• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.1
• /
• pp.46-53
• /
• 2001

The purpose of this paper is to develop a new feature selection method for AE signal classification. The neural network of back propagation algorithm is used. The proposed feature selection method uses the difference between feature coordinates in feature space. This method is compared with the existing methods such as Fisher's criterion, class mean scatter criterion and eigenvector analysis in terms of the recognition rate and the convergence speed, using the signals from the defects in welding zone of austenitic stainless steel and in the metal contact of the rotary compressor. The proposed feature selection methods such as 2-D and 3-D criteria showed better results in the recognition rate than the existing ones.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.165-172
• /
• 2010

In clinical data minig, choosing the optimal subset of features is such important, not only to reduce the computational complexity but also to improve the usefulness of the model constructed from the given data. Moreover the threshold values (i.e., cut-off points) of selected features are used in a clinical decision criteria of experts for differential diagnosis of diseases. In this paper, we propose a fuzzy discretization approach, which is evaluated by measuring the degree of separation of redundant attribute values in overlapping region, based on spatial distribution of data with continuous attributes. The weighted average of the redundant attribute values is then used to determine the threshold value for each feature and rough set theory is utilized to select a subset of relevant features from the overall features. To verify the validity of the proposed method, we compared experimental results, which applied to classification problem using 668 patients with a chief complaint of dyspnea, based on three discretization methods (i.e., equal-width, equal-frequency, and entropy-based) and proposed discretization method. From the experimental results, we confirm that the discretization methods with fuzzy partition give better results in two evaluation measures, average classification accuracy and G-mean, than those with hard partition.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.13-16
• /
• 2008

본 논문은 가중퍼지소속함수 기반신경망(neural network with weighted fuzzy membership functions, NEWFM)기반의 자동 특징 추출기법을 사용하여 인체의 세 방향에서 발생하는 가속도 값으로부터 낙상을 탐지하는 방안을 제시하고 있다. 10명의 피검자로부터 8가지 시나리오로 낙상/비낙상 데이터 800개를 수집하고 웨이블릿 변환(wavelet transform, WT)을 통해 추출한 계수중 비중복면적 분산법에 의해 중요도가 가장 낮은 특징입력을 하나씩 제거하면서 최소의 특징 입력을 선택하였다. 특징입력으로는 가속도 값을 웨이블릿 변환한 11개의 d4계수들 중 비중복면적 분산법에 의해서 중요도가 가장 높은 5개의 계수가 사용되었고, 이들 특징입력을 통해 93%의 전체 분류율을 나타내었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.496-498
• /
• 2000

동영상 비디오 시퀸스에서 필요로 하는 장면을 빠르고 쉽게 찾을 수 있도록 해주는 내용 기반 검색에 대한 연구가 활발히 이루어져 오고 있다. 특히, 내용 기반 검색 시스템의 기초 기술인 비디오 데이터의 샷(shot)에 따른 분할 연구는 다양한 방법으로 소개되었으나 정확도가 높은 분할 알고리즘이 아직 개발되지 않고 있는 실정이다. 본 논문에서는 비압축 비디오에서 컷(cut) 검출의 효율성을 향상시키기 위해 기존의 히스토그램 비교법과 시공간 영상을 활용하는 계층적인(hierarchical) 방법을 제안한다. 이를 위해 먼저 동영상의 각 프레임에서 한 행(row)씩 추출하여 동영상 전체를 대표하도록 시공간 영상을 생성하고, 생성된 시공간 영상에서 수평 에지(edge)를 이용한 프레임(frame) 특징값으로 장면 전화의 후보 영역을 선택하였다. 그리고 선택된 후보 영역을 히스토그램 비교법으로 분석하게 된다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.107-114
• /
• 2022

In this paper, we have enhanced the risk prediction of hypertension using the feature selection method in the Korean National Health and Nutrition Examination Survey (KNHANES) database of the Korea Centers for Disease Control and Prevention. The study identified various risk factors correlated with chronic hypertension. The paper is divided into three parts. Initially, the data preprocessing step of removes missing values, and performed z-transformation. The following is the feature selection (FS) step that used a factor analysis (FA) based on the feature selection method in the dataset, and feature importance (FI) and multicollinearity analysis (MC) were compared based on FS. Finally, in the predictive analysis stage, it was applied to detect and predict the risk of hypertension. In this study, we compare the accuracy, f-score, area under the ROC curve (AUC), and mean standard error (MSE) for each model of classification. As a result of the test, the proposed MC-FA-RF model achieved the highest accuracy of 80.12%, MSE of 0.106, f-score of 83.49%, and AUC of 85.96%, respectively. These results demonstrate that the proposed MC-FA-RF method for hypertension risk predictions is outperformed other methods.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.137-140
• /
• 2002

본 연구에서는 할선법에 기초한 고정점 알고리즘의 독립성분분석기법을 이용한 영상의 특징추출을 제안하였다. 여기서 할선법은 엔트로피 최적화를 위한 목적함수의 근을 구하기 위해 단순히 함수 값만을 이용하여 계산을 간략하게 함으로써 역혼합행렬의 경신속도를 빠르게 하기 위함이다. 제안된 기법을 256×256 픽셀(pixel)의 10개 지문영상들로부터 선택된 16×16 픽셀의 20,000개 패치를 대상으로 시뮬레이션 한 결과. 추출된 16×16 픽셀의 160개 독립성분 기저벡터 각각은 지문영상들에 포함된 공간적인 주파수 특성과 방향성을 가지는 경계 특성이 잘 드러나는 국부적인 특징들임을 확인할 수 있었다.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.397-402
• /
• 2019

Accurately predicting cancer prognosis to provide appropriate treatment strategies for patients is one of the critical challenges in bioinformatics. Many researches have suggested machine learning models to predict patients' outcomes based on their gene expression data. Gene expression data is high-dimensional numerical data containing about 17,000 genes, so traditional researches used feature selection or dimensionality reduction approaches to elevate the performance of prognostic prediction models. These approaches, however, have an issue of making it difficult for the predictive models to grasp any biological interaction between the selected genes because feature selection and model training stages are performed independently. In this paper, we propose a novel two-dimensional image formatting approach for gene expression data to achieve feature selection and prognostic prediction effectively. Node2Vec is exploited to integrate biological interaction network and gene expression data and a convolutional neural network learns the integrated two-dimensional gene expression image data and predicts cancer prognosis. We evaluated our proposed model through double cross-validation and confirmed superior prognostic prediction accuracy to traditional machine learning models based on raw gene expression data. As our proposed approach is able to improve prediction models without loss of information caused by feature selection steps, we expect this will contribute to development of personalized medicine.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.347-350
• /
• 2003

표면정보 기반 영상정합기법은 대상기관에서 추출된 표면정보를 기반으로 변환을 추정하여 서로 다른 영상의 전체적 형태의 유사성 정도를 최대화함으로써 정합을 수행하는 방법이다. 정합 수행에 있어 전체 객체를 가장 잘 대표하는 특정 개수의 표면점을 추출하고, 이 대표점으로부터 변환 값을 계산하는 것이 영상정합의 합리적인 최적화 단계를 위해 필수적이다. 대표점 추출결과에 따라 전체 정합의 결과가 달라지게 되므로 정합의 변환요소 값을 정확하게 구해낼 수 있는 대표점을 추출하기 위해 적절한 샘플링 기법의 선택이 요구된다. 본 연구에서는 효율적인 표면정보 기반 다중 모달리티 영상정합을 위해 계통추출법 기반 샘플링 기법과 특징점 탐지 기법 기반 샘플링 기법의 성능을 비교 분석하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.6
• /
• pp.319-324
• /
• 2008

In this paper, we propose a novel approach to improve the performance of speech/music classification for the selectable mode vocoder (SMV) of 3GPP2 using the discriminative weight training which is based on the minimum classification error (MCE) algorithm. We first present an effective analysis of the features and the classification method adopted in the conventional SMV. And then proposed the speech/music decision rule is expressed as the geometric mean of optimally weighted features which are selected from the SMV. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme of the SMV.

• Explosives and Blasting
• /
• v.35 no.1
• /
• pp.27-33
• /
• 2017

In this study, two fracture toughness test procedures are modelled for selected metal and rock on LS-DYNA, which is a commercial finite element code. The tests are conducted by using the 3-point bend test procedure for rectangular bar specimen. Because it takes a relatively long time to conduct the test, the implicit solver based on the Newmark method is adopted for the analyses. The values of stress intensity factor obtained from the analyses are 73 and $0.3MPa.m^{0.5}$ for the metal and rock material, respectively. It can be thought that the resulting small value of the fracture toughness of the rock material model well represents the brittleness of rock material.