Air quality based optimal path search model for spatio-temporal data set

CAVisAP: Context-Aware Visualization of Outdoor Air Pollution with IoT Platforms

“…[14], [17] and [28] cover majority of the pollutants mentioned in the above standards, while [29] consider 12 pollutants. However, pollutant types are not specified in several studies such as [16], [18] and [30]. Overall, findings from review show that majority of the studies consider carbon oxides or particulate matter which demonstrate significance and widespread nature of the pollutants.…”

“…Hence numerous works propose systems to monitor and predict ambient air pollution. Studies in [17], [18], [19] demonstrate various solutions for outdoor air quality, while other papers such as [20], [21], [22] and [23] consider both environment types.…”

“…For example, in [20] sensor node with 12 built-in sensors is equipped, while authors in [12] and [15] use individual pollutant sensors. [18], [30] and [31] work with historical air pollution datasets and [30] further considers traffic datasets to estimate more accurate pollution rates. Crowd-sensing is another widespread approach to monitor air pollution.…”

“…[23], [32] and [33] visualizes data with pollution heatmaps. [18] and [23] provide pollution-based routes from origin to destination. [14], [19], [28] and [36] and visualize real-time and historical data with line charts.…”