Search

Previous studies have estimated ground-level concentrations of particulate matter 2.5 (PM2.5) using satellite-derived aerosol optical depth (AOD) in conjunction with meteorological and land use variables. However, the impacts of urbanization on air pollution for predicting PM2.5 are seldom considered. Nighttime light (NTL) data, acquired with the Visible Infrared Imaging Radiometer Suite (VIIRS) aboard the Suomi National Polar-orbiting Partnership (S-NPP) satellite, could be useful for predictions because they have been shown to be good indicators of the urbanization and human activity that can affect PM2.5 concentrations. This study investigated the potential of incorporating VIIRS NTL data in statistical models for PM2.5 concentration predictions. We developed a mixed-effects model to derive daily estimations of surface PM2.5 levels in the Beijing-Tianjin-Hebei region using 3 km resolution satellite AOD and VIIRS NTL data. The results showed the addition of NTL information could improve the performance of the PM2.5 prediction model. The NTL data revealed additional details for predication results in areas with low PM2.5 concentrations and greater apparent seasonal variation due to the seasonal variability of human activity. Comparison showed prediction accuracy was improved more substantially for the model using NTL directly than for the model using the vegetation-adjusted NTL urban index that included NTL. Our findings indicate that VIIRS NTL data have potential for predicting PM2.5 and that they could constitute a useful supplemental data source for estimating ground-level PM2.5 distributions. [ABSTRACT FROM AUTHOR]

Wearable sensors-based human activity recognition introduces many useful applications and services in health care, rehabilitation training, elderly monitoring and many other areas of human interaction. Existing works in this field mainly focus on recognizing activities by using traditional features extracted from Fourier transform (FT) or wavelet transform (WT). However, these signal processing approaches are suitable for a linear signal but not for a nonlinear signal. In this paper, we investigate the characteristics of the Hilbert-Huang transform (HHT) for dealing with activity data with properties such as nonlinearity and non-stationarity. A multi-features extraction method based on HHT is then proposed to improve the effect of activity recognition. The extracted multi-features include instantaneous amplitude (IA) and instantaneous frequency (IF) by means of empirical mode decomposition (EMD), as well as instantaneous energy density (IE) and marginal spectrum (MS) derived from Hilbert spectral analysis. Experimental studies are performed to verify the proposed approach by using the PAMAP2 dataset from the University of California, Irvine for wearable sensors-based activity recognition. Moreover, the effect of combining multi-features vs. a single-feature are investigated and discussed in the scenario of a dependent subject. The experimental results show that multi-features combination can further improve the performance measures. Finally, we test the effect of multi-features combination in the scenario of an independent subject. Our experimental results show that we achieve four performance indexes: recall, precision, F-measure, and accuracy to 0.9337, 0.9417, 0.9353, and 0.9377 respectively, which are all better than the achievements of related works. [ABSTRACT FROM AUTHOR]