• 제목/요약/키워드: Dynamic Recurrent Neural Networks

검색결과 50건 처리시간 0.039초

Gamma 다층 신경망을 이용한 비선형 적응예측 (Nonlinear Prediction using Gamma Multilayered Neural Network)

  • 김종인;고일환;최한고
    • 융합신호처리학회논문지
    • /
    • 제7권2호
    • /
    • pp.53-59
    • /
    • 2006
  • 동적 신경망은 시스템 식별과 신호예측과 같이 temporal 신호처리가 요구되는 여러 분야에서 적용되어 왔다. 본 논문에서는 신경망의 동특성을 향상시키기 위해 순방향 다층 신경망의 히든 층에 감마(Gamma) 메모리 커넬을 사용하는 감마 신경망(GAM)을 제안하고, 적응필터로 제안된 신경망을 사용하여 비선형 적응예측을 다루고 있다. 제안된 신경망은 비선형 신호예측을 통해 평가되었으며, 예측성능의 상대적인 비교를 위해 순방향 신경망(FNN)과 리커런트 신경망(RNN)과 비교하였다. 시뮬레이션 결과에 의하면 GAM 신경망은 수렴속도와 예측의 정확도에서 이러한 신경망보다 더 우수한 동작을 수행함으로써, 제안된 신경망이 기존의 다층 신경망보다 비정적 신호에 대한 비선형 예측에 더 효과적인 예측모델임을 확인하였다.

  • PDF

Video Expression Recognition Method Based on Spatiotemporal Recurrent Neural Network and Feature Fusion

  • Zhou, Xuan
    • Journal of Information Processing Systems
    • /
    • 제17권2호
    • /
    • pp.337-351
    • /
    • 2021
  • Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

수정된 카오스 신경망을 이용한 무제약 서체 숫자 인식 (Recognition of Unconstrained Handwritten Numerals using Modified Chaotic Neural Networks)

  • 최한고;김상희;이상재
    • 융합신호처리학회논문지
    • /
    • 제2권1호
    • /
    • pp.44-52
    • /
    • 2001
  • 본 논문은 수정된 카오틱 신경망(MCNN)을 이용하여 완전 무제약 서체 숫자 인식을 다루고 있다. 카오틱 신경망(CNN)의 동적 특성과 학습과정을 강화함으로써 복잡한 패턴인식 문제를 해결할 수 있는 유용한 신경망으로 수정하였다. MCNN은 신경망 구조와 뉴런 자체가 높은 차수의 비선형 동적특성을 갖고 있으므로 복잡한 서체 숫자를 분류할 수 있는 적합한 신경망이다. 숫자 확인은 원래의 숫자 이미지로부터 특징을 추출하고 MCNN에 근거한 분류기를 이용하여 숫자를 인식한다. MCNN 분류기의 성능은 Canada, Montreal의 Concordia 대학의 숫자 데이터 베이스로 평가하였다. 인식성능의 상대적인 비교를 위해 MCNN 분류기는 리커런트 신경망(RNN) 분류기와 비교하였다. 실험결과에 의하면 인식율은 98.0%이었으며, 이는 MCNN 분류기가 같은 데이터 베이스에 대해 발표되었던 다른 분류기와 RNN 분류기보다 성능이 우수함을 나타낸다.

  • PDF

비선형 비행 시스템을 위한 H 접근법 기반 적응 신경망 동적 표면 제어 (Adaptive Neural Dynamic Surface Control via H Approach for Nonlinear Flight Systems)

  • 유성진;최윤호
    • 제어로봇시스템학회논문지
    • /
    • 제14권3호
    • /
    • pp.254-262
    • /
    • 2008
  • In this paper, we propose an adaptive neural dynamic surface control (DSC) approach with $H_{\infty}$ tracking performance for full dynamics of nonlinear flight systems. It is assumed that the model uncertainties such as structured and unstrutured uncertainties, and external disturbances influence the nonlinear aircraft model. In our control system, self recurrent wavelet neural networks (SRWNNs) are used to compensate the model uncertainties of nonlinear flight systems, and an adaptive DSC technique is extended for the disturbance attenuation of nonlinear flight systems. All weights of SRWNNs are trained on-line by the smooth projection algorithm. From Lyapunov stability theorem, it is shown that $H_{\infty}$ performance nom external disturbances can be obtained. Finally, we present the simulation results for a nonlinear six-degree-of-freedom F-16 aircraft model to confirm the effectiveness of the proposed control system.

진화연산을 이용한 동적 귀환 신경망의 구조 저차원화 (Structure Pruning of Dynamic Recurrent Neural Networks Based on Evolutionary Computations)

  • 김대준;심귀보
    • 한국지능시스템학회논문지
    • /
    • 제7권4호
    • /
    • pp.65-73
    • /
    • 1997
  • 본 논문에서는 진화연산을 이용하여 동적 귀환 신경망의 구조를 저차원화하는 방법을 제안한다. 일반적으로 진화연산을 개체군을 이용한 탐색 방법으로서 신경회로망의 여러 가지 다른 성질을 동시에 최적화할 필요가 있을 때 유용한 방법이다. 본 연구에서는 동적 귀환 신경망의 구조를 조차원화하기 위하여 진화 프로그래밍으로 신경망의 구조를 탐색하고, 진화전략으로 신경망의 연결강도를 학습시킴으로서 전체적인 구조를 저차원화하였다.신경망의 중간층 노드의 추가/삭제는 돌연변이 확률에 의하여 결정한다. 노드를 삭제할 경우에는 입력 연결강도의 총합이 가장 작은 노드를 삭제하고, 노드를 추가할 경우에는 미리 지정한 확률함스에 따라 노드를 추가한다. 그리고 추가된 노드와 다른 노드와의 연결방법은 서로 영향을 미칠 수 있는 모든 연결강도 중에서 확률적으로 선택하여 연결하였다. 마지막으로 제안한 저차원화 동적 귀환 신경망이 완전 연결된 신경망보다 더 좋은 성능을 얻을 수 있음을 예제로서 본 논문에서는 도립진자의 안정화 및 제어와 로봇 매니퓰레이터의 비주얼 서보잉에 적용하여 컴퓨터 시뮬레이션을 통하여 그 유효성을 확인한다.

  • PDF

Recurrent Neural Network Modeling of Etch Tool Data: a Preliminary for Fault Inference via Bayesian Networks

  • Nawaz, Javeria;Arshad, Muhammad Zeeshan;Park, Jin-Su;Shin, Sung-Won;Hong, Sang-Jeen
    • 한국진공학회:학술대회논문집
    • /
    • 한국진공학회 2012년도 제42회 동계 정기 학술대회 초록집
    • /
    • pp.239-240
    • /
    • 2012
  • With advancements in semiconductor device technologies, manufacturing processes are getting more complex and it became more difficult to maintain tighter process control. As the number of processing step increased for fabricating complex chip structure, potential fault inducing factors are prevail and their allowable margins are continuously reduced. Therefore, one of the key to success in semiconductor manufacturing is highly accurate and fast fault detection and classification at each stage to reduce any undesired variation and identify the cause of the fault. Sensors in the equipment are used to monitor the state of the process. The idea is that whenever there is a fault in the process, it appears as some variation in the output from any of the sensors monitoring the process. These sensors may refer to information about pressure, RF power or gas flow and etc. in the equipment. By relating the data from these sensors to the process condition, any abnormality in the process can be identified, but it still holds some degree of certainty. Our hypothesis in this research is to capture the features of equipment condition data from healthy process library. We can use the health data as a reference for upcoming processes and this is made possible by mathematically modeling of the acquired data. In this work we demonstrate the use of recurrent neural network (RNN) has been used. RNN is a dynamic neural network that makes the output as a function of previous inputs. In our case we have etch equipment tool set data, consisting of 22 parameters and 9 runs. This data was first synchronized using the Dynamic Time Warping (DTW) algorithm. The synchronized data from the sensors in the form of time series is then provided to RNN which trains and restructures itself according to the input and then predicts a value, one step ahead in time, which depends on the past values of data. Eight runs of process data were used to train the network, while in order to check the performance of the network, one run was used as a test input. Next, a mean squared error based probability generating function was used to assign probability of fault in each parameter by comparing the predicted and actual values of the data. In the future we will make use of the Bayesian Networks to classify the detected faults. Bayesian Networks use directed acyclic graphs that relate different parameters through their conditional dependencies in order to find inference among them. The relationships between parameters from the data will be used to generate the structure of Bayesian Network and then posterior probability of different faults will be calculated using inference algorithms.

  • PDF

Robust Recurrent Wavelet Interval Type-2 Fuzzy-Neural-Network Control for DSP-Based PMSM Servo Drive Systems

  • El-Sousy, Fayez F.M.
    • Journal of Power Electronics
    • /
    • 제13권1호
    • /
    • pp.139-160
    • /
    • 2013
  • In this paper, an intelligent robust control system (IRCS) for precision tracking control of permanent-magnet synchronous motor (PMSM) servo drives is proposed. The IRCS comprises a recurrent wavelet-based interval type-2 fuzzy-neural-network controller (RWIT2FNNC), an RWIT2FNN estimator (RWIT2FNNE) and a compensated controller. The RWIT2FNNC combines the merits of a self-constructing interval type-2 fuzzy logic system, a recurrent neural network and a wavelet neural network. Moreover, it performs the structure and parameter-learning concurrently. The RWIT2FNNC is used as the main tracking controller to mimic the ideal control law (ICL) while the RWIT2FNNE is developed to approximate an unknown dynamic function including the lumped parameter uncertainty. Furthermore, the compensated controller is designed to achieve $L_2$ tracking performance with a desired attenuation level and to deal with uncertainties including approximation errors, optimal parameter vectors and higher order terms in the Taylor series. Moreover, the adaptive learning algorithms for the compensated controller and the RWIT2FNNE are derived by using the Lyapunov stability theorem to train the parameters of the RWIT2FNNE online. A computer simulation and an experimental system are developed to validate the effectiveness of the proposed IRCS. All of the control algorithms are implemented on a TMS320C31 DSP-based control computer. The simulation and experimental results confirm that the IRCS grants robust performance and precise response regardless of load disturbances and PMSM parameters uncertainties.

감마 다층 신경망을 이용한 시스템 식별 (System Identification Using Gamma Multilayer Neural Network)

  • 고일환;원상철;최한고
    • 융합신호처리학회논문지
    • /
    • 제9권3호
    • /
    • pp.238-244
    • /
    • 2008
  • 동적 신경망은 temporal 신호처리가 요구되는 여러 분야에 사용되어 왔다. 본 논문에서는 다층 신경망의 동특성을 향상시키기 위해 감마 신경망(GAM) 다루고 있다. GAM 신경망은 순방향 다층 신경망의 히든층에 감마 메모리 커널을 사용하고 있다. GAM 신경망은 선형 및 비선형 시스템 식별을 통해 평가되었으며 상대적인 성능평가를 위해 순방향 신경망(FNN)과 리커런트 신경망(RNN)과 비교하고 있다. 실험결과에 의하면 GAM 신경망은 학습속도와 정확도에서 더 우수하게 동작하였으며, 이러한 사실은 시스템 식별에 있어서 GAM 신경망이 기존의 다른 다층 신경망보다 더 효과적인 신경망이 될 수 있음을 보여주었다.

  • PDF

변분법을 이용한 재귀신경망의 온라인 학습 (A on-line learning algorithm for recurrent neural networks using variational method)

  • 오원근;서병설
    • 제어로봇시스템학회논문지
    • /
    • 제2권1호
    • /
    • pp.21-25
    • /
    • 1996
  • In this paper we suggest a general purpose RNN training algorithm which is derived on the optimal control concepts and variational methods. First, learning is regared as an optimal control problem, then using the variational methods we obtain optimal weights which are given by a two-point boundary-value problem. Finally, the modified gradient descent algorithm is applied to RNN for on-line training. This algorithm is intended to be used on learning complex dynamic mappings between time varing I/O data. It is useful for nonlinear control, identification, and signal processing application of RNN because its storage requirement is not high and on-line learning is possible. Simulation results for a nonlinear plant identification are illustrated.

  • PDF

비선형 비행 시스템을 위한 $H_{\infty}$ 접근법 기반 적응 신경망 동적 표면 제어 (Adaptive Neural Dynamic Surface Control via $H_{\infty}$ Approach for Nonlinear Flight System)

  • 유성진;최윤호;박진배
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2007년도 제38회 하계학술대회
    • /
    • pp.1728-1729
    • /
    • 2007
  • This paper presents an adaptive neural dynamic surface control (DSC) approach with $H_{\infty}$ tracking performance for a full dynamics of a nonlinear flight system. It is assumed in this paper that model uncertainties such as structured and unstrutured uncertainties and external disturbances influence the nonlinear aircraft model. In our control system, self recurrent wavelet neural networks (SRWNNs) are used to compensate model uncertainties of the nonlinear flight system, and an adaptive DSC technique is extended for disturbance attenuation of the nonlinear flight system. From Lyapunov stability theorem, it is shown that $H_{\infty}$ performance from external disturbances can be obtained. Finally, we perform the simulation for the nonlinear six-degree-of-freedom F-16 aircraft model to confirm the effectiveness of the proposed control system.

  • PDF