• Journal of KIISE:Software and Applications
• /
• v.28 no.5
• /
• pp.412-421
• /
• 2001

본 논문은 문서 영상에 존재하는 개별 단어들에 대한 속성정보 추출 방법을 제안한다. 단어 단위의 속성 인식은 단어 영상 매칭의 정확도 및 속도 개선, OCR 시스템에서 인식률 향상, 문서의 재생산 등 다양한 응용 가치를 찾을 수 있으며, 메타정보(meta-information) 추출을 통해 영상 검색(image retrieval)이나 요약(summary) 생성 등에 활용할 수 있다. 제안하는 시스템에서 고려하는 단어 영상의 속성은 언어의 종류(한글, 영문), 스타일(볼드, 이탤릭, 보통, 밑줄), 문자 크기(10, 12, 14 포인트), 문자 개수 (한글: 2, 3, 4, 5, 영문: 4, 5, 6, 7, 8, 9, 10), 서체(명조, 고딕)의 다섯 가지 정보이다. 속성 인식을 위한 특징은, 언어 종류 인식에 2개, 스타일 인식에 3개, 문자 크기와 개수는 각각 1개, 한글 서체 인식은 1개, 영문 서체 인식은 2개를 사용한다. 분류기는 신경망, 2차형 판별함수(QDF), 선형 판별함수(LDF)를 계층적으로 구성한다. 다섯 가지 속성이 조합된 26,400개의 단어 영상을 사용한 실험을 통해, 제안된 방법이 소수의 특징만으로도 우수한 속성 인식 성능을 보임을 입증하였다.

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1684-1690
• /
• 2004

This paper presents a method for classifier selection that uses distribution information of the training samples in a small region surrounding a sample. The conventional DCS-LA(Dynamic Classifier Selection - Local Accuracy) selects a classifier dynamically by comparing the local accuracy of each classifier at the test time, which inevitably requires long classification time. On the other hand, in the proposed approach, the best classifier in a local region is stored in the FSA(Feature Space Attribute) table during the training time, and the test is done by just referring to the table. Therefore, this approach enables fast classification because classification is not needed during test. Two feature space attributes are used entropy and density of k training samples around each sample. Each sample in the feature space is mapped into a point in the attribute space made by two attributes. The attribute space is divided into regular rectangular cells in which the local accuracy of each classifier is appended. The cells with associated local accuracy comprise the FSA table. During test, when a test sample is applied, the cell to which the test sample belongs is determined first by calculating the two attributes, and then, the most accurate classifier is chosen from the FSA table. To show the effectiveness of the proposed algorithm, it is compared with the conventional DCS -LA using the Elena database. The experiments show that the accuracy of the proposed algorithm is almost same as DCS-LA, but the classification time is about four times faster than that.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.665-668
• /
• 2018

본 논문에서는 제약기반 KBQA를 위한 질문분석 기술에 대해서 소개한다. 핵심개체와 속성에 대한 연결 모호성을 해소하기 위해서 세 종류의 제약정보 활용을 제안한다. 세 종류의 제약은 핵심개체에 기반한 제약, 의미정답유형에 기반한 제약, 속성단서에 기반한 제약이다. 제약을 위해서는 질문 내에서 핵심개체와 속성단서를 인식하여야 한다. 본 논문에서는 규칙과 휴리스틱에 기반한 핵심개체와 속성단서 인식 방법에 대해서 소개한다. 핵심개체와 속성단서 인식 실험은 구축된 229개의 질문을 대상으로 수행하였으며, 핵심개체와 속성단서가 모두 정확히 인식된 정확도(accuracy)가 57.21%이고, KBQA 대상질문에서는 71.08%를 보였다.

• Culinary science and hospitality research
• /
• v.17 no.4
• /
• pp.140-152
• /
• 2011

As increased demand for well-being food caused more interest in hangwa, or Korean traditional sweets and cookies, this study attempted to analyze the effects of psychological well-being awareness on selection attributes for it and customer satisfaction based on the customers who buy hangwa. As a result of statistical analysis, psychological well-being awareness positively affects selection attributes for hangwa. It also bas a positive effect on customer satisfaction.

• Journal of Digital Convergence
• /
• v.13 no.6
• /
• pp.327-339
• /
• 2015

The present study explored how 1) individuals' perception about attributes of exercise/fitness apps and 2) their motivation for exercise/fitness behaviors influence perceived usefulness and usage of the apps. A survey of 323 males and females in their 20's and 30's revealed that attributes of apps that satisfy their basic psychological needs are crucial in promoting perceived usefulness and usage of the apps. Participants were more likely to perceive exercise/fitness apps useful as they perceive them having more attributes related to autonomy and competence. The perception regarding relatedness attributes did not have the main effect on perceived usefulness but showed an interaction effect with relative autonomous motivation. This convergence study which examined health apps from the perspectives of psychology and public health provides practical implications to development and evaluation of health apps.

• Korean journal of communication and information
• /
• v.72
• /
• pp.52-91
• /
• 2015

The purpose of this study is to examine the effects of attribute agenda-setting and priming through content analysis and a survey about Particulate Matter($PM_{10}$ & $PM_{2.5}$) using both promotional news and general news. The study results were as follows. First, promotional news and general news were found to showcase similar cognitive attributes. Second, the results did not show a significant relationship between highlighted attributes in media coverage and the public's salient attributes, but media attributes had been generally reflected in the public's perception because the public was highly aware of the importance of all media attributes. Third, the recognition of the public's attribute importance affected the direction of public opinion, which resulted in the acceptance of priming effects. Meanwhile, the recognition of the public's attribute importance towards economic damage, international cooperation, individual response, and the recognition of promotional news had affected risk perception. Furthermore, the recognition of promotional news and involvement appeared to have an interaction effect on risk perception.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.591-601
• /
• 2024

As generative AI-based educational content and services targeting child users rapidly increase, the need for research related to children's perception of generative AI is increasing. Accordingly, this study sought to determine the type of generative AI recognized by children and whether cognitive, behavioral, and emotional properties were assigned to it. To understand this, we collected responses through workshop activities to create storybooks with children, semi-structured interviews, and drawing. As a result, children viewed generative AI as an artifact with a high cognitive level, but it was not a type of existing artifact.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.3
• /
• pp.85-94
• /
• 1989

This paper proposes a method to recognize vowels and consonants in a handwritten Hangul text, in which the sizes of chracters and the spaces between characters are not uniform. In this method, all characters in the thinned image of a handwritten Hangul text are transformed into strokes, and the attributes which represent the relations between strokes are extracted from these strokes, and the attributes which represent the relations between strokes are extracted from these strokes. The vowels and consonants are recognized by applying attributed grammars to the strokes and attributes.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.81-89
• /
• 2019

The purpose of this paper was to investigated the effect of the constituents of Facebook advertisement on ad fitness recognition and WOM intension. In addition, we confirmed the mediating effect of ad fitness recognition. For this purpose, data were collected for Facebook 371 users. The research method used factor analysis and covariance structure analysis. The results of this study were as follows: First, the advertising interest characteristics of Facebook ads had a significant effect on ad fitness and word-of-mouth intension. Second, personalized fit informational attributes of Facebook ads had a significant effect on ad fitness and WOM intension. Third, the perceived responsiveness had a significant effect on perceived fitness of advertisement and WOM intention. Fourth, perceived fitness recognition of Facebook advertisement had a significant effect on WOM intension. The results of this study provide consumers with information on what to consider when creating an identity advertisement and effective advertisement as Facebook advertisement.

• Proceedings of the Korea Contents Association Conference
• /
• 2011.05a
• /
• pp.431-432
• /
• 2011

본 연구는 고등교육기관으로서 국가의 발전과 산업인재양성에 중요한 역할을 수행하고 있는 전문대학의 속성 유형을 Q-방법론을 적용하여 조사 분석하여 전문대학에 대학 인식유형을 분류하고 유형간 차이를 분석하고자 한다.