• Communications for Statistical Applications and Methods
• /
• 제9권1호
• /
• pp.155-166
• /
• 2002

Neural networks have been studied as a popular tool for classification and they are very flexible. Also, they are used for many applications of pattern classification and pattern recognition. This paper focuses on Bayesian approach to feed-forward neural networks with single hidden layer of units with logistic activation. In this model, we are interested in deciding the number of nodes of neural network model with p input units, one hidden layer with m hidden nodes and one output unit in Bayesian setup for fixed m. Here, we use the latent variable into the prior of the coefficient regression, and we introduce the 'sequential step' which is based on the idea of the data augmentation by Tanner and Wong(1787). The MCMC method(Gibbs sampler and Metropolish algorithm) can be used to overcome the complicated Bayesian computation. Finally, a proposed method is applied to a simulated data.

• 한국통신학회논문지
• /
• 제30권4C호
• /
• pp.185-190
• /
• 2005

IS-95와 IMT-2000 시스템에서 사용되고 있는 여러 종류의 길쌈 부호기를 부호율 1/2, 구속장 3인 길쌈 부호기로 한정하여, 비터비 복호기에 복호길이 6인 Sliding-Window와 Neural Network의 LVQ(Learning Vector Quantization)및 PVSL(Prototype Vectors Selecting Logic)을 적용하여 순방향 실시간 복호기를 구현한다. 이론적으로 제한된 AWGN 채널환경에서의 심볼 전송전력 $S/(N_{0}/2)=1$을 성능비교 조건으로 하여 순방향 실시간 복호기와 기존의 비터비 복호기의 $강\cdot연판정$ BER 성능과 하드웨어 구성을 $비교\cdot분석$하여, 본 논문에서 제시된 순방향 실시간 복호기의 BER 성능의 우수성과 비화통신의 장점 및 하드웨어 구성의 단순합을 검증하였다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.464-467
• /
• 1996

This paper aims to exploit inter/intra-speaker phoneme sub-class variations as criteria for adaptation in a phoneme recognition system based on a novel neural network architecture. Using a subcluster neural network design based on the One-Class-in-One-Network (OCON) feed forward subnets, similar to those proposed by Kung (2) and Jou (1), joined by a common front-end layer. the idea is to adapt only the neurons within the common front-end layer of the network. Consequently resulting in an adaptation which can be concentrated primarily on the speakers vocal characteristics. Since the adaptation occurs in an area common to all classes, convergence on a single class will improve the recognition of the remaining classes in the network. Results show that adaptation towards a phoneme, in the vowel sub-class, for speakers MDABO and MWBTO Improve the recognition of remaining vowel sub-class phonemes from the same speaker

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

• Nuclear Engineering and Technology
• /
• 제54권11호
• /
• pp.4209-4214
• /
• 2022

Precise modelling of the interaction of ions with materials is important for many applications including material characterization, ion implantation in devices, thermonuclear fusion, hadron therapy, secondary particle production (e.g. neutron), etc. In this study, a new approach using the Geant4 toolkit in combination with the Bayesian regularization (BR) learning algorithm of the feed-forward neural network (FFNN) is developed to estimate the range of ions in materials accurately and quickly. The different incident ions at different energies are interacted with the target materials. The Geant4 is utilized to model the interactions and to calculate the range of the ions. Afterward, the appropriate architecture of the FFNN-BR with the relevant input features is utilized to learn the modelled ranges and to estimate the new ranges for the new cases. The notable achievements of the proposed approach are: 1- The range of ions in different materials is given as quickly as possible and the time required for estimating the ranges can be neglected (i.e. less than 0.01 s by a typical personal computer). 2- The proposed approach can generalize its ability for estimating the new untrained cases. 3- There is no need for a pre-made lookup table for the estimation of the range values.

• Water Engineering Research
• /
• 제4권2호
• /
• pp.59-68
• /
• 2003

The applicabilities and validities of two methodologies fur the prediction of THM (trihalomethane) formation in a water pipeline system were proposed and discussed. One is the multiple regression technique and the other is an artificial neural network technique. There are many factors which influence water quality, especially THMs formations in water pipeline systems. In this study, the prediction models of THM formation in water pipeline systems are developed based on the independent variables proposed by American Water Works Association(AWWA). Multiple linear/nonlinear regression models are estimated and three layer feed-forward artificial neural networks have been used to predict the THM formation in a water pipeline system. Input parameters of the models consist of organic compounds measured in water pipeline systems such as TOC, DOC and UV254. Also, the reaction time to each measuring site along pipeline is used as input parameter calculated by a hydraulic analysis. Using these variables as model parameters, four models are developed. And the predicted results from the four developed models are compared statistically to the measured THMs data set. It is shown that the artificial neural network approaches are much superior to the conventional regression approaches and that the developed models by neural network can be used more efficiently and reproduce more accurately the THMs formation in water pipeline systems, than the conventional regression methods proposed by AWWA.

• 한국컴퓨터정보학회논문지
• /
• 제4권1호
• /
• pp.62-67
• /
• 1999

신경회로망은 입력층. 출력층, 하나 이상의 은닉층으로 구성된 네드워크이다. 학습능력과 근사화 능력으로 말미암아 신경회로망은 패턴인식 및 시스템제어분야에서 많이 사용되고 있다. Elman 신경회로망은 J. Elman에 의해 제안되었으며, recurrent network의 형태로 구성되어 있다. Elman 신경회로망은 기존의 신경회로망에 context층을 새로 추가하여, 은닉층의 출력을 context층의 입력으로 피드백 하는 구조로 되어 있다. 본 논문에서는 Elman 신경회로망을 변형한 형태로, 은닉층 뿐 만 아니라 출력층의 출력도 context층으로 피드백 하는 새로운 형태의 Elman 신경회로망을 제안한다. 제안한 방식의 유용성을 확인하기 위해 X-Y cartesian에 적용하여 시뮬레이션한 결과는 기존의 신경회로망 및 Elman 신경회로망 보다 우수한 방식임을 보여 주고 있다.

• 한국컴퓨터정보학회논문지
• /
• 제4권3호
• /
• pp.67-72
• /
• 1999

신경회로망은 학습능력과 근사화 능력으로 말미암아 패턴인식 및 시스템제어분야에서 많이 사용되고 있으며, 입력층. 출력층. 하나 이상의 은닉층으로 구성된 네드워크이다. Elman 신경회로망은 J. Elman에 의해 제안되었으며. recurrent network의 형태로 구성되어 있다. Elman 신경회로망은 기존의 신경회로망에 context층을 새로 추가하여, 은닉층의 출력을 context층의 입력으로 피드백 하는 구조로 되어 있다. 본 논문에서는 새로운 형태의 Elman 신경회로망을 제안한다. 제안한 방식은 Elman 신경회로망을 변형한 형태로. 은닉층 뿐 만 아니라 출력층의 출력도 context층으로 피드백 하는 형태이다. 제안한 방식의 유용성을 확인하기 위해 multi target system에 적용한다. 시뮬레이션 결과는 제안한 방식이 기존의 신경회로망 및 Elman 신경회로망 보다 우수한 방식임을 보여 주고 있다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.516-518
• /
• 1999

This paper presents an feed-forward neural network design instead PI controller for the speed control of an Induction Motor. The design employs the training strategy with Neural Network Controller(NNC) and Neural Network Emulator(NNE). Emulator identifies the motor by simulating the input and output map. In order to update the weights of the Controller. Emulator supplies the error path to the output stage of the controller using backpropagation algorithm. and then Controller produces an adequate output to the system due to neural networks learning capability. Therefore it becomes adjustable to the system with changing characteristics caused by a load. The speed control based on neural networks for induction motor is implemented by a vector controlled induction motor. The simulation results demonstrate that actual motor speed with neural network system well follows the reference speed minimizing the error and is available to implement on the vector control theory.

• 한국컴퓨터정보학회논문지
• /
• 제26권1호
• /
• pp.69-76
• /
• 2021

최근 특이성 교란 미적분 경계값 문제를 해결하기 위해 신경회로망 접근이 연구되고 있다. 특히 다양한 학습 알고리즘을 가진 백프로파게이션 알고리즘에 의해 훈련하는 피드-포워드 신경회로망의 이론적 모델이 제시되고 있으며, 딥러닝, 전이학습, 연합학습 등의 신경회로망 모델이 매우 빠르게 개발되고 있다. 본 논문의 목적은 특이성 교란 문제를 점근법적 방법과 함께 해결하기 위해 고도의 정확성과 속도를 가진 신경회로망 접근법에 관해 연구하는 것이다. 이를 위해 본 논문에서는 특이성 교란문제의 결과치와 교란되지 않은 문제의 결과치의 차이에 대해 신경회로망 접근 식을 사용하여 시뮬레이션 하였고 신경회로망 접근식의 효율성도 제시하였다. 결론적으로 특이성 교란 문제를 수식이 아닌 단순한 신경회로망 접근으로 효율적으로 해결할 수 있음을 제시한 것이 본 논문의 주요 기여사항이다.