• Journal of information and communication convergence engineering
• /
• 제8권1호
• /
• pp.19-22
• /
• 2010

A finger language helping hearing impaired people in communication A sign language helping hearing impaired people in communication is not popular to ordinary healthy people. In this paper, we propose a method for real-time sign language recognition from a vision system using color information and fuzzy clustering system. We use YCbCr color model and canny mask to decide the position of hands and the boundary lines. After extracting regions of two hands by applying 8-directional contour tracking algorithm and morphological information, the system uses FCM in classifying sign language signals. In experiment, the proposed method is proven to be sufficiently efficient.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2009년도 제40회 하계학술대회
• /
• pp.1899_1900
• /
• 2009

본 논문에서는 주어진 데이터의 입자화 특성을 효과적으로 모델 구축에 반영하고자 재구성 평가 기준을 통한 새로운 형태의 입자화 기반 RBF 뉴럴 네트워크를 개발한다. 주어진 데이터들의 입자화 특성을 파악하기 위해서 새로운 형태의 FCM 클러스터링(-Context-based fuzzy clustering)을 이용한다. 즉, 출력 공간의 입자화 특성은 K-means clustering 방법을 사용한 것에 반해, 입력 공간에서의 정보들은 Context-based fuzzy clustering 방법을 이용하여 효율적으로 데이터의 특성을 파악하여 모델의 구축에 반영하였으며, 또한 모델의 최적화를 위하여 RBF 뉴럴 네트워크의 은닉층의 수를 재구성 평가 기준을 통하여 모델의 최적화를 꾀하였다. 제안된 모델의 효율적인 특성을 보여주기 위해 저차원 합성 데이터를 이용하여 모델을 평가한다.

• 한국정밀공학회지
• /
• 제20권11호
• /
• pp.47-54
• /
• 2003

Research during the past several years has established the effectiveness of acoustic emission (AE)-based sensing methodologies for machine condition analysis and process. AE has been proposed and evaluated for a variety of sensing tasks as well as for use as a technique for quantitative studies of manufacturing process. STD11 has been known as difficult-to-cut materials. The micro-grooving machine was developed for this study and the experiments were performed using CBN blade for machining STD11. Evaluating the machining conditions, frequency spectrum analysis of acoustic emission (AE) signals according to each conditions were applied. Fuzzy clustering method for associating the preprocessor outputs with the appropriate decisions was followed by frequency spectrum analysis. FFT is used to decompose AE signal into different frequency bands in time domain, the root mean square (RMS) values extracted from the decomposed signal of each frequency band were used as features.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2003년도 학술발표논문집
• /
• pp.163-166
• /
• 2003

In this study, a grouping of particle-size distributions(PSDs) by means of the fuzzy c-means clustering method(FCM) was presented. The classification was performed with the whole and the major soil series representing pedological origin. In case of the major soil series, PSDs were clustered as $2{\sim}4$ groups and the characteristics of clustering results were quite different between the soil series. It was found that the characteristics of PSDs at center of each class can be explained by formation process of each soil series. In case of whole soil data, PSDs were classified to 8 classes in which 4 classes were single mode and 4 classes were bimode distributions. Through this study, it is concluded that pedogenetic process is a plausible explanation for grain size distribution of soils.

• Journal of information and communication convergence engineering
• /
• 제6권1호
• /
• pp.94-99
• /
• 2008

Segmentation for the region of nucleus in the image of uterine cervical cytodiagnosis is known as the most difficult and important part in the automatic cervical cancer recognition system. In this paper, the region of nucleus is extracted from an image of uterine cervical cytodiagnosis using the HSI model. The characteristics of the nucleus are extracted from the analysis of morphemetric features, densitometric features, colormetric features, and textural features based on the detected region of nucleus area. The classification criterion of a nucleus is defined according to the standard categories of the Bethesda system. The fuzzy C-means clustering algorithm is employed to the extracted nucleus and the results show that the proposed method is efficient in nucleus recognition and uterine cervical Pap-Smears extraction.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제26권1호
• /
• pp.130-130
• /
• 1999

In this paper, we propose a novel design method for improving performance of existing FCM-type clustering algorithms. First, we define the performance measure which focuses on bothcompactness and separation of clusters. Next, we optimize this measure using evolution program.Especially the proposed method has following merits: ① using evolution program, it solves suchproblems as initialization, number of clusters, and convergence to local optimum ② it reduces searchspace and improves convergence speed of algorithm since it represents chromosome with possiblepotential centers which are selected possible candidates of centers by density measure ③ it improvesperformance of clustering algorithm with the performance index which embedded both compactnessand separation Properties ④ it is robust to noise data since it minimizes its effect on center search.

• Journal of Multimedia Information System
• /
• 제6권2호
• /
• pp.87-90
• /
• 2019

Machine learning techniques have been applied in almost all the domains of human life to aid and enhance the problem solving capabilities of the system. The field of medical science has improved to a greater extent with the advent and application of these techniques. Efficient expert systems using various soft computing techniques like artificial neural network, Fuzzy Logic, Genetic algorithm, Hybrid system, etc. are being developed to equip medical practitioner with better and effective diagnosing capabilities. In this paper, a comparative study to evaluate the predictive performance of subtractive clustering based ANFIS hybrid system (SCANFIS) with Fuzzy C-Means (FCM) based ANFIS system (FCMANFIS) for Alzheimer disease (AD) has been taken. To evaluate the performance of these two systems, three parameters i.e. root mean square error (RMSE), prediction accuracy and precision are implemented. Experimental results demonstrated that the FCMANFIS model produce better results when compared to SCANFIS model in predictive analysis of Alzheimer disease (AD).

• 인지과학
• /
• 제14권4호
• /
• pp.33-42
• /
• 2003

본 논문은 내적상태의 차원모형을 기반으로 한 얼굴 표정인식을 위한 새로운 시스템을 제시한다. 얼굴표정 정보는 3단계로 추출된다. 1단계에서는 Gabor 웨이브렛 표상이 얼굴 요소들의 경계선을 추출한다. 2단계에서는 중립얼굴상에서 얼굴표정의 성긴 특징들이 FCM 군집화 알고리즘을 사용하여 추출된다. 3단계에서는 표정영상에서 동적인 모델을 사용하여 성긴 특징들이 추출된다. 마지막으로 다층 퍼셉트론을 사용하여 내적상태의 차원모델에 기반한 얼굴표정 인식을 보인다. 정서의 이차원 구조는 기본 정서와 관련된 얼굴표정의 인식 뿐만 아니라 다양한 정서의 표정들로 인식할 수 있음을 제시한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1534-1538
• /
• 2005

In this paper, we propose a method to detect contours of a face, eyes, and a mouth of a person in the color image in order to make an avatar automatically. First, we use the HSI color model to exclude the effect of various light conditions, and find skin regions in the input image by using the skin color defined on HS-plane. And then, we use deformable templates and genetic algorithm (GA) to detect contours of a face, eyes, and a mouth. Deformable templates consist of B-spline curves and control point vectors. Those represent various shapes of a face, eyes and a mouth. GA is a very useful search algorithm based on the principals of natural selection and genetics. Second, the avatar is automatically created by using GA-detected contours and Fuzzy C-Means clustering (FCM). FCM is used to reduce the number of face colors. In result, we could create avatars which look like handmade caricatures representing user's identity. Our approach differs from those generated by existing methods.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 춘계학술대회
• /
• pp.478-481
• /
• 2017

본 논문에서는 기존의 삼각형 타입의 퍼지 스트레칭을 개선한 사다리꼴 형태의 퍼지 스트레칭 기법과 FCM 기반 양자화 기법을 적용하여 결절종을 추출하는 방법을 제안한다. 제안된 결절종 추출방법은 결절종 영역과 그 외의 영역 간의 명암 대비를 강조하기 위해 사다리꼴 형태의 퍼지 스트레칭 기법을 적용한 후에 Monotone Cubic Spline 기법을 적용하여 ROI 영역을 추출한다. 추출된 ROI 영역에 대해 FCM 기반 양자화 기법을 적용하고 양자화된 결과를 이용하여 ROI 영역을 이진화한다. 결절종이 타원 형태와 명암도가 낮은 값을 가진다는 형태학적 특징을 이용하기 위해서 이진화 ROI 영역에 팽창 기법을 적용하여 결절종의 후보 영역을 추출하고 8방향 윤곽선 추적 알고리즘을 적용하여 잡음 영역이 제거한다. 잡음이 제거된 결절종 후보 영역에서 최종 결절종 영역을 추출하기 위해 라벨링 기법을 적용한다. 제안된 결절종 추출 방법의 성능을 분석하기 위해서 20명의 환자를 대상으로 20장을 실험한 결과, 기존의 방법보다 TPR(Ture Positive Rate)이 높게 나타나는 것을 확인하였다.