Jeongyeop Baek
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jeongyeop Baek has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Lisa Lim
Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea.
5 shared publications - Seongju Chang
Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea
3 shared publications - Daehwa Baek
Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, Yuseong-gu, Republic of Korea
2 shared publications - Duc Minh Le2 shared publications
- Jaechang Noh
Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, Yuseong-gu, Republic of Korea
2 shared publications - Albert Tonghoon Han
Korea Advanced Institute of Science and Technology
1 shared publication
Latest Publications
- 29 October 2025
- Published by SAGE Publications in Indoor and Built Environment
- Vol. 35 (1) , 84-100
Designing liveable underground spaces: The role of experiences and attitudes in shaping environmental perceptions
This study investigated the interplay between prior experiences, attitudes and the willingness to reside (WR) in underground spaces, providing insights for improving public acceptance of such environments. This study employed partial least squares structural equation modelling to evaluate the relationships amongst the variables using data from 215 South Korean participants. The findings revealed that prior playing experiences significantly could enhance safety and calmness attitudes and strongly predicting people's WR in underground spaces. Conversely, prior living and working experiences exert minimal influence. While negative effects and confinement attitudes are less impactful, fostering positive emotional experiences is crucial for promoting acceptance. This study has highlighted the importance of designing underground spaces that prioritise leisure activities that cultivate positive perceptions. Additionally, although this research primarily focused on psychological and experiential factors, future investigations are encouraged to explore environmental variables, such as lighting and ventilation, which are critical in shaping public attitudes. These findings offer practical guidance for urban planners and policymakers aiming to develop sustainable and liveable underground environments to address urban density challenges.
- 29 October 2025
- Published by SAGE Publications in Indoor and Built Environment
- Vol. 35 (1) , 84-100
Designing liveable underground spaces: The role of experiences and attitudes in shaping environmental perceptions
This study investigated the interplay between prior experiences, attitudes and the willingness to reside (WR) in underground spaces, providing insights for improving public acceptance of such environments. This study employed partial least squares structural equation modelling to evaluate the relationships amongst the variables using data from 215 South Korean participants. The findings revealed that prior playing experiences significantly could enhance safety and calmness attitudes and strongly predicting people's WR in underground spaces. Conversely, prior living and working experiences exert minimal influence. While negative effects and confinement attitudes are less impactful, fostering positive emotional experiences is crucial for promoting acceptance. This study has highlighted the importance of designing underground spaces that prioritise leisure activities that cultivate positive perceptions. Additionally, although this research primarily focused on psychological and experiential factors, future investigations are encouraged to explore environmental variables, such as lighting and ventilation, which are critical in shaping public attitudes. These findings offer practical guidance for urban planners and policymakers aiming to develop sustainable and liveable underground environments to address urban density challenges.
- 13 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (10) , 7643-7656
An Interpretable AI for Smart Homes: Identifying Fall Prevention Strategies for Older Adults Using Multimodal Deep Learning
Falls are a significant cause of mortality among older adults and are considered preventable emergencies. We developed an interpretation framework, including multimodal predictive models that capture both static and timeseries data, and analyzed global feature importance via a perturbation approach, permutation importance (PIMP), and SHapley Additive exPlanations (SHAP) to identify fall prevention strategies at home. Our predictive model utilizing the BiCrossNet architecture achieved a prediction accuracy of 98% when 12,540 data points were used. It was found that activity-related and indoor thermal environment features are important for predicting fall emergency occurrences (FEOs). Interestingly, extended active time in the living room/kitchen and outdoors decreases the FEO ratio, whereas extended active time in the bedroom and bathroom increases the FEO ratio. For example, increasing the active time in the living room/kitchen from 60−70 to 130−140 minutes reduced the FEO ratio by 32%. Furthermore, indoor temperature and humidity were found to be important depending on the outdoor conditions. Moreover, this study shows the importance of personalized prevention strategies depending on the underlying health conditions of older adults
- 13 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (10) , 7643-7656
An Interpretable AI for Smart Homes: Identifying Fall Prevention Strategies for Older Adults Using Multimodal Deep Learning
Falls are a significant cause of mortality among older adults and are considered preventable emergencies. We developed an interpretation framework, including multimodal predictive models that capture both static and timeseries data, and analyzed global feature importance via a perturbation approach, permutation importance (PIMP), and SHapley Additive exPlanations (SHAP) to identify fall prevention strategies at home. Our predictive model utilizing the BiCrossNet architecture achieved a prediction accuracy of 98% when 12,540 data points were used. It was found that activity-related and indoor thermal environment features are important for predicting fall emergency occurrences (FEOs). Interestingly, extended active time in the living room/kitchen and outdoors decreases the FEO ratio, whereas extended active time in the bedroom and bathroom increases the FEO ratio. For example, increasing the active time in the living room/kitchen from 60−70 to 130−140 minutes reduced the FEO ratio by 32%. Furthermore, indoor temperature and humidity were found to be important depending on the outdoor conditions. Moreover, this study shows the importance of personalized prevention strategies depending on the underlying health conditions of older adults
- 12 April 2024
- Published by SAGE Publications in HERD: Health Environments Research & Design Journal
- Vol. 17 (3) , 411-427
Toward Healthy Underground Spaces: A Review of Underground Environmental Design Factors and Their Impacts on Users' Physiological and Psychological Health
Objective: This study aims to review and synthesize what design factors are associated with the physiological and psychological health of occupants in underground spaces. Background: The development of underground spaces offers options to global challenges, such as traffic congestion, urban overcrowding, the revitalization of dormant underground areas, disaster mitigation, and adaptation to extreme environments. Despite these advantages, concerns persist about potential adverse effects on human health in these environments. This situation underlines the necessity of systematically identifying concerns and perceptions related to health in underground spaces. Methods: A narrative literature review was conducted to examine the relationship between design factors and health factors across 21 empirical studies. Based on the review of the identified literature, a relationship diagram was developed to depict the interconnections between the identified design and health factors. Results: The analysis identified design factors related to the air, sound, light, nature, transport, and spatial context of underground spaces, each of which exerted relationships with occupants’ physiological and psychological health factors. The relationship diagram indicated that the psychological factor “feeling of confinement” was mentioned most frequently, suggesting that it is one of the most extensively researched factors in this context. Conclusions: The relationship diagram aims to bridge the existing knowledge gap and set the stage for future research endeavors. The ultimate goal is to refine urban living standards by leveraging the potential of underground spaces while ensuring health and well-being.
- 12 April 2024
- Published by SAGE Publications in HERD: Health Environments Research & Design Journal
- Vol. 17 (3) , 411-427
Toward Healthy Underground Spaces: A Review of Underground Environmental Design Factors and Their Impacts on Users' Physiological and Psychological Health
Objective: This study aims to review and synthesize what design factors are associated with the physiological and psychological health of occupants in underground spaces. Background: The development of underground spaces offers options to global challenges, such as traffic congestion, urban overcrowding, the revitalization of dormant underground areas, disaster mitigation, and adaptation to extreme environments. Despite these advantages, concerns persist about potential adverse effects on human health in these environments. This situation underlines the necessity of systematically identifying concerns and perceptions related to health in underground spaces. Methods: A narrative literature review was conducted to examine the relationship between design factors and health factors across 21 empirical studies. Based on the review of the identified literature, a relationship diagram was developed to depict the interconnections between the identified design and health factors. Results: The analysis identified design factors related to the air, sound, light, nature, transport, and spatial context of underground spaces, each of which exerted relationships with occupants’ physiological and psychological health factors. The relationship diagram indicated that the psychological factor “feeling of confinement” was mentioned most frequently, suggesting that it is one of the most extensively researched factors in this context. Conclusions: The relationship diagram aims to bridge the existing knowledge gap and set the stage for future research endeavors. The ultimate goal is to refine urban living standards by leveraging the potential of underground spaces while ensuring health and well-being.
- Open Access
- 29 December 2023
- Published by Elsevier in Sustainable Cities and Society
- Vol. 101
Unveiling pedestrian injury risk factors through integration of urban contexts using multimodal deep learning
- 29 December 2023
- Published by Elsevier in Sustainable Cities and Society
- Vol. 101
Open AccessUnveiling pedestrian injury risk factors through integration of urban contexts using multimodal deep learning
- 28 November 2022
- Published by Elsevier in Building and Environment
- Vol. 228
Vision-based personal thermal comfort prediction based on half-body thermal distribution
- 28 November 2022
- Published by Elsevier in Building and Environment
- Vol. 228
Vision-based personal thermal comfort prediction based on half-body thermal distribution
- 4 August 2022
- Published by Taylor & Francis in Journal of Building Performance Simulation
- Vol. 15 (6) , 717-734
Enhanced LSTM-based community energy consumption prediction model leveraging shared building cluster datasets
Unlike in the past, as the scale of buildings expands from a single building to a group of buildings, it is necessary to respond to the demand for energy consumption for the entire community. This study attempted to improve the electricity consumption prediction performance of single buildings by reflecting the inherent occupant behaviour patterns embedded in the shared electricity consumption data of single buildings. The proposed method utilized electricity consumption data for all other 7 target buildings as a part of LSTM model inputs in combination with meteorological data to predict the electricity consumption profile of a specific building. As a result, the proposed method reduced the error by utilizing the similar energy profiles of the surrounding buildings, *and the prediction performance of the total electricity consumption of the community was increased by 5.11% based on RMSE. The newly proposed method reflects the inherent occupant behaviour patterns and temporal electricity consumption patterns from energy profiles of nearby buildings.
- 4 August 2022
- Published by Taylor & Francis in Journal of Building Performance Simulation
- Vol. 15 (6) , 717-734
Enhanced LSTM-based community energy consumption prediction model leveraging shared building cluster datasets
Unlike in the past, as the scale of buildings expands from a single building to a group of buildings, it is necessary to respond to the demand for energy consumption for the entire community. This study attempted to improve the electricity consumption prediction performance of single buildings by reflecting the inherent occupant behaviour patterns embedded in the shared electricity consumption data of single buildings. The proposed method utilized electricity consumption data for all other 7 target buildings as a part of LSTM model inputs in combination with meteorological data to predict the electricity consumption profile of a specific building. As a result, the proposed method reduced the error by utilizing the similar energy profiles of the surrounding buildings, *and the prediction performance of the total electricity consumption of the community was increased by 5.11% based on RMSE. The newly proposed method reflects the inherent occupant behaviour patterns and temporal electricity consumption patterns from energy profiles of nearby buildings.