Evaluation of Key Parameters Using Deep Convolutional Neural Networks for Airborne Pollution (PM10) Prediction

<div>Visualization of the one-dimensional kernel sliding through the input. It is displayed the full dataset as input, it is processed in batches with size 7 × <i>n</i> (<i>n</i> is the number of inputs). Then certain number of kernels is applied to each batch.</div>

Discrete Dynamics in Nature and Society

fig7

Figure 7

Figure 7: Evaluation of Key Parameters Using Deep Convolutional Neural Networks for Airborne Pollution (PM10) Prediction 