• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.1
• /
• pp.77-88
• /
• 1993

In this paper, we propose a stereo vision system to solve correspondence problem with large disparity and sudden change in environment which result from small distance between camera and working objects. First of all, a specific feature is divided by predfined elementary feature. And then these are combined to obtain coded data for solving correspondence problem. We use Neural Network to extract elementary features from specific feature and to have adaptability to noise and some change of the shape. Fourier transformation and Log-polar mapping are used for obtaining appropriate Neural Network input data which has a shift, scale, and rotation invariability. Finally, we use associative memory to obtain coded data of the specific feature from the combination of elementary features. In spite of specific feature with some variation in shapes, we could obtain satisfactory 3-dimensional data from corresponded codes.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.11-16
• /
• 2005

Recently, there are a lot of endeavor to implement a fuzzy theory to artificial neural network. Goh proposed the fuzzy single layer perceptron algorithm and advanced fuzzy perceptron based on the generalized delta rule to solve the XOR Problem and the classical Problem. However, it causes an increased amount of computation and some difficulties in application of the complicated image recognition. In this paper, we propose an enhanced fuzzy single layer Perceptron using the dynamic adjustment of threshold. This method is applied to the XOR problem, which used as the benchmark in the field of pattern recognition. The method is also applied to the recognition of digital image for image application. In a result of experiment, it does not always guarantee the convergence. However, the network show improved the learning time and has the high convergence rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.8
• /
• pp.2119-2132
• /
• 1996

This paper proposes four approaches for approximately realizing nonlinear mappling of interval vectors by neural networks. In the proposed approaches, training data for the learning of neural networks are the paris of interval input vectors and interval target output vectors. The first approach is a direct application of the standard BP (Back-Propagation) algorithm with a pre-processed training data. The second approach is an application of the two BP algorithms. The third approach is an extension of the BP algorithm to the case of interval input-output data. The last approach is an extension of the third approach to neural network with interval weights and interval biases. These approaches are compared with one another by computer simulations.

• Journal of KIISE:Software and Applications
• /
• v.28 no.11
• /
• pp.822-832
• /
• 2001

We have implemented an inductive learning system that learns PROSPECTOR-rule-style classification rules from sets of examples. In our a approach, a genetic algorithm is used in which a population consists of rule-sets and rule-sets generate offspring through the exchange of rules relying on genetic operators such as crossover, mutation, and inversion operators. In this paper, we describe our learning environment centering on the syntactic structure and meaning of classification rules, the structure of a population, and the implementation of genetic operators. We also present a method to evaluate the performance of rules and a heuristic approach to generate rules, which are developed to implement mutation operators more efficiently. Moreover, a method to construct a classification system using multiple learned rule-sets to enhance the performance of a classification system is also explained. The performance of our learning system is compared with other learning algorithms, such as neural networks and decision tree algorithms, using various data sets.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.201-202
• /
• 2008

난청은 가장 흔한 선천성 장애이다. 이 질병의 발생 빈도는 신생아 1000명 출생 당 $1{\sim}3$명 정도로 상당히 높다. 이러한 청력 장애가 조기에 발견된다면 수술적인 치료 등으로 예방할 수 있으나 그렇지 못할 경우 언어와 학습장애를 초래하게 된다. 이런 관점을 근거로 신생아를 대상으로 한 선천성 난청의 선별검사는 큰 의미를 가지며 난청환자의 조기발견을 위한 노력이 필수적이라 할 수 있다. 기존의 수동 청력검사 시스템은 신생아 청력 평가시 검사자의 주관성에 의존하게 되므로, 청성뇌간 반응의 뇌파분석이 잘못될 가능성이 커진다. 따라서 본 연구에서는 청력 역치를 자동으로 판독하여 결과를 나오도록 개발하고자 하였으며, 또한 기존 제품들과는 차별화하여 휴대용으로 개발하여 차폐실이 아닌 일반 병실에서도 검사가 가능하도록 함에 따라 유소아의 청각 장애를 극복시키는데 기여하고자 하였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.629-635
• /
• 2019

In Deep Learning models derivative is implemented by error back-propagation which enables the model to learn the error and update parameters. It can find the global (or local) optimal points of parameters even in the complex models taking advantage of a huge improvement in computing power. However, deliberately generated data points can 'fool' models and degrade the performance such as prediction accuracy. Not only these adversarial examples reduce the performance but also these examples are not easily detectable with human's eyes. In this work, we propose the method to detect adversarial datasets with random noise addition. We exploit the fact that when random noise is added, prediction accuracy of non-adversarial dataset remains almost unchanged, but that of adversarial dataset changes. We set attack methods (FGSM, Saliency Map) and noise level (0-19 with max pixel value 255) as independent variables and difference of prediction accuracy when noise was added as dependent variable in a simulation experiment. We have succeeded in extracting the threshold that separates non-adversarial and adversarial dataset. We detected the adversarial dataset using this threshold.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.39 no.4
• /
• pp.269-275
• /
• 2003

In this paper, We examined auditory threshold and critical ratio of amberjack seriola dumerili, in the Jeju Island coastal waters, to find out hearing ability of the fish. The auditory threshold level, critical ratio and hearing index of amberjack were determinded by conditioning method using a sound coupled with electric shock in the condition of ambient noise or white noise in an experimental water tank. The audio-signals of pure tone and electric shock were from 80 HZ to 800 Hz and DC 7 V, respectively. Values for the critical ratios were calculated in terms of the masked thresholds using the noise projected to stable spectrum levels at all measurement frequencies of background noise. Masking noises were in the spectrum level range of 65 dB∼75 dB $(re 1{\mu}Pa\sqrt{Hz})$. The auditory thresholds of amberjack within the test the frequencies were most sensitive at 300HZ as 94.5 dB. The critical ratios of fishes ranged from 36.4 to 52.8 dB. The noise spectrum level that started masking was about 58∼72 dB within frequencies.