• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.195-199
• /
• 2021

본 논문에서는 재귀 신경망을 통해 동적 비전 센서 (DVS: Dynamic Vision Sensor)의 출력에서 엣지를 추정하는 방법을 제안한다. 동적 비전 센서는 기존의 일반적인 카메라들과 달리 급격한 움직임이나 밝기 변화에 강인하게 동작한다. 그러나 동적 비전 센서에서 획득한 출력은 각각이 독립적이기 때문에 화소들의 상관관계를 이용한 알고리즘을 사용함에 어려움이 따른다. 제안하는 방법은 센서에서 획득한 출력을 일정한 시간단위로 분할하고 2차원 평면에 투영함으로써 출력의 정보량 및 상관관계를 향상시키고, 이를 재귀 신경망에 통과시켜 엣지 정보를 추정한다. 이 방법은 센서의 출력에 의해 형성된 패턴을 학습하여 엣지를 잘 추출하였으며, 기존의 컴퓨터 비전 알고리즘의 적용 및 시각 관성 측위 등의 분야에서 활용될 수 있다.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.14 no.5
• /
• pp.179-186
• /
• 2010

When a structure is damaged, its dynamic responses (natural frequency, acceleration, strain) are found to be changed. The ANN(Artificial Neural Network) damage-assesment method is that some measured dynamic signals from the structural changing dynamic responses are applied to ANN to assess the structural damage. Although there have been some studies on a certain typical cases so far, it is rare to find studies about the characteristics of the ANN damage-assesment method or about its applicability, its strength and weakness. So this study researches on the characteristics of ANN damage assesment method and on a problem in application of the various dynamic responses to ANN. What the ANN damage assessment method usually does in past researches is to teach an ANN by using some response signals obtained from damaged structures under one kind of excitations and to identify the locations and the extents of damage of same structures under the same excitations. However, the excitations inflicted on the structures are not always the same. Thus this study experiments whether a ANN which is trained using the same excitations is able to identify the damage when different excitations inflict. All response signals are obtained from experimental models.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.3
• /
• pp.3-11
• /
• 1997

One of major research areas in the recurrent neural network is to develop stable learning algorithm. In this paper, the stable learning algorithm is developed by utilizing the evolutionary programming. The effectiveness of the proposed learning algorithm will be verified by simulating two d.0.f. robot manipulator.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.119-128
• /
• 2002

This paper proposes an efficient recognition method of car license plate from the car images by using both the dynamical thresholding and the neural network with enhanced learning algorithm. The car license plate is extracted by the dynamical thresholding based on the structural features and the density rates. Each characters and numbers from the p]ate is also extracted by the contour tracking algorithm. The enhanced neural network is proposed for recognizing them, which has the algorithm of combining the modified ART1 and the supervised learning method. The proposed method has applied to the real-world car images. The simulation results show that the proposed method has better the extraction rates than the methods with information of the gray brightness and the RGB, respectively. And the proposed method has better recognition performance than the conventional backpropagation neural network.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.4
• /
• pp.22-27
• /
• 2000

In this paper, new neural network called dynamic multidimensional wavelet neural network (DMWNN) is proposed. The resulting network from wavelet theory provides a unique and efficient representation of the given function. Also the proposed DMWNN have ability to store information for later use. Therefore it can represent dynamic mapping and decreases the dimension of the inputs needed for network. This feature of DMWNN can compensate for the weakness of diagonal recurrent neural network(DRNN) and feedforward wavelet neural network(FWNN). The efficacy of this type of network is demonstrated through experimental results.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.139-147
• /
• 2003

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing such as signal prediction. This paper proposes the hybrid network, composed of locally(LRNN) and globally recurrent neural networks(GRNN), to improve dynamics of multilayered recurrent networks(RNN) and then describes nonlinear adaptive prediction using the proposed network as an adaptive filter. The hybrid network consists of IIR-MLP and Elman RNN as LRNN and GRNN, respectively. The proposed network is evaluated in nonlinear signal prediction and compared with Elman RNN and IIR-MLP networks for the relative comparison of prediction performance. Experimental results show that the hybrid network performs better with respect to convergence speed and accuracy, indicating that the proposed network can be a more effective prediction model than conventional multilayered recurrent networks in nonlinear prediction for nonstationary signals.

• Journal of KIISE:Software and Applications
• /
• v.28 no.4
• /
• pp.338-345
• /
• 2001

본 연구에서는 시계열자료를 예측하기 위해 적용한 n$\times$n$\times$1 신경망 구조에서 초기값의 시각적인 선택을 통한 개선된 학습과정을 제안한다. 적용된 Easton[1]의 제어상자는 시각적인 면과 실용적인 적용측면에서 다차원 구조를 논의하기에는 제한적이지만, 적은 개수의 은닉노드를 갖는 단순한 신경망구조에서는 초기 가중값들의 동적인 선택을 통하여 가능한 빨리 효과적인 학습이 이루어질 수 있게 할 수 있다. 신경망 학습의 오차 판단기준은 기존의 평균제곱오차(MSE)를 고려한다. 실증연구에는 모의생성된 ARMA(1,0) 자료와 담배생산량 자료를 이용한다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.3
• /
• pp.238-244
• /
• 2008

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing. This paper presents gamma neural network(GAM) to improve the dynamics of multilayer network. The GAM network uses the gamma memory kernel in the hidden layer of feedforword multilayer network. The GAM network is evaluated in linear and nonlinear system identification, and compared with feedforword(FNN) and recurrent neural networks(RNN) for the relative comparison of its performance. Experimental results show that the GAM network performs better with respect to the convergence and accuracy, indicating that it can be a more effective network than conventional multilayer networks in system identification.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.2
• /
• pp.53-59
• /
• 2006

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing such as system identification and signal prediction. This paper proposes the gamma neural network(GAM), which uses gamma memory kernel in the hidden layer of feedforward multilayered network, to improve dynamics of networks and then describes nonlinear adaptive prediction using the proposed network as an adaptive filter. The proposed network is evaluated in nonlinear signal prediction and compared with feedforword(FNN) and recurrent neural networks(RNN) for the relative comparison of prediction performance. Simulation results show that the GAM network performs better with respect to the convergence speed and prediction accuracy, indicating that it can be a more effective prediction model than conventional multilayered networks in nonlinear prediction for nonstationary signals.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.1
• /
• pp.45-52
• /
• 2005

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing. This paper describes system identification using the hybrid neural network, composed of locally(LRNN) and globally recurrent neural networks(GRNN) to improve dynamics of multilayered recurrent networks(RNN). The structure of the hybrid nework combines IIR-MLP as LRNN and Elman RNN as GRNN. The hybrid network is evaluated in linear and nonlinear system identification, and compared with Elman RNN and IIR-MLP networks for the relative comparison of its performance. Simulation results show that the hybrid network performs better with respect to the convergence and accuracy, indicating that it can be a more effective network than conventional multilayered recurrent networks in system identification.