• The Journal of the Korea Contents Association
• /
• v.9 no.2
• /
• pp.97-105
• /
• 2009

This paper presents a combination of the generalized Cascade Correlation and generalized Recurrent Cascade Correlation learning algorithms. The new network will be able to grow with vertical or horizontal direction and with recurrent or without recurrent units for the quick solution of the pattern classification problem. The proposed algorithm was tested learning capability with the sigmoidal activation function and hyperbolic tangent activation function on the contact lens and balance scale standard benchmark problems. And results are compared with those obtained with Cascade Correlation and Recurrent Cascade Correlation algorithms. By the learning the new network was composed with the minimal number of the created hidden units and shows quick learning speed. Consequently it will be able to improve a learning capability.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.107-115
• /
• 2006

This paper presents a new class of activation functions for Cascade Correlation learning algorithm, which herein will be called CosGauss function. This function is a cosine modulated gaussian function. In contrast to the sigmoidal, hyperbolic tangent and gaussian functions, more ridges can be obtained by the CosGauss function. Because of the ridges, it is quickly convergent and improves a pattern recognition speed. Consequently it will be able to improve a learning capability. This function was tested with a Cascade Correlation Network on the two spirals problem and results are compared with those obtained with other activation functions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.10C
• /
• pp.836-843
• /
• 2008

In this paper we derive the theoretical performance of orthogonal STBC algorithms in spatially correlated Rayleigh fading environments and compare their performances for various correlation conditions. We first derive the theoretical BER of the orthogonal STBC algorithms for both M-ary PSK and M-ary QAM modulation schemes by using the eigenvalues of the channel correlation matrix and then investigate the effect of the spatial correlation on the performance for various transmission rates of $1{\sim}4bps/Hz$. Performance analysis illustrates that the Alamouti scheme provides the better performance than the Tarokh scheme for all the transmission rates in highly correlated fading environments with a correlation being larger than 0.9.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.2
• /
• pp.347-354
• /
• 2011

This paper presents a time-domain based asynchronous IR-UWB ranging system. This system accomplishes the ranging by detecting peaks from the outputs of a correlator implemented by a FIR filter. To discriminate the peaks due to a signal component, we use windowing for the correlated data within which the data are sorted in amplitude-ascending order and the noise level is calculated. Comparing with the recently presented frequency-domain based ranging system, we show the system structure and explain how it operates for ranging. Moreover, through the simulations, the proposed system is compared with the frequency-domain based system in terms of performance.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1990.06a
• /
• pp.788-793
• /
• 1990

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.661-662
• /
• 2016

컴퓨터비전의 한 분야인 추적은 다양한 방법론들에 근거하여 활발히 연구되어온 분야이다. 추적알고리즘은 연속되는 영상 시퀀스의 객체를 지속적으로 추적하는 방법으로, 객체의 외형 변형, 이동, 회전, 폐색등 복잡한 환경에서도 강건히 추적하는 것에 초점이 맞춰져 있다. 본 논문에서는 딥러닝의 한 부류인 CNN의 컨볼루션 레이어에서 출력되는 특징맵과 변화되는 객체에 적응적으로 대응하는 코릴레이션 필터를 결합하여 복잡한 환경에서도 객체를 추적하는 방법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.868-869
• /
• 2023

보병이 레이저로 표적을 지시하고 원격사격통제체계가 타격하는 방식의 유무인 복합체계에서 전자광학 추적장비를 통한 표적지시용 레이저 검출은 필수적이다. 이를 위해 본 연구에서는 영상기반 코릴레이션 필터를 통해 적외선 레이저를 기존의 색상기반, 기계학습 등의 기법보다 효과적으로 검출하는 방법을 구현하였다. 또한 실험을 통해 주간에는 직사광선 노이즈를 효과적으로 제거하고 200mw 출력의 적외선 레이저를 10-20m 거리에서 검출, 노이즈가 없는 야간에는 100m 이상의 거리에서 안정적으로 검출하는 것을 확인하였다. 이를 통하여 원격사격통제체계의 전자광학 추적장비를 통한 표적지시 레이저 검출 및 추적 구현의 기반을 마련하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.10
• /
• pp.2461-2469
• /
• 1997

Target detection and recognition problems, in which neural networks are widely used, require translation invariant and real-time processing in addition to the requirements that general pattern recognition problems need. This paper presents a novel architecture that meets the requirements and explains effective methodology to train the network. The proposed neural network is an architectural extension of the shared-weight neural network that is composed of the feature extraction stage followed by the pattern recognition stage. Its feature extraction stage performs correlational operation on the input with a weight kernel, and the entire neural network can be considered a nonlinear correlation filter. Therefore, the output of the proposed neural network is correlational plane with peak values at the location of the target. The architecture of this neural network is suitable for implementing with parallel or distributed computers, and this fact allows the application to the problems which require realtime processing. Net training methodology to overcome the problem caused by unbalance of the number of targets and non-targets is also introduced. To verify the performance, the proposed network is applied to detection and recognition problem of a specific automobile driving around in a parking lot. The results show no false alarms and fast processing enough to track a target that moves as fast as about 190 km per hour.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.34D no.10
• /
• pp.1-6
• /
• 1997

This paper presents the theoretical derivaion relating and image correlationcoeffcient capable of assessing image quality, with phase-error variance in antenna aperture domain. We show that when the phase-error variance of a range bin selected as an adaptive beamformer is known, the quality of the reconstructed image is predictable and moreover, the resultant correlation coeffcient is obviously greater than the derive dlower boudn. To support the derivation, real data are used for image formation where the dominant scatterer algorithm (DSA) is applied for phase compensations.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.275-278
• /
• 2002

본 논문에서는 한국의 전파환경을 도시 계획법에서 지정한 지역세분을 기초로 4개의 대분류와 8개로 소구분하여 Kor-231 모델을 제안하였다. 전파전파 특성을 측정하기 위해 슬라이딩 코릴레이션 기법을 이용한 대역확산 송${\cdot}$수신 방식으로 구현하여 수신전력, 평균 초과지연 그리고 RMS 지연확산을 가장 도시계획적으로 개발된 공업 지역과 주거지역에서 직선 도로에 마이크로셀을 배치하여 도로를 따라 진행하는 LOS와 건물들로 둘러쌓인 N-LOS에서 측정된 데이터를 분석하여 한국의 전파환경에서 잘 적용됨을 확인 하였다.