• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.180-191
• /
• 2002

We present a new text localization method in images using a multi-layer perceptron(MLP) and a multiple continuously adaptive mean shift (MultiCAMShift) algorithm. An automatically constructed MLP-based texture classifier generates a text probability image for various types of images without an explicit feature extraction. The MultiCAMShift algorithm, which operates on the text probability Image produced by an MLP, can place bounding boxes efficiently without analyzing the texture properties of an entire image.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.3
• /
• pp.39-44
• /
• 2006

In this study, we nodestructive test based on ultrasonic test as inspection method and compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as pattern recognition algorithm of welding flasw. For this purpose, variables are applied the same to two algorithms. Where, feature variables are zooming flaw signals of reflected whole signals from welding flaws in time domain. Through this process, we confirmed advantages/disadvantages of two algorithms and identified application methods of two algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.501-507
• /
• 2020

This paper proposes a new frame synchronization technique based on convolutional neural network (CNN). The conventional frame synchronizers usually find the matching instance through correlation between the received signal and the preamble. The proposed method converts the 1-dimensional correlator ouput into a 2-dimensional matrix. The 2-dimensional matrix is input to a convolutional neural network, and the convolutional neural network finds the frame arrival time. Specifically, in additive white gaussian noise (AWGN) environments, the received signals are generated with random arrival times and they are used for training data of the CNN. Through computer simulation, the false detection probabilities in various signal-to-noise ratios are investigated and compared between the proposed CNN-based technique and the conventional one. According to the results, the proposed technique shows 2dB better performance than the conventional method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.175-182
• /
• 2023

Differential cryptanalysis is one of the analysis techniques for block ciphers, and uses the property that the output difference with respect to the input difference exists with a high probability. If random data and differential data can be distinguished, data complexity for differential cryptanalysis can be reduced. For this, many studies on deep learning-based neural distinguisher have been conducted. In this paper, a deep learning-based neural distinguisher for PIPO 64/128 is proposed. As a result of experiments with various input differences, the 3-round neural distinguisher for the differential characteristics for 0, 1, 3, and 5-rounds achieved accuracies of 0.71, 0.64, 0.62, and 0.64, respectively. This work allows distinguishing attacks for up to 8 rounds when used with the classical distinguisher. Therefore, scalability was achieved by finding a distinguisher that could handle the differential of each round. To improve performance, we plan to apply various neural network structures to construct an optimal neural network, and implement a neural distinguisher that can use related key differential or process multiple input differences simultaneously.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5B
• /
• pp.485-493
• /
• 2008

The Artificial Neural Network (ANN) model was suggested for predicting probability of precipitation (PoP) using RDAPS NWP model, observation at AWS and upper-air sounding station. The prediction work was implemented for flood season and the data period is the July, August of 2001 and June of 2002. Neural network input variables (predictors) were composed of geopotential height 500/750/1000 hPa, atmospheric thickness 500-1000 hPa, X & Y-component of wind at 500 hPa, X & Y-component of wind at 750 hPa, wind speed at surface, temperature at 500/750 hPa/surface, mean sea level pressure, 3-hr accumulated precipitation, occurrence of observed precipitation, precipitation accumulated in 6 & 12 hrs previous to RDAPS run, precipitation occurrence in 6 & 12 hrs previous to RDAPS run, relative humidity measured 0 & 12 hrs before RDAPS run, precipitable water measured 0 & 12 hrs before RDAPS run, precipitable water difference in 12 hrs previous to RDAPS run. The suggested ANN has a 3-layer perceptron (multi layer perceptron; MLP) and back-propagation learning algorithm. The result shows that there were 6.8% increase in Hit rate (H), especially 99.2% and 148.1% increase in Threat Score (TS) and Probability of Detection (POD). It illustrates that the suggested ANN model can be a useful tool for predicting rainfall event prediction. The Kuipers Skill Score (KSS) was increased 92.8%, which the ANN model improves the rainfall occurrence prediction over RDAPS.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.196-196
• /
• 2012

전 지구적으로 발생하고 있는 잦은 기상이변과 기후변화의 가속화로 자연재해 발생빈도 및 피해규모는 증가하는 추세로 나타나고 있다. 이러한 기상이변은 우리나라 또한 예외가 아니며 최근 한반도에서 발생한 적설로 인하여 많은 인명과 재산피해가 증가하고 있다. 본 연구에서는 기상청에서 제공하는 KMA-RCM 기후자료를 바탕으로 관측자료 및 시나리오의 온도, 강수, 적설량 간의 관계를 이용하여 기상청 산하 기상관측소 58개 대상 지점으로부터 목표기간별(목표 I:1979~2008년, 목표 II:2011~2040년, 목표 II:2041~2070년, 목표IV:2071~2100년) 적설량을 예측하였으며, 빈도별(20년, 30년, 50년, 80년, 100년, 200년) 확률적설량을 산정하고자 하였다. KMA-RCM 자료를 이용한 미래 적설량 예측은 기상인자들의 복잡한 비선형 조합으로 발생하기 때문에 적설량에 영향을 미치는 온도, 강수, 적설량의 비선형 과정들을 고려할 수 있는 신경망 모형을 이용하여 적설량 예측 모형을 구성하였고, 58개 대상 지점의 30년 이상 관측기상자료 중 온도, 강수, 적설량 자료를 이용하여 지점별로 훈련을 시켜 이를 기후변화 시나리오에 활용하였다. 확률적설량에서 매개변수 추정은 확률가중모멘트법(PWM)을 이용하였고 적정확률분포형으로는 시나리오적 방법 및 비시나리오적 방법에 대한 분포형 검정결과 가장 적합하다고 판정되는 Gumbel분포형을 선정하였다. 위의 방법론을 통하여 미래 목표기간별로 확률적설량을 확률적설량을 산정하였으며 본 연구결과는 기후변화 시나리오를 고려한 목표기간별 적설량 산정 및 관련 방재기준의 개선 방안 및 재설정 기준 마련에 기초자료로 활용될 수 있을 것으로 기대된다.

• Computational Structural Engineering
• /
• v.19 no.4 s.74
• /
• pp.52-61
• /
• 2006

• Journal of Korean Society of Steel Construction
• /
• v.17 no.6 s.79
• /
• pp.661-672
• /
• 2005

For the efficient stochastic optimization of steel structures for which a large number of analyses is required, artificial neural networks,which have emerged as a powerful tool that could have been used to replace time-consuming procedures in many scientific or engineering applications, are applied. They are utilized for the solution of the equilibrium equations resulting from the application of the finite element method in connection with the reanalysis type of problem, for which a large number of finite element analyses are required in this study. As such, the use of artificial neural networks to predict finite element analysis outputs simplifies and facilitates the performance of the stochastic optimal design of structural systems where a trained neural network is used to replace the structural reanalysis phase. Moreover, to improve efficiency of used artificial neural networks, genetic algorithm is utilized. The stochastic optimizer used in this study is an algorithm based on the evolution theory. The efficiency of the proposed procedure is examined in problems with both volume (weight) functions and real-world cost functions

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.668-673
• /
• 2017

Deep neural networks have shown remarkable performance in various fields of pattern recognition such as voice recognition, image recognition and object detection. However, underlying mechanisms of the network have not been fully revealed. In this paper, we focused on empirical analysis of the network parameters. The Faster R-CNN(region-based convolutional neural network) was used as a baseline network of our work and three important parameters were analyzed: the dropout ratio which prevents the overfitting of the neural network, the size of the anchor boxes and the activation function. We also compared the performance of dropout and batch normalization. The network performed favorably when the dropout ratio was 0.3 and the size of the anchor box had not shown notable relation to the performance of the network. The result showed that batch normalization can't entirely substitute the dropout method. The used leaky ReLU(rectified linear unit) with a negative domain slope of 0.02 showed comparably good performance.

• Annual Conference on Human and Language Technology
• /
• 1995.10a
• /
• pp.137-142
• /
• 1995

코호넨의 SOFM(Self-Organizing Feature Map)온 빠른 검증 학습이 가능하여 다층 퍼셉트론의 단점을 보완할 수 있는 패턴분류기로 부각되고 있다. 그러나 기본적으로 고정된 크기와 구조의 네트워크를 사용하기 때문에 실재 문제에 적용하기가 쉽지 않다는 문제가 있다. 본 논문에서는 패턴에 대한 사전 정보없이 복잡한 패턴공간을 적응적으로 분할하기 위해 구조적응되는 자기조직화 신경망을 소개하고 이를 인쇄체 한글 문자의 인식에 적용한 결과를 보여준다. 여기에서 제안하는 신경망은 SOFM의 각 셀이 좀더 자세한 SOFM으로 확장될 수 있도록하며, 확률분포가 0인 셀을 제거함으로써 패턴 공간에 보다 근사한 분류를 가능하게 한다. 실제로 이러한 방식이 한글과 같은 복잡한 분류 문제에서 어떻게 작동하는지 설명하고, 한글 완성형 2350자에 대해 실험한 결과를 보여준다.