Acoustic Scene Classification and Visualization of Beehive Sounds Using Machine Learning Algorithms and Grad-CAM

Figure 10

Visualization of MFCCs. Discriminative regions captured using VGG-13 are shown in heatmaps for the last convolutional layer. (a), (b), and (c) are annotated Bee; (d), (e), and (f) are annotated noBee.

(a)

(b)

(c)

(d)

(e)

(f)