@article{ART003383489},
author={Joonwoo Lee and Seungho Kim and Scott Uk-Jin Lee},
title={Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2026},
volume={31},
number={9},
pages={77-84}
TY - JOUR
AU - Joonwoo Lee
AU - Seungho Kim
AU - Scott Uk-Jin Lee
TI - Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting
JO - Journal of The Korea Society of Computer and Information
PY - 2026
VL - 31
IS - 9
PB - The Korean Society Of Computer And Information
SP - 77
EP - 84
SN - 1598-849X
AB - Generative image models can rapidly produce UI prototypes, but uncontrolled sampling reduces comparability and may omit functional requirements. This study proposes a controlled generation and evaluation procedure using predefined layout archetypes for a scientific dashboard visualizing underwater multi-sensor fusion and BOTMA tracking simulations. Twelve prototypes were generated by crossing three model groups with four layout archetypes and evaluated by three blinded experts using quality ratings and requirement coding. Sixteen implementation paths were also tested via automated browser checks. Results showed good reliability for quality ratings (ICC(2,3)=0.839) but low agreement for requirement coding (Fleiss’ κ=0.248). OpenAI achieved the highest quality scores, while Gemini showed the highest requirement coverage. The findings suggest that layout archetypes enable traceable structural variation, while static prototypes should be complemented with validation and verification.
KW - Generative-AI;UI Prototype;Dashboard Design;Info Visualization;Expert Evaluation
DO -
UR -
ER -
Joonwoo Lee, Seungho Kim and Scott Uk-Jin Lee. (2026). Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting. Journal of The Korea Society of Computer and Information, 31(9), 77-84.
Joonwoo Lee, Seungho Kim and Scott Uk-Jin Lee. 2026, "Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting", Journal of The Korea Society of Computer and Information, vol.31, no.9 pp.77-84.
Joonwoo Lee, Seungho Kim, Scott Uk-Jin Lee "Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting" Journal of The Korea Society of Computer and Information 31.9 pp.77-84 (2026) : 77.
Joonwoo Lee, Seungho Kim, Scott Uk-Jin Lee. Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting. 2026; 31(9), 77-84.
Joonwoo Lee, Seungho Kim and Scott Uk-Jin Lee. "Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting" Journal of The Korea Society of Computer and Information 31, no.9 (2026) : 77-84.
Joonwoo Lee; Seungho Kim; Scott Uk-Jin Lee. Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting. Journal of The Korea Society of Computer and Information, 31(9), 77-84.
Joonwoo Lee; Seungho Kim; Scott Uk-Jin Lee. Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting. Journal of The Korea Society of Computer and Information. 2026; 31(9) 77-84.
Joonwoo Lee, Seungho Kim, Scott Uk-Jin Lee. Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting. 2026; 31(9), 77-84.
Joonwoo Lee, Seungho Kim and Scott Uk-Jin Lee. "Expert Evaluation and Implementation Feasibility of AI-Generated Scientific Dashboard Prototypes Using Controlled Layout Prompting" Journal of The Korea Society of Computer and Information 31, no.9 (2026) : 77-84.
