http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
효율적 고차 신경회로망을 이용한 비선형 함수 근사에 대한 연구
신요안 한국통신학회 1996 韓國通信學會論文誌 Vol.21 No.1
In this paper, a higher-order feedforward neural network called ridge polynomial network (RPN) which shows good approximation capability for nonlnear continuous functions defined on compact subsets in multi-dimensional Euclidean spaces, is presented. This network provides more efficient and regular structure as compared to ordinary higher-order feedforward networks based on Gabor-Kolmogrov polynomial expansions, while maintating their fast learning property. the ridge polynomial network is a generalization of the pi-sigma network (PSN) and uses a specialform of ridge polynomials. It is shown that any multivariate polynomial can be exactly represented in this form, and thus realized by a RPN. The approximation capability of the RPNs for arbitrary continuous functions is shown by this representation theorem and the classical weierstrass polynomial approximation theorem. The RPN provides a natural mechanism for incremental function approximation based on learning algorithm of the PSN. Simulation results on several applications such as multivariate function approximation and pattern classification assert nonlinear approximation capability of the RPN.
Complex radial basis function network을 이용한 비선형 디지털 위성 통신 채널의 등화
신요안,윤병문,임영선 한국통신학회 1996 韓國通信學會論文誌 Vol.21 No.9
A digital satellite communication channel has a nonlinearity with memory due to saturation characeristis of the high poer amplifier in the satellite and transmitter/receiver linear filter used in the overall system. In this paper, we propose a complex radial basis function network(CRBFN) based adaptive equalizer for compensation of nonlinearities in digital satellite communication channels. The proposed CRBFN untilizes a complex-valued hybrid learning algorithm of k-means clustering and LMS(least mean sequare) algorithm that is an extension of Moody Darken's algorithm for real-valued data. We evaluate performance of CRBFN in terms of symbol error rates and mean squared errors nder various noise conditions for 4-PSK(phase shift keying) digital modulation schemes and compare with those of comples pth order inverse adaptive Volterra filter. The computer simulation results show that the proposed CRBFN ehibits good equalization, low computational complexity and fast learning capabilities.
점진 형성형 고차 신경회로망을 이용한 수동 해저 소나 신호의 분류
신요안 崇實大學校 生産技術硏究所 1995 論文集 Vol.25 No.1
In this paper, an incrementally constructive higher-order feedforward neural network algorithm called the ridge polynomial network, is exploited for the classification of passive oceanic sonar signals from natural sources. For the experiments, Gabor wavelet coefficients and other time and frequency information are used for the input features, and some multi-layered perceptron based algorithms are also used for the comparison as classifiers. The performance of the classifiers is measured in terms of classification accuracy in the case of zero rejection and computational complexity for the training of neural networks. The simulation results show that all the neural networks used exhibit good classification performance for a moderate-size test data set,however,the ridge polynomial network's incrementally constructive learning algorithm requires much less computational complexity.
신요안,양석철,오종옥 에스케이텔레콤 (주) 2003 Telecommunications Review Vol.0 No.-
향후 무선통신에서는 데이터 전송의 고속화 및 고품질화를 기반으로 하는 자동화된 소규모 네트워크 구축에 더욱 많은 관심이 집중될 것으로 예상된다. 본 논문에서는 이러한 추세에 발맞추어, 최근 각광받고 있는 WPAN (Wireless Personal Area Network)에 대해 표준화 단체인 IEEE 802.15 Working Group (WG)의 활동을 기반으로 기술하고자 한다. 특히, IEEE 802.15 WG에서 추구하는 연구 목표와 더불어, WPAN의 세부적인 연구를 위해 편성된 5개의 TG (Task Group)들 각각의 설립 목적과 기술 사양, 그리고 현재 활동 동향에 대해 알아보고자 한다.