• 한국음향학회지
• /
• 제18권3호
• /
• pp.62-67
• /
• 1999

본 논문은 회귀신경망을 이용한 음성인식에 관한 연구이다. 예측형 신경망으로 음절단위로 모델링한 후 미지의 입력음성에 대하여 예측오차가 최소가 되는 모델을 인식결과로 한다. 이를 위해서 예측형으로 구성된 신경망에 음성의 시변성을 신경망 내부에 흡수시키기 위해서 회귀구조의 동적인 신경망인 회귀예측신경망을 구성하고 Elman과 Jordan이 제안한 회귀구조에 따라 인식성능을 서로 비교하였다. 음성DB는 ETRI의 샘돌이 음성 데이터를 사용하였다. 그리고, 신경망의 최적모델을 구하기 위하여 예측차수와 은닉층 유니트 수의 변화에 따른 인식률의 변화와 문맥층에서 자기회귀계수를 두어 이전의 값들이 문맥층에서 누적되도록 하였을 경우에 대한 인식률의 변화를 비교하였다. 실험결과, 최적의 예측차수, 은닉층 유니트수, 자기회귀계수는 신경망의 구조에 따라 차이가 나타났으며, 전반적으로 Jordan망이 Elman망보다 인식률이 높았으며, 자기회귀계수에 대한 영향은 신경망의 구조와 계수값에 따라 불규칙하게 나타났다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2008년도 추계학술대회 논문집
• /
• pp.127-128
• /
• 2008

• International Journal of Control, Automation, and Systems
• /
• 제6권5호
• /
• pp.755-766
• /
• 2008

This study presents a recurrent compensatory fuzzy neural network (RCFNN) for dynamic system identification. The proposed RCFNN uses a compensatory fuzzy reasoning method, and has feedback connections added to the rule layer of the RCFNN. The compensatory fuzzy reasoning method can make the fuzzy logic system more effective, and the additional feedback connections can solve temporal problems as well. Moreover, an online learning algorithm is demonstrated to automatically construct the RCFNN. The RCFNN initially contains no rules. The rules are created and adapted as online learning proceeds via simultaneous structure and parameter learning. Structure learning is based on the measure of degree and parameter learning is based on the gradient descent algorithm. The simulation results from identifying dynamic systems demonstrate that the convergence speed of the proposed method exceeds that of conventional methods. Moreover, the number of adjustable parameters of the proposed method is less than the other recurrent methods.

• Journal of Power Electronics
• /
• 제14권5호
• /
• pp.1008-1027
• /
• 2014

An electric scooter with a V-belt continuously variable transmission (CVT) driven by a permanent magnet synchronous motor (PMSM) has a lot of nonlinear and time-varying characteristics, and accurate dynamic models are difficult to establish for linear controller designs. A PMSM servo-drive electric scooter controlled by a novel hybrid modified recurrent Legendre neural network (NN) control system is proposed to solve difficulties of linear controllers under the occurrence of nonlinear load disturbances and parameters variations. Firstly, the system structure of a V-belt CVT driven electric scooter using a PMSM servo drive is established. Secondly, the novel hybrid modified recurrent Legendre NN control system, which consists of an inspector control, a modified recurrent Legendre NN control with an adaptation law, and a recouped control with an estimation law, is proposed to improve its performance. Moreover, the on-line parameter tuning method of the modified recurrent Legendre NN is derived according to the Lyapunov stability theorem and the gradient descent method. Furthermore, two optimal learning rates for the modified recurrent Legendre NN are derived to speed up the parameter convergence. Finally, comparative studies are carried out to show the effectiveness of the proposed control scheme through experimental results.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2000년도 춘계학술대회 학술발표 논문집
• /
• pp.195-198
• /
• 2000

We propose a new wavelet neural network structure, for which we apply new recurrent nodes to the network, in this paper for the dynamic system identification and control. We will construct the wavelet neural network by using wavelet frame function. The function does not have the best approximation property, but it may be possible to apply some modification to the structure of the network because the constriction of orthogonality is loosened a little. This wavelet neural network we propose can obtain previous state information by its structure of the network without any addition of input, though the conventional wavelet network needs additional previous state input for the improvement of the dynamic performance. In numerical experience, the performance of the new wavelet neural network we propose in the nonlinear system with uncertainity of parameter Is equal to that of the wavelet network which used the additional previous information input, superior to that of the conventional wavelet network.

• 전기학회논문지P
• /
• 제59권2호
• /
• pp.163-172
• /
• 2010

A robust positioning control system has been studied using a friction parameter observer and a recurrent fuzzy neural network based on the sliding model. To estimate a nonlinear friction parameters of the LuGre friction model, a dual friction model-based observer is introduced. In addition, an approximating method for a system uncertainty has been developed using a recurrent fuzzy neural network technique to improve positioning performance. Experimental results have been presented to validate the performance of a proposed intelligent compensation scheme.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.423-433
• /
• 1996

This study was conducted to predict the drafts of various tillage tools with a model tool and a neural network. Drafts of tillage tools were measured and a time lagged recurrent neural network was developed. The neural network had a structure to predict dynamic draft, having a function of one step ahead prediction . The results showed the model tool draft had linear relations with high coefficient of determinations to the drafts of the tillage tools. Also, the drafts of tillage tools were successfully predicted by the developed neural network.

• 한국지능시스템학회논문지
• /
• 제13권3호
• /
• pp.334-341
• /
• 2003

본 논문에서는 신경망제어기의 출력을 보상하는 퍼지보상기를 갖는 리커런트 시간 지연 신경망(RTDNN) 제어기를 제안하였다. 학습이 완료된 신경망제어기를 사용하더라도 예상치 못한 외란으로 인해 플랜트의 출력이 좋지 못한 경우가 있는데, 이것을 적절하게 조절해 주기 위해 퍼지보상기를 사용하여 원하는 결과를 얻을 수 있도록 하였다. 그리고 플랜트의 역모델 신경망을 학습시킨 결과를 이용하여 주 신경망의 가중치를 변경시킴으로서 원하는 플랜트의 동적 특성을 얻게 된다. 2차 플랜트를 통한 모의실험 결과가 시간 지연 신경망(TDNN)제어기보다 더 좋은 응답 특성을 가짐을 확인할 수 있다. 제안한 제어기의 성능을 확인하기 위해 유압 서보시스템을 대상으로 DSP 프로세서를 사용하여 구현한 후 실험결과를 통하여 제안된 방법의 유용성을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.538-561
• /
• 2020

Recommender Systems (RecSys) have a major role in e-commerce for recommending products, which they may like for every user and thus improve their business aspects. Although many types of RecSyss are there in the research field, the state of the art RecSys has focused on finding the user similarity based on sequence (e.g. purchase history, movie-watching history) analyzing and prediction techniques like Recurrent Neural Network in Deep learning. That is RecSys has considered as a sequence prediction problem. However, evaluation of similarities among the customers is challenging while considering temporal aspects, context and multi-component ratings of the item-records in the customer sequences. For addressing this issue, we are proposing a Deep Learning based model which learns customer similarity directly from the sequence to sequence similarity as well as item to item similarity by considering all features of the item, contexts, and rating components using Dynamic Temporal Warping(DTW) distance measure for dynamic temporal matching and 2D-GRU (Two Dimensional-Gated Recurrent Unit) architecture. This will overcome the limitation of non-linearity in the time dimension while measuring the similarity, and the find patterns more accurately and speedily from temporal and spatial contexts. Experiment on the real world movie data set LDOS-CoMoDa demonstrates the efficacy and promising utility of the proposed personalized RecSys architecture.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 춘계학술대회 학술발표 논문집
• /
• pp.259-262
• /
• 1997

This paper presents a visual servoing of RV-M2 robot manipulators to track and grasp moving object, using pruned dynamic recurrent neural networks(DRNN). The object is stationary in the robot work space and the robot is tracking and grasping the object by using CCD camera mounted on the end-effector. In order to optimize the structure of DRNN, we decide the node whether delete or add, by mutation probability, first in case of delete node, the node which have minimum sum of input weight is actually deleted, and then in case of add node, the weight is connected according to the number of case which added node can reach the other nodes. Using evolutionary programming(EP) that search the struture and weight of the DRNN, and evolution strategies(ES) which train the weight of neuron, we pruned the net structure of DRNN. We applied the DRNN to the Visual Servoing of a robot manipulators to control position and orientation of end-effector, and the validity and effectiveness of the pro osed control scheme will be verified by computer simulations.