만 2, 3세 유아의 패턴 인식에 관한 연구: 시각적 패턴을 중심으로

최현정 한국영유아교원교육학회 2010 유아교육학논집 Vol.14 No.1

The purpose of this study was to investigate the differences in pattern recognition ability of 2, 3 year old children. The research questions of this study were as follows; 1. Are there any differences in pattern recognition ability of each the age of the moon according to the type of pattern? 2. Are there any differences in pattern recognition ability according to gender?The subjects in this study were 65 people, the age of 2 or 3 year old children, who attended 3 nurseries in Gyeonggi province. And it was conducted as 'random sampling way and the final subject was 60 people. It figured out the difference of visual pattern recognition ability as per the month and gender unit. Regarding month, it was classified in six months unit. Through this, with identified the developing times and characteristics regarding the pattern form toddlers. And it can improve the understanding of developing aspects for infancy regarding pattern and suggests the evidence that considers the level of suitable pattern recognition activities for infancy. As a result, it shows that as the month increased, the pattern recognition ability appeared high. Regarding the type of pattern, it shows the order of AB, AABB, ABC so that AB type would be easy to accept. In addition, the content of pattern is in order of subject, picture, color and figure so that the subject would be easy to understand for toddlers. Additionally, the pattern recognition ability of toddlers did not show the significant difference as per the gender. 본 연구는 만 2세, 3세 유아들의 패턴 인식에 대해 알아봄으로써 이 시기 유아의 발달 수준에 적합한 패턴 활동에 대한 이해를 돕고 활동의 근거를 제시하고자 하였다. 이를 위해 경기도 지역의 어린이집 3곳에 다니는 만 2, 3세 유아 총 65명을 무선표집하여 실시하였으며 최종 통계 처리 대상은 총 60명이었다. 월령에 따라 6개월 단위로 구분하여 월령과 성별에 따른 시각적 패턴 인식 능력을 패턴 인식 도구를 사용하여 조사하였다. 연구결과 유아의 패턴 인식능력은 월령이 증가할수록 높게 나타났으며 패턴의 유형에서는 AB형, AABB형, ABC형 순으로 나타나는 것으로 보아 AB형의 패턴이 가장 쉽게 받아들여짐을 알 수 있다. 또한 패턴의 내용으로는 구체물, 그림, 색, 도형 패턴 순으로 나타난 것으로 보아 유아들에게 친숙한 구체물이 가장 쉽게 패턴을 이해할 수 있음을 알 수 있었으며 유아의 패턴 인식 능력은 성에 따른 유의미한 차이는 나타나지 않았다.

인공신경회로망을 이용한 젖소 무늬에 따른 개체인식

이종환 안성산업대학교 2002 論文集 Vol.33 No.-

Individual recognition of cattle is very important to automate the stock farm. This study has been conducted to present the cattle-friendly image acquisition method and the pattern learning system for individual recognition of cattle. Every cattle has the unique speckle pattern. In this study, the individual recognition of cattle was carried out using the speckle pattern of cattle and the neural network technique. The back-propagation neural network was utilized to recognize a cattle by varying input pattern, unit number of hidden layer, and conversion of input values of the network. The results of this study were as following: 1. Images of twenty-three cattle were captured under outdoor illumination without imposing any restriction to the cattle posture and shadow effect. After segmentation of sample images, cattle body regions in binary image (pixel values consist of 255 and 0) were divided into 10×0 sub-areas. Ratio of pixels (WHITERATIO) having 255 to total pixel number of each sub-areas was calculated and WHITERATIO was used as the index value for speckle pattern of individual cattle. 2. The structure of the pattern learning system (input layer - hidden layer - output layer) was 1-1-1. Sixty images and ten images of cattle were used for studying and verifying the pattern learning system, respectively. Success rate of individual recognition of the trained network with different types of input pattern, unit number of hidden layer, and preprocessed input values were 80%. Using the input values converted to integer number (0, 1, 2, ....., 99, 100) made the pattern learning system more efficient than using the original WHITERATIO as inputs. 3. Speckle pattern of cow was a good feature for individual recognition of cattle and the efficiency of the individual recognition system using image analysis will be improved by a little more elaborated approach for developing pattern learning system.

초등학교 1학년 학생들의 수학적 패턴 인식과 사고 과정 분석

최병훈,방정숙 대한수학교육학회 2011 수학교육학연구 Vol.21 No.1

This study aimed to examine first graders’ recognition and thinking about mathematical patterns. To attain the goal, this paper analyzed 116 students’ response with regard to repeating, growing, and changing patterns represented in both picture and number, and also analyzed four students' thinking process of the patterns through interview. It was found that students showed high recognition in repeating, growing, and changing patterns in order. Whereas there was no significant difference between picture and number representation in both repeating and growing patterns, pictures gained a bit higher scores than numbers in changing patterns. Also, according to the result of examining the thinking process by the patterns, students tended to consider the patterns as a bundle and tried to solve problems with counting strategies. The result of this paper provides an empirical foundation on how first graders recognize and think of various patterns. 본 논문의 목적은 초등학교 1학년 학생들의 수학적 패턴 인식과 사고 과정을 살펴보는 것이다. 이를 위해 반복, 증가, 변형 패턴을 각각 그림과 숫자형태로 구별하여 116명 학생들의 패턴 인식 경향을 분석하였고, 4명의 학생들과 면담을 통해 패턴 인식과 관련된 사고 과정을 분석하였다. 패턴 인식에 관한 연구결과 학생들은 반복, 증가, 변형패턴 순으로 인식이 높았다. 또한 반복과 증가패턴에서는 그림과 숫자 형태간에 유의미한 차이가 없었으나, 변형패턴에서는 그림 형태에서 더 높은 점수를 얻었다. 패턴에 따른 사고과정을 분석한 결과 학생들은 패턴을 하나의 묶음으로 생각하는 경향이 있었고, 세기 전략을 통해 문제를 해결하고자 하였다. 이와 같은 연구 결과를 통해 본 논문은 1학년 학생들이 패턴을 어떻게 인식하고 사고하는지에 대한 경험적 근거를 제공한다.

Movement Pattern Recognition of Medaka for an Insecticide

Yountae Kim,Daehoon Park,Sungshin Kim 한국지능시스템학회 2007 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.7 No.1

Behavioral sequences of the medaka (Oryzias latipes) were continuously investigated through an automatic image recognition system in response to medaka treated with the insecticide and medaka not treated with the insecticide, diazinon (0.1 ㎎/l) during a 1 hour period. The observation of behavior through the movement tracking program showed many patterns of the medaka. After much observation, behavioral patterns were divided into four basic patterns: active-smooth, active-shaking, inactive-smooth, and inactive-shaking. The “smooth” and “shaking” patterns were shown as normal movement behavior. However, the “shaking” pattern was more frequently observed than the “smooth” pattern in medaka specimens that were treated with insecticide. Each pattern was classified using classification methods after the feature choice. It provides a natural way to incorporate prior knowledge from human experts in fish behavior and contains the information in a logical expression tree. The main focus of this study was to determine whether the decision tree could be useful for interpreting and classifying behavior patterns of the medaka.

Emergent damage pattern recognition using immune network theory

Chen, Bo,Zang, Chuanzhi Techno-Press 2011 Smart Structures and Systems, An International Jou Vol.8 No.1

This paper presents an emergent pattern recognition approach based on the immune network theory and hierarchical clustering algorithms. The immune network allows its components to change and learn patterns by changing the strength of connections between individual components. The presented immune-network-based approach achieves emergent pattern recognition by dynamically generating an internal image for the input data patterns. The members (feature vectors for each data pattern) of the internal image are produced by an immune network model to form a network of antibody memory cells. To classify antibody memory cells to different data patterns, hierarchical clustering algorithms are used to create an antibody memory cell clustering. In addition, evaluation graphs and L method are used to determine the best number of clusters for the antibody memory cell clustering. The presented immune-network-based emergent pattern recognition (INEPR) algorithm can automatically generate an internal image mapping to the input data patterns without the need of specifying the number of patterns in advance. The INEPR algorithm has been tested using a benchmark civil structure. The test results show that the INEPR algorithm is able to recognize new structural damage patterns.

교육대학교 신입생들의 갈등에 관한 인식 양상 연구

김재봉 ( Kim Chaebong ) 국어교육학회 2017 國語敎育學硏究 Vol.52 No.2

이 연구에서는 Berko 등이 제안한 설문지를 활용하여 갈등에 대한 인식의 양상을 탐색했다. 그 결과는 다음과 같다. 첫째, 교육대학교 신입생들은 갈등에 대해 “회피>통합>타협>경쟁>조화”와 같은 인식의 양상을 보였다. 또한 Berko 등이 제안한 갈등 유형과는 별도로 “융합형”이 새롭게 발견되었다. 둘째, 혈액형에 따른 인식의 양상 차이는 통계적으로 의미가 없다. 하지만 남녀 구별 없이 처리할 경우 인식의 양상은 “회피>통합>타협>경쟁>조화”와 같은 양상을 보인다. 셋째, 대화 시간과 갈등 반응 유형 간의 상관관계를 탐색했을 때 대화시간이 많을수록 조화형에 통계적으로 의미 있는 반응을 보였다. 넷째, 대화 형태와 갈등 반응 유형 간의 상관관계를 탐색했을 때 토의형토론이 통합형과 통계적으로 유의미한 반응을 보였다. 다섯째, 인지적 측면에서는 일반적인 지적 능력을, 정의적 측면에서는 동기를 인식의 근거로 삼고 있다. 또한 인지적 측면과 정의적 측면을 모두 고려했을 때 인지적 측면보다는 정의적 측면을 우선하여 갈등 양상을 인식하는 근거로 활용하고 있다. The purpose of this thesis is to explore the patterns of conflict recog-nition which has made questionnaire by Berko etc.. The results are sum-marized as follows: First, the pre-service school teachers` realized the aspects of conflict as “avoidance > integration> compromise> competition> accommoda-tion”. Berko etc. suggested five patterns. But the new pattern of conflict is discovered in this research. This type is another. We name it “conver-gence type”. Second, the difference of recognition aspects by blood type is mean-ingless statistically. But the aspects of conflict recognition without distinc-tion of sex are exposed to “avoidance > integration > compromise > com-petition > accommodation”. Third, when we explored the correlation between talk time and con-flict response patterns, the more we have talk time, the more we have meaningful accommodation pattern statistically. Forth, when we explored the correlation between talk patterns and conflict response patterns, the debate of discussion pattern has statistically meaningful response to accommodation pattern. Finally, when the pre-service school teachers` judge the aspects of con-flict, they are based on a general intellectual ability in cognitive perspective and a motivation in an affective perspective. Also when we consider both cognitive perspective and affective perspective, they judge the aspects of conflict recognition which motivation take priority over cognition.

Emergent damage pattern recognition using immune network theory

Bo Chen,Chuanzhi Zang 국제구조공학회 2011 Smart Structures and Systems, An International Jou Vol.8 No.1

This paper presents an emergent pattern recognition approach based on the immune network theory and hierarchical clustering algorithms. The immune network allows its components to change and learn patterns by changing the strength of connections between individual components. The presented immunenetwork- based approach achieves emergent pattern recognition by dynamically generating an internal image for the input data patterns. The members (feature vectors for each data pattern) of the internal image are produced by an immune network model to form a network of antibody memory cells. To classify antibody memory cells to different data patterns, hierarchical clustering algorithms are used to create an antibody memory cell clustering. In addition, evaluation graphs and L method are used to determine the best number of clusters for the antibody memory cell clustering. The presented immune-network-based emergent pattern recognition (INEPR) algorithm can automatically generate an internal image mapping to the input data patterns without the need of specifying the number of patterns in advance. The INEPR algorithm has been tested using a benchmark civil structure. The test results show that the INEPR algorithm is able to recognize new structural damage patterns.

DEVELOPMENT OF PATTERN MAKING USING VECTORISING TECHNIQUE

Hyang Ran Jeon,Min Kyun Kim 글로벌지식마케팅경영학회 2015 Global Fashion Management Conference Vol.2015 No.06

The process of Apparel Product Development requires several major steps such as Pattern Digitizing, Grading, Marker Making, and Cutting Out. The current operation for Pattern Digitizing is conducted operators who amend apparel patterns on a computer after digitizing them based on a point-input method. The current process is laborious, time-consuming, and expensive due to error-prone work that leaves much to be desired in solution expansion. These studies develop an automated system for apparel pattern input based on vectorising technique. Supporting industrial standardization (the detailed targets for the system development) minimizes the involvement of operators and include: automatic recognition of pattern domain, automatic recognition of sample shape, and inner part recognition performing apparel characteristic function. The following picture shows an example using our system developed with a women bra pattern. Figure 2 represents women a bra pattern Figure 3 represents data implemented on the automated system we developed The results of our study : 1. Analytical speed: under 4 seconds in resolution 150 dpi, image size A3. 2. Length error: under 0. 2mm. 3. Outline: 100% extract of outlines cutting and marker pattern. 4. Pattern elements: classification automatically and editing available by user. 5. Pattern division: try one acting scanning various pattern. 6. Data entry/output: converting of DXF, AAMA, TIP, DIGIT. We developed an automated system based on vectorising software for implementation of apparel patterns. The cost of effective system repeatedly processes digitizing tasks with high quality in a few minutes. The system will contribute to the apparel industry field by implementing automatic steps for recognition and classification pattern.

Discrimination and description of repetitive patterns for enhancing the performance of feature-based recognition

Ha, S.J.,Lee, S.H.,Cho, N.I. Butterworths ; Elsevier Science Ltd 2012 Image and vision computing Vol.30 No.11

Conventional object retrieval or recognition methods based on feature matching sometimes fail when an object contains repetitive patterns, because features from repetitive patterns are too similar to each other. Specifically, when there arise many similar features in a query object due to repetitive patterns, they are usually not matched to the ones at the same positions of the reference object. Hence, the matching pairs between the query and reference image do not appear regular and thus homography estimation fails. In case when we use ''nearest neighbor distance ratio'' as a matching criterion, where enough distinction between the matched pairs should be secured, matching also fails due to similarity of features. In this paper, we propose a new feature matching strategy to alleviate this problem by discriminating repetitive patterns from the other salient ones and also by developing a way of utilizing the patterns for robust feature matching. Specifically, we first apply a conventional feature extraction method to a given image. Then we cluster features based on their similarity, i.e., we design a classifier that tells whether a feature is from a repetitive pattern or from a salient structure. For the effective use of repetitive patterns, we define a new descriptor based on support vector data description (SVDD) for describing clusters of similar features. In other words, a set of features from a pattern is defined to be a new feature in terms of its center and radius. For object recognition, the homography is found over the salient features by excluding repetitive features at first, which is then validated and refined by the repetitive patterns. The proposed method is tested with examples of matching buildings with repetitive patterns, and it is shown to be robuster and more reliable than the conventional methods.

Partial Discharge Pattern Recognition of Cast Resin Current Transformers Using Radial Basis Function Neural Network

Wen-Yeau Chang 대한전기학회 2014 Journal of Electrical Engineering & Technology Vol.9 No.1

This paper proposes a novel pattern recognition approach based on the radial basis function (RBF) neural network for identifying insulation defects of high-voltage electrical apparatus arising from partial discharge (PD). Pattern recognition of PD is used for identifying defects causing the PD, such as internal discharge, external discharge, corona, etc. This information is vital for estimating the harmfulness of the discharge in the insulation. Since an insulation defect, such as one resulting from PD, would have a corresponding particular pattern, pattern recognition of PD is significant means to discriminate insulation conditions of high-voltage electrical apparatus. To verify the proposed approach, experiments were conducted to demonstrate the field-test PD pattern recognition of cast resin current transformer (CRCT) models. These tests used artificial defects created in order to produce the common PD activities of CRCTs by using feature vectors of field-test PD patterns. The significant features are extracted by using nonlinear principal component analysis (NLPCA) method. The experimental data are found to be in close agreement with the recognized data. The test results show that the proposed approach is efficient and reliable.