• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.939-942
• /
• 1996

This paper presents a stable learning algorithm for diagonal recurrent neural network(DRNN). DRNN is applied to a problem of controlling nonlinear dynamical systems. A architecture of DRNN is a modified model of the Recurrent Neural Network(RNN) with one hidden layer, and the hidden layer is comprised of self-recurrent neurons. DRNN has considerably fewer weights than RNN. Since there is no interlinks amongs in the hidden layer. DRNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. To guarantee convergence and for faster learning, an adaptive learning rate is developed by using Lyapunov function. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed algorithm is demonstrated by computer simulation.

• 한국통신학회논문지
• /
• 제34권3C호
• /
• pp.257-267
• /
• 2009

This paper presents a training method for neural networks and the employment of MSE (mean scare error) values as the basis of a decision regarding the identity claim of a speaker in a recurrent neural networks based speaker verification system. Recurrent neural networks (RNNs) are employed to capture temporally dynamic characteristics of speech signal. In the process of supervised learning for RNNs, target outputs are automatically generated and the generated target outputs are made to represent the temporal variation of input speech sounds. To increase the capability of discriminating between the true speaker and an impostor, a discriminative training method for RNNs is presented. This paper shows the use and the effectiveness of the MSE value, which is obtained from the Euclidean distance between the target outputs and the outputs of networks for test speech sounds of a speaker, as the basis of speaker verification. In terms of equal error rates, results of experiments, which have been performed using the Korean speech database, show that the proposed speaker verification system exhibits better performance than a conventional hidden Markov model based speaker verification system.

• 전기학회논문지
• /
• 제67권11호
• /
• pp.1536-1541
• /
• 2018

For effective electricity consumption in urban railway station such as peak load shaving, it is important to know each electrical load pattern by various usage. The total electricity consumption in the urban railway substation is already measured in Korea, but the electricity consumption for each usage is not measured. The author proposed the deep learning method to estimate the electrical load pattern for each usage in the urban railway substation with public data such as weather data. GRU (gated recurrent unit), a variation on the LSTM (long short-term memory), was used, which aims to solve the vanishing gradient problem of standard a RNN (recursive neural networks). The optimal model was found and the estimation results with that were assessed.

• 한국지능시스템학회논문지
• /
• 제14권3호
• /
• pp.273-278
• /
• 2004

본 논문은 주인식기로 흔히 사용되는 HMM 인식 알고리즘을 보완하기 위한 방법으로 회귀신경회로망(Recurrent neural networks : RNN)을 적용하였다. 이 회귀신경회로망 중에서 실 시간적으로 동작이 가능하게 한 방법인 다층회귀신경예측 모델 (Multi-layer Recurrent Neural Prediction Model : MRNPM)을 사용하여 학습 및 인식기로 구현하였으며, HMM과 MRNPM 을 이용하여 Hybrid형태의 주 인식기로 설계하였다. 설계된 음성 인식 알고리즘을 잘 구별되지 않는 한국어 숫자음(13개 단어)에 대해 화자 독립형으로 인식률 테스트 한 결과 기존의 HMM인식기 보다 5%정도의 인식률 향상이 나타났다. 이 결과를 이용하여 실제 DSP(TMS320C6711) 환경 내에서 최적(인식) 코드만을 추출하여 임베디드 음성 인식 시스템을 구현하였다. 마찬가지로 임베디드 시스템의 구현 결과도 기존 단독 HMM 인식시스템보다 향상된 인식시스템을 구현할 수 있게 되었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.263-266
• /
• 1998

This paper propose a prefilter type inverse control algorithm using chaotic neural networks. Since the chaotic neural networks show robust characteristics in approximation and adaptive learning for nonlinear dynamic system, the chaotic neural networks are suitable for controlling robotic manipulators. The structure of the proposed prefilter type controller compensate velocity of the PD controller. To estimate the proposed controller, we implemented to the Cartesian space control of three-axis PUMA robot and compared the final result with recurrent neural network(RNN) controller.

• 한국음향학회지
• /
• 제42권5호
• /
• pp.395-401
• /
• 2023

음향 이벤트 검출(Sound Event Detection, SED)은 음향 신호에서 관심 있는 음향의 종류와 발생 구간을 검출하는 기술로, 음향 감시 시스템 및 모니터링 시스템 등 다양한 분야에서 활용되고 있다. 최근 음향 신호 분석에 관한 국제 경연 대회(Detection and Classification of Acoustic Scenes and Events, DCASE) Task 4를 통해 다양한 방법이 소개되고 있다. 본 연구는 다양한 영역에서 성능 향상을 이끌고 있는 Dense Convolutional Networks(DenseNet)을 음향 이벤트 검출에 적용하기 위해 설계 변수에 따른 성능 변화를 비교 및 분석한다. 실험에서는 DenseNet with Bottleneck and Compression(DenseNet-BC)와 순환신경망(Recurrent Neural Network, RNN)의 한 종류인 양방향 게이트 순환 유닛(Bidirectional Gated Recurrent Unit, Bi-GRU)을 결합한 DenseRNN 모델을 설계하고, 평균 교사 모델(Mean Teacher Model)을 통해 모델을 학습한다. DCASE task4의 성능 평가 기준에 따라 이벤트 기반 f-score를 바탕으로 설계 변수에 따른 DenseRNN의 성능 변화를 분석한다. 실험 결과에서 DenseRNN의 복잡도가 높을수록 성능이 향상되지만 일정 수준에 도달하면 유사한 성능을 보임을 확인할 수 있다. 또한, 학습과정에서 중도탈락을 적용하지 않는 경우, 모델이 효과적으로 학습됨을 확인할 수 있다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.652-654
• /
• 2023

The accurate prediction of User Equipment (UE) paths in wireless networks is crucial for improving handover mechanisms and optimizing network performance, particularly in the context of Beyond 5G and 6G networks. This paper presents a comprehensive evaluation of unidirectional and bidirectional recurrent neural network (RNN) architectures for UE path prediction. The study employs a sequence-to-sequence model designed to forecast user paths in a wireless network environment, comparing the performance of unidirectional and bidirectional RNNs. Through extensive experimentation, the paper highlights the strengths and weaknesses of each RNN architecture in terms of prediction accuracy and computational efficiency. These insights contribute to the development of more effective predictive path-based mobility management strategies, capable of addressing the challenges posed by ultra-dense cell deployments and complex network dynamics.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.269-271
• /
• 2022

최근 몇 년 동안 LSTM 블록이 있는 RNN 네트워크는 순차적 데이터를 처리하는 기계 학습 작업에 광범위하게 사용되어왔다. 이러한 네트워크는 주어진 시퀀스에서 가능성이 다음으로 가장 높은 단어를 기존 신경망보다 더 정확하게 예측할 수 있기 때문에 순차적 언어 처리 작업에서 특히 우수한 것으로 입증되었다. 이 연구는 영어와 한국어로 된 150개의 성경 시편에 대한 세 가지 다른 번역에 대해 RNN/LSTM 신경망을 훈련하였다. 그런 다음 결과 모델에 입력 단어와 길이 번호를 제공하여 훈련 중에 인식한 패턴을 기반으로 원하는 길이의 새 시편을 자동으로 생성하였다. 영어 텍스트와 한국어 텍스트에 대한 네트워크 훈련 결과를 상호 비교하고 개선할 점을 기술한다.

• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.6-10
• /
• 2021

Recognition of characters printed or marked on the PCB components from images captured using cameras is an important task in PCB components inspection systems. Previous optical character recognition (OCR) of PCB components typically consists of two stages: character segmentation and classification of each segmented character. However, character segmentation often fails due to corrupted characters, low image contrast, etc. Thus, OCR without character segmentation is desirable and increasingly used via deep neural networks. Typical implementation based on deep neural nets without character segmentation includes convolutional neural network followed by recurrent neural network (RNN). However, one disadvantage of this approach is slow execution due to RNN layers. LPRNet is a segmentation-free character recognition network with excellent accuracy proved in license plate recognition. LPRNet uses a wide convolution instead of RNN, thus enabling fast inference. In this paper, LPRNet was adapted for recognizing characters printed on PCB components with fast execution and high accuracy. Initial training with synthetic images followed by fine-tuning on real text images yielded accurate recognition. This net can be further optimized on Intel CPU using OpenVINO tool kit. The optimized version of the network can be run in real-time faster than even GPU.

• 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.