期刊名称：International Journal of Distributed Sensor Networks
印刷版ISSN：1550-1329
电子版ISSN：1550-1477
出版年度：2018
卷号：14
期号：10
页码：1
DOI：10.1177/1550147718804702
出版社：Hindawi Publishing Corporation
摘要：It is a great challenge to offer a fine-grained and accurate PM 2.5 monitoring service in urban areas as required facilities are very expensive and huge. Since PM 2.5 has a significant scattering effect on visible light, large-scale user-contributed image data collected by the mobile crowdsensing bring a new opportunity for understanding the urban PM 2.5 . In this article, we propose a fine-grained PM 2.5 estimation method based on random forest with data announced by meteorological departments and collected from smartphone users without any PM 2.5 measurement devices. We design and implement a platform to collect data in the real world including the image provided by users. By combining online learning and offline learning, the method based on random forest performs well in terms of time complexity and accuracy. We compare our method with two kinds of baselines: subsets of the whole data sets and six classical models (such as logistic, naive Bayes). Six kinds of evaluation indexes (precision, recall, true-positive rate, false-positive rate, F -measure, and receiver operating characteristic curve area) are used in the evaluation. The experimental results show that our method achieves high accuracy (precision: 0.875, recall: 0.872) on PM 2.5 estimation, which outperforms the other methods.
关键词：Air quality estimation; mobile crowdsensing; semi-supervised random forest; online random forest; data fusion
