• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 The 6th International Symposium of East Asian Resources Recycling Technology
• /
• pp.759-764
• /
• 2001

The separation performance of zigzag air classifier with angle of 90 degrees was studied using narrow size fractions of thin square samples and granular samples. The simulation results of air velocity inside the classifier indicated that the zigzag geometry induces a new pattern consisting of an upward flow and a circulation flow, Experimental results showed that overflow product recovery was described as an integral calculus of normal distribution as a function of dimensionless air velocity ( $V_{A}$ $V_{A50}$), where $V_{A}$ is superficial air velocity and $V_{A50}$ is the $V_{A}$ at the fifty percent recovery. The $V_{A}$ values were predicted using the equations derived from dynamics for a particle dropping in air. A monitoring system that utilizes changes in acoustic signals emitted during the process of air classification was developed to separate PET with desired recovery or grade. The technical feasibility of the on-line monitoring of the PET recovery and grade was demonstrated by measuring relative energy of the signals.signals.als.

• 한국정밀공학회지
• /
• 제19권3호
• /
• pp.52-58
• /
• 2002

The purpose of condition monitoring and fault diagnosis is to detect faults occurring in machinery in order to improve the level of safety in plants and reduce operational and maintenance costs. The recognition performance is important not only to gain a high recognition rate bur a1so to minimize the diagnosis failures error rate by using off effective rejection module. We examined the problem of performance evaluation for the rejection scheme considering the accuracy of individual c1asses in order to increase the recognition performance. We use the Smith's method among the previous studies related to rejection method. Nearest neighbor classifier is used for classifying the machine conditions from the vibration signals. The experiment results for the performance evaluation of rejection show the modified optimum rejection method is superior to others.

• 한국지능시스템학회논문지
• /
• 제18권4호
• /
• pp.549-554
• /
• 2008

Support Vector Machine(SVM)은 통계적 학습 이론에 기반을 둔 분류기이다. 또한 Twin Support Vector Machine(TWSVM)은 이진 SVM 분류기의 한 종류로써, 서로 관련된 두 개의 SVM 유형 문제를 통해 평행하지 않은 두개의 평면을 결정하고 이 두 평면을 통해 분류기를 완성하는 방식이다. 이러한 방식의 TWSVM은 학습 시간이 SVM에 비해 훨씬 짧으며, SVM과 비교하여 떨어지지 않는 성능을 보여준다. 본 논문은 분류기 입력에 Fuzzy Membership을 적용하는 방식의 TWSVM을 제안하고, 전리층 레이더 데이터를 이용한 실험을 통하여 기존에 세시 되었던 분류기와 비교한다.

• ETRI Journal
• /
• 제32권3호
• /
• pp.395-405
• /
• 2010

A novel multiclassifier system (MCS) strategy is proposed and applied to a text-dependent speaker verification task. The presented scheme optimizes the linear combination of classifiers on an on-line basis. In contrast to ordinary MCS approaches, neither a priori distributions nor pre-tuned parameters are required. The idea is to improve the most accurate classifier by making use of the incremental information provided by the second classifier. The on-line multiclassifier optimization approach is applicable to any pattern recognition problem. The proposed method needs neither a priori distributions nor pre-estimated weights, and does not make use of any consideration about training/testing matching conditions. Results with Yoho database show that the presented approach can lead to reductions in equal error rate as high as 28%, when compared with the most accurate classifier, and 11% against a standard method for the optimization of linear combination of classifiers.

• 한국정보처리학회논문지
• /
• 제4권2호
• /
• pp.456-464
• /
• 1997

본 논문에서는 클래스내부와 클래스간의를 확정하게 제어할 수 있는 랜덤 프로세스 모델을 제어하는 프리세스 내부의 파라메다들을 변화시키며, 프로세스간의 통계적인 차이와 랜덤 잡음을 변화시켜 학습을 위한 패턴들을 생성한다. 이 랜덤 프로세스 모델에서 생성된 패턴들을 이용하여 역전파알고리즘으로 학습된 다단 신경망의 성능 성능을 평가한다. 평가 실험결과는 패턴 분류문제에서 일반화된 통계적인 거리가 분류문제의 난이도에 대한 좋은 예측기가 되는 것을 보여 준다. 또한 본 논문에서는 다단신경망의 성능과 베이스패턴분류기의 성능을 비교하기 위하여 베이스분류기의 이론적인 성능분석과 모의실험을 통한 평가를 하였다. 다단신경망의 분류성능이 이론적인 성능과 실헝치와 매우 근사하며 그 두 성능 중간에 위치함을 발견하였다.

• 설비공학논문집
• /
• 제20권7호
• /
• pp.508-516
• /
• 2008

Fault detection and diagnosis(FDD) system is beneficial in equipment management by providing the operator with tools which can help find out a failure of the system. An experimental study has been performed on fault detection and diagnosis method for a water chiller. Bayes classifier, which is one of classical pattern classifiers, is adopted in deciding whether fault occurred or not. Failure modes in this study include refrigerant leakage, decrease in mass flow rate of the chilled water and cooling water, and sensor error of the cooling water inlet temperature. It is possible to detect and diagnose faults in this study by adopting FDD algorithm using only four parameters(compressor outlet temperature, chilled water inlet temperature, cooling water outlet temperature and compressor power consumption). Refrigerant leakage failure is detected at 20% of refrigerant leakage. When mass flow rate of the chilled and cooling water decrease more than 8% or 12%, FDD algorithm can detect the faults. The deviation of temperature sensor over $0.6^{\circ}C$ can be detected as fault.

• 전기학회논문지
• /
• 제61권1호
• /
• pp.135-142
• /
• 2012

In this paper, we proposed a new architecture called radial basis function-based polynomial neural networks classifier that consists of heterogeneous neural networks such as radial basis function neural networks and polynomial neural networks. The underlying architecture of the proposed model equals to polynomial neural networks(PNNs) while polynomial neurons in PNNs are composed of Fuzzy-c means-based radial basis function neural networks(FCM-based RBFNNs) instead of the conventional polynomial function. We consider PNNs to find the optimal local models and use RBFNNs to cover the high dimensionality problems. Also, in the hidden layer of RBFNNs, FCM algorithm is used to produce some clusters based on the similarity of given dataset. The proposed model depends on some parameters such as the number of input variables in PNNs, the number of clusters and fuzzification coefficient in FCM and polynomial type in RBFNNs. A multiobjective particle swarm optimization using crowding distance (MoPSO-CD) is exploited in order to carry out both structural and parametric optimization of the proposed networks. MoPSO is introduced for not only the performance of model but also complexity and interpretability. The usefulness of the proposed model as a classifier is evaluated with the aid of some benchmark datasets such as iris and liver.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2007년도 추계학술발표대회
• /
• pp.34-37
• /
• 2007

Face recognition is still a challenging problem in pattern recognition field which is affected by different factors such as facial expression, illumination, pose etc. The facial feature such as eyes, nose, and mouth constitute a complete face. Mouth feature of face is under the undesirable effect of facial expression as many factors contribute the low performance. We proposed a new approach for face recognition under facial expression applying two cascaded classifiers to improve recognition rate. All facial expression images are treated by general purpose classifier at first stage. All rejected images (applying threshold) are used for adaptation using GA for improvement in recognition rate. We apply Gabor Wavelet as a general classifier and Gabor wavelet with Genetic Algorithm for adaptation under expression variance to solve this issue. We have designed, implemented and demonstrated our proposed approach addressing this issue. FERET face image dataset have been chosen for training and testing and we have achieved a very good success.

• 전기학회논문지P
• /
• 제52권1호
• /
• pp.35-41
• /
• 2003

In this paper, a machine vision system for recognizing and classifying the patterns and marks engraved by die molding or laser marking on the glass panels of computer monitors is suggested and evaluated experimentally. The vision system is equipped with a neural network and an NGC pattern classifier including searching process based on normalized grayscale correlation and adaptive binarization. This system is found to be applicable even to the cases in which the segmentation of the pattern area from the background using ordinary blob coloring technique is quite difficult. The inspection process is accomplished by the use of the NGC hypothesis and ANN verification. The proposed pattern recognition system is composed of three parts: NGC matching process and the preprocessing unit for acquiring the best quality of binary image data, a neural network-based recognition algorithm, and the learning algorithm for the neural network. Another contribution of this paper is the method of generating the training patterns from only a few typical product samples in place of real images of all types of good products.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.345-350
• /
• 2002

In this study, researchers classifying the artificial flaws in semiconductor packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method fur entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.