• The Transactions of the Korea Information Processing Society
• /
• v.2 no.5
• /
• pp.626-633
• /
• 1995

It is vary hard to identify the fuzzy rules and tune the membership functions of the fuzzy inference in fuzzy systems modeling, We propose a fuzzy neural network model which can automatically identify the fuzzy rules and tune the membership functions of fuzzy inference simultaneously using artificial neural networks, and modify backpropagation algorithm for improving the convergence. The proposed method is verified by the simulation for a robot manipulator.

• Tunnel and Underground Space
• /
• v.13 no.6
• /
• pp.434-443
• /
• 2003

In this study, it was purposed to develop the new method for the prediction of pollutant concentration in road tunnels. The new method was the use of artificial neural network with the back-propagation algorithm which can model the non-linear system of tunnel environment. This network system was separated into two parts as the visibility and the CO concentration. For this study, data was collected from two highway road tunnels on Yeongdong Expressway. The tunnels have two lanes with one-way direction and adopt the longitudinal ventilation system. The actually measured data from the tunnels was used to develop the neural network system for the prediction of pollutant concentration. The output results from the newly developed neural network system were analysed and compared with the calculated values by PIARC method. Results showed that the prediction accuracy by the neural network system was approximately five times better than the one by PIARC method. In addition, the system predicted much more accurately at the situation where the drivers have to be stayed for a while in tunnels caused by the low velocity of vehicles.

• The KIPS Transactions:PartD
• /
• v.10D no.4
• /
• pp.689-696
• /
• 2003

Criticality prediction models that determine whether a design entity is fault-prone or non fault-prone are used for identifying trouble spots of software system in analysis or design phases. Many criticality prediction models for identifying fault-prone modules using complexity metrics have been suggested. But most of them need training data set. Unfortunately very few organizations have their own training data. To solve this problem, this paper builds a new prediction model, KSM, based on Kohonen SOM neural networks. KSM is implemented and compared with a well-known prediction model, BackPropagation neural network Model (BPM), considering internal characteristics, utilization cost and accuracy of prediction. As a result, this paper shows that KSM has comparative performance with BPM.

• Proceedings of the KIEE Conference
• /
• 2008.09a
• /
• pp.255-257
• /
• 2008

초고속 전기정보의 전송 시대와 U-정보전자시대에 응용하는 최신 정보기기와 의료기기 및 군사정보의 실시간 전송을 위하여 많은 실시간 알고리즘과 모델링의 연구가 필수적이다. 또한 원격지에 많은 전기 및 전력정보를 비선형적 특성이 있는 환경하에서도 정보의 오차가 없이 실시간으로 전송하는 기술은 현대 정보사회에서 해결해야 할 매우 중요한 요소중에 하나이다. 이러한 내용으로 수행되어지는 신경회로망을 이용한 실시간 모델링을 제안하고자 한다. 이와 관련한 일반적인 방법으로 역전파 학습 알고리즘을 들 수 있다. 파라미터에도 덜 민감하며, 특히 온라인으로 인식과 제어가 가능하도록 수렴속도를 향상 시켜야하는 새로운 모델의 필요성이 요구된다. 본 연구에서는 기존의 신경회로망이 가지고 있는 여러 단점들을 개선하고자 새로운 학습 알고리즘과 새로운 구조의 신경회로망을 제시한다. 또한 제시한 알고리즘을 이용하여 불규칙적 시스템 모델망과 다양한 센서 모델링 등에 연결하여 다양한 실험을 수행하여 그 결과를 보여 실시간 특성을 갖는 것을 입증해 보였다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.276-279
• /
• 2019

의존 구문 분석은 문장을 구성하는 성분들 간의 의존 관계를 분석하고 문장의 구조적 정보를 얻기 위한 기술이다. 의미역 결정은 문장에서 서술어에 해당하는 어절을 찾고 해당 서술어의 논항들을 찾는 자연어 처리의 한 분야이다. 두 기술은 서로 밀접한 상관관계가 존재하며 기존 연구들은 이 상관관계를 이용하기 위해 의존 구문 분석의 결과를 의미역 결정의 자질로써 사용한다. 그러나 이런 방법은 의미역 결정 모델의 오류가 의존 구문 분석에 역전파 되지 않으므로 두 기술의 상관관계를 효과적으로 사용한다고 보기 어렵다. 본 논문은 포인터 네트워크 기반의 의존 구문 분석 모델과 병렬화 순환 신경망 기반의 의미역 결정 모델을 멀티 태스크 방식으로 학습시키는 통합 모델을 제안한다. 제안 모델은 의존 구문 분석 및 의미역 결정 말뭉치인 UProbBank를 실험에 사용하여 의존 구문 분석에서 UAS 0.9327, 의미역 결정에서 PIC F1 0.9952, AIC F1 0.7312의 성능 보였다.

• Journal of The Korean Association of Information Education
• /
• v.12 no.3
• /
• pp.267-274
• /
• 2008

A neural network is a modeling technique useful for finding out hidden patterns from data through repetitive learning process and for predicting target values for new data. In this study, we built multilayer perceptron neural networks for prediction of the students' computer literacy based on their personal characteristics, home and social environment, and academic record of other subjects. Prediction performance of the network was compared with that of a widely used prediction method, the regression model. From our experiments, it was found that personal characteristic features best explained computer proficiency level of a student, whereas the features of home and social environment resulted in the worse prediction accuracy among all. Moreover, the developed neural network model produced far more accurate prediction than the regression model.

• Geotechnical Engineering
• /
• v.10 no.3
• /
• pp.79-96
• /
• 1994

A tunnel design expert system entitled NESTED is developed using the artificial neural network. The expert system includes three neural network computer models designed for the stability assessment of underground openings and the estimation of correlation between the RMR and Q systems. The expert system consists of the three models and the computerized rock mass classification programs that could be driven under the same user interface. As the structure of the neural network, a multi -layer neural network which adopts an or ror back-propagation learning algorithm is used. To set up its knowledge base from the prior case histories, an engineering database which can control the incomplete and erroneous information by learning process is developed. A series of experiments comparing the results of the neural network with the actual field observations have demonstrated the inferring capabilities of the neural network to identify the possible failure modes and the support timing. The neural network expert system thus complements the incomplete geological data and provides suitable support recommendations for preliminary design of tunnels in rock masses.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.11a
• /
• pp.159-162
• /
• 2004

플라즈마 공정 모델 개발에 역전파 신경망이 가장 많이 응용되고 있으나, 관여하는 다수의 학습인자로 인해 그 최적화가 매우 어렵다. Radial basis function network (RBFN)은 관여하는 학습인자의 수가 적어 그 최적화가 상대적으로 용이하지만, 두인자의 다양한 조합에 의해 RBFN의 예측성능이 상당히 영향을 받을 수 있다. 본 연구에서는 학습인자 상호간의 작용을 유전자 알고리즘 (genetic algorithm-GA)을 이용하여 최적화하는 기법을 소개한다. 제안하는 알고리즘을 광도파로 제작을 위해 수행한 실리카 식각공정 데이터에 적용하여 평가하였다. 평가에 이용된 식각 응답은, 실리카 식각률, aluminum (Al) 식각률, Al 선택비, 그리고 실리카 프로파일 각도이다. 최적화한 모델은 종래의 모델과 비교하였으며, 그 향상도는 실리카 식각률, Al 식각률, Al 선택비, 그리고 실리카 프로파일 각도에 대해서 각 기 0.8%, 32.4%, 20.3%, 1.3% 등이었다. Al 식각률과 선택비에 대해서 예측성능은 상당이 향상되었다.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.10 no.2
• /
• pp.133-144
• /
• 2006

In order to catch out such Bond Strength, the preceding researchers had ever examined the Bond Strength of FRP Plate through their experimentations by setting up of various fluent. However, since the experiment for research on such Bond Strength takes much of expenditure for equipment structure and time-consuming, also difficult to carry out, it is conducting limitedly. This Study purposes to develop the most suitable Artificial Neural Network Model by application of various Neural Network Model and Algorithm to the adhering experiment data of the preceding researchers. Output Layer of Artificial Neural Network Model, and Input Layer of Bond Strength were performed the learning by selection as the variable of the thickness, width, adhered length, the modulus of elasticity, tensile strength, and the compressive strength of concrete, tensile strength, width, respectively. The developed Artificial Neural Network Model has applied Back-Propagation, and its error was learnt to be converged within the range of 0.001. Besides, the process for generalization has dissolved the problem of Over-Fitting in the way of more generalized method by introduction of Bayesian Technique. The verification on the developed Model was executed by comparison with the resulted value of Bond Strength made by the other preceding researchers which was never been utilized to the learning as yet.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2012.11a
• /
• pp.253-254
• /
• 2012

The purpose of this study is to suggest and verify high-strength concrete mix design model applying neural network theory, in order to minimize effort and time wasted by using trial and error method utill now. There are 7 input and 2 output to predict mix design. 40 data of mix design were learned with back-propagation algorithm. Then they are repeatedly learned back-propagation in neural network theory. Also, to verify predicted model, we analyzed and compared value predicted from 60MPa mix design with value measured by actual compressive strength test.