Imperial College London
Portrait Picture

ProfessorFrankKelly

Faculty of Medicine, School of Public Health

Battcock Chair in Community Health and Policy
 
 
 
//

Contact

 

+44 (0)20 7594 8098 ext 48098frank.kelly Website

 
 
//

Location

 

Sir Michael Uren HubWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Chatzidiakou:2022:10.1186/s12940-022-00939-8,
author = {Chatzidiakou, L and Krause, A and Kellaway, M and Han, Y and Li, Y and Martin, E and Kelly, FJ and Zhu, T and Barratt, B and Jones, RL},
doi = {10.1186/s12940-022-00939-8},
journal = {Environmental Health},
title = {Automated classification of time-activity-location patterns for improved estimation of personal exposure to air pollution},
url = {http://dx.doi.org/10.1186/s12940-022-00939-8},
volume = {21},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - BackgroundAir pollution epidemiology has primarily relied on measurements from fixed outdoor air quality monitoring stations to derive population-scale exposure. Characterisation of individual time-activity-location patterns is critical for accurate estimations of personal exposure and dose because pollutant concentrations and inhalation rates vary significantly by location and activity.MethodsWe developed and evaluated an automated model to classify major exposure-related microenvironments (home, work, other static, in-transit) and separated them into indoor and outdoor locations, sleeping activity and five modes of transport (walking, cycling, car, bus, metro/train) with multidisciplinary methods from the fields of movement ecology and artificial intelligence. As input parameters, we used GPS coordinates, accelerometry, and noise, collected at 1 min intervals with a validated Personal Air quality Monitor (PAM) carried by 35 volunteers for one week each. The model classifications were then evaluated against manual time-activity logs kept by participants.ResultsOverall, the model performed reliably in classifying home, work, and other indoor microenvironments (F1-score>0.70) but only moderately well for sleeping and visits to outdoor microenvironments (F1-score=0.57 and 0.3 respectively). Random forest approaches performed very well in classifying modes of transport (F1-score>0.91). We found that the performance of the automated methods significantly surpassed those of manual logs.ConclusionsAutomated models for time-activity classification can markedly improve exposure metrics. Such models can be developed in many programming languages, and if well formulated can have general applicability in large-scale health studies, providing a comprehensive picture of environmental health risks during daily life with readily gathered parameters from smartphone technologies.
AU  - Chatzidiakou,L
AU  - Krause,A
AU  - Kellaway,M
AU  - Han,Y
AU  - Li,Y
AU  - Martin,E
AU  - Kelly,FJ
AU  - Zhu,T
AU  - Barratt,B
AU  - Jones,RL
DO  - 10.1186/s12940-022-00939-8
PY  - 2022///
SN  - 1476-069X
TI  - Automated classification of time-activity-location patterns for improved estimation of personal exposure to air pollution
T2  - Environmental Health
UR  - http://dx.doi.org/10.1186/s12940-022-00939-8
UR  - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000895967900002&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=a2bf6146997ec60c407a63945d4e92bb
UR  - https://ehjournal.biomedcentral.com/articles/10.1186/s12940-022-00939-8
UR  - http://hdl.handle.net/10044/1/110126
VL  - 21
ER  -
Download