• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.936-940
• /
• 1987

This paper describes the recognition boundary of Hangeul character to interpret variance factor in accordance with various combination. When the recognition algorithm based on comparing the MSE value with the one of the standard pattern in $16{\times}16$ images is performed, we come to a conclusion that we have towe must make a decision MSE value above 34 in order to achive theve recognition rate larger than 90%. Also we understand that varing component coordinates method based on statistical process of each character pattern is preferred.

• 대한전기학회논문지
• /
• 제39권5호
• /
• pp.494-499
• /
• 1990

A new compact hierarchical representation method image is proposed. This method represents a binary image with the set of decimal numbers. Each decimal number represents the pattern of nonterminal node(gray node) in the quadtree. This pattern implies the combination of its four child nodes. The total number of gray nodes is one third of that terminal nodes. We show that gray tree method is efficient comparing with others which have been studied.

• 한국의류산업학회지
• /
• 제15권4호
• /
• pp.504-513
• /
• 2013

This study evaluates the difference of visual effect according to pant style and geometric pattern. The researcher made 28 stimuli-combination of four pant Stiles (classic, baggy, skinny, and bell-bottom) and seven geometric pattern (large vertical stripe, small vertical stripe, large horizontal stripe, small horizontal stripe, large check, small check, and hound's tooth check). The test involved 96 female college students. The stimuli were made with the i-Designer computer program. The panels tested the computer screen images of all manikins wearing pants. A 7-point scale was used to evaluate each image. For the data analysis, ANOVA and Duncan-test were applied along with an SPSS program. The results of this study are as follows. Three factors (lower-body compensation, abdomen highlight, and length compensation) influenced the visual effect pant styles and geometric patterns. The skinny style and large vertical stripe evaluated positively in elongated height and leg length and a slimmer overall body. It was shown that the vertical stripe pattern was evaluated as more positive than the horizontal stripe pattern in the visual effect; particularly, the results showed distinct aspects in the classic pants style. The mutual influence of the visual effect (according to pants style and geometric pattern) were indicated as two factors of lower-body compensation and length compensation. A more positive visual effects resulted in a higher mutual influence on pant style and geometric pattern.

• 대한치과교정학회지
• /
• 제25권2호
• /
• pp.143-152
• /
• 1995

이 연구는 다양한 형태의 closing loops의 activation에 따른 치주조직에서의 응력분포를 평가하고 상악 절치의 이동 양상을 예측하기 위하여 3차원 유한요소법에 의하여 시행되었다. 동시에 상악 절치의 견인시 사용되는 bull loop, key-hole loop, T-loop, combination loop 그리고 asymmetrical T-loop도 3차원 유한요소법에 의해 분석 되었다. 이 연구로부터 얻어진 결과는 다음과 같다. 1. 여러가지 형태의 공간폐쇄용 루프중 bull loop에서 가장 큰 수평력을 나타냈으며 , key-hole, combination loop, T-loop 순이었다. 이들 모두 치아이동의 양상은 uncontrolled tipping을 나타냈다. 2. Asymmetrical TMA T-loop에서는 수평력이 현저히 감소하였으며, 절치부위에 함입력이 나타났다. 3. 절치부에서 torque의 증가에 따라 모멘트가 증가하였고, 선형적인 증가를 보였다. 4. 모멘트의 증가에 따라 치아의 초기 이동양상은 uncontrolled tipping에서 치근이동 양상으로 변화되었다.

• 한국정보통신학회논문지
• /
• 제12권7호
• /
• pp.1243-1248
• /
• 2008

최근 생명 정보학 기술의 발달로 마이크로 단위의 실험조작이 가능해짐에 따라 하나의 chip상에서 전체 genome의 expression pattern을 관찰할 수 있게 되었고, 동시에 수 만개의 유전자들 간치 상호작용도 연구 가능하게 되었다. 본 논문에서는 암에 걸린 흰쥐 외피 기간 세포 분화 실험에서 얻어진 3840 유전자의 마이크로어레이 cDNA를 이용해 데이터의 정규화를 거쳐 본 논문에서 제안한 유사성 척도 조합 방법으로 정보력 있는 유전자들을 추출한 후, 유사성 척도 조합 방법과 결합한 멀티퍼셉트론 신경망 분류기와 기존의 DT, NB, SVM 분류기를 이용하여 클래스 분류 시스템을 구축하고, 성능을 비교분석하였다. 피어슨 적률 상관 계수와 유클리디안 거리 계수 조합을 이용하여 선택된 200 유전사들을 멀티퍼셉트론 신경망 분류기로 분류한 결과 98.84%의 정확도를 보여 다른 분류기를 이용하여 실험을 수행한 경우보다 향상된 분류 성능을 보였다.

• 한국의류학회지
• /
• 제26권6호
• /
• pp.821-832
• /
• 2002

The purpose of this study was to develop grading method of the basic brassiere patterns therewith, provide for 12 size's brassiere patterns and prove fitness of their's and shape. The collected data were statistically processed using the SAS 6.12 for Means, Standard Deviation, etc. The results of this study can be summarized as follows; 1. The basic sizes adopted at the first design stage (see fig.1-2) were 75AA, 75A and 75B each of which was designed as upper foundation basic pattern in reference to the cup size. At the second stage, each of the upper body foundation basic pattern was used to design lower cup, upper up, front panel and wing in their order(see fig.3-6). At the third stage, the other sizes were graded in reference to the three brassiere patterns (75AA, 75A and 75B) to produce 12 brassiere sizes(see Tab. 7-8). In order to develop the basic patterns of adult women's brassieres, 33 women were selected per 11 size combination(3 women per size combination), and then, their brassiere fitting was teated. As a result, the fronts of the basic patterns were found to have such problems as undone front center, poor levelling of upper cup's bottom line or lower cup's top line, poor shape of upper cup's outside top line and shoulder strip position. On the other hand, on the rear side of the basic patterns, the central part of the wing was slightly lifted, while the wing width and straps'interval did not befit the ful1-cup brassiere. The result of this first brassiere fitting test showed that the functionality and aesthetics of the basic pattern brassieres were more or less satisfactory, and thus, the problems were addressed for the second teat. In the second test, the aesthetics, breast-shaping effect and functionality of the basic pattern brassieres were much improved. 2. We were to present the final brassiere sizing system to extend the interior length of breast and the exterior length of breast on the basis of fitting test. Thereby, 75B$.$80A$.$80B$.$85A$.$85B's the interior lengths of breast were enlarged to 0.7cm, the rest size was enlarged to 0.5cm and the exterior length of breast was enlarged to 0.5cm regardless of sizes. 3. The upper foundation basic patterns of 75AA and 75B were presented and and the basic brassiere pattern and grading pattern were presented through to.

• Journal of Biosystems Engineering
• /
• 제24권5호
• /
• pp.431-438
• /
• 1999

The environmental control based on interactive thermoregulatory behavior for swine production has many advantages over the conventional temperature-based control methods. Therefore, this study was conducted to compare various feature selection methods using postural images of growing pigs under various environmental conditions. A color CCD camera was used to capture the behavioral images which were then modified to binary images. The binary images were processed by thresholding, edge detection, and thinning techniques to separate the pigs from their background. Following feature were used for the input patterns to the neural network ; \circled1 perimeter, \circled2 area, \circled3 Fourier coefficients (5$\times$5), \circled4 combination of (\circled1 ＋ \circled2), \circled5 combination of (\circled1 ＋ \circled3), \circled6 combination of (\circled2 ＋ \circled3), and \circled7 combination of (\circled1 ＋ \circled2 ＋ \circled3). Using the above each input pattern, the neural network could classify training images with the success rates of 96%, 96%, 96%, 100%, 100%, 96%, 100%, and testing images with those of 88%, 86%, 93%, 96%, 91%, 90%, 98%, respectively. Thus, the combination of perimeter, area and Fourier coefficients of the thinning images as neural network features gave the best performance (98%) in the behavioral classification.

• 대한의용생체공학회:의공학회지
• /
• 제15권4호
• /
• pp.455-464
• /
• 1994

The intelligent trajectory control method that controls moving direction and average velocity for a prosthetic arm is proposed by pattern recognition and force estimations using EMG signals. Also, we propose the real time trajectory planning method which generates continuous accelleration paths using 3 stage linear filters to minimize the impact to human body induced by arm motions and to reduce the muscle fatigue. We use combination of MLP and fuzzy filter for pattern recognition to estimate the direction of a muscle and Hogan's method for the force estimation. EMG signals are acquired by using a amputation simulator and 2 dimensional joystick motion. The simulation results of proposed prosthetic arm control system using the EMG signals show that the arm is effectively followed the desired trajectory depended on estimated force and direction of muscle movements.

• 한국컴퓨터정보학회논문지
• /
• 제20권11호
• /
• pp.9-16
• /
• 2015

We propose a hybrid pattern recognition method that effectively combines two different features for improving data classification. We first extract the PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) features, both of which are widely used in pattern recognition, to construct a set of basic features, and then evaluate the separability of each basic feature. According to the results of evaluation, we select only the basic features that contain a large amount of discriminative information for construction of the combined features. The experimental results for the various data sets in the UCI machine learning repository show that using the proposed combined features give better recognition rates than when solely using the PCA or LDA features.

• 디지털산업정보학회논문지
• /
• 제9권4호
• /
• pp.33-41
• /
• 2013

In this paper, we implemented the pattern matching with the Arduino and App Inventor platform under the bluetooth mobile environment between Android phone and Arduino Platform. The combination between Arduino and App Inventor makes the feasibility of Android programming easy by wireless communications and provides the opportunity to broaden the functionality for mobile device. We used the softwares which were Arduino IDE, VC++, OpenCV, Processing and App Inventor. And also compared the performance of mobile Arduino platform with LabView GUI programming, we reduced the usage of libraries that compiled and executed the pattern matching programming. We experimented the mobile embedded platform performance under bluetooth communication and verified the functionality of the mobile Arduino platform design for identifying the pattern matching.