• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.901-906
• /
• 2007

Algorithms of path planning and obstacle avoidance are essential to autonomous mobile robots that are working in unknown environments in the real time. This paper presents a new navigation algorithm for an autonomous mobile robot with vision and IR sensors using fuzzy rules. Temporary targets are set up by distance variation method and then the algorithms of trajectory planning and obstacle avoidance are designed using fuzzy rules. In this approach, several digital image processing technique is employed to detect edge of obstacles and the distances between the mobile robot and the obstacles are measured. An autonomous mobile robot with single vision and IR sensors is built up for experiments. We also show that the autonomous mobile robot with the proposed algorithm is navigating very well in complex unknown environments.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.3
• /
• pp.449-459
• /
• 1996

The main goal of this paper is to introduce a novel definition for fuzzy mathematical morphology and a neural network implementation. The generalized- mean operator plays the key role for the definition. Such definition is well suited for neural network implementation. The first stage of the shared-weight neural network has adequate architecture to perform morphological operation. The shared- weight network performs classification based on the features extracted with the fuzzy morphological operation defined in this paper. Therefore, the parameters for the fuzzy definition can be optimized using neural network learning paradigm. Learning rules for the structuring elements, degree of membership, and weighting factors are 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.270-275
• /
• 2007

Motion capture technology is widely used for manufacturing animation since it produces high quality character motion similar to the actual motion of the human body. However, motion capture has a significant weakness due to the lack of an industry wide standard for archiving and retrieving motion capture data. In this paper, we propose a framework to integrate, store and retrieve heterogeneous motion capture data files effectively. We define a standard format for integrating different motion capture file formats. Our standard format is called MCML (Motion Capture Markup Language). It is a markup language based on XML (eXtensible Markup Language). The purpose of MCML is not only to facilitate the conversion or integration of different formats, but also to allow for greater reusability of motion capture data, through the construction of a motion database storing the MCML documents. We propose a fuzzy string searching method to retrieve certain MCML documents including strings approximately matched with keywords. The method can be used to retrieve desired series of frames included in MCML documents not entire MCML documents.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.374-379
• /
• 2007

This paper focuses on the improvement of fault detection algorithm in FRTU(feeder remote terminal unit) on the feeder of distribution power system. FRTU is applied to fault detection schemes for phase fault and ground fault. Especially, cold load pickup and inrush restraint functions distinguish the fault current from the normal load current. FRTU shows FI(Fault Indicator) when the fault current is over pickup value or inrush current. STFT(Short Time Fourier Transform) analysis provides the frequency and time Information. FCM(Fuzzy C-Mean clustering) algorithm extracts characteristics of harmonics. The neural network system as a fault detector was trained to distinguish the inruih current from the fault status by a gradient descent method. In this paper, fault detection is improved by using FCM and neural network. The result data were measured in actual 22.9kV distribution power system.

• Journal of KIISE:Software and Applications
• /
• v.32 no.1
• /
• pp.1-9
• /
• 2005

In this paper we propose a modified fuzzy min-max neural network model for pattern classification and discuss the usefulness of the model. We define a new hypercube membership function which has a weight factor to each of the feature within a hyperbox. The weight factor makes it possible to consider the degree of relevance of each feature to a class during the classification process. Based on the proposed model, a knowledge extraction method is presented. In this method, a list of relevant features for a given class is extracted from the trained network using the hyperbox membership functions and connection weights. Ft)r this purpose we define a Relevance Factor that represents a degree of relevance of a feature to the given class and a similarity measure between fuzzy membership functions of the hyperboxes. Experimental results for the proposed methods and discussions are presented for the evaluation of the effectiveness and feasibility of the proposed methods.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1910-1911
• /
• 2011

본 논문에서는 네트워크 카메라를 이용한 물체 감시 및 비정상 행위의 판단을 위한 실시간 시스템을 제안한다. 제안된 시스템은 먼저 물체의 감시를 위해 SIFT 알고리즘에 기반으로 감시 물체의 특징 정보를 DB화 하고, 히스토그램(Histogram)기법을 활용하여 감시지역을 설정한다. 또한 인간의 행동 및 비정상 행위를 판단하기 위하여, 가상 인간 스켈레톤 모델을 이용하여 입력된 영상에서의 인간의 특징점을 추출한다. 추출된 특징점을 바탕으로 PCA(Principal Component Analysis)를 이용하여 인간의 움직임을 보다 정확하게 표현할 수 있는 특징벡터를 생성하였다. 생성된 특징벡터를 기반으로 퍼지분류기를 이용하여 인간의 행동을 분류하고, 생성된 특징벡터와 특정물체의 거리를 기반으로 인간의 비정상행위를 판단한다. 제안된 방법은 실험을 통해 시스템의 응용 가능성을 증명한다.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.167-168
• /
• 2007

본 논문에서는 얼굴, 지문 등의 생체특징을 안전하게 은닉하고 효과적으로 은닉정보를 추출할 수 있는 웨이블렛 기반 워터마킹 기법을 제안한다. 제안된 방법은 웨이블렛을 이용하여 워터마크 삽입위치를 결정하고 웨이블렛 변환된 영상과 배경영상간의 차와 삽입위치 주변의 영상에 분산값을 이용해 퍼지 함수를 이용하여 적응적 가중치 값을 결정한다. 은닉된 워터마크 데이터는 워터마크가 삽입된 영상에 웨이블렛 변환을 적용하여 효과적으로 생체특징을 추출한다. 제안된 방법의 타당성을 검증하기 위하여 워터마크 데이터인 생체특징의 은닉 전과 후의 특성분석과 워터마크 알고리즘이 생체 인식시스템에 미치는 영향을 평가하였다. 실험한 결과 제안된 방법은 효과적으로 생체정보를 은닉하고 생체인식률의 저하 없이 효과적으로 생체정보를 보호할 수 있음을 확인 할 수 있었다.

• Journal of KIISE:Software and Applications
• /
• v.29 no.10
• /
• pp.726-735
• /
• 2002

E-mail service has been a general method for communication as internet is widely used instead of post mails. Many companies have invested in e-mail advertisement as e-mail service is spread. E-mail advertisement has an advantage that it can consider personal characters. A lot of e-mail users have been given e-mails that they did not want to receive because their e-mail addresses were opened out to companies on internet. Therefore, they need junk mail checking systems and several e-mail service providers have supported junk mail filters. However, the junk mail filters can check the junk mail with constraint because they don't check the junk degree of mails by the contents of e-mail. This paper suggests a content-based junk mail checking model using fuzzy relational products. The process of the junk mail checking model using fuzzy relational products is as following: (1) analyzes semantic relation between junk words-base and e-mails, (2) checks the junk degree of the e-mail using the semantic relation, (3) checks the mails with SVJ(Standard Value of Junk) if those are junk mail or non-junk mail. The efficiency of the proposed technique is proved by comparing the junk degree of the e-mail and the number of junk mails that was checked by e-mail users and checked by the proposed junk mail checking model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.511-513
• /
• 2016

본 논문에서는 세라믹 영상에서 사람의 눈으로 판단하기 어려운 결함 영역을 검출하기 위해 배경을 제거한 후에 지역 기반 오츠 이진화와 양방향 소벨 마스크를 적용하여 세라믹 영상의 윤곽선을 검출한다. 윤곽선이 검출된 영상을 수평으로 4등분하고, 각각의 영역에서 밝기 값이 변화는 지점을 탐색한다. 탐색된 좌표 중에서 최대 명암도 값을 이용하여 ROI 영역을 추출한다. 결함 영역 검출의 효율성을 높이기 위한 전 단계로 배경을 제거하기 위해 ROI 영역과 최소값 필터가 적용된 ROI 영역 간의 명암도의 차이를 이용하여 배경을 제거한다. 명암도의 차이를 통해 배경이 제거된 ROI 영역에서 개선된 명암 대비 스트레칭 기법을 적용하여 ROI 영역의 명암 대비를 강조한다. 명암이 강조된 ROI 영역에서 10mm, 11mm, 16mm, 22mm 영상의 결함 영역을 검출하기 위해 히스토그램 이진화 기법을 적용하여 결함의 후보 영역을 추출한다. 결함 후보 영역이 검출된 ROI 영역에서 미세 잡음을 제거하기 위해 중간값 필터와 침식과 팽창을 적용한 후에 최종적인 결함 영역을 검출한다. 제안된 방법을 8mm, 10mm, 11mm, 16mm, 22mm 세라믹 영상을 대상으로 실험한 결과, 제안된 검출 방법이 기존의 검출 방법보다 모든 mm 세라믹 영상에서 효과적으로 결함 영역이 검출되는 것을 확인하였다.

• Journal of KIISE:Software and Applications
• /
• v.33 no.8
• /
• pp.692-702
• /
• 2006

In this study, a weighted fuzzy min-max (WFMM) neural network model for pattern classification is proposed. The model has a modified structure of FMM neural network in which the weight concept is added to represent the frequency factor of feature values in a learning data set. First we present in this paper a new activation function of the network which is defined as a hyperbox membership function. Then we introduce a new learning algorithm for the model that consists of three kinds of processes: hyperbox creation/expansion, hyperbox overlap test, and hyperbox contraction. A weight adaptation rule considering the frequency factors is defined for the learning process. Finally we describe a feature analysis technique using the proposed model. Four kinds of relevance factors among feature values, feature types, hyperboxes and patterns classes are proposed to analyze relative importance of each feature in a given problem. Two types of practical applications, Fisher's Iris data and Cleveland medical data, have been used for the experiments. Through the experimental results, the effectiveness of the proposed method is discussed.