Research Article
A DBN-Based Deep Neural Network Model with Multitask Learning for Online Air Quality Prediction
Table 1
The 21 elements in the candidate feature set.
| # | Feature |
| 1 | The current concentration of the target station (μg/m3) | 2 | The current PM10 concentration of the target station(μg/m3) | 3 | The current NO2 concentration of the target station (μg/m3) | 4 | The current CO concentration of the target station (mg/m3) | 5 | The current O3 concentration of the target station (μg/m3) | 6 | The current SO2 concentration of the target station (μg/m3) | 7 | Weather | 8 | Temperature (°C) | 9 | Atmospheric pressure (hPa) | 10 | Relative humidity | 11 | Wind speed (m/s) | 12 | Wind direction | 13 | The current concentration of the selected nearby station (μg/m3) | 14 | The current PM10 concentration of the selected nearby station (μg/m3) | 15 | The current NO2 concentration of the selected nearby station (μg/m3) | 16 | The current CO concentration of the selected nearby station (mg/m3) | 17 | The current O3 concentration of the selected nearby station (μg/m3) | 18 | The current SO2 concentration of the selected nearby station (μg/m3) | 19 | The day of year | 20 | The day of week | 21 | The hour of day |
|
|