• International Journal of Advanced Culture Technology
• /
• v.9 no.1
• /
• pp.105-113
• /
• 2021

Through the analysis of Gerhard Richter's works of art in the period of "fuzzy image", this paper expounds the special internal quality of fuzzy image in Richter's works and reveals an important direction of the development of contemporary easel painting, The special essence of Richter's vague image is that he uses photos to reflect the power and authenticity of the existence of the objective things. He was not satisfied with the radical way of modern painting and tried to return to the traditional way of painting, but in fact Richter kept a special distance between classical painting and modern art. Richter not only blurs the image in his creation, but also shows that he wants to show the objectivity of things, keep the distance, authenticity and give up painting. Richter used fuzzy images to capture the concept of "visual unconsciousness", and finally separated from the concept. When we read how Richter showed the reality of things in the way of painting, we also saw a kind of contradictory psychology when he faced the complicated objective.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.365-369
• /
• 2002

퍼지 ART 알고리즘에서 경계 변수는 패턴들을 클러스터링하는데 있어서 반지름 값이 되며 임의의 패턴과 저장된 패턴과의 불일치(mismatch) 허용도를 결정한다. 이 경계 변수가 크면 입력 벡터와 기대 벡터 사이에 약간의 차이가 있어도 새로운 카테고리(category)로 분류하게 핀다. 반대로 경계 변수가 작으면 입력 벡터와 기대 벡터 사이에 많은 차이가 있더라도 유사성이 인정되어 입력 벡터들을 대략적으로 분류한다. 따라서 영상 인식에 적용하기 위해서는 경험적으로 경계 변수를 설정해야 단점이 있다. 그리고 연결 가중치를 조정하는 과정에서 저장된 패턴들의 정보들이 손실되는 경우가 발생하여 인식율을 저하시킨다. 된 논문에서는 퍼지 ART 알고리즘의 문제점을 개선하기 위하여 퍼지 논리 접속 연산자를 이용하여 경계 변수를 동적으로 조정하고 저장 패턴들과 학습 패턴간의 실제적인 왜곡 정도를 충분히 고려하여 승자 노드로 선택된 빈도수를 가중치 조정에 적용한 개선된 퍼지 ART 알고리즘을 제안하였다. 제안된 방법의 성능을 확인하기 위해서 실제 운송 컨테이너 영상들을 대상으로 실험한 결과, 기존의 ART2 알고리즘이나 퍼지 ART 알고리즘보다 클러스터의 수가 적게 생성되었고 인식 성능도 기존의 방법들보다 우수한 성능이 있음을 확인하였다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.9
• /
• pp.117-123
• /
• 1996

In this paper, we present a new learning method for the fuzzy ARTMAP which is effective for the noisy input patterns. Conventional fuzzy ARTMAP employs only fuzzy AND operation between input vector and weight vector in learning both top-down and bottom-up weight vectors. This fuzzy AND operation causes excessive update of the weight vector in the noisy input environment. As a result, the number of spurious categories are increased and the recognition ratio is reduced. To solve these problems, we propose a new method in updating the weight vectors: the top-down weight vectors of the fuzzy ART system are updated using weighted average of the input vector and the weight vector itself, and the bottom-up weight vectors are updated using fuzzy AND operation between the updated top-down weitht vector and bottom-up weight vector itself. The weighted average prevents the excessive update of the weight vectors and the fuzzy AND operation renders the learning fast and stble. Simulation results show that the proposed method reduces the generation of spurious categories and increases the recognition ratio in the noisy input environment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.2
• /
• pp.34-42
• /
• 1997

This paper deals with the recognition of closed planar shape using a three dimensional spectral feature vector which is derived from the FFT(Fast Fourier Transform) spectrum of contour sequence and fuzzy ARTMAP neural network classifier. Contour sequences obtained from 2-D planar images represent the Euclidean distance between the centroid and all boundary pixels of the shape, and are related to the overall shape of the images. The Fourier transform of contour sequence and spectrum analyzer are used as a means of feature selection and data reduction. The three dimensional spectral feature vectors are extracted by spectrum analyzer from the FFT spectrum. These spectral feature vectors are invariant to shape translation, rotation and scale transformation. The fuzzy ARTMAP neural network which is combined with two fuzzy ART modules is trained and tested with these feature vectors. The experiments including 4 aircrafts and 4 industrial parts recognition process are presented to illustrate the high performance of this proposed method in the recognition problems of noisy shapes.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.343-346
• /
• 1998

This paper deals with the decision in vague knowledge, One method is a classic theory. That is to say, constraints and goals in the vague knowledge. Another method is the fuzzy catastrophe. If there exist two fuzzy variables, there may be a discontinuity which plays an important role in decision.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.189-192
• /
• 2010

본 논문에서는 개선된 Fuzzy ART 알고리즘을 이용하여 한의학을 기반으로 증상에 대한 질병을 진단하고 민간요법을 제시하는 한방 자가 검진 시스템을 제안한다. 제안된 방법은 신체 부위를 전신, 머리, 배, 다리 등 17부위로 분류하여 사용자가 증상을 선택하도록 제시하고, 사용자가 선택한 증상과 질병에 포함된 증상 그리고 결과로 도출될 질병간의 선택증상 비율에 대한 우선순위를 개선된 Fuzzy ART 알고리즘에 적용하여 증상을 분류한 후, 퍼지 추론 규칙을 적용하여 질병을 도출한다. 도출된 질병과 그 질병에 대한 원인 및 민간요법을 결과로 제시한다. 데이터베이스에 구축되어 있는 질병 데이터는 통계청에서 정리하여 배포한 한국표준질병 사인분류(K.C.D)를 토대로 표준 질병 정보를 얻어 각 질병의 증상과 원인, 민간요법을 정리한 후, 마지막으로 한의학 전문의의 검증을 거쳐 데이터베이스를 구축하였다. 제안된 한방 자가 검진 시스템에 대한 한의학 전문의의 분석 및 검증 결과, 본 시스템의 증상에 대한 질병 도출이 높은 정확도를 보임을 확인하였다.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12
• /
• pp.223-227
• /
• 2021

A treatment based on the algebraic operations on fuzzy numbers is used to replace the fuzzy problem into an equivalent crisp one. The finite difference technique is used to replace the continuous boundary value problem (BVP) of arbitrary order 1<α≤2, with fuzzy boundary parameters into an equivalent crisp (algebraic or differential) system. Three numerical examples with different behaviors are considered to illustrate the treatment of the singular perturbed case with different fractional orders of the BVP (α=1.8, α=1.9) as well as the classical second order (α=2). The calculated fuzzy solutions are compared with the crisp solutions of the singular perturbed BVP using triangular membership function (r-cut representation in parametric form) for different values of the singular perturbed parameter (ε=0.8, ε=0.9, ε=1.0). Results are illustrated graphically for the different values of the included parameters.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1108-1118
• /
• 2019

Non-local means (NLM) algorithm is an effective and successful denoising method, but it is computationally heavy. To deal with this obstacle, we propose a novel NLM algorithm with fuzzy metric (FM-NLM) for image denoising in this paper. A new feature metric of visual features with fuzzy metric is utilized to measure the similarity between image pixels in the presence of Gaussian noise. Similarity measures of luminance and structure information are calculated using a fuzzy metric. A smooth kernel is constructed with the proposed fuzzy metric instead of the Gaussian weighted L2 norm kernel. The fuzzy metric and smooth kernel computationally simplify the NLM algorithm and avoid the filter parameters. Meanwhile, the proposed FM-NLM using visual structure preferably preserves the original undistorted image structures. The performance of the improved method is visually and quantitatively comparable with or better than that of the current state-of-the-art NLM-based denoising algorithms.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.207-210
• /
• 2000

학습법칙은 신경회로망의 성능을 좌우하는 중요한 요소의 하나이다. Kohonen의 합습법칙등이 개발되어 사용되어 왔으나 Underutilization 문제가 있어 실제 사용사에 문제가 있어 왔다. 본 논문에서 제시하는 학습법칙은 이를 부분적으로 해결하였다. 또한 이 학습법칙을 ART(Adaptive Resonance Theory)-1과 Kohonen의 자기 구조 특징 지도의 장점을 조합한 개선된 IAFC(Integrated Adaptive Fuzzy Clustering) 신경회로망에 적용하였고, 성능을 평가하기 위해 가우시안 분포의 데이터와 IRIS 데이터를 각각 사용하여 실험하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1995.10b
• /
• pp.52-58
• /
• 1995

A shared-weight neural network that performed classification based on the features extracted with the fuzzy morphological operation is introduced. Learning rules for the structuring elements, degree of membership, and weighting factors are also precisely described. In application to handwritten digit recognition problem, the fuzzy morphological shared-weight neural network produced the results which are comparable to the state-of-art for this problem.