. In the text region classification, each text region is classified into large character region or small character region by using the density of information pixels and an averaged horizontal and vertical run-lengths of information pixels. Experimental results show that the proposed method yields good performance of region segmentation, information region classification, and text region classification for test images of several types of business cards acquired by a PDA under various surrounding conditions. In addition, the error rates of the proposed region segmentation are about 2.2-10.1% lower than those of the conventional region segmentation methods. It is also shown that the error rates of the proposed information region classification is about 1.7% lower than that of the conventional information region classification method.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.184-192
• /
• 2022

Valve internal leakage is caused by damage to the internal parts of the valve, resulting in accidents and shutdowns of the piping system. This study investigated the possibility of a real-time leak detection method using the acoustic emission (AE) signal generated from the piping system during the internal leakage of a butterfly valve. Datasets of raw time-domain AE signals were collected and postprocessed for each operation mode of the valve in a systematic manner to develop a data-driven model for the detection and classification of internal leakage, by applying machine learning algorithms. The aim of this study was to determine whether it is possible to treat leak detection as a classification problem by applying two classification algorithms: support vector machine (SVM) and convolutional neural network (CNN). The results showed different performances for the algorithms and datasets used. The SVM-based binary classification models, based on feature extraction of data, achieved an overall accuracy of 83% to 90%, while in the case of a multiple classification model, the accuracy was reduced to 66%. By contrast, the CNN-based classification model achieved an accuracy of 99.85%, which is superior to those of any other models based on the SVM algorithm. The results revealed that the SVM classification model requires effective feature extraction of the AE signals to improve the accuracy of multi-class classification. Moreover, the CNN-based classification can be a promising approach to detect both leakage and valve opening as long as the performance of the processor does not degrade.

• Spatial Information Research
• /
• v.21 no.1
• /
• pp.63-73
• /
• 2013

Geographic features are reflected in satellite images, which contain characteristic elements. Information on changes can be obtained through a comparison of images taken at different times. If multi-temporal images can be classified through the use of an unsupervised method, this is likely to improve the accuracy of image classification and contribute to various applications. A rule-based image classification algorithm for automatic processing without human involvement has been developed, but it must be verified that its results are not affected by imperfect elements. In this study, Landsat images of Jeju Island were used to carry out a rule-based image classification. The application results were examined for complex cases, including the presence of clouds in the images, different photographed times, and the type of target area, such as city, mountain, or field. The presence of clouds did not affect calculations, and appropriate classification rules were applied, depending on the different photographed times. The expansion of the urban areas of Jeju and the increase of facilities such as vinyl greenhouses in Seoguipo were identified. Furthermore, space information changes and accurate classifications for Jeju Island were obtained. With the goal of performing high-quality unsupervised classifications, measures to generalize and improve the methods employed were searched for. The findings of this study could be used in time-series analyses of images for various applications, including urban development and environmental change monitoring.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.9C
• /
• pp.817-824
• /
• 2006

The crest factor properties of 16-QAM modulated one- and two-code assisted multi-carrier code-division multiple-access (MC-CDMA) signals employing complementary pair as spreading sequences are characterized. It is shown that a set of relationship between the two 16-QAM symbols entirely characterize the power envelope waveforms of the signals. There exists 60 different sets of relationship, which results in 16 different crest factors as a result of various equivalent transforms on the corresponding message symbols. It is also shown that the individual crest factor corresponding to each message combination is always bounded by 3dB.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.11
• /
• pp.2486-2491
• /
• 2013

There are invisible defects by naked eyes in ceramic material images such as internal stomata, cracks and foreign substances. In this paper we propose a method to detect and extract such defects from ceramic pipe weld zone by applying ART2 learning. In pre-processing, we apply Ends-in Search Stretching to enhance the intensity and then perform fuzzy binarization with triangle type membership function followed by enhanced ART2 that interacts with random input patterns to extract such invisible defects. The experiment verifies that this proposed method is sufficiently effective.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.419-423
• /
• 2008

사람의 손동작은 오랫동안 하나의 언어역할을 하는 통신 수단으로 사용되어 왔다. 이러한 손동작 중에서 가장 체계를 갖춘 수화는 청각장애인이 일반인과 일상 대화를 할 수 있도록 도와주는 주요한 통신 수단이다. 하지만 건청인들의 대부분이 습득하고 있지 않아 청각장애인들과 의사소통이 거의 불가능 한 것이 현실이다. 따라서 본 논문에서는 건청인과 청각장애인들 간의 의사소통을 원활하게 하기 위해 색상 정보와 퍼지 클러스터링 알고리즘을 이용한 실시간 수화 인식 방법을 제안한다. 제안된 방법은 화상 카메라를 통해 얻어진 실시간 영상에서 YCbCr 컬러 공간에서 색차 정보에 해당하는 Cb, Cr 정보를 각각 추출한 후, 이진화한 영상과 원본 영상에서 마스크를 통한 에지를 추출한 이진화 영상에 대해 논리연산을 통해 두 손의 위치와 외곽을 추출한다. 추출된 각 정보를 조합하여 8 방향 윤곽선 추적 알고리즘을 적용하여 객체의 위치를 추적한다. 그리고 추적한 객체의 영역에 대해 형태학적 정보를 이용하여 잡음을 제거한 후, 최종적으로 두 손의 영역을 추출한다. 추출된 손의 영역은 퍼지 클러스터링 기법 중의 FCM 알고리즘을 적용하여 수화의 특징들을 분류하고 인식한다. 제안된 방법의 성능을 평가하기 위해 화상카메라를 통해 얻어진 실시간 영상을 대상으로 실험한 결과, 제안된 방법이 두 손 영역의 추출에 효과적이고 수화 인식에 있어서 가능성을 확인하였다.

• Proceedings of the KAIS Fall Conference
• /
• 2011.05b
• /
• pp.926-929
• /
• 2011

이 연구는 음주 관련 요인을 일반적 특성과 사회-경제적, 건강행태 측면에서 규명하기 위하여 일개 광역시에 거주하는 만 19세 이상 남녀를 대상으로 한국 갤럽의 표준조사로 2007년 7월 30일부터 2달간 시행하였고, 전화 설문조사에 참여한 총 1,013명을 대상으로 일반적 사항, 건강 행태관련 설문지를 이용하여 관련 요인들을 추출하였고, 음주도를 산출하였다. 연구대상자의 지난 1년간 음주여부를 결과 변수로 하는 로지스틱 회귀분석 결과 연령에 따른 분류에서 19-29세와 30-39세에서 음주에 유의하게 영향을 미치는 것으로 나타났고, 가계수입에 따른 분류에서는 300~499만원과 500만원 이상에서 음주에 유의하게 영향을 미치는 것으로 나타났으며, 변수별 95% 신뢰구간에서는 유의하게 영향을 미치지 않는 것으로 나타났다. 연구대상자의 지난 한 달간 음주여부를 결과변수로 하는 로지스틱 회귀분석 결과 성별에 따른 분류에서 여성의 경우 음주에 유의하게 영향을 미치는 것으로 나타났고, 연령에 따른 분류에서 19-29세와 40-49세에서 음주에 유의하게 영향을 미치는 것으로 나타났으며, 가계수입에 따른 분류에서는 300~499만원과 500만원 이상이 음주에 유의하게 영향을 미치는 것으로 나타났고, 흡연에 따른 분류에서 현재 흡연의 경우 음주에 유의하게 영향을 미치는 것으로 나타났고, 스트레스 여부에 따른 분류에서 대단히 많이 느낌과, 조금 느끼는 편임의 경우 음주에 유의하게 영향을 미치는 것으로 나타났으며, 다른 변수들의 경우 95% 신뢰구간에서는 유의하게 영향을 미치지 않는 것으로 나타났다. 연구대상자의 주2회 이상 음주여부를 결과변수로 하는 로지스틱 회귀분석 결과 성별에 따른 분류에서 여성의 경우 음주에 유의하게 영향을 미치는 것으로 나타났고, 직업에서 가정주부, 학생의 경우 음주에 유의하게 영향을 미치는 것으로 나타났고, 흡연에서 현재 흡연과 과거 흡연에서 음주에 유의하게 영향을 미치는 것으로 나타났으며, 다른 변수들의 경우 95% 신뢰구간에서는 유의하게 영향을 미치지 않는 것으로 나타났다. 이상의 연구 결과를 종합해 볼 때, 직업분류에서 가정주부와 학생의 경우 음주에 유의하게 영향을 미치는 것으로 판단된다. 적정 섭취 알코올 기준이 남, 여가 다르게 제시되고 있기 때문에 성별에 따른 비교분석자료를 통하여 남, 여 적정 음주 기준에 따른 일반적 특성과 사회적 특성 및 건강행태와의 관련성에 대한 후속 연구가 필요하다고 생각된다.