Safe Indoor Environment

Indoor environments play a critical role in health, safety, and infection control. From healthcare facilities to shared public interiors, spatial configuration can either mitigate or exacerbate health risks. Our work investigates how airflow, visibility, circulation patterns, and zoning can reduce exposure to infectious diseases and support psychological comfort.

By analyzing spatial attributes and their relationship with user behavior, we develop design strategies that improve air quality, minimize contamination risk, and enable adaptive responses in times of public health crisis. We aim to create indoor environments that are not only functional but also resilient and healing.

AI home monitoring for behavioral markers of cerebrovascular disease

Baek, J., Cho, K. H., Lim, L., & Chong, J. W. (2026). AI home monitoring for behavioral markers of cerebrovascular disease. npj Digital Medicine.

Cerebrovascular disease (CeVD) is a major health concern in aging populations, and early identification is crucial for improving outcomes. We propose a framework to identify potential CeVD prodromal individuals and estimate diagnostic risk using behavioral and environmental data collected from contactless sensors in real-world homes. We used 13,362 samples (14-day windows) from 1224 older adults (598 healthy, 28 prodromal, 598 diagnosed) in South Korea. The framework achieved an area under the precision-recall curve of 0.85 for prodromal identification and accuracy of 96.53% for predicting imminent diagnostic risk within the prodromal group. Model interpretation identified key digital behavioral markers, including frequent continuous activity and shorter inactive time during bedtime preparation hours and evening hours. Our approach offers the potential to facilitate early detection of CeVD at home.

Smart home healthcare using artificial intelligence of things: Emergency prediction and prevention for cerebrovascular disease patients

Baek, J., Chong, J. W., Cho, K. H., & Lim, L. (2026). Smart home healthcare using artificial intelligence of things: Emergency prediction and prevention for cerebrovascular disease patients. Engineering Applications of Artificial Intelligence, 163, 112870.

This study leveraged smart home data and AI to predict Cerebrovascular disease (CeVD) emergencies early. The dataset included individual health conditions and sequential lifelogs from 1130 CeVD patients, including 130 emergencies. We achieved an AUPRC of 0.94 with 28 days of data, using the CrossNet architecture. We further identified emergency prevention strategies, including: increasing both low and high active time by 1 and 1.5 h/day, while decreasing inactive time for patients aged 85+; maintaining 7 h of sleep (8 h if cardiovascular); minimizing sleep fragmentation for patients aged 85+ and with diabetes; and cold indoor temperatures increase the emergency risk, while hot indoor temperatures are risky in cold weather. These findings highlight the potential of smart home monitoring based on AIoT to predict emergencies and identify prevention strategies.

An Interpretable AI for Smart Homes: Identifying Fall Prevention Strategies for Older Adults Using Multimodal Deep Learning

Baek, J., Li, Y., Lim, L., & Chong, J. W. (2025). An Interpretable AI for Smart Homes: Identifying Fall Prevention Strategies for Older Adults Using Multimodal Deep Learning. IEEE Journal of Biomedical and Health Informatics.

Falls are a significant cause of mortality among older adults and are considered preventable emergencies. We developed an interpretation framework, including multi-modal predictive models that capture both static and time-series data, global feature importance analysis via a perturbation approach, permutation importance (PIMP), SHap-ley Additive exPlanations (SHAP) for time-series data ex-planation, and intervention of selected features 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 (FEO).

Evaluating the impact of windows, artificial windows, and ceiling height on stress levels through subjective and objective measures

Baek, D., Kim, H., Wei, Q., Lee, S., & Lim, L. (2025). Evaluating the impact of windows, artificial windows, and ceiling height on stress levels through subjective and objective measures. Building and Environment, 113182.

This study examined how specific indoor design factors affect stress levels, focusing on four physical mock-up rooms: (1) a wall-only, (2) a window, (3) an artificial window, and (4) a higher ceiling height. When the stress levels in the four rooms were compared, the participants in the rooms with a window presented significantly lower stress levels than did those in the three other rooms, with a wall-only, an artificial window, and a higher ceiling height. Interestingly, the room with a higher ceiling height presented varying stress levels relative to other rooms. The stress levels at higher ceiling heights were significantly higher than those in the room with a window. However, compared with a wall-only room or an artificial window room, stress levels in a room with a higher ceiling height statistically insignificantly differed and fluctuated depending on the type of stress measurement.

Page updated

Google Sites

Report abuse