• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 전기.전자공학 학술대회 논문집
• /
• pp.457-460
• /
• 1988

We present here a numerical solution for obtaining propagation characteristics including lossess for various modes of an multi-layered optical waveguide structure. The method is based on transmission line analogy. A comparison with other method shows the our results are accurate and simple.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 춘계학술대회 학술발표 논문집
• /
• pp.49-52
• /
• 1998

Neural Network has good performance in pattern classification, control and many other fields by learning ability. However, there is effective rule or systematic approach to determine optimal structure. In this paper, we propose a new method to find optimal structure of feed-forward multi-layer neural network as a kind of pruning method. That eliminating redundant elements of neural network. To find redundant elements we analysis error and weight changing with Rough Set Theory, in condition of executing back-propagation leaning algorithm.

• 대한전기학회논문지
• /
• 제45권3호
• /
• pp.444-450
• /
• 1996

A digital hardware architecture for artificial neural network with learning capability is described in this paper. It is a modified hardware architecture known as HANNIBAL(Hardware Architecture for Neural Networks Implementing Back propagation Algorithm Learning). For implementing an efficient neural network hardware, we analyzed various type of multiplier which is major function block of neuro-processor cell. With this result, we design a efficient digital neural network hardware using serial/parallel multiplier, and test the operation. We also analyze the hardware efficiency with logic level simulation. (author). refs., figs., tabs.

• 전기학회논문지P
• /
• 제53권3호
• /
• pp.129-133
• /
• 2004

As In DS/CDMA(direct sequence code division multiple access) system, the system capacity is limited by multiple access interference(MAI), and self-interference(SI) resulting from the multi-path propagation of the desired user signal. This paper, which the approximated analytic chip waveforms are nearly the same as the computer generated chip waveforms are shown. And then, the BER(Bit Error Rate) performances in CDMA system using the approximated analytic chip waveforms are shown.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2008년도 춘계학술발표논문집
• /
• pp.258-260
• /
• 2008

본 논문에서 다중경로 전파환경에서 전파특성을 연구하였다. 목표지점에서 전계의 세기는 직접파와 지면 반사파의 합으로 구성된다. 이 논문에서는 지면의 반사를 고려하여 목표물 근처 공간의 3차원 전계분포를 계산하는 프로그램을 개발하였다. 실제 목표물의 궤적에 따라 목표물의 수신기에서의 신호세기를 예측하는 3차원 모델을 개발 하였다.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 FIFTH WESTERN PACIFIC REGIONAL ACOUSTICS CONFERENCE SEOUL KOREA
• /
• pp.1003-1008
• /
• 1994

This paper is about an experiment of speaker-independent automation Korean spoken words recognition using Multi-Layered Perceptron and Error Back-propagation algorithm. The words were not segmented into syllables or phonemes, and some feature components extracted from the words in equal gap were applied to the neural network. This paper tried to find out the optimum conditions through various experiment which are comparison between total and pre-classified training.

• 한국정보통신학회논문지
• /
• 제17권7호
• /
• pp.1577-1582
• /
• 2013

본 논문에서는 수조에서 실험을 통해 획득한 데이터를 이용하여 MIMO (Multi-Input Multi-Output) 수중음향통신의 성능을 분석하였다. 이를 위하여 먼저 여러 송수신 위치에서 채널 전달 특성을 측정하였다. 송신신호는 QPSK (Quadrature Phase Shift Keying)로 변조하였으며, 수신신호는 Zero Forcing 등화기 등을 포함하는 검출기를 거쳐 복원되었다. 실험이 이루어진 수조 환경이 물리적으로 폐쇄된 매우 심한 다중 경로 전달 환경이어서 최대 30~40 ms의 지연 현상이 나타났다. 실험 결과 송신 및 수신 센서가 각각 두 개인 $2{\times}2$ MIMO 시스템을 사용하였을 때 채널 특성으로 인해 비트 오차율이 비교적 크게 나타났지만 SISO (Single-Input Single-Output) 시스템에 비해 약 15% 정도 향상된 성능을 갖는 것을 확인하였다.

• 한국통신학회논문지
• /
• 제16권2호
• /
• pp.128-136
• /
• 1991

A neural network of multi layer perception type, learned by error back propagation learning rule, is generally used for the verification or clustering of similar type of patterns. When learning is completed, the network has a constant value of output depending on a pattern. This paper shows that the intensity of neuron's out put can be controlled by a function which intensifies the excitatory interconnection coefficients or the inhibitory one between neurons in output layer and those in hidden layer. In this paper the value of factor in the function to control the output is derived from the know values of the neural network after learning is completed And also this paper show that the amount of an increased neuron's output in output layer by arbitary value of the factor is derived. For the applications increased recognition performance of a pattern than has distortion is introduced and the output of partially damaged neurons are first managed and this paper shows that the reduced recognition performance can be recovered.

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제54권7호
• /
• pp.332-338
• /
• 2005

PD(Partial Discharge) signal emitted from PD sources has their intrinsic features in the region of time and frequency STFT(Short Time Fourier Transform) shows time-frequency distribution at the same time. 2-Dimensional matrices(33$\times$77) from STFT for PD pulse signals are a good feature vectors and can be decreased in dimension by wavelet 2D data compression technique. Decreased feature vectors(13$\times$24) were used as inputs of Back-propagation ANN(Artificial Neural Network) for discrimination of Multi-PD sources(air discharge sources(3), surface discharge(1)). They are a good feature vectors for discriminating Multi-PD sources in the air.

• 한국우주과학회:학술대회논문집(한국우주과학회보)
• /
• 한국우주과학회 2008년도 한국우주과학회보 제17권2호
• /
• pp.26.4-27
• /
• 2008

The completion ('initiation' de facto) of the KASI Orbit Propagator and Estimator (KASIOPEA) has been delayed for several reasons unfortunately. Due to the lack of working staffs and the Division priority rearrangement, the initial plan was dismantled and ignored for many years. However, fundamental researches regarding the essential parts of KASIOPEA has been done by author. The numerical integration module of the KASIOPEA is the most sensitive part in the precision of the final output in general. There is no silver bullet in the numerical integration in an orbit propagation as a non-stiff ODE case. Many numerical integration method like single-step methods, multi-step method, and extrapolation methods have been used in overly populated orbit propagator or estimator. In this study, several popular methods from single-step, multi-step, and extrapolation methods have been tested in numerical accuracy and stability.