• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.503-510
• /
• 2002

This paper presents a fault diagnosis method using neural network-based multi-fault models and statistical method to detect and isolate faults in nonlinear systems. In the proposed method, faults are 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 fault classifier statistically isolates the fault by using the error between each neural network-based fault model output and the system output. 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.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.5
• /
• pp.45-53
• /
• 2000

This paper presents an analysis of the dynamical behavor in the chaotic neuron fabricated using 0.8${\mu}{\textrm}{m}$ single poly CMOS technology. An approximated empirical equation models for the sigmoid output function and chaos generative block of the chaotic neuron are extracted from the measurement data. Then the dynamical responses of the chaotic neuron such as biurcation diagram, frequency responses, Lyapunov exponent, and average firing rate are calculated with numerical analysis. In addition, we construct the chaotic neural networks which are composed of two chaotic neurons with four synapses and obtain bifurcation diagram according to synaptic weight variation. And results of experiments in the single chaotic neuron and chaotic neural networks by two neurons with the $\pm$2.5V power supply and sampling clock frequency of 10KHz are shown and compared with the simulated results.

• Proceedings of the IEEK Conference
• /
• 2001.06e
• /
• pp.115-118
• /
• 2001

In this paper we propose an FDI(fault detection and isolation) algorithm using neural network-based multi-fault models to detect and isolate single faults in nonlinear systems. When a change in the system occurs, the errors between the system output and the neural network nominal system output cross a threshold, and once a fault in the system is detected, the fault classifier statistically isolates the fault by using the error between each neural network-based fault model output and the system output.

• Journal of Korea Multimedia Society
• /
• v.11 no.9
• /
• pp.1213-1226
• /
• 2008

A recommender system supports people in making recommendations finding a set of people who are likely to provide good recommendations for a given person, or deriving recommendations from implicit behavior such as browsing activity, buying patterns, and time on task. We proposed new recommender system which combined SOM(Self-Organizing Map) neural networks with the Collaborative filtering which most recommender systems hat applied First, we segmented user groups according to demographic characteristics and then we trained the SOM with people's preferences as ito inputs. Finally we applied the classic collaborative filtering to the clustering with similarity in which an recommendation seeker belonged to, and therefore we didn't have to apply the collaborative filtering to the whose data set. Experiments were run for EachMovies data set. The results indicated that the predictive accuracy was increased in terms of MAE(Mean-Absolute-Error).

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.33 no.2
• /
• pp.84-91
• /
• 2005

For long time, the takeoff and landing control of airship was worked by human handling. With the development of the autonomous control system, the exact controls during the takeoff and landing were required and lots of methods and algorithms were suggested. This paper presents the result of airship take-off and landing by buoyancy control using air ballonet volume change and performance control of pitch angle for stable flight within the desired altitude. For the complexity of airship's dynamics, firstly, simple PID controller was applied. Due to the various atmospheric conditions, this controller didn't give satisfactory results. Therefore, new control method was designed to reduce rapidly the error between designed trajectory and actual trajectory by learning algorithm using an artificial neural network. Generally, ANN has various weaknesses such as large training time, selection of neuron and hidden layer numbers required to deal with complex problem. To overcome these drawbacks, in this paper, the RBFN (radial basis function network) controller developed. The weight value of RBFN is acquired by learning which to reduce the error between desired input output through and airship dynamics to impress the disturbance. As a result of simulation, the controller using the RBFN is superior to PID controller which maximum error is 15M.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.11
• /
• pp.57-63
• /
• 1996

Monitoring of grinding troble occurring during the process is classified into the quantitative data which depends upon a sensor and the qualitative knowledge which relies upon an empirical knowledge. Since grinding operation is highly related with a large amount of functional parameters, it is actually deficulty in copying wiht the grinding troubles through the process. To cope with grinding trouble, it is an effective monitoring systems when occurring the grinding process. The use of neural networks is an effective method of detection and/or monitroing on the grinding trouble. In this paper, four parameters which are derived from the AE(Acoustic Emission) signatures are identified, and grinding monitoring system utilized a back propagation learning algorithm of PDP neural networks is presented.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.247-248
• /
• 2008

본 논문에서는 TYPE-2 퍼지 추론 기반의 RBF 뉴럴 네트워크(TYPE-2 Radial Basis Function Neural Network, T2RBFNN)를 설계하고 PSO(Particle Swarm Optimization) 알고리즘을 이용하여 모델의 파라미터를 동정한다. 제안된 모델의 은닉층은 TYPE-2 가우시안 활성 함수로 구성되며, 출력층은 Interval set 형태의 연결가중치를 갖는다. 여기에서 규칙 전반부 활성함수의 중심 선택은 C-means 클러스터링 알고리즘을 이용하고, 규칙 후반부 Interval set 형태의 연결가중치 결정에는 경사 하강법(Gradient descent method)을 이용한 오류 역전파 알고리즘을 사용하여 학습한다. 또한, 최적의 모델을 설계하기 위한 학습율 및 활성함수의 활성화 영역 결정에는 입자 군집 최적화(PSO; Particle Swarm Optimization) 알고리즘으로 동조한다. 마지막으로, 제안된 모델의 평가를 위하여 모의 데이터 집합(Synthetic dadaset)을 적용하고 근사화 및 일반화 능력에 대하여 토의한다.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.809-812
• /
• 2021

Air bubbles which may be generated during the PCB coating process can be a major cause of malfunction. so it is necessary to detect the bubbles in advance. In previous studies, candidates for bubbles were extracted using the brightness characteristics of bubbles, and the candidates were verified using CNN(Convolutional Neural Networks). In this paper, we propose a bubble detection method using a transfer learning-based CNN model. The VGGNet is adopted and sigmoid is used as a classification layer, and the last convolutional layer and classification layer are trained together when transfer learning is applied. The performance of the proposed method is F1-score 0.9044, which shows an improvement of about 0.17 compared to the previous study.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4
• /
• pp.43-49
• /
• 1996

This research proposes a system for speaker independent Korean continuous speech recognition with 247 DDD area names using keyword spotting technique. The applied recognition algorithm is the Dynamic Programming Neural Network(DPNN) based on the integration of DP and multi-layer perceptron as model that solves time axis distortion and spectral pattern variation in the speech. To improve performance, we classify word model into keyword model and non-keyword model. We make an experiment on postprocessing procedure for the evaluation of system performance. Experiment results are as follows. The recognition rate of the isolated word is 93.45% in speaker dependent case. The recognition rate of the isolated word is 84.05% in speaker independent case. The recognition rate of simple dialogic sentence in keyword spotting experiment is 77.34% as speaker dependent, and 70.63% as speaker independent.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.31-34
• /
• 2009

ART2 알고리즘은 신경 회로망 모델로서 실시간 학습이 가능하여 저속 및 고속을 지원할 뿐만 아니라 지역 최소화(local minima) 문제가 발생하지 않는 장점을 갖는다. 그러나 ART2 알고리즘은 경계 변수 설정에 따라 클러스터의 수가 달라지며, 이러한 경계 변수 설정은 패턴의 분류와 인식 성능을 좌우한다. 따라서 본 논문에서는 ART2 알고리즘에서 효율적으로 경계 변수를 설정하기 위해 패턴셋 설정을 통한 경계 변수 설정 방법을 제안한다. 제안된 경계 변수 설정 방법의 성능을 평가하기 위해 숫자 및 영문 패턴을 대상으로 실험한 결과, 패턴 분류의 성능이 기존의 방식 보다 개선된 것을 확인하였다.