• Journal of the Korean Data and Information Science Society
• /
• v.15 no.2
• /
• pp.477-483
• /
• 2004

One of the major paradigms for supervised learning in neural network community is back-propagation learning. The standard implementations of back-propagation learning are optimal under the assumptions of identical and independent Gaussian noise. In this paper, for regression function estimation, we introduce $\varepsilon-insensitive$ back-propagation learning algorithm, which corresponds to minimizing the least absolute error. We compare this algorithm with support vector machine(SVM), which is another $\varepsilon-insensitive$ supervised learning algorithm and has been very successful in pattern recognition and function estimation problems. For comparison, we consider a more realistic model would allow the noise variance itself to depend on the input variables.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.1041-1044
• /
• 2000

The enhancement to the back-propagation algorithm presented in this paper has resulted from the need to extract sparsely connected networks from networks employing product terms. The enhancement works in conjunction with the back-propagation weight update process, so that the actions of weight zeroing and weight stimulation enhance each other. It is shown that the error measure, can also be interpreted as rate of weight change (as opposed to ${\Delta}W_{ij}$), and consequently used to determine when weights have reached a stable state. Weights judged to be stable are then compared to a zero weight threshold. Should they fall below this threshold, then the weight in question is zeroed. Simulation of such a system is shown to return improved learning rates and reduce network connection requirements, with respect to the optimal network solution, trained using the normal back-propagation algorithm for Multi-Layer Perceptron (MLP), Higher Order Neural Network (HONN) and Sigma-Pi networks.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.119-122
• /
• 2011

The Stereo vision using belief propagation algorithm that has been studied recently yields good performance in disparity extraction. In this paper, BP algorithm is proved theoretically to high precision for a stereo matching algorithm. We derive disparity map from stereo image by using Belief Propagation (BP) algorithm and area-based matching algorithm. Two algorithms are compared using stereo images provided by Middlebury web site. Disparity map error rate decreased from 52.3% to 2.3%.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06d
• /
• pp.106-108
• /
• 2006

본 논문에서는 오버레이 네트워크 환경에서 비디오 스트리밍 서비스의 성능을 향상시키기 위한 수직 핸드오버 메커니즘을 제안한다. 본 논문에서는 error propagation 문제를 완화함으로써 비디오 스트리밍 서비스의 성능을 향상시킨다. 이를 위해 프레임들의 전송 경로를 유형별로 분리하고, 프레임들의 손실률을 최소화하는 재전송 정책을 사용하며, forced 수직 핸드오버 시 멀티캐스팅 방법을 사용하였다. 또한 stability period 정의하여 핑퐁 현상이 전송성능에 미치는 영향을 줄였다. 시뮬레이션을 통해 제안하는 방안이 error propagation 문제를 개선함으로써 이동 사용자에게 끊김없는 비디오 스트리밍 서비스를 제공함을 알 수 있었다.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.671-674
• /
• 2004

We propose accurate classification method of EEG signals during mental tasks. In the experimental task, the tasks of subjects show 3 major measurements; there are mathematical tasks, color decision tasks, and Chinese phrase tasks. The classifier implemented for this work is a feed-forward neural network that trained with the error back-propagation algorithm. The new BCI system is proposed by using neural network. In this system, tr e architecture of the neural network is composed of three layers with a feed-forward network, which implements the error back propagation-learning algorithm. By applying this algorithm to 4 subjects, we achieved $95{\%}$ classification rates. The results for BCI mathematical task experiments show performance better than those of the Chinese phrase tasks. The selection time of each task depends on the mental task of subjects. We expect that the proposed detection method can be a basic technology for brain-computer interface by combining with left/right hand movement or yes/no discrimination methods.

• Proceedings of the KIPE Conference
• /
• 2000.07a
• /
• pp.620-623
• /
• 2000

A very simple control approach using neural network for the robust position control of a Permanent Magnet Synchronous Motor(PMSM) is presented The linear quadratic controller plus feedforward neural network is employed to obtain the robust PMSM system approximately linearized using field-orientation method for an AC servo. The neural network is trained in on-line phases and this neural network is composed by a fedforward recall and error back-propagation training. Since the total number of nodes are only eight this system can be easily realized by the general microprocessor. During the normal operation the input-output response is sampled and the weighting value is trained multi-times by error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. And the state space analysis is performed to obtain the state feedback gains systematically. IN addition the robustness is also obtained without affecting overall system response. This method is realized by a floating-point Digital Singal Processor DS1102 Board (TMS320C31) The basic DSP software is used to write C program which is compiled by using ANSI-C style function prototypes.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.774-783
• /
• 2010

Many chaos-based encryption methods have been presented and discussed in the last two decades, but very few of them are suitable to secure transmission on noisy channels or respect the standard of the National Institute of Standards and Technology (NIST). This paper tackles the problem and presents a novel chaos-based cryptosystem for secure transmitted images. The proposed cryptosystem overcomes the drawbacks of existing chaotic algorithms such as the Socek, Xiang, Yang, and Wong methods. It takes advantage of the increasingly complex behavior of perturbed chaotic signals. The perturbing orbit technique improves the dynamic statistical properties of generated chaotic sequences, permits the proposed algorithm reaching higher performance, and avoids the problem of error propagation. Finally, many standard tools, such as NIST tests, are used to quantify the security level of the proposed cryptosystem, and experimental results prove that the suggested cryptosystem has a high security level, lower correlation coefficients, and improved entropy.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2001.10a
• /
• pp.59-64
• /
• 2001

The objectives of the thesis are to propose a pattern classification method for remote sensing data using artificial neural network. First, we apply the error back propagation algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. Using the training data set and the error back propagation algorithm, a layered neural network is trained such that the training pattern are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of Landsat TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method.

• International Journal of Contents
• /
• v.12 no.1
• /
• pp.49-53
• /
• 2016

"Hahoe Village" in Andong region is an UNESCO World Heritage Site. It should be protected against various disasters such as fire, flooding, earthquake, etc. Among these disasters, flooding has drastic impact on the lives and properties in a wide area. Since "Hahoe Village" is adjacent to Nakdong River, it is important to monitor the water level near the village. In this paper, we developed a hydrological modelling using multi-layer perceptron (MLP) to predict the water level of Nakdong River near "Hahoe Village". To develop the prediction model, error back-propagation (EBP) algorithm was used to train the MLP with water level data near the village and rainfall data at the upper reaches of the village. After training with data in 2012 and 2013, we verified the prediction performance of MLP with untrained data in 2014.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.177.4-177
• /
• 2001

In this paper, we propose a new type of nonlinear fixed interval smoothing filter which is modified from the existing nonlinear smoothing filter. A nonlinear smoothing filter is derived from two-filter formulas. For the backward filter, the propagation and update equation of error states are derived. Particularly the modified update equation of the backward filter use the estimated error terms from the forward filter. Smoothing algorithm is altered into the compatible form with the new type of the backward fitter. An advantage of the proposed algorithm is more efficient than the existing one because propagation in backward filter is very simple from the implementation point of view. We apply the proposed nonlinear smoothing ...