• Journal of the Korea Society of Computer and Information
• /
• v.17 no.2
• /
• pp.49-57
• /
• 2012

Conventional fuzzy c-means (FCM) algorithms have achieved a good clustering performance. However, they do not fully utilize the spatial information in the image and this results in lower clustering performance for images that have low contrast, vague boundaries, and noises. To overcome this issue, we propose an enhanced spatial fuzzy c-means (ESFCM) algorithm that takes into account the influence of neighboring pixels on the center pixel by assigning weights to the neighbors in a $3{\times}3$ square window. To evaluate between the proposed ESFCM and various FCM based segmentation algorithms, we utilized clustering validity functions such as partition coefficient ($V_{pc}$), partition entropy ($V_{pe}$), and Xie-Bdni function ($V_{xb}$). Experimental results show that the proposed ESFCM outperforms other FCM based algorithms in terms of clustering validity functions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.423-426
• /
• 2007

클러스터링은 주어진 데이터 포인트들을 주어진 개수의 그룹으로 나누는 비지도 학습의 한 방법이다. 클러스터링의 방법 중 하나로 널리 알려진 퍼지 클러스터링은 하나의 포인트가 모든 클러스터에 서로 다른 정도로 소속될 수 있도록 함으로써 각 포인트가 하나의 클러스터에만 속할 수 있도록 하는 K-means와 같은 방법에 비해 자연스러운 클러스터 형태의 유추가 가능하고, 잡음에 강한 장점이 있다. 이 논문에서는 기존의 퍼지 클러스터링 방법 중 소속도(membership)와 전형성(typicality)을 동시에 계산해 낼 수 있는 Possibilistic Fuzzy C-Means (PFCM) 방법에 Gath-Geva (GG)의 방법 을 적용하여 PFCM을 확장한다. 제안한 방법은 PFCM의 장점을 그대로 가지면서도, GG의 거리 척도에 의해 클러스터들 사이의 경계를 강조함으로써 분류 목적에 적합한 소속도를 계산할 수 있으며, 전형성은 가우스 형태의 분포에서 생성된 포인트들의 분포 함수를 정확하게 모사함으로써 확률 밀도 추정의 방법으로도 사용될 수 있다. 또한 GG 방법은 Gustafson-Kessel 방법과 달리 클러스터에 포함된 포인트의 개수가 확연히 차이 나는 경우에도 정확한 결과를 얻을 수 있다는 사실을 실험 결과를 통해 확인할 수 있었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.2
• /
• pp.101-108
• /
• 2001

본 논문에서는 배전선로에서 발생하는 여러 고장유형을 판별하기 위해서 적응형 퍼지추론 시스템을 적용하는 새로운 기법을 제시하였다. 배전선로의 고장과 고장유사현상 데이터를 추출하기 위해서 EMTP를 이용하여 RL부하, 아크로부하, 컨버터부하가 있는 배전계통을 구성하고 여러 형태의 고장과 고장유사현상에 대해 시뮬레이션을 하였다. 이를 통해 얻은 전류 파형으로부터 기본파성분, 영상분전류, 짝수 고조파성분의 합, 홍수 고조파성분의 합, 그리고 비정규 고조파성분의 합의 5개의 입력변수를 추출하고 학습을 통해서 각 입력변수의 소속함수의 소속도를 자동으로 결정하였다. 이 적응형 퍼지추론 시스템을 이용한 기법을 평가하기 위해서 학습시와 다른 고장상황을 모의하여 얻은 데이터와 실증시험 데이터를 이용하였다. 결과적으로 제안한 기법은 배전선로에서 발생하는 고장유형을 빠르고 정확하게 판별할 수 있었다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.99-102
• /
• 1998

본 논문에서는 복잡하고 비선형적인 시스템의 최적 모델링을 우해서 지능형 퍼지-뉴럴네트워크의 최적 모델 구축을 위한 방법을 제안한다. 기본 모델은 퍼지 추론 시스템의 언어적인 규칙생성의 장점과 뉴럴 네트워크의 학습기능을 결합한 FNNs 모델을 사용한다. FNNs 모델의 퍼지 추론부는 간략추론이 사용되고, 학습은 요류 역전파 알고리즘을 사용하여 다른 모델들에 비해 학습속도가 빠르고 수렴능력이 우수하다. 그러나 기본 모델은 주어진 시스템에 대하여 퍼지 공간을 균등하게 분할하여 퍼지 소속을 정의한다. 이것은 비선형 시스템의 모델링에 있어어서 성능을 저하시켜 최적의 모델을 얻기가 어렵다. 논문에서는 주어진 데이터의 특성을 부여한 공간을 설정하기 위하여 클러스터링 알고리즘을 사용한다. 클러스터링 알고리즘은 주어진 시스템에 대하여 상호 연관성이 있는 데이터들끼리 특성을 나누어 몇 개의 클래스를 이룬다. 클러스터링 알고리즘을 사용하여 초기 FNNs 모델의 퍼지 공간을 나누고 소속함수를 정의한다. 또한, 최적화 기법중의 하나로 자연선택과 자연계의 유전자 메카니즘에 바탕을 둔 탐색 알고리즘인 유전자 알고리즘을 사용하여 주\ulcorner 진 모델에 대하여 최적화를 수행한다. 또한 본 연구에서는 학습 및 테스트 데이터의 성능 결과의 상호 균형을 얻기 위한 하중값을 가긴 성능지수가 제시된다.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.2
• /
• pp.77-84
• /
• 2004

In this thesis, We propose the self-directed learning and test-performing abilities assessment method to evaluate the learning and the test-performing abilities in which learners can not only control their own learning abilities for themselves, but also judge objectively learning and test-performing abilities. This method shows the membership degree of learning and test-performing abilities by using both the triangle-type membership function and the fuzzy logic. In addition, it gives the fuzzy grades to each item. The final membership degrees are calculated and the fuzzy grades are decided by the operation and composition of fuzzy relations on the membership degrees of learning and test-performing abilities. In this method, which is applicable to a writing subject for information searchers, learners are asked to analyse the membership degrees of the learning and test-performing abilities and the final fuzzy grades and to adjust a learning process for themselves.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.10
• /
• pp.1852-1859
• /
• 2016

The effectiveness of a binarization algorithm in image processing depends on how to eliminate the uncertainty of determining threshold in a reasonable way and on minimizing information loss due to the binarization effect. Fuzzy binarization technique was proposed to handle that uncertainty with fuzzy logic. However, that method is known to be inefficient when the given image has low intensity contrast. In this paper, we propose an improved fuzzy binarization method to overcome such known drawbacks. Our method proposes a trapezoid type fuzzy membership function instead of most-frequently used triangle type one. We also propose an adaptive ${\alpha}$_cut determination policy. Our proposed method has less information loss than other algorithms since we do not use any stretching based preprocessing for enhancing the intensity contrast. In experiment, our proposed method is verified to be more effective in binarization with less information loss for many different types of images with low intensity contrast such as night scenery, lumber scoliosis, and lipoma images.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.635-642
• /
• 2003

Reinforcement learning got successful results in a lot of applications such as control and scheduling. Various function approximation methods have been studied in order to improve the learning speed and to solve the shortage of storage in the standard reinforcement learning algorithm of Q-Learning. Most function approximation methods remove some special quality of reinforcement learning and need prior knowledge and preprocessing. Fuzzy Q-Learning needs preprocessing to define fuzzy variables and Local Weighted Regression uses training examples. In this paper, we propose a function approximation method, Fuzzy Q-Map that is based on on-line fuzzy clustering. Fuzzy Q-Map classifies a query state and predicts a suitable action according to the membership degree. We applied the Fuzzy Q-Map, CMAC and LWR to the mountain car problem. Fuzzy Q-Map reached the optimal prediction rate faster than CMAC and the lower prediction rate was seen than LWR that uses training example.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.7
• /
• pp.1387-1393
• /
• 2007

Even if the linearly separable patterns can be classified by the conventional single layer perceptron, the non-linear problems such as XOR can not be classified by it. A fuzzy single layer perceptron can solve the conventional XOR problems by applying fuzzy membership functions. However, in the fuzzy single layer perception, there are a couple disadvantages which are a decision boundary is sometimes vibrating and a convergence may be extremely lowered according to the scopes of the initial values and learning rates. In this paper, for these reasons, we proposed an enhanced fuzzy single layer perceptron algorithm that can prevent from vibration the decision boundary by introducing a bias term and can also reduce the learn time by applying the modified delta rule which include the learning rates and the momentum concept and applying the new linear activation function. Consequently, the simulation results of the XOR and pattern classification problems presented that the proposed method provided the shorter learning time and better convergence than the conventional fuzzy single layer perceptron.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.373-378
• /
• 2001

The optimization method based on an enhanced genetic algorithms is for multimodal function optimization in this paper. This method is consisted of two main steps. The first step is a global search step using the genetic algorithm(GA) and function assurance criterion(FAC). The belonging of an population to initial solution group is decided according to the FAC. The second step is to decide the similarity between individuals, and to research the optimum solutions by single point method in reconstructive search space. Four numerical examples are also presented in this papers to comparing with conventional methods.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.25-31
• /
• 2011

Principal component analysis (PCA) is a well-known method for dimensionality reduction and feature extraction. Although PCA has been applied in many areas successfully, it is sensitive to outliers due to the use of sum-square-error. Several variants of PCA have been proposed to resolve the noise sensitivity and, among the variants, improved robust fuzzy PCA (RF-PCA2) demonstrated promising results. RF-PCA2, however, still can fall into a local optimum due to equal initial membership values for all data points. Another reason comes from the fact that RF-PCA2 is based on sum-square-error although fuzzy memberships are incorporated. In this paper, a variant of RF-PCA2 called RF-PCA3 is proposed. The proposed algorithm is based on the objective function of RF-PCA2. RF-PCA3 augments RF-PCA2 with the objective function of PCA and initial membership calculation using data distribution, which make RF-PCA3 to have more chance to converge on a better solution than that of RF-PCA2. RF-PCA3 outperforms RF-PCA2, which is demonstrated by experimental results.