repository
창의적 관념화 촉진을 위한 인공지능 기반의 창의성 지원 시스템
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | 한경식 | - |
| dc.contributor.author | 전영승 | - |
| dc.date.accessioned | 2022-11-29T02:32:40Z | - |
| dc.date.available | 2022-11-29T02:32:40Z | - |
| dc.date.issued | 2021-02 | - |
| dc.identifier.other | 30647 | - |
| dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/20226 | - |
| dc.description | 학위논문(석사)--아주대학교 일반대학원 :인공지능학과,2021. 2 | - |
| dc.description.abstract | 최근 창의력 지원 시스템(CST: Creativity Support Tools)은 빅데이터와 빠른 계산 능력을 갖춘 인공지능을 이용하여 창의성을 필요한 작업을 지원한다. 본 연구는 이론적 근거를 바탕으로 패션 디자인에서 인공지능 CST 사례 연구를 통해, 창의성 지원에서 있어서 인공지능의 역할을 명확히 하고자 한다. 본 연구에서는 확산적 사고와 수렴적 사고와 관련된 인지적 메커니즘(확장, 제한, 융합)을 표면화하여 인공지능 모델을 개발한다. 세 가지 상호 시각화 시스템(StyleQ, TrendQ, MergeQ) 포함한 인공지능 기반의 창의력 지원 시스템인 'FashionQ'를 제안한다. 총 20명의 패션 디자인 전문가들과의 인터뷰(10명)와 사용자 실험(10명)을 통해, 확산적 사고와 수렴적 사고를 가능케 하는 FashionQ의 사용성을 입증하고, 관념화 과정에서 인공지능을 접목하는 어려움과 기회를 파악한다. 연구 결과는 전문가의 지식을 바탕으로 각 인지적 메커니즘에서 인공지능의 역할과 활용을 강조하고, 인공지능 기반의 CST 개발의 향후 시사점을 제시한다. | - |
| dc.description.tableofcontents | Chapter 1. Introduction and Contributions of this Dissertation 1 Chapter 2. Related Works and Research Procedure 3 2.1 Cognitive operations for supporting creativity 3 2.2 Creativity support tool (CST) research 4 2.3 Computer-based support for creativity in the design domain 5 2.4 Research Procedure 5 Chapter 3. Formative Study 7 3.1 Interviews with fashion design professionals 7 3.2 Results 7 3.2.1 Fashion design ideation process 7 3.2.2 Challenges and possible solutions 8 3.3 System design goals 10 Chapter 4. FashionQ 12 4.1 StyleQ: Attribute-based style recommendation (Goal 1) 12 4.2 TrendQ: Quantitative de_x000C_nition of trends (Goal 2) 12 4.3 MergeQ: Style combinations (Goal 3) 13 Chapter 5. AI Modeling 15 5.1 Attribute Veri_x000C_cation 15 5.1.1 Dataset for attribute veri_x000C_cation 15 5.1.2 Data annotation 15 5.1.3 Attributes veri_x000C_cation 16 5.1.4 Modeling with feature combination 18 5.1.5 Signi_x000C_cance of fashion attributes 18 5.2 Attribute-labeled dataset 19 5.2.1 Dataset from ADM 19 5.2.2 Modeling 20 5.2.3 Results 20 5.2.4 Large-scale attribute dataset 21 5.3 Style clustering 21 5.3.1 Non-negative factorization (NMF) 21 5.3.2 Clustering fashion styles 22 Chapter 6. User Study 23 6.1 Participants 23 6.2 Study procedure 23 6.3 Survey questions 24 6.4 Statistical analysis 24 6.5 Interview analysis 25 6.5.1 Fashion design ideation with AI-based CST 25 6.5.2 Weaknesses of AI in CST 28 Chapter 7. Discussion and Conclusion 29 7.1 Discussion 29 7.1.1 CST for creativity support 29 7.1.2 Human and AI interaction for creativity support 29 7.1.3 Challenges in developing AI-based CST 31 7.1.4 Limitations and future work 32 7.2 Conclusion 32 Bibliography 34 | - |
| dc.language.iso | eng | - |
| dc.publisher | The Graduate School, Ajou University | - |
| dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
| dc.title | 창의적 관념화 촉진을 위한 인공지능 기반의 창의성 지원 시스템 | - |
| dc.title.alternative | An AI-Driven Creativity Support Tool for Facilitating Creative Ideation in Fashion Design | - |
| dc.type | Thesis | - |
| dc.contributor.affiliation | 아주대학교 일반대학원 | - |
| dc.contributor.alternativeName | Youngseung Jeon | - |
| dc.contributor.department | 일반대학원 인공지능학과 | - |
| dc.date.awarded | 2021. 2 | - |
| dc.description.degree | Master | - |
| dc.identifier.localId | 1204601 | - |
| dc.identifier.uci | I804:41038-000000030647 | - |
| dc.identifier.url | http://dcoll.ajou.ac.kr:9080/dcollection/common/orgView/000000030647 | - |
| dc.subject.keyword | AI-based interface | - |
| dc.subject.keyword | creativity | - |
| dc.subject.keyword | creativity supporting tool | - |
| dc.subject.keyword | fashion | - |
| dc.subject.keyword | 창의성 | - |
| dc.subject.keyword | 창의성 지원 인터페이스 | - |
| dc.subject.keyword | 패션 | - |
| dc.description.alternativeAbstract | Recent research on creativity support tools (CST) adopts artificial intelligence (AI) that leverages big data and computational capabilities to facilitate creative work. Our work aims to articulate the role of AI in supporting creativity with a case study of an AI-based CST tool in fashion design based on theoretical groundings. We developed AI models by externalizing three cognitive mechanisms (extending, constraining, and blending) that are associated with the divergent and convergent thinking. We present FashionQ, an AI-based CST that has three interactive visualization tools (StyleQ, TrendQ, and MergeQ). Through 20 fashion design professionals - 10 participants for the interviews and 10 for the user study, we demonstrate the effectiveness of FashionQ on facilitating divergent and convergent thinking and identify opportunities and challenges of incorporating AI in the ideation process. Our findings highlight the role and use of AI in each cognitive mechanism based on professionals’ expertise and suggest future implications of AI-based CST development. | - |
| dc.title.subtitle | 패션 디자인 사례 중심으로 | - |
- Appears in Collections:
- Graduate School of Ajou University > Department of Artificial Intelligence > 3. Theses(Master)
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
-
- License
- STATISTICS
- Total Visit :3,626,389
- Total Download :1,804
- Today View :6,869
