Deep Learning Based Proactive Caching for Effective WSN-Enabled Vision Applications

Table 1

Architecture structure for SSAEs. Table 1 is reproduced from F. Lei et al. (2018) (under the Creative Commons Attribution License/public domain).

Timeslot	Dimension of input layer	Hidden Layers	Hidden Layers units	MAPE (%)	MAE	RMSE
2	400	3		25.73	13.92	24.79
4	800	3		23.68	12.89	21.91
6	1200	3		22.11	13.95	20.24
8	1600	3		24.64	15.94	23.56
10	2000	4		26.32	16.28	25.73