Design Computing and Cognition'24

Name: Design Computing and Cognition'24 | Volume 2
Brand: Springer
Price: 245.03 EUR
Availability: OnlineOnly

Volume 2

John S. Gero(Editor)

Springer (Publisher)

1st Edition

Published on 27. September 2024

XI, 276 pages

E-Book

PDF with digital watermarking

System requirements

978-3-031-71922-6 (ISBN)

€245.03incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Person

Content

Intro
Preface
List of Reviewers
Contents
I Design Technology
How Do We Know if a Design Space Representation Is Useful? Insights from the DS-Viz Method
1 Introduction
1.1 Computational Approaches to Design Space Representation
1.2 Creativity-Focussed Approaches to Design Space Representations
2 DS-Viz: Creating Design Space Visualisations
3 Strategies for the Evaluation of DS-Viz Usefulness
3.1 Brief Notes on Steps A and B
3.2 Evaluation of Step C: Distance Measure
3.3 Evaluation of Step D: Embedding Creation
3.4 Evaluation of Step E: Creation of Space Visualisations
3.5 Evaluation of Step F: Relevant Metrics
4 Discussion
5 Conclusions
References
Visual Attention to Biophilic Elements in Virtual Classroom Design: A VR Eye-Tracking Study
1 Background
2 Aims
3 Experiment Methods
3.1 Participants
3.2 Virtual Classroom Simulation
3.3 Hardware and Software
3.4 Experiment Procedure
3.5 Data Collection and Processing
3.6 Data Analysis Methods
4 Data Analysis and Results
4.1 Heatmaps and Distribution of AOI
4.2 Statistical Analysis of Fixations and Saccades
5 Discussions
6 Limitations and Directions for Future Research
7 Conclusion
References
Optimization in Parametric Design Thinking: Are New Models Needed?
1 Introduction
2 Background
2.1 Models of Design Thinking
2.2 Models of Parametric Design Thinking
2.3 Optimization in Architectural Design
3 Method
3.1 Criteria for a Parametric Design as a Novel Process
3.2 Optimization Strategies
4 Results
4.1 Overview of the Iterative Cycles from Our Study
4.2 Comparing Optimization Behaviors Against Criteria for New Forms of Design Thinking
5 Discussion: A Proposal for Future Updates
5.1 Limitations
6 Conclusion
References
Symmetry Heuristics for Stable Reinforcement Learning Design Agents
1 Introduction
2 Background
2.1 The Synergy Between Configuration Design and Graph-Based Frameworks
2.2 Configuration Design with Graph Neural Network Based Reinforcement Learning Agents
2.3 Heuristic-Guided Reinforcement Learning
3 Methods
3.1 Foundational RL Framework for Configuration Design
3.2 Symmetry Reward Formulation
4 Case Study
4.1 Truss Design Problem
4.2 Training and Evaluating the RL Agents
5 Results and Discussion
6 Conclusion and Future Work
References
II AI and Design
Using Personas to Increase the Diversity of Design Concepts Generated by Large Language Models
1 Introduction
2 Background
2.1 Design Ideation
2.2 Large Language Models (LLMs)
2.3 Design Representations
3 Methods
3.1 Knowledge Base Construction
3.2 Design Problems and Professional Persona Selection
3.3 Prompt Design and Evolution
4 Experiment with Design Problems
4.1 Evaluation Metrics
4.2 Sample Outputs from ChatGPT
4.3 Results and Discussion
5 Conclusion
References
A Multi-case Study of Traditional, Parametric, and Generative Design Thinking of Engineering Students
1 Background and Motivation
2 Methods
2.1 Participants
2.2 Curriculum Materials
2.3 Aladdin and Design Process Behavior
2.4 Data Collection
2.5 Data Analysis Approach
3 Results and Discussion
3.1 Case Study 1: Sabrina (P102)
3.2 Case Study 2: Suyash (P103)
3.3 Case Study 3: Ricky (P108)
3.4 Cross-Case Analysis and Discussion
3.5 Quantitative Results and Discussion
4 Limitations and Future Work
5 Conclusion
References
MazeMind: Exploring the Effects of Hand Gestures and Eye Gazing on Cognitive Load and Task Efficiency in an Augmented Reality Environment
1 Background/Motivation
2 Objectives and Significance
3 Materials and Methods
3.1 Hypotheses
3.2 Laboratory Experiments
4 Results and Analysis
4.1 Participants
4.2 Statistical Results and Analysis
4.3 Hypothesis Analysis
5 Discussion
References
What Is Generative in Generative Artificial Intelligence? A Design-Based Perspective
1 Introduction: The Generative Trend in Artificial Intelligence
2 Background and Scope: Generativity and Artificial Intelligence, Two Disciplines that Can Enlighten One Another
2.1 Generative Artificial Intelligence: Definition and Models
2.2 Generativity: What Can Engineering Design Bring to Artificial Intelligence
2.3 Characterizing Generativity in Artificial Intelligence?
3 Method: A Canonical Model of Generativity to Analyze Systematically GenAI Models
3.1 A Theoretical Framework of Generativity
3.2 A Systematic Analysis of GenAI Models
4 Artificial Intelligence Models Within This Framework
4.1 Objective and Scope of the Section
4.2 Generativity in Generative Design Algorithms (GDA)
4.3 Generativity in Variational Auto-Encoders (VAE)
4.4 Generativity in Generative Diffusion Models (GDM)
4.5 Generativity in Generative Adversarial Networks (GAN)
4.6 Generativity in Generative Pre-Trained Transformers (GPT)
5 Results: An Overview of Generativity on Generative AI
6 Discussions
6.1 Confirming the Generative Power of GenAI
6.2 Identifying Generative Mechanisms as an Open Debate for GenAI
6.3 Confirming Some Limits of GenAI Tools
6.4 Avenues to Enrich the Generative Power of GenAI Tools
7 Conclusion
References
Design and Brain Behaviors
An Exploration of Brain Lateralization During Engineering Design Ideation Using fNIRS
1 Introduction
2 Background
3 Research Questions
4 Methodology
4.1 Data Collection and Processing
4.2 Data Analysis
5 Results
6 Discussion
7 Conclusion
References
A New Approach for Examining the Changes of Brain Behaviors Between Problem-Finding and Problem-Solving in Design Teamwork
1 Introduction
1.1 Neuroscience in Design Teamwork
2 Methodology
2.1 Pilot Study
2.2 Inter-Brain Synchrony Data Analysis
3 Discussion and Limitation
4 Conclusion
References
Higher-Order Cognitive States Recognition in Open-Ended Design Creation Tasks Using EEG Microstate Analysis and Convolutional Neural Networks
1 Introduction
2 Methods
2.1 Dataset
2.2 Experiment Design
2.3 Participants and Procedure
2.4 Reconstruction of EEG Microstates Sequences
2.5 Classification of EEG Microstate Sequences and Network Configuration
2.6 Network Configuration
3 Results
4 Discussion
5 Conclusion
References
Neuro-Cognitive Feedback as a Tool for Improving Cognitive Endurance in Engineering Design
1 Introduction
2 Background
2.1 Neuro-Cognitive Feedback to Enhance Engineering Design Ideation
2.2 How Does Neuro-Cognitive Feedback Enhance Ideation?
2.3 Why Functional Near-Infrared Spectroscopy?
3 Research Questions
4 Methods
4.1 Neuro-Cognitive Feedback Display
4.2 Ideation Task
4.3 Data Analysis
5 Results
6 Discussion
7 Conclusion
References
Comparing Engineering Designers' Brain Activity in Visuospatial Reasoning Tasks
1 Introduction
2 Background and Related Work
2.1 Models of Visuospatial Reasoning in (Engineering) Design
2.2 Assessing Visuospatial Reasoning in Engineering Design
2.3 EEG Studies of Visuospatial Reasoning Tasks
3 Research Methodology
3.1 Visuospatial Reasoning Tasks
3.2 Experimental Procedure
3.3 Experimental Setup
3.4 EEG Data Pre-Processing
3.5 Data Analysis
4 Results
4.1 Developments vs. Rotations
4.2 Developments vs. Views
4.3 Rotations vs. Views
5 Discussion
6 Conclusions and Further Work
References
DESIGN AI APPLICATIONS
Assessing the Alignment Between Word Representations in the Brain and Large Language Models
1 Introduction
2 Background
2.1 Modeling Neural Representations of Language With Language Models
2.2 Applying Representational Similarity Analysis (RSA) to Compare Representations of Language
2.3 Cognitive Processes Underlying Creativity and Design
3 Methods
3.1 Word Association Task
3.2 fMRI Data Analysis
3.3 Language Model: Llama-2 7b
3.4 RSA Analysis
4 Results and Discussion
4.1 Assessing Brain-LLM Alignment Across Participants and LLM Layers
4.2 Comparing Brain-LLM Alignment Between Task Conditions
4.3 Implications for Design
5 Limitations and Future Work
6 Conclusion
References
Architectural Creativity Stranded at Mid Journey? Evaluating Creative Potential of Prompts and Images in Generative AI
1 Generative Artificial Intelligence in the Design Process
2 Intelligence and Creativity: Intersecting or Disjointed Concepts?
3 Computable Approaches to Design and the Evolution of Generative AI
4 The Use of Mid-Journey Diffusion Model in Architectural Design: A Case Study
5 Design Verbalization
6 Methodology
7 GAI Images and Prompts Considered Most and Least Creative
8 Prompt Structure and Their Characteristics: Implications for Design Verbalization
9 Creative Descriptors of Design Experts and AI
10 Conclusions
References
Semantic Properties of Word Prompts Shape Design Outcomes: Understanding the Influence of Semantic Richness and Similarity
1 Introduction
2 Related Work
2.1 The Use of Semantic and Visual Representations in Design
2.2 Semantic Properties and Their Impact on Cognition and Creativity
3 Experimental Design
3.1 Participants
3.2 Design Task and Interface
3.3 Semantic Richness and Similarity of Prompt Words
4 Design Outcome Characterization and Modeling Procedure
4.1 Relationship with Semantic Richness
4.2 Relationship with Semantic Similarity
5 Results
5.1 The Relationship Between Outcomes and Semantic Richness Dimensions
5.2 Semantic Richness Does Not Fully Account for Outcome Variation
5.3 The Relationship Between Semantic Similarity and Outcome Distinctiveness
6 Discussion
6.1 Types of Design Outcomes Can Predict Semantic Richness Dimensions
6.2 Increasingly Similar Word Prompts Are Associated with Harder-To-Distinguish Design Outcomes
6.3 Implications for Design and Future Directions
6.4 Limitations
7 Conclusion
References
Overcoming Design Challenges in Coupled System Device Problems Using Agent-Based Models
1 Introduction
2 Background
2.1 Agent-Based Modeling and Multi-Agent Systems
2.2 Agent-Based Models in Engineering
2.3 Design Variables in Agent-Based Models
3 Methodology
3.1 Firefighting Drones Case Study
3.2 Modeling and Analysis
4 Results
5 Discussion
6 Conclusion
References
Correction to: How Do We Know if a Design Space Representation Is Useful? Insights from the DS-Viz Method
Correction to: Chapter 1 in: J. S. Gero (Ed.): Design Computing and Cognition'24, https://doi.org/10.1007/978-3-031-71922-6_1
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Design Computing and Cognition'24

Description

More details

Other editions

Additional editions

Person

Content

System requirements