• 전기학회논문지
• /
• 제67권8호
• /
• pp.1071-1079
• /
• 2018

In this study, the design methodology as well as network architecture of Support Vector Machine based Polynomial Neural Network, which is a kind of the dynamically generated neural networks, is introduced. The Support Vector Machine based polynomial neural networks is given as a novel network architecture redesigned with the aid of polynomial neural networks and Support Vector Machine. The generic polynomial neural networks, whose nodes are made of polynomials, are dynamically generated in each layer-wise. The individual nodes of the support vector machine based polynomial neural networks is constructed as a support vector machine, and the nodes as well as layers of the support vector machine based polynomial neural networks are dynamically generated as like the generation process of the generic polynomial neural networks. Support vector machine is well known as a sort of robust pattern classifiers. In addition, in order to enhance the structural flexibility as well as the classification performance of the proposed classifier, multi-objective particle swarm optimization is used. In other words, the optimization algorithm leads to sequentially successive generation of each layer of support vector based polynomial neural networks. The bench mark data sets are used to demonstrate the pattern classification performance of the proposed classifiers through the comparison of the generalization ability of the proposed classifier with some already studied classifiers.

• 한국정보통신학회논문지
• /
• 제12권7호
• /
• pp.1243-1248
• /
• 2008

최근 생명 정보학 기술의 발달로 마이크로 단위의 실험조작이 가능해짐에 따라 하나의 chip상에서 전체 genome의 expression pattern을 관찰할 수 있게 되었고, 동시에 수 만개의 유전자들 간치 상호작용도 연구 가능하게 되었다. 본 논문에서는 암에 걸린 흰쥐 외피 기간 세포 분화 실험에서 얻어진 3840 유전자의 마이크로어레이 cDNA를 이용해 데이터의 정규화를 거쳐 본 논문에서 제안한 유사성 척도 조합 방법으로 정보력 있는 유전자들을 추출한 후, 유사성 척도 조합 방법과 결합한 멀티퍼셉트론 신경망 분류기와 기존의 DT, NB, SVM 분류기를 이용하여 클래스 분류 시스템을 구축하고, 성능을 비교분석하였다. 피어슨 적률 상관 계수와 유클리디안 거리 계수 조합을 이용하여 선택된 200 유전사들을 멀티퍼셉트론 신경망 분류기로 분류한 결과 98.84%의 정확도를 보여 다른 분류기를 이용하여 실험을 수행한 경우보다 향상된 분류 성능을 보였다.

• 정보보호학회논문지
• /
• 제25권5호
• /
• pp.1001-1009
• /
• 2015

스마트 그리드 안에서 고안된 스마트 미터는 우리가 사용하는 전력 신호를 실시간으로 데이터화해서 전력 공급단의 메인 서버로 전송한다. 이를 통해 전력 관리의 효율성은 증가한 반면, 사용자의 정보를 담은 데이터의 보안 문제가 새로운 위협으로 부상하였다. 본 논문은 스마트 미터에서 추출한 전력 데이터를 통해 가정 내 기기의 식별 및 기기별 사용패턴에 대한 추론을 보안 관점에서 해석함으로써 스마트 기기 환경에서 데이터 노출의 위협을 지적한다. 주성분분석(Principal Component Analysis)으로 데이터의 특징을 추출하였고 k-근접 이웃(k- Nearest Neighbor)분류기로 기기를 식별하고 기기상태를 추론하였으며, 검증방법으로는 10차 교차검증(10-fold Cross Validation)을 활용하였다.

• 대한원격탐사학회지
• /
• 제30권4호
• /
• pp.537-546
• /
• 2014

본 논문은 비 접근 지역에 존재하는 관심물체의 위치를 고해상도 광학 위성영상을 이용하여 찾아내기 위한 방법을 제안한다. 관심물체는 정확하게 규정된 크기와 모양을 갖는 것이 아니라, 개념적으로 유사한 패턴을 가진 물체들의 집합이다. 본 논문에서는 유사 객체 검색에서 Histogram of Gradients (HOG) feature를 이용하여 입력 영상의 관심물체의 특징을 추출하고, 추출된 특징 데이터를 이용하여 다른 영상들의 관심물체를 탐색하는 Support Vector Machine (SVM) 학습 및 분류기를 개발하였다. 제안한 방법은 관심물체를 자동으로 찾아줌으로써, 넓은 영역에서 수동으로 관심물체를 탐색하는데 소요되는 시간과 노력을 줄일 수 있는 효과가 있음을 확인하였다.

• 전기학회논문지
• /
• 제64권9호
• /
• pp.1347-1355
• /
• 2015

In this study, we compare the recognition performance using PCA and RBFNNs for introducing robust face recognition system to pose variations based on pose estimation. proposed face recognition system uses Honda/UCSD database for comparing recognition performance. Honda/UCSD database consists of 20 people, with 5 poses per person for a total of 500 face images. Extracted image consists of 5 poses using Multiple-Space PCA and each pose is performed by using (2D)²PCA for performing pose classification. Linear polynomial function is used as connection weight of RBFNNs Pattern Classifier and parameter coefficient is set by using Particle Swarm Optimization for model optimization. Proposed (2D)²PCA-based face pose classification performs recognition performance with PCA, (2D)²PCA and RBFNNs.

• 센서학회지
• /
• 제13권6호
• /
• pp.436-445
• /
• 2004

In this study, a uroflowmetry system was developed to detect a voiding symptom conveniently at home or hospital. A implemented hardware was composed of mechanism and system circuit part, the software was developed to process uroflow data, graph display, extraction of parameter, and evaluation of congregate rate so as to analysis obtaining uroflow data. The following experiment was performed to evaluate an ability of classification and fitness. The curve pattern of uroflow was classified into each symptom. Various parameters were calculated in the curve pattern of each uroflow as follows. The parameters are MFR, AFR, VOL, VT, and FT. A significant difference among parameters was examined by a statistical analysis for extracted parameters between normal and abnormal experimental group. The uroflow data with the various symptom was divided into normal and abnormal group using fuzzy classifier. The result of the fuzzy classification using MFR and AFR was superior by 91.23 % than grouping evaluation including VOL.

• 대한안전경영과학회지
• /
• 제11권1호
• /
• pp.27-33
• /
• 2009

A study of fracture to material is getting interest in nuclear and aerospace industry as a viewpoint of safety. Acoustic emission (AE) is a non-destructive testing and new technology to evaluate safety on structures. In previous research continuously, all tensile tests on the pre-defected coupons were performed using the universal testing machine, which machine crosshead was move at a constant speed of 5mm/min. This study is to evaluate an AE source characterization of SM45C steel by using k-nearest neighbor classifier, k-NNC. For this, we used K-means clustering as an unsupervised learning method for obtained multi -variate AE main data sets, and we applied k-NNC as a supervised learning pattern recognition algorithm for obtained multi-variate AE working data sets. As a result, the criteria of Wilk's $\lambda$, D&B(Rij) & Tou are discussed.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.105-116
• /
• 2022

Stay cables play an essential role in cable-stayed bridges. Severe vibrations and/or harsh environment may result in cable failures. Therefore, an efficient structural health monitoring (SHM) solution for cable damage detection is necessary. This study proposes a data-driven method for immediately detecting cable damage from measured cable forces by recognizing pattern transition from the intact condition when damage occurs. In the proposed method, pattern recognition for cable damage detection is realized by time series classification (TSC) using a deep learning (DL) model, namely, the long short term memory fully convolutional network (LSTM-FCN). First, a TSC classifier is trained and validated using the cable forces (or cable force ratios) collected from intact stay cables, setting the segmented data series as input and the cable (or cable pair) ID as class labels. Subsequently, the classifier is tested using the data collected under possible damaged conditions. Finally, the cable or cable pair corresponding to the least classification accuracy is recommended as the most probable damaged cable or cable pair. A case study using measured cable forces from an in-service cable-stayed bridge shows that the cable with damage can be correctly identified using the proposed DL-TSC method. Compared with existing cable damage detection methods in the literature, the DL-TSC method requires minor data preprocessing and feature engineering and thus enables fast and convenient early detection in real applications.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 추계학술대회 논문집
• /
• pp.81-84
• /
• 2000

Rotating machine is used extensively and plays important roles in the industrial field. Therefore when rotating machine get out of order, it is necessary to know reasons then deal with the troubles immediately. So many studies far diagnosis of rotating machine are being done. However by this time most of study has an interest in gaining a high recognition But without considering error $rate^{(1)(2)(3)}$ , it is not desirable enough to apply h the actual application system. If the manager of system receives the result misjudging the condition of rotating machine and takes measures, we would lose heavily. So in order to play the creditable diagnosis, we must consider error rate. T h ~ t is. it must be able to reject the result of misjudgment. This study uses nearest neighbor classifier for diagnosis of rotating $machine^{(4)(8)}$ And the Smith's rejection $method^{(1)}$ used to recognize handwritten charter is done. Consequently creditable diagnosis of rotating machine is proposed.

• 전기학회논문지
• /
• 제64권1호
• /
• pp.99-106
• /
• 2015

In this study, we propose Radial basis function Neural Network(RBFNN) using Recursive Weighted Least Square Estimation(RWLSE) to effectively deal with big data class meteorological radar data. In the condition part of the RBFNN, Fuzzy C-Means(FCM) clustering is used to obtain fitness values taking into account characteristics of input data, and connection weights are defined as linear polynomial function in the conclusion part. The coefficients of the polynomial function are estimated by using RWLSE in order to cope with big data. As recursive learning technique, RWLSE which is based on WLSE is carried out to efficiently process big data. This study is experimented with both widely used some Machine Learning (ML) dataset and big data obtained from meteorological radar to evaluate the performance of the proposed classifier. The meteorological radar data as big data consists of precipitation echo and non-precipitation echo, and the proposed classifier is used to efficiently classify these echoes.