Design Quantification & Automation

This research area requires interdisciplinary knowledge such as combinations of data analysis, genetic algorithms, and deep learning. DI Lab promotes research that quantifies and automates design processes and outcomes based on engineering knowledge.

해당 연구 분야는 데이터 분석과 딥러닝·유전 알고리즘 등과 결합하여 폭넓은 학제 간 연구를 의미한다. 디자인 인포매틱스 연구실은 공학적 지식을 기반으로 디자인 프로세스 와 디자인 결과물을 정량화하고, 이를 자동화하는 연구를 장려한다.

Example Papers:

• Interior Design Network of Furnishing and Color Pairing with Object Detection and Color Analysis based on Deep Learning
  Communications in Computer and Information Science (2022) 1465: 237-249
  
  SCOPUS
  (Computer Science, Mathematics)
• Balancing Homogeneity and Heterogeneity in Design Exploration by Synthesizing Novel Design Alternatives based on Genetic Algorithm and Strategic Styling Decision
  Advanced Engineering Informatics (2018) 38: 113-128.
  
  SCIE
  (Environmental Science; Green, Sustainable Science, Technology, IF=2.075)
• The Gap between Design Intent and User Response: Identifying Typical and Novel Car Design Elements among Car Brands for Evaluating Visual Significance
  Journal of Intelligent Manufacturing (2017) 28.7: 1729-1741
  
  SCIE
  (Computer Science, Artificial Intelligence; IF=3.667)
• Style Synthesis and Analysis of Car Designs for Style Quantification based on Product Appearance Similarities
  Advanced Engineering Informatics (2015) 29.3: 483-494
  
  SCIE
  (Computer Science, Artificial Intelligence; IF=2.000)

Computer-Coordinated Design System

The research area aims to assist designers' creativity by developing designer-centered support methods and systems that aid design exploration, collaboration, and implementation. DI Lab aims to lead computational design research that develops design exploration and generation algorithms and applies them to the design process.

해당 연구 분야는 디자인 탐색·협업·구현 과정을 지원하는 디자이너 중심 지원 방법 및 시스템을 개발하여 디자이너의 창의성을 확장하는 목적을 지니고 있다. 디자인 인포매틱스 연구실은 디자인 탐색 및 생성 알고리즘 등을 개발하고 이를 디자인 과정에 적용하는 컴퓨테이셔널 디자인 연구를 선도한다.

Example Papers:

• BIGexplore: Bayesian Information Gain Framework for Information Exploration
  ACM CHI 2022 Paper. New Orleans, USA
  
  SCIE
  (BKCSA003, h-index=189)
• Designer-Centric Spatial Design Support
  Automation in Construction (2022) 137: 104195
  
  SCIE
  (Construction & Building Technology, IF=7.700)
• C-Space: An Interactive Prototyping Platform for Collaborative Spatial Design Exploration
  ACM CHI 2020 Paper. Honolulu, USA
  
  SCIE
  (BKCSA003, h-index=189)
• 3D Computational Sketch Synthesis Framework: Assisting Design Exploration Through Generating Variations of User Input Sketch and Interactive 3D Model Reconstruction
  Computer-Aided Design (2020) 120: 102789
  
  SCI
  (Computer Science, Software Engineering, IF=2.947)

Interaction Techniques & Devices

This research area focuses on discovering novel interaction methods that improve the user experience. DI Lab continuously develops techniques and devices that create new visual, tactile, and immersive experiences.

해당 연구 분야는 사용자 경험에 주목하여, 기존 경험을 개선하는 새로운 상호작용 방안을 발굴하는 것을 목표로 한다. DI 랩은 새로운 시각적·촉각적·몰입적 경험을 생성하는 기술 및 장비를 꾸준히 연구하고 있으며, 나아가 도움이 필요한 사용자 경험을 고려한 사회적 기여 연구 또한 관심을 두고 있다.

Example Papers:

• Pixel of Matter: New Ways of Seeing with an Active Volumetric Filmmaking System
  Leonardo (SIGGRAPH - Art Paper) (2020) 53.4: 434-437
  
  A&HCI
  (Art, Art & Architecture)
• Image-based Tactile Emojis: Improved Interpretation of Message Intention and Higher Emotional Clarity for Visually Impaired Individuals
  Human-Computer Interaction (2020) 35.1: 40-69
  
  SCI
  (Computer Science, Cybernetics, IF=4.667)
• Directional Force Feedback: Mechanical Force Concentration for Immersive Experience in Virtual Reality
  Applied Sciences (2019) 9.18: 3692
  
  SCIE
  (Physics, Applied, IF=2.217)