• 한국지능시스템학회논문지
• /
• 제13권4호
• /
• pp.409-415
• /
• 2003

Recently, the modular learning are very popular and receive much attention for pattern classification. The modular learning method based on the "divide and conquer" strategy can not only solve the complex problems, but also reach a better result than a single classifier′s on the learning quality and speed. In the neural network area, some researches that take the modular learning approach also have been made to improve classification performance. In this paper, we propose a simple modular neural network for characters recognition of vehicle number plate and evaluate its performance on the clustering methods of feature vectors used in constructing subnetworks. We implement two clustering method, one is grouping similar feature vectors by K-means clustering algorithm, the other grouping unsimilar feature vectors by our proposed algorithm. The experiment result shows that our algorithm achieves much better performance.

• 한국지능시스템학회논문지
• /
• 제18권5호
• /
• pp.638-641
• /
• 2008

본 논문에서는 데이터를 사전처리 한 후 Fuzzy TAM을 이용하여 분류하는 방법을 개발하였다. 사전 처리 방식은 category형 특성인 경우는 그 특성을 이용하여 문제를 분해시키고, 계량형 특성의 경우는 클래스별 영역을 설정하고 겹치지 않는 특성 영역이 있다면 그 영역의 자료를 고정시켜 분류에서 제외시킨다. 이러한 사전 처리를 한 후 Fuzzy TAM을 이용하여 분류를 수행한다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2007년도 추계학술대회논문집
• /
• pp.903-912
• /
• 2007

One of the crucial factors which determine the quality and the accuracy of SEA model is how subsystems are defined. Experimental SEA technique had been a unique way to divide entire systems accurately for mid-frequency range, until FEA based virtual FRF response technique, virtual SEA method presented. Virtaul SEA has been developed for predictive SEA tool in early design process. In this study, Modal analysis results from modified crash FE model is used for Statistical transfer matrix. Observation nodes on the cockpit are grouped by attractive substructuring method based on point to point transfer and correlation matrix. Complex cockpit structure is divided into subsystems by automatic substructuring. Comparison with experimental SEA results validates the application of Virtual SEA to cockpit.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1998년도 학술발표대회 논문집 제17권 1호
• /
• pp.159-162
• /
• 1998

Speech synthesis coding is classified into three categories: waveform coding, source coding and hybrid coding. To obtain the synthetic speech with high quality, the synthesis by waveform coding is desired. However, it is difficult to apply waveform coding to synthesis by syllable or phoneme unit, because it does not divide the speech into excitation and formant component. Thus it is required to alter the excitation in waveform coding for applying waveform coding to synthesis by rule. In this paper we propose a new pitch alteration method that minimizes the spectrum distortion by using the behavior of cepstrum. This method splits the spectrum of speech signal into excitation spectrum and formant spectrum and transforms the excitation spectrum into cepstrum domain. The pitch of excitation cepstrum is altered by zero insertion or zero deletion and the pitch altered spectrum is reconstructed in spectrum domain. As a result of performance test, the average spectrum distortion was below 2.29%.

• 한국해양공학회지
• /
• 제15권4호
• /
• pp.108-114
• /
• 2001

Petri nets have been introduced as a powerful analyzing and design tool for the discrete systems such as sequential control systems. However, one of the important problems in its applications is that the model can be analyzed hardly when we deal with large scale systems because of increase of the number of Petri net components. To overcome this problem, some methods for dividing or reducing of Petri net have been suggested. In this paper, an approach for hierarchical expression of Petri net based on Sequential function Chart(SFC) and Bottom Up oriented Mehodology(BUM) is proposed. Especially, some definitions and rules are defined in order to divide and compose sub Petri nets. A measuring tank system will be described as a typical kind of discrete systems and modeled by some sub Petri nets based on the SFC and BUM by the proposed method in this paper.

• 전기학회논문지
• /
• 제58권6호
• /
• pp.1200-1206
• /
• 2009

In this study, a new method of dental plaque scoring is proposed by adopting new criteria to divide the tooth surface with utilizing the geometrical features of a tooth color image. For the possible clinical usage of our new plaque scoring system, GUI(Graphic User Interface) system is also implemented to estimate the numerical plaque index for a specific tooth by designing the supplementary database management module that handles dental plaque scores.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.567-569
• /
• 2006

This study proposes the method to make a map of moving environment area and passed area by sensor using for recognizing environment or avoiding obstacle. We win develop an efficient algorithm to use sensors and get the data by the user friendly system. Through this system, we win study the way to know of the driving environment of moving robot on the long distance point. To this, we use only one ultra-sonic sensor with a servo motor which rotates 180 degree and loads an ultra-sonic sensor. A sensor can measure 1m${\sim}$8m range and a servo motor can distinguish 15 degree by 12 divide of 180 degree. By this feature of operating system, the robot which has these sensor module detects around of area and moves another point. In this way, users gather the data of detecting distance and change the data to X-Y coordinates. And users derive a map from these accumulate data.

• 한국융합학회논문지
• /
• 제2권1호
• /
• pp.15-20
• /
• 2011

최근 민족적 사회문화적 배경이 다른 다문화가정의 사회통합을 위한 교육적, 사회복지적 측면의 다양한 방안들이 제시되고 있다. 본 연구는 다문화 가정의 유아 정보 리터러시 교육을 위한 교육과정 모델을 제시한다. 기존의 정보 리터러시 기준을 분석하여 추출한 다섯 가지 핵심요소를 교육과정 모델의 기초자료로 사용함으로써 정보격차 해소의 측면을 고려하였고 제안된 교육과정 모델의 성격, 세부 목표, 교육내용, 교수학습방법과 평가방법 항목을 제시한다.

• 한국통신학회논문지
• /
• 제21권4호
• /
• pp.834-847
• /
• 1996

A selective coding scheme is proposed that describes a method for coding image sequences distinguishing bits between background and target region. The suggested method initially estimates global motion parameters and local motion vectors. Then segmentation is performed with a hierarchical clustering scheme and a quadtree algorithm in order to divide the processing image into the backgraound and target region. Finally image coding is done by assigning more bits to the target region and less bits to background so that the target region may be reconstructed with high quality. Simulations show that the suggested algorithm performs well especially in the circumstances where background changes and target regionis small enough compared with that of background.

• Journal of information and communication convergence engineering
• /
• 제6권1호
• /
• pp.80-85
• /
• 2008

Images are often corrupted by noises during signal acquisition and transmission. Among those noises, additive white Gaussian noise (AWGN) and impulse noise are most representative. For different types of noise have different characters, how to remove them separately from degraded image is one of the most fundamental problems. Thus, a modified image restoration algorithm is proposed in this paper, which can not only remove impulse noise of random values, but also remove the AWGN selectively. The noise detection step is by calculating the intensity difference and the spatial distance between pixels in a mask. To divide two different noises, the method is based on three weighted parameters. And the weighted parameters in the filtering mask depend on spatial distances, positions of impulse noise and standard deviation of AWGN. We also use the peak signal-to-noise ratio (PSNR) to evaluate restoration performance, and simulation results demonstrate that the proposed method performs better than conventional median-type filters, in preserving edge details.