Automated classification of time-activity-location patterns for improved estimation of personal exposure to air pollution.
Automated classification of time-activity-location patterns for improved estimation of personal exposure to air pollution.
复制标题
DOI：
10.1186/s12940-022-00939-8
复制
发表时间：
2022-12-09
影响因子：
6
通讯作者：
Jones, Roderic L.
中科院分区：
文献类型：
--
作者：
Chatzidiakou, Lia;Krause, Anika;Kellaway, Mike;Han, Yiqun;Li, Yilin;Martin, Elizabeth;Kelly, Frank J.;Zhu, Tong;Barratt, Benjamin;Jones, Roderic L.
关键词：
空气污染流行病学主要依赖于固定的室外空气质量监测站的测量结果，以得出人口规模的暴露。由于污染物浓度和吸入率因地点和活动的不同而有很大差异，因此，确定个人时间-活动-地点模式的特征对于准确估计个人接触和剂量至关重要。我们开发并评估了一个自动化模型，用于对主要的与安全相关的微环境（家庭，工作，其他静态，在途）进行分类，并将其分为室内和室外位置，睡眠活动和五种交通方式（步行，骑自行车，汽车，公共汽车，地铁/火车），并采用运动生态学和人工智能领域的多学科方法。作为输入参数，我们使用GPS坐标，加速度计和噪音，收集在1分钟的时间间隔与一个有效的个人空气质量监测器（PAM）进行了35名志愿者一周。然后根据参与者保存的手动时间活动日志对模型分类进行评估。总体而言，该模型在对家庭、工作和其他室内微环境进行分类时表现可靠（F1得分>0.70），但在对睡眠和访问室外微环境时表现一般（F1得分分别为0.57和0.3）。随机森林方法在运输方式分类方面表现很好（F1得分>0.91）。我们发现，自动化方法的性能显着超过手动日志。用于时间-活动分类的自动化模型可以显著改善暴露度量。这些模型可以用许多编程语言开发，如果制定得很好，可以在大规模健康研究中具有普遍适用性，通过智能手机技术随时收集的参数提供日常生活中环境健康风险的全面情况。在线版本包含补充材料，可通过10.1186/s12940-022-00939-8获取。
Air 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. We 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. Overall, 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. Automated 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. The online version contains supplementary material available at 10.1186/s12940-022-00939-8.
登录
查看更多内容
影响因子：
4.5
作者：
通讯作者：
--
中国北京不同通勤方式PM2.5和CO个人暴露量比较
影响因子：
9.8
作者：
Huang, Jing;Deng, Furong;Guo, Xinbiao
通讯作者：
Guo, Xinbiao
影响因子：
3
作者：
Asimina, Stamatelopoulou;Chapizanis, D.;Sarigiannis, D.
通讯作者：
Sarigiannis, D.
影响因子：
5.1
作者：
Genuer, Robin;Poggi, Jean-Michel;Tuleau-Malot, Christine
通讯作者：
Tuleau-Malot, Christine
DOI：
10.1038/jes.2014.78
发表时间：
2016-07-01
影响因子：
4.5
作者：
Glasgow, Mark L.;Rudra, Carole B.;Mu, Lina
通讯作者：
Mu, Lina