• 한국멀티미디어학회논문지
• /
• 제13권8호
• /
• pp.1142-1153
• /
• 2010

결막 충혈은 결막염, 각막염, 포도막염 등의 안과질환의 초기 증세로서 정량적으로 평가할 수 있다면 진단과 경과 관찰에 도움이 된다. 충혈의 정량화에서 공막의 크기는 중요한 지표이지만 기존의 공막 분할 방법이 정확하지 않기 때문에 수동으로 분할하고 있다. 본 논문에서는 충혈의 정량화를 위하여 level set 방법을 이용한 공막 분할 알고리즘을 제안한다. Level set의 초기 모델은 Lab 색상 모드와 k-means 알고리즘, 기하학적인 정보를 이용하여 지정된다. 헤이시안(hessian) 분석으로 공막과 피부 사이의 골을 향상시킨 영상에 level set을 적용하였다. 제안 방법의 성능 측정을 위하여 52개의 전안부 영상에 대하여 실험하였다. 실험 결과, 제안 방법이 화소값만 이용하는 region growing이나 level set의 초기 모델로 임의의 원을 이용하는 방법보다 성능이 우수하였다. 이 논문에서 제안한 공막 분할 방법은 객관적인 충혈도 측정에서 중요한 요소 기술의 역할을 할 것이다.

• 대한산업공학회지
• /
• 제30권3호
• /
• pp.175-180
• /
• 2004

The machine-part group formation is to group the sets of parts having similar processing requirements into part families, and the sets of machines needed to process a particular part family into machine cells using grid computing. It forms machine cells from the machine-part incidence matrix by means of Self-Organizing Maps(SOM) whose output layer is one-dimension and the number of output nodes is the twice as many as the number of input nodes in order to spread out the machine vectors. It generates machine-part group which are assigned to machine cells by means of the number of bottleneck machine with processing part. The proposed algorithm was tested on well-known machine-part grouping problems. The results of this computational study demonstrate the superiority of the proposed algorithm.

• 산업기술연구
• /
• 제29권B호
• /
• pp.9-15
• /
• 2009

In the case of traditional binary encoding technique, it takes long time to converge the optimal solutions and brings about complexity of the systems due to encoding and decoding procedures. However, the ROGAs (real-coded genetic algorithms) do not require these procedures, and the k-means clustering algorithm can avoid global searching space. Thus, this paper proposes a new approach by using their advantages. The proposed method constructs the multiple predictors using the optimal differences that can reveal the patterns better and properties concealed in non-stationary time series where the k-means clustering algorithm is used for data classification to each predictor, then selects the best predictor. After selecting the best predictor, the cluster centers of the predictor are tuned finely via RCGKA in secondary tuning procedure. Therefore, performance of the predictor can be more enhanced. Finally, we verifies the prediction performance of the proposed system via simulating typical time series examples.

• 산업경영시스템학회지
• /
• 제19권37호
• /
• pp.41-51
• /
• 1996

This paper evaluates the clustering performance of a neural network and a statistical method. Algorithms which are used in this paper are the GLVQ(Generalized Learning vector Quantization) for a neural method and the k-means algorithm fer a statistical clustering method. For comparison of two methods, we calculate the Rand's c statistics. As a result, the mean of c value obtained with the GLVQ is higher than that obtained with the k-means algorithm, while standard deviation of c value is lower. Experimental data sets were the Fisher's IRIS data and patterns extracted from handwritten numerals.

• 전기학회논문지
• /
• 제57권7호
• /
• pp.1260-1272
• /
• 2008

This paper proposes object detection algorithm using laser scanner and vision system for the path planning of autonomous mobile agents. As the scanner-based method can observe the obstacles in only two dimensions, it is hard to detect the shape and the number of obstacles. On the other hand, vision-based method is sensitive to the environment and has its difficulty in the accurate distance measurement. Thus, we combine these two methods based on K-means algorithm such that the obstacle avoidance and optimal path planning of autonomous mobile agents can be achieved.

• 반도체디스플레이기술학회지
• /
• 제19권3호
• /
• pp.12-18
• /
• 2020

In semiconductor manufacturing, defect detection is critical to maintain high yield. Currently, computer vision systems used in semiconductor photo lithography still have adopt to digital image processing algorithm, which often occur inspection faults due to sensitivity to external environment. Thus, we intend to handle this problem by means of using Mask R-CNN instead of digital image processing algorithm. Additionally, Mask R-CNN can be trained with image dataset pre-processed by means of the specific designed digital image filter to extract the enhanced feature map of Convolutional Neural Network (CNN). Our approach converged advantage of digital image processing and instance segmentation with deep learning yields more efficient semiconductor photo lithography inspection system than conventional system.

• 대한전기학회논문지
• /
• 제45권4호
• /
• pp.602-611
• /
• 1996

In this paper, radial basis function networks with two hidden layers, which employ the K-means clustering method and the hierarchical training, are proposed for improving the short-term predictability of chaotic time series. Furthermore the recursive training method of radial basis function network using the recursive modified Gram-Schmidt algorithm is proposed for the purpose. In addition, the radial basis function networks trained by the proposed training methods are compared with the X.D. He A Lapedes's model and the radial basis function network by nonrecursive training method. Through this comparison, an improved radial basis function network for predicting chaotic time series is presented. (author). 17 refs., 8 figs., 3 tabs.

• 대한수학회보
• /
• 제40권3호
• /
• pp.425-435
• /
• 2003

In this paper, a new kind of matrices, i.e., $level-{\kappa}$ II-circulant matrices is considered. Algorithms for computing minimal polynomial of this kind of matrices are presented by means of the algorithm for the Grobner basis of the ideal in the polynomial ring. Two algorithms for finding the inverses of such matrices are also presented based on the Buchberger's algorithm.

• 한국지능시스템학회논문지
• /
• 제25권1호
• /
• pp.91-96
• /
• 2015

본 연구는 조명변화에 강인한 CT 전처리 기법 기반 개선된 얼굴인식 시스템을 소개한다. 전처리 알고리즘으로 CT알고리즘은 조명이 없는 환경에서도 얼굴의 지역적인 특징만을 추출한다. 얼굴의 지역적인 특징 추출을 가능하게 해준다. 처리된 데이터는 $(2D)^2$ 기반 대표적인 차원축소 알고리즘인 PCA를 사용하여 특징을 추출하였다. 전처리 알고리즘을 통한 특징 데이터는 제안한 방사형 기저함수 신경회로망의 입력으로 사용하였다. 방사형 기저함수 신경회로망의 은닉층은 FCM으로 구성하였고, 연결가중치는 1차 선형식을 사용하였다. 또한 ABC 알고리즘을 이용하여 제안된 분류기의 파라미터, 즉 입력의 수, 퍼지 클러스터링의 퍼지화 계수를 최적화 한다. 본 연구는 제안된 시스템의 성능 평가를 위해 Yale Face database B와 CMU PIE database로 실험하였다.

• 대한의용생체공학회:의공학회지
• /
• 제26권3호
• /
• pp.177-184
• /
• 2005

In this paper, we proposed a new hearing aid algorithm to improve SNR(signal to noise ratio) of noisy speech signal and speech perception. The proposed hearing aid algorithm is a multi-band loudness compensation based independent component analysis (ICA). The proposed algorithm was compared with a conventional spectral subtraction algorithm on behind-the-ear type hearing aid. The proposed algorithm successfully separated a target speech signal from background noise and from a mixture of the speech signals. The algorithms were compared each other by means of SNR. The average improvement of SNR by ICA based algorithm was 16.64dB, whereas spectral subtraction algorithm was 8.67dB. From the clinical tests, we concluded that our proposed algorithm would help hearing aid user to hear clearly a target speech in noisy conditions.