Assessing Personal PM_2.5 Exposure: A Method Leveraging Movement Routes and Activity Space Information

Indoor Air, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

Previous studies have consistently shown a significant correlation between air pollution, particularly PM 2.5 , and various diseases, as well increased mortality rates. This study introduces novel approach for predicting time‐specific indoor exposure by incorporating individual movement routes activity spaces using GPS tracking data time–activity diary. The models were trained separately each hour of the day (e.g., 0:00–0:59, 1:00–1:59) with total 24 models. Their applicability was demonstrated gathered from actual participants. Additionally, automated machine learning ( AutoML ) utilized to optimize prediction performance. results revealed that proposed model effectively accounted influence outdoor concentrations meteorological factors. performance varied across different environments, subway station showing highest accuracy. Future research should address these uncertainties, adopt more advanced modeling techniques, consider diverse variables comprehensive understanding. insights this could significantly enhance health risk assessments associated fine particulate matter exposure.

Language: Английский

Predicting indoor PM levels in shared office using LSTM method

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 112407 - 112407

Published: March 1, 2025

Language: Английский

Assessing PM_2.5 Exposure and Contribution Rates by Cluster Microenvironments via a Time-Use Survey

Korean Journal of Environmental Health Sciences, Journal Year: 2024, Volume and Issue: 50(5), P. 311 - 321

Published: Oct. 30, 2024

Language: Английский