• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.484-489
• /
• 2003

본 논문에서는 역전파 알고리즘의 성능 개선을 위해 퍼지 논리 시스템을 이용한 학습률 자동 조정 방법을 제안한다. 제안된 방법은 목표값과 출력값의 차이에 대한 절대값이 $\varepsilon$ 보다 적거나 같으면 정확성으로 분류하고 크면 부정확성으로 분류한다. 정확성의 총 개수를 퍼지 논리 시스템에 적용하여 학습률과 모멘텀을 동적으로 조정한다. 제안된 방법을 XOR 문제와 숫자패턴 문제에 적용하여 실험한 결과, 기존의 역전파 알고리즘, 모멘텀 방식, Jacob의 delta-bar-delta 방식보다 성능이 개선됨을 확인하였다.

• Journal of the Korean Chemical Society
• /
• v.25 no.3
• /
• pp.152-159
• /
• 1981

The rates of solvolysis for p-nitrobenzyl chloride have been measured by the electric conductivity method in aqueous ethanol from 0.0 to 0. 5 mole fraction of ethanol under various pressures up to 1200bar at 50 and $60{\circ}C$. The activation parameters, ${\Delta}V_\0^{\neq},\ {\Delta}H^{\neq}$ and ${\Delta}S^{\neq}$ are evaluated from the rate constants. The results indicated that ${\Delta}V_\0^{\neq}$ exhibits an extremum behaviors near 0.3 mole fraction of ethanol and ${\Delta}H^{\neq}$ and ${\Delta}S^{\neq}$ near 0.1 mole fraction of ethanol. This behaviors are discussed in terms of solvent structure variation and the pressure dependences of ${\Delta}H^{\neq},\ {\Delta}H^{\neq}$ and ${\Delta}S^{\neq}$ are also discussed individually. The signs of the pressure dependence of ${\Delta}H^{\neq}$${\Delta}S^{\neq}$ are shown to be consistent with those required by the Maxwell relationships for classical thermodynamic systems.

• Journal of Electrical Engineering and Technology
• /
• v.6 no.3
• /
• pp.384-390
• /
• 2011

To evaluate the condition of stator winding insulation in generators that have been operated for a long period of time, diagnostic tests were performed on the stator bars of a 500 MW, 22 kV generator under accelerated thermal and electrical aging procedures. The tests included measurements of AC current (${\Delta}I$), dissipation factor ($tan{\delta}$), partial discharge (PD) magnitude, and capacitance (C). In addition, the AC current test was performed on the stator winding of a 350 MW, 24 kV generator under operation to confirm insulation deterioration. The values of ${\Delta}I$, ${\Delta}tan{\delta}$, and PD magnitude in one stator bar indicated serious insulation deterioration. In another stator bar, the ${\Delta}I$ measurements showed that the insulation was in good condition, whereas the values of ${\Delta}tan{\delta}$ and PD magnitude indicated an incipient stage of insulation deterioration. Measurements of ${\Delta}I$ and PD magnitude in all three phases (A, B, C) of the remaining generator stator windings showed that they were in good condition, although the ${\Delta}tan{\delta}$ measurements suggested that the condition of the insulation should be monitored carefully. Overall analysis of the results suggested that the generator stator windings were in good condition. The patterns of PD magnitude in all three phases (A, B, C) were attributed to internal discharge.

• Kyungpook Mathematical Journal
• /
• v.59 no.3
• /
• pp.537-562
• /
• 2019

The aim of the present paper is to study the ${\delta}$-Lorentzian trans-Sasakian manifold endowed with semi-symmetric metric connections admitting ${\eta}$-Ricci Solitons and Ricci Solitons. We find expressions for the curvature tensor, the Ricci curvature tensor and the scalar curvature tensor of ${\delta}$-Lorentzian trans-Sasakian manifolds with a semisymmetric-metric connection. Also, we discuses some results on quasi-projectively flat and ${\phi}$-projectively flat manifolds endowed with a semi-symmetric-metric connection. It is shown that the manifold satisfying ${\bar{R}}.{\bar{S}}=0$, ${\bar{P}}.{\bar{S}}=0$ is an ${\eta}$-Einstein manifold. Moreover, we obtain the conditions for the ${\delta}$-Lorentzian trans-Sasakian manifolds with a semisymmetric-metric connection to be conformally flat and ${\xi}$-conformally flat.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.71-75
• /
• 2003

오류 역전파 학습 알고리즘을 이용하여 영상 인식에 적용 할 경우에는 은닉층의 노드 수를 경험적으로 설정하므로, 학습시간과 지역최소화 및 정체현상이 발생한다. 그리고 ARTI 알고리즘은 입력 패턴과 저장 패턴간의 측정 방법인 유사성 검증 방법과 경계 변수의 설정에 따라 인식률이 좌우된다. 경계 변수의 값이 크면 입력 패턴과 저장 패턴사이에 약간의 차이만 있어도 새로운 카테고리(Category)로 분류하고, 반대로 경계 변수의 값이 적으면 입력 패턴과 저장 패턴 사이에 많은 차이가 있더라도 유사성이 인정되어 입력 패턴들을 대략적으로 분류한다. 따라서 ART1 알고리즘을 영상 인식에 적용하기 위해서는 경계 변수를 경험적으로 설정하므로 인식률에 부정적인 영향을 갖는 문제점이 있다. 따라서 본 논문에서는 개선된 ART1 알고리즘과 지도 학습 방법을 결합하여 신경망의 은닉층 노드를 동적으로 변화시키는 자가 생성지도 학습 알고리즘을 제안한다. 제안된 신경망에서 입력층과 은닉층의 학습 구조에는 ART1 알고리즘을 개선하여 적용하고, 은닉층과 출력층의 학습 구조에는 은닉층에서 승자로 선택된 노드와 출력층 노드와 연결된 가중치만을 조정하고 Delta-Bar-Delta 알고리즘을 적용한다. 제안된 방법의 학습 성능을 분석하기 위하여 학생증 영상에서 추출한 학번 패턴 분류에 적용한 결과, 기존의 신경망 학습 알고리즘보다 학습 성능이 개선됨을 확인하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2C
• /
• pp.31-40
• /
• 2005

we propose an enhanced self-generation supervised algorithm that by combining an ART algorithm and the delta-bar-delta method. Form the input layer to the hidden layer, ART-1 and ART-2 are used to produce nodes, respectively. A winner-take-all method is adopted to the connection weight adaption so that a stored pattern for some pattern is updated. we test the recognition of student identification, a certificate of residence, and an identifier from container that require nodes of hidden layers in neural network. In simulation results, the proposed self-generation supervised learning algorithm reduces the possibility of local minima and improves learning speed and paralysis than conventional neural networks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.464-470
• /
• 2004

We propose an enhanced backpropagation algorithm by auto-tuning of learning rate using fuzzy control system for performance improvement of backpropagation algorithm. We propose two methods, which improve local minima and loaming times problem. First, if absolute value of difference between target and actual output value is smaller than $\varepsilon$ or the same, we define it as correctness. And if bigger than $\varepsilon$, we define it as incorrectness. Second, instead of choosing a fixed learning rate, the proposed method is used to dynamically adjust learning rate using fuzzy control system. The inputs of fuzzy control system are number of correctness and incorrectness, and the output is the Loaming rate. For the evaluation of performance of the proposed method, we applied the XOR problem and numeral patterns classification The experimentation results showed that the proposed method has improved the performance compared to the conventional backpropagatiot the backpropagation with momentum, and the Jacob's delta-bar-delta method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1278-1290
• /
• 2008

This paper proposes a preprocessing method and a neural network based character recognizer to enhance the overall performance of the license plate recognition system. First, plate outlines are extracted by virtual line matching, and then the 4 vertexes are obtained by calculating intersecting points of extracted lines. By these vertexes, plate image is reconstructed as rectangle-shaped image by bilinear transform. Finally, the license plate is recognized by the neural network based classifier which had been trained using delta-bar-delta algorithm. Various license plate images were used in the experiments, and the proposed plate normalization enhanced the recognition performance up to 16 percent.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.10
• /
• pp.1977-1985
• /
• 2007

The character recognition technique is one of the artificial intelligence and has been widely applied in the automated system robot HCI(Human Computer Interaction), etc. This paper introduces the character set and the representative character that can be used in the recognition of the mage ROI. The character codes in this ROI include the digit, symbol, English and Hereat etc. We proposed the efficient multi-classifier structure by combining the small-size classifiers hierarchically. Moreover, we generated each small-size classifiers by delta-bar-delta learning algorithm. We tested the performance with various kinds of images and achieved the accuracy of 99%. The proposed multi-classifier showed the efficiency and the reliability for the mixed character code set.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.7
• /
• pp.1375-1379
• /
• 2009

Insulation tests have been performed on two generator stator bars under accelerated aging under a laboratory environment. Electrical stress was applied to stator bar No.1, and electrical and thermal stresses were applied to stator bar No.2. Nondestructive stator insulation tests including the ac current, dissipation factor($tan{\delta}$), and partial discharge tests have been performed on both bars as the bars were aged for 11460 hours. Experimental test results show that ${\Delta}I$, ${\Delta}tan{\delta}$, and partial discharge of No. 1 and No.2 stator bars increased with increased in aging time. It has been concluded from the test that the stator insulation of the two generators are in good condition.