Gated Recurrent Unit with RSSIs from Heterogeneous Network for Mobile Positioning

Table 1

Training parameters.

Parameters	Value
Memory length	2
Number of hidden layers	1
Number of neurons of hidden layer	30
Optimizer	Adam
Learning rate	0.001
Decay rates	0.9, 0.999
Training epoch	20000
Batch size	5
Loss function	Quadratic loss