Ongoing
2

Development of Customized Generative Housing Design System: Integrating Cased-Based Reasoning and Shape Grammar
2025/03/01 → 2028/03/01
한국연구재단(NRF)
Computational Design
Housing
Case-Based Reasoning
Shape Grammar
Project
Finished
19
Graph Approach to Dynamic Visuospatial Perception (Gibbeum Lee)
2021/03/01 → 2025/06/15
Visuospatial perception
Graph theory
Digital twin
Behavior model
Environmental psychology
Data-driven approach
AI
User benavior data
Thesis/Dissertation
Building a GIS Framework for Real-Space Metaverse: AI-Based Prediction of Spatial Information Use and Efficient Maintenance
실공간 기반 메타버스의 GIS 구축방안: AI 기반의 공간정보 사용 예측 및 효율적 유지보수 방법 개발 연구
2022/08 → 2023/07 한국국토정보공사 (LX)
Project Introduction
This project addresses the challenge of managing spatial information in Digital Twin (DT)–based metaverse environments. By integrating real-world spatial information with user behavioral data collected in virtual environments, we developed a framework for efficient spatial management and personalized user experiences.
Using a large-scale Minecraft testbed of Daejeon city, we collected more than 750,000 user logs and survey responses from 232 participants. Based on this dataset, we created methods for graph-based spatial importance analysis and applied Graph Neural Networks (GNNs) to detect communities and predict priority areas for spatial information maintenance.
Achievements
Building a Metaverse GIS based on Spatial Information and User Perception
Placemaking based on Augmented Proximity
Like the term Urban Assemblage, cities include creating local contexts through diverse networks and relationships created by human and non-human elements.The emergence of Urban Assemblage in early 2010 is changing the flow of urban research, emphasizing the importance of network understanding in cities. Therefore, this study aims to analyze the regional structure of Daejeon from the perspective of ‘visiting’ and ‘education’ through the understanding of residents in different contexts and environments. In addition, the local value is improved by solving the limitations of physical proximity through metaverse-based virtual proximity. Augmented proximity, a concept that unifies physical and virtual proximity, is important here. With the continuing increase in online communications, virtual proximity as well as physical proximity has become a common way to connect individuals. Virtual proximity refers to the psychological closeness felt by people based on their participation in a virtual space. Hence, augmenting physical proximity with virtual types is believed to enhance connectivity within social networks, and applications that consider both types have the capability to provide new forms of interaction. In the end, we plan to provide a metaverse-based solution that can actually help users along with SKT data analysis by applying the augmented proximity concept to cities.
Publications
Placemaking based on Augmented Proximity
2021/07/01 → 2023/06/30
한국연구재단 (NRF)
AI
Augmented Proximity
Good Placemaking
Urban Network Analysis
SKT Data
Metaverse
Project
Augmented Proximity in Urban Network for Visitor Mobility: A Conceptual Proposal and Application to Cities
Cities create different local contexts through various networks created by human and non-human elements. City network analysis is used to analyze the mobility of various users, including city visitors, and to understand the space. However, existing studies have limitations in three respects. The first is that comparative indicators are limited for the proximity of cities that are being virtualized, such as smart cities and digital twins. Second, there needs to be more research on spatial patterns considering both physical and virtual environments regarding urban connectivity. Finally, even if the problem of intra-city movement is found, connecting to a user-centered rather than a technology-centered solution is not easy. In this dissertation, two stages were conducted to study the city to overcome the above three limitations. First, we defined Augmented Proximity (AP) considering physical and virtual proximity simultaneously and developed an index to compare applications such as area-based platforms implemented based on this. This concept comes from Mixed Reality (MR) and has the property of a continuum where physical and virtual proximity coexists. Second, a practical plan to understand the regional context through augmented proximity-based network analysis and overcome the physical limitations of city visitors was also established. The first experiment was conducted using the campus as a living lap, and the local context was first understood through spacial networks, and services were applied. Extending this analysis to the city, a secondary study was conducted targeting 850 POIs (Points of Interest) in Daejeon Metropolitan City, which many visitors visit. Pedestrian center physical proximity was analyzed with actual visitor data (95,817) based on a 50-meter unit cell provided by SK Telecom. Among them, ten POIs were extracted and built in the Minecraft environment. We found that the user’s destination image of Daejeon and intention to visit Daejeon were improved, and the degree of attachment to Daejeon, that is, virtual proximity, increased. This study proposed augmented proximity, a new concept that considers physical and virtual proximity and proposed an indicator to compare services or platforms to augmented proximity-based networks. In addition, for areas with low physical proximity, a virtual solution with a new perspective that can overcome physical limitations was provided through a plan to activate visits.
Publications
Augmented Proximity in Urban Network for Visitor Mobility: A Conceptual Proposal and Application to Cities (Mi Chang)
2018/03/01 → 2023/03/01
Augmented Proximity
Spatial Pattern
Urban Network Analysis
City Activation
Metaverse
Thesis/Dissertation

The purpose of this study is to analyze the behavior and reactions of visitors to the virtual art museum for the purpose of a virtual art museum centered on the audience, to help the visitor to experience the optimal virtual exhibition of the spectator, to analyze the behavior and reaction analysis data transmission method for museum and art museum officials or virtual exhibition space designers, and to assist in the efficient planning and operation of the virtual exhibition.
Publications
Museum Project
2019/03/01 → 2023/02/28
한국연구재단 (NRF)
UI/UX
Tracking & Time Technology
User Behavior Analysis
Museum Informatics
AI
Project
프로젝트 설명
해당 프로젝트는 ETRI 에서 개발하는 배송로봇과 드론의 외형을 디자인한 프로젝트 입니다.
최종 디자인 결과물은 현재 정해졌으나 보안상의 이유로 추후 업데이트 예정입니다! 기대해주세요 


Logistics Robot Design
.png&blockId=8848249b-44f8-45cc-bde0-6e2f60f96f79)
.png&blockId=fc295e60-2f4c-45d2-8304-9c5ef9084d25)

Model-Based Medical Information Classifier
2021/09/01 → 2022/08/31
(주)MedAlls
AI
Natural Language Processing
BERT
Multi-Label Classification
Project


E-Learning Platform Design based on HCI
2021/01/01 → 2022/06/30
정철어학원 (주)젭스
Future Education
HCI
User-Centered Design
Project







Smart Mirror Project
2017/09/01 → 2022/02/28
KAIST
HCI
Product Service System Design (PSSD)
Rule-based system
AI
Project
Museum Informatics centered on Visitor Experience in Art Museum
Visitor-centered approaches have been widely discussed in the museum experience research field. One notable approach was suggested by Falk and Dierking, who defined museum visitor experience as having a physical, personal, and social context. Many studies have been conducted based on this approach, yet only a few have focused on the information provided by art museums based on the integrated contexts of the visitor experience. To fill this gap, the first study was focused on the personal visitor’s information needs and viewing behavioral features according to the information delivery media as physical context. To do that, first, an online survey was conducted to grasp the types of information that visitors wanted to know, and five elements were obtained. Second, eye-tracking experiments were performed with semi-structured interviews. The information delivery media was set as follows: wall and mobile texts as commonly used in art museums. The results showed that patterns of eye movement of visitors were different according to the information delivery media. The second study investigated the influence of social contextual information contributed by individual visitors about their art museum experience. This data, called “visitor-based social contextual information” (VSCI), is the social information individuals provide—feedback, reactions, or behavioral data—that can be applied to facilitate interactions in a social context. The study included three stages: First, an online survey was conducted for a preliminary investigation of visitors’ requirements for VSCI. Second, a mobile application prototype was developed. Finally, the prototype was used in an experiment to investigate the influence of VSCI on museum experience based on visitors’ behaviors and reactions. The results indicate that VSCI has a positive impact on visitors’ museum experience.
By synthesizing the above studies, an integrated framework for museum informatics centered on the visitor experience was developed. As a result of expert evaluation, this research confirmed the high potential to enhance visitors’ museum experience. In addition, practical feedback for commercialization in actual art museums was discussed, and a deep learning-based predictive model for art museum experts was presented. Based on the suggested research of museum informatics, museums can develop information content based on a visitor-centered approach, and providing the integrated information enables visitors to experience the exhibition from new perspectives.
Publications
Museum Informatics centered on Visitor Experience (Taeha Yi)
2016/03/01 → 2021/12/31
UI/UX
Tracking & Time Technology
User Behavior Analysis
Museum Informatics
Thesis/Dissertation
Study on Motion Adaptation for Telepresence Avatars in Dissimilar Remote Spaces
In order to provide intelligent services in an indoor environment at furniture level, it is important to understand not only the physical attributes but also the semantic features of an interior space. Spatial similarity measurement is a comparison method conducted on top of a hierarchical graph representation to calculate numeric values considering quantified spatial features. Three consecutive tasks are required: indoor space modeling, user study acquiring spatial context, and spatial similarity calculation. To evaluate the effectiveness of the method, a comparison was made
with the existing random sampling method. The findings surpassed the random sampling results in four experimental cases. Spatial similarity measurement is therefore capable of analyzing the spatial context with proposed similarity criteria and equations, and it also suggests the probability of local similarity of a functional space.
Publications
Hong, S., Chang, M., Dwivedi, U., Porcellini, V., Lee, C. S., & Lee, J. H. (2020). Spatial Similarity Measurement in Dissimilar Indoor Environments Using Semantic Features for Virtual Space Services. 융합연구학회지, 4 (1), 93-110.
Dwivedi, U., Porcellini, V., Hong, S., Chang, Z., & Lee, J. H. (2019). Computing Spatial Features to Allocate Collision-free Motion-paths for Tele-presence Avatars. Proceedings of the 24th International Conference of the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA) 2019, 1, 245-254.
Telepresence Avatars in Dissimilar Remote Spaces
2017/06/01 → 2019/05/31
삼성전자 (Samsung)
Telepresence
FBS
Semantic features
Similarity Measurement
Topology
Project
Development of Intelligent Interaction Technology
based on Context Awareness and Human Intention Understanding
Publications
•
Lai, P. Y., Kim, M., Choi, M., Lee, C.-S., Porcellini, V., Yi, T. & Lee, J.-H. (2019). Framework of Judgement System for Smart Home Assistant utilizing Collective Intelligence Case-Based Reasoning
, In M.H. Haeusler, M.A. Schnabel & T. Fukuda (Eds.), Intelligent & Informed: Proceedings of the 24th International Conference of the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA) , 15-18 April, 2019 , Victoria University of Wellington, New Zealand, pp. 695-704.
•
Yi, T., Lee, I., Lee, C.-S., Lee, G., Kim, M. & Lee, J.-H. (2018). Interactive Data Acquisition for CBR System Based Smart Home Assistant
, In T. Fukuda, W. Huang, P. Jenssen, K. Crolla, and S. Alhadidi (Eds.), Learning, Ptorotyping and Adapting: Proceedings of the 23rd International Conference of the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA) , 17-19 May, 2018, Tsinghua University, Beijing, China (Vol.2, pp. 525-534). Beijing: Jingcai Xueyun Printing House.
•
Yi, T., Rhim, J., Lee, I., Narangerel, A., & Lee, J.-H. (2017). Service Design of Intergeneration Home-Sharing System Using VR-Based Simulation Technology and Optimal Matching Algorithms
. In C. Stephanidis (Ed.), HCI International Posters 2017, Part II, CCIS 714 , 9-14 July 2017, Vancouver Convention Centre, Vancouver, Canada (pp. 95-100). Springer International Publishing, AG 2017.
AI Flagship: Smart Home Assistant
2016/12/01 → 2019/04/30
과학기술정보통신부 (MSIT)
IoT
Case-Based Reasoning
FBS
Recommender system
Project
RCMS (제조업의 서비스화) Project
2014/12/01 → 2016/11/30
성균관대학교산학협력단
Case-Based Reasoning
Product Service System Design (PSSD)
Similarity Measurement
Project

Developing a case-based reasoning system to analyze environmental structures and soft services to support leisure space management
Servicescape design of leisure spaces such as theme parks influence the level of visitor satisfaction and the re-visitation rate. However, only a few large theme park operators have a separate theme of specialists with heuristic knowledge for servicescaping. In response, small companies turn to the specialists paying high fees and royalties usually leading to outdated servicescape designs. In order to help small companies to design servicescape that provide satisfying experience to the visitors, a systematical understanding of the multi-layered and complex service environment of theme parks is necessary. The purpose of this research is to integrate the concept of precedent-based design into a rule-based system by identifying and organizing the design patterns of servicescape into reusable knowledge, propose a servicescape design support system, and confirm whether if the system helps to increase designers’ credence regarding their design in terms of its market success. To accomplish these research aims, six steps were carried out: (1) selection of globally accepted facilities for being successful, (2) analysis of precedents for the discovery of repeating servicescape design patterns, (3) knowledge acquisition and organization for each design patterns, (4) formulation of servicescape rules using the acquired and organized knowledge, (5) integration of the rules into a general design process of a facility as a system, and (6) application of the system in practice. The resulting system was presented to an expert in the field of theme park designs to confirm whether the design process is applicable and how it will perform in practice. From this interview, we received positive feedbacks and well as feedbacks for improvements in the aspects of the system’s applicability in practice, its functionality, and usability. After confirming the applicability of the overall process of the system, we conducted an experiment to experts in practice from various design and planning fields and asked to go through two sets of scenarios in which the first is to design a given site without the system and the second is to design the same site with the system. After each scenario, the subjects were asked to fill out a revised After-Scenario Questionnaire (ASQ). From this experiment, the results indicate that the subjects felt an increase in their credence toward their designs in terms of its market success while the satisfaction with the easiness and the time it took decreased. If our system is revised in the aspects of usability and functionality, our system which uses precedent design patterns could be used to help small company designers to produce servicescape concept designs with more design credence.
Publications
Theme Park Project
2013/06/01 → 2016/05/31
한국연구재단 (NRF)
Case-Based Reasoning
Rule-based system
Servicescape
Design Pattern
Project
Bio-inspired design was introduced as an alternative method to encourage breakthrough innovations during design projects by stimulating analogical reasoning and thinking of designers.
However, the method did not perform as well as researchers expected because most designers, who are novices in the fields of biology and ecology, cannot infer the proper analogue (i.e. biological system) from nature. To resolve this fundamental problem, a causal model based representation framework for ‘analogical reasoning’ – searching and selecting the biological systems to apply – have been developed. In addition, ontology based repository structures and retrieval systems have been proposed to support ‘analogical thinking’ of designers. Nevertheless, these systematic approaches still restrict the candidates and inevitably lose potential biological systems relevant to the design project, due to the ‘physical relation’ biased problem and the ambiguity of the indexing mechanism of both current representation frameworks and retrieval systems. For example, the causality based support system known as a robust representation framework for a single biological system, stores information of a biological system only by its internal ‘physical relations’ and retrieves biological systetabms only by the physical relevance. However, from the perspective of ecological thinking, the further relatedness of ‘physical, biological, and ecological relations’ composes the holistic concept used to identify an organism in the flow of evolution because the ‘biological and ecological relations’ are also involved in the traits that designers may be interested in. Therefore, the supplementary information for ‘biological and ecological relations’ must be added to index the biological and environmental interactions, and to use the connectivity among entire organisms in the retrieval process. In this research, a causality based holistic representation framework for biological systems and an ‘all-connected’ ontology based repository and retrieval system are developed as a knowledge based recommendation system to support bio-inspired design. The knowledge-based system we developed allows engineering designers to search and select a particular biological system and extract design strategy without much biological knowledge. This effort provides more opportunities in a bio-inspired design process by adding potential biological systems that might previously not have been considered.
Publications
Homo Mimicus (Sun-Joong Kim)
2012/03/01 → 2016/03/01
Bio-inspired design
Ontology
Biological metadata
Recommender system
Thesis/Dissertation
Style synthesis and analysis of car designs for style quantification
Understanding how similar design appears is a key element to understanding companies’ design strategies. However, it is difficult to evaluate companies’ design strategies with conventional style measurement methods since they only taxonomically measure whether a specific characteristic is included in a specific style. This study numerically measured car design similarities to synthesize and analyze car brand styles, thereupon discovering the design trends among car brands for strategic design positioning. This paper aims to find methods for quantifying style differences and identifying unique design elements of car designs among 23 automobile manufacturers based on design similarities of a large quantity of car designs (N
= 119). To achieve this goal, a hybrid style quantification methodology – a mixture of Fourier decomposition, eye tracker, and shape grammar – was created to evaluate similarities, visual significance, and combinations of 19 car design elements. Fourier decomposition was incorporated to find the quantifiable values of design similarities of car design elements. Visual significance analysis was also conducted for each car design element through eye tracker to measure the importance of certain design elements for weighting factors. Then, each combination of design elements was compared with car design elements of other cars for similarity calculations. Finally, car design alternatives were synthesized, and transitions of design positioning were analyzed based on the similarity values weighed by the visual significance results. Using the suggested methods, alternate designs can be synthesized while preserving brands’ design styles, and design trends can be analyzed for strategic evaluation.
Publications
Style Synthesis and Analysis of Car Designs (Kyung-Hoon Hyun)
2012/03/01 → 2016/02/29
Design strategy
Product asethetics
Brand identity
Visual significance
Style analysis
Thesis/Dissertation

Image-based Tactile Emojis: Improved Interpretation of Message Intention and Subtle Nuance for Visually Impaired Individuals
To enhance missing nonverbal cues in computer-mediated communication using text, those who can see often use emojis or emoticons. Although emojis for the sighted have transformed throughout the years to animated forms and added sound effects, emojis for visually impaired people remain underdeveloped. This study tested how tactile emojis based on visual imagery combined with the Braille system can enhance clarity in the computer-mediated communication environment for those with visual impairments. Results of this study confirmed three things: Visually impaired subjects were able to connect emotional emojis to the emotion they represented without any prior guidance, image-based (picture-based) and non-image-based (abstraction-based) tactile emoji were equally learnable, and the clarity of intended meaning was improved when an emoji was used with text (Braille). Thirty visually impaired subjects were able to match an average of 67% of emotions without prior guidance, and three of the four subjects who matched perfectly both before and after guidance were congenitally blind. The subjects had the most trouble discriminating the facial feature of “fear” between “sadness” or “surprised” for they shared similar traits. After guidance, the image-based tactile design elicited an average of 81% correct answers, whereas the non-image-based tactile design elicited an average of 37%, showing that the image-based tactile design was more effective for learning the meaning of emojis. The clarity of the sentence was also improved. This study shows that image-based tactile emojis can improve the texting experience of visually impaired individuals to a level where they can communicate subtle emotional cues through tactile imagery. This advance could minimize the service gap between sighted and visually impaired people and offer a much more abundant computer-mediated communication environment for visually impaired individuals.
Publications
Image-based Tactile Emojis (Yuri Choi)
2013/03/01 → 2015/03/01
HCI
UI/UX
Computer-mediated communication (CMC)
Instant Messaging (IM)
Tactile feedback
Thesis/Dissertation

A similarity measurement framework of PSSD cases based on context-based activity model
Design experience from previous design cases could help designers solving current design problems. Therefore, a case-based recommender system can recall suitable design cases for designers based on a similarity measurement mechanism. In the context of Product-Service System (PSS) design, the measurement of similarity between different cases becomes more challenging because of the complex nature of the PSS design. In this research, we propose a similarity measurement framework of PSS design cases based on the context-based activity model. In the proposed framework, a PSS design case is indexed and quantified by design activity element, design process, and function requirement. Ways to measure similarity between design indexes and design cases are also specified. A case study along with an empirical validation was conducted to validate the framework.
Publications
PSSD Project
2011/10/01 → 2013/09/30
에스팜소프트주식회사
Case-Based Reasoning
Product Service System Design (PSSD)
Recommender system
Project
A quantitative approach for assessment of creativity in product design
Most of the assessment of creativity in product design is based on the outcome, not the design process from which the creative ideas are derived. In this paper, we revealed the correlation coefficient of 20 factors critical in the product design process and the quality of design creativity via investigation of the design processes and outcomes of 30 senior student designers. Six closely related factors were identified as variables to calculate the design creativity. An assessment formula was proposed: the corresponding correlation coefficient is the weight factor of each variable, and the sum represents the design creativity degree. Our quantitative approach can improve the validity and reliability of assessment of creativity in product design.
Publications
Assessment of creativity in product design (Xiaofang Yuan)
2009/03/01 → 2013/03/01
Creativity
Quantitative assessment
Design process
Product Service System Design (PSSD)
Thesis/Dissertation



.png&blockId=29275710-81b2-808f-8bbd-ea7c1ee333e5)









