• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.53-63
• /
• 2004

Recurrent-Cascade-Correlation(RCC) is a supervised teaming algorithm that automatically determines the size and topology of the network. RCC adds new hidden neurons one by one and creates a multi-layer structure in which each hidden layer has only one neuron. By second order RCC, new hidden neurons are added to only one hidden layer. These created neurons are not connected to each other. We present a generalization of the RCC Architecture by combining the standard RCC Architecture and the second order RCC Architecture. Whenever a hidden neuron has to be added, the new RCC teaming algorithm automatically determines whether the network topology grows vertically or horizontally. This new algorithm using sigmoid, tanh and new activation functions was tested with the morse-benchmark-problem. Therefore we recognized that the number of hidden neurons was decreased by the experiments of the RCC network generalization which used the activation functions.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.12-19
• /
• 2017

In this paper a super-resolution time delay estimation algorithm that estimates the time delays of spread spectrum signals using sparse signal reconstruction approach is introduced. So far, the correlation method has been mostly used to estimate the time delays of spread spectrum signals. However it fails to accurately estimate the time delays in the case where the signals are spaced within approximately 1 PN chip duration and a further processing should be applied to the correlation outputs in order to enhance the resolution capability. Recently sparse signal approaches attract much interest in the area of directions-of-arrival estimation, of which SPICE is the most representative. Thus we introduce a super-resolution time delay estimation algorithm based on the SPICE approach and compare its performance with that of MUSIC algorithm by applying them to the ISO/IEC 24730-2.1 RTLS system.

• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.10-18
• /
• 2010

This paper presents a optimization of sigmoid activation function parameter using genetic algorithms and pattern recognition analysis in input space of two spirals benchmark problem. To experiment, cascade correlation learning algorithm is used. In the first experiment, normal sigmoid activation function is used to analyze the pattern classification in input space of the two spirals problem. In the second experiment, sigmoid activation functions using different fixed values of the parameters are composed of 8 pools. In the third experiment, displacement of the sigmoid function to determine the value of the three parameters is obtained using genetic algorithms. The parameter values applied to the sigmoid activation functions for candidate neurons are used. To evaluate the performance of these algorithms, each step of the training input pattern classification shows the shape of the two spirals.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.318-320
• /
• 1999

본 논문에서는 디지털 카메라를 통해 얻어진 자동차 영상으로부터 이산코사인변환(Discrete Cosin Transform : DCT)를 이용한 자동차번호판 추출방법을 제안한다. 번호판은 문자와 배경으로 이루어져 있으며 번호판 내에는 문자들이 조밀하게 모여 있다는 특징과 번호판 영역이 직사각형으로 되어 있다는 것을 이용하여 DCT에 의해서 자동차영상에서 수직, 수평, 대각선 성분만을 추출한후 이 추출된 에지영상에서 코릴레이션(Correlation)을 이용하여 번호판영역을 검출하고 이 검출된 번호판영역을 투영 히스토그램(Histogram)에 의해서 날씨가 흐리거나 아주 밝거나 밤에 찍은 영상들에 대해서는 번호판 추출이 힘들었다. 그러나 제안된 본 논문은 날씨와 납과 밤에 상관없이 일관된 번호판 영상을 추출할 수 있었다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.11
• /
• pp.83-88
• /
• 2011

The spectral field data on the observation planes inside a mode stirred chamber have been computed by using the FDTD method. They can describe the directional dependence of all supported modes in the reverberation chamber (RC). Correlation coefficients have been found to evaluate the stirring effects. The correlation coefficients were obtained and compared for three different sizes of stirrers and statistical uniformity was investigated.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.646-649
• /
• 2011

Differential detection algorithm for DBO-CSS based on maximum signal energy detection (MSED) using viterbi algorithm is proposed. In order to mitigate SNR degradation caused by differential decoding, a modified viterbi algorithm with so called correlation metric (CM) in every state is proposed. It is shown that the performance gain of the proposed algorithm when compared with that of the conventional differential detection with the block decoding algorithm is about 2.5dB at BER = $10^{-5}$.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1724-1733
• /
• 2014

This paper presents a pattern recognition analysis of two spirals problem and optimization of Cascade Correlation learning algorithm using in combination with a non-monotone function as CosExp(cosine-modulated symmetric exponential function) and a monotone function as sigmoid function. In addition, the algorithm's optimization is attempted. By using genetic algorithms the optimization of the algorithm will attempt. In the first experiment, by using CosExp activation function for candidate neurons of the learning algorithm is analyzed the recognized pattern in input space of the two spirals problem. In the second experiment, CosExp function for output neurons is used. In the third experiment, the sigmoid activation functions with various parameters for candidate neurons in 8 pools and CosExp function for output neurons are used. In the fourth experiment, the parameters are composed of 8 pools and displacement of the sigmoid function to determine the value of the three parameters is obtained using genetic algorithms. The parameter values applied to the sigmoid activation functions for candidate neurons are used. To evaluate the performance of these algorithms, each step of the training input pattern classification shows the shape of the two spirals. In the optimizing process, the number of hidden neurons was reduced from 28 to15, and finally the learning algorithm with 12 hidden neurons was optimized.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.7
• /
• pp.25-36
• /
• 2008

The plane strain test can reproduce the real field condition and failure behavior precisely over other laboratory shear tests. Accordingly, this test has been utilized to investigate the shearing behaviors associated with overall failure behavior and local deformation of soils. However, most plane strain tests have been carried out with restrained end plates due to difficulties in manufacturing the equipment and also performing it. This restraint induces different results with real field because of shear stress on end plates. In this study, plane strain tests with/without bottom plate restraint were performed on Jumunjin-sand. The measurement of overall and local deformation was accomplished by digital image correlation technique as well as external LVDT. By applying digital image correlation method using two consecutive images captured through the transparent wall, local deformation behavior of various parts inside the specimen was estimated. And the formation and development of shear band caused by the restrained effect of end plate and the deformation mechanism of sand under plane strain condition were examined.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.03a
• /
• pp.22-33
• /
• 2008

The plane strain test has been used widely in order to examine the stress-strain relation and failure behavior. Its advantages are more realistic simulation of deformation and failure behaviors of soils. Most plane strain tests have been carried out with restrained end plates due to difficulties in manufacturing the equipment with free end condition and also performing it. In this study, plane strain tests with/without bottom plate restraint were performed on Jumunjin-sand. The measurement of overall and local deformation was accomplished by digital image correlation technique as well as external LVDT. By applying digital image correlation method using two consecutive images captured through the transparent wall, local deformation behavior of various parts inside the specimen was estimated. From digital image analysis result, the restrained effect of end plate was examined about formation and development of shear band, and deformation mechanism of sand under plane strain condition.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.115-122
• /
• 2012

We present here a new class of activation functions for neural networks, which herein will be called CosGauss function. This function is a cosine-modulated gaussian function. In contrast to the sigmoidal-, hyperbolic tangent- and gaussian activation functions, more ridges can be obtained by the CosGauss function. It will be proven that this function can be used to aproximate polynomials and step functions. The CosGauss function was tested with a Cascade-Correlation-Network of the multilayer structure on the Tic-Tac-Toe game and iris plants problems, and results are compared with those obtained with other activation functions.