• 한국지능시스템학회논문지
• /
• 제14권7호
• /
• pp.830-837
• /
• 2004

본 논문에서는 비선형시스템에서 발생한 고장을 감지하고 분류하기 위한 신경회로망기반 고장진단 방법을 제안한다. 제안한 알고리듬에서는 시스템의 출력과 다층신경회로망 공칭모델 출력 사이의 오차가 미리 설정한 문턱값을 넘으면 고장을 감지한다. 고장이 감지되면 다층신경회로망과 ART2 신경회로망을 이용한 고장분류기에서 시스템에서 발생한 고장을 분류한다. 컴퓨터 시뮬레이션 결과로부터 제안한 고장진단방법이 비선형시스템에서의 고장감지 및 분류문제에 잘 적용됨을 알 수 있다.

• 한국지능시스템학회논문지
• /
• 제19권5호
• /
• pp.706-712
• /
• 2009

본 논문에서는 프레스공정라인에서 발생하는 고장을 감지하고 분류하기 위한 고장진단기법을 제안한다. 또한 윤활유 레벨을 자동감지 하기 위한 방법도 제안하다. 제안한 방법에서는 FFT 주파수해석과 여러 경계인수를 갖는 ART2 신경회로망을 사용하며, LabVIEW를 이용하여 고장진단 및 윤활유 레벨 자동감시를 위한 GUI(Graphical User Interface) 프로그램을 제작하여 고장진단을 수행하였다. 실험결과들로부터 제안한 유도전동기 고장진단 및 윤활유 레벨 자동감시시스템의 성능을 확인하였다.

• Journal of Information Processing Systems
• /
• 제14권2호
• /
• pp.418-434
• /
• 2018

With the increasing use of the Internet and electronic documents, automatic text categorization becomes imperative. Several machine learning algorithms have been proposed for text categorization. The k-nearest neighbor algorithm (kNN) is known to be one of the best state of the art classifiers when used for text categorization. However, kNN suffers from limitations such as high computation when classifying new instances. Instance selection techniques have emerged as highly competitive methods to improve kNN through data reduction. However previous works have evaluated those approaches only on structured datasets. In addition, their performance has not been examined over the text categorization domain where the dimensionality and size of the dataset is very high. Motivated by these observations, this paper investigates and analyzes the impact of instance selection on kNN-based text categorization in terms of various aspects such as classification accuracy, classification efficiency, and data reduction.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1727-1731
• /
• 2004

We propose an ART2 neural network-based fault diagnosis method to diagnose of sensor in the gas monitoring system. In the proposed method, using thermal modulation of operating temperature of sensor, the signal patterns are extracted from the voltage of load resistance. Also, fault classifier by ART2 NN (adaptive resonance theory 2 neural network) with uneven vigilance parameters is used for fault isolation. The performances of the proposed fault diagnosis method are shown by simulation results using real data obtained from the gas monitoring system.

• 제어로봇시스템학회논문지
• /
• 제3권3호
• /
• pp.244-251
• /
• 1997

In this paper, we propose a fault diagnosis algorithm to detect and isolate multiple faults in a system. The proposed fault diagnosis algorithm is based on a multiple fault classifier which consists of two ART2 NN(adaptive resonance theory2 neural network) modules and the algorithm is composed of three main parts - parameter estimation, fault detection and isolation. When a change in the system occurs, estimated parameters go through a transition zone in which residuals between the system output and the estimated output cross the threshold, and in this zone, estimated parameters are transferred to the multiple faults classifier for fault isolation. From the computer simulation results, it is verified that when the proposed diagnosis algorithm is performed successfully, it detects and isolates faults in the position control system of a DC motor.

• International journal of advanced smart convergence
• /
• 제2권2호
• /
• pp.40-42
• /
• 2013

Recent medical industry is an aging society and the application of national health insurance, with state-of-the-art research and development, including the pharmaceutical market is greatly increased. The nation's health care industry through new support expansion and improve the quality of life for the research and development will be needed. In addition, systemic administration of basic medical supplies, or drugs are needed, the drug at the same time managing how systematic analysis of pharmaceutical ingredients, based on data through the purchase of new medicines and pharmaceutical ingredients automatically classified by analyzing the statistics of drug purchases and the future a system that can predict a patient is needed. In this study, the drugs to the patient according to the component analysis and predictions for future research techniques, k-means clustering and k-NN (Nearest Neighbor) Comparative studies through experiments using the techniques employ a more efficient method to study how to proceed. In this study, the effects of the drugs according to the respective components in time according to the number of pieces in accordance with the patient by analyzing the statistics by predicting future patient better medical industry can be built.

• 한국지능시스템학회논문지
• /
• 제15권6호
• /
• pp.673-681
• /
• 2005

원자력 발전소는 안정성 및 신뢰성 확보가 가장 중요하므로 고장의 감지 및 진단 시스템의 개발은 원전 자체가 구축하고 있: 다중의 하드웨어 중첩도(hardware redundancy)에도 불구하고 가장 중요한 문제로 취급되고 있다. 본 논문에서는 원저 PWR 증기발생기에서 발생한 고장을 진단하기 위한 알고리듬의 개발을 위해 시스템에서 발생한 고장을 감지하고 분류할 수 있는 ART2 시경회로망 기반 고장진단방법을 제안한다. 고장진단시스템은 발생한 고장을 감지하기 위한 고장감지부, 변화된 시스템파라미터를 추정하기 위한 파라미터 추정부 및 발생한 고장의 종류를 알아내기 위한 고장분류부로 구성된다. 고장분류부는 여러 경계인수를 갖는 ART2(adaptive resonance theory 2) 신경회로망을 이용한 고장분류기로 구성된다. 제안한 고장진단 알고리듬을 증기발생기의 고장진단문제에 적용하여 성능을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 V
• /
• pp.2775-2778
• /
• 2003

Neural network-based fault diagnosis algorithm to detect and isolate faults in the nonlinear systems is proposed. In the proposed method, the fault is detected when the errors between the system output and the neural network nominal system output cross a predetermined threshold. Once a fault in the system is detected, the system outputs are transferred to the fault classifier by ART2 NN (adaptive resonance theory 2 neural network) for fault isolation. From the computer simulation results, it is verified that the proposed fault diagonal method can be performed successfully to detect and isolate faults in a nonlinear system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.742-762
• /
• 2015

In this study, we propose a distance metric learning approach called discriminant metric learning (DML) for face verification, which addresses a binary-class problem for classifying whether or not two input images are of the same subject. The critical issue for solving this problem is determining the method to be used for measuring the distance between two images. Among various methods, the large margin nearest neighbor (LMNN) method is a state-of-the-art algorithm. However, to compensate the LMNN's entangled data distribution due to high levels of appearance variations in unconstrained environments, DML's goal is to penalize violations of the negative pair distance relationship, i.e., the images with different labels, while being integrated with LMNN to model the distance relation between positive pairs, i.e., the images with the same label. The likelihoods of the input images, estimated using DML and LMNN metrics, are then weighted and combined for further analysis. Additionally, rather than using the k-nearest neighbor (k-NN) classification mechanism, we propose a verification mechanism that measures the correlation of the class label distribution of neighbors to reduce the false negative rate of positive pairs. From the experimental results, we see that DML can modify the relation of negative pairs in the original LMNN space and compensate for LMNN's performance on faces with large variances, such as pose and expression.