A LSTM-RNN-Based Fiber Optic Gyroscope Drift Compensation

Algorithm 1

CART-Bagging. Algorithm procedure of the CART-Bagging model.

(i)	Initialization: the maximum depth of CART d; the maximum number of leaf nodes m; the number of decision trees L.
(ii)	Input: Training samples
(iii)	for M = 1, 2, 3, ^… do
(iv)	Extract S(i) from S according to a set proportion.
(v)	Training CART-Bagging model with S(i).
(vi)	If the termination condition is reached on a node
(vii)	The node is defined as a leaf node.
(viii)	Else
(ix)	Continue training.
(x)	M = M + 1
(xi)	end for
(xii)	Output: Average value of each basic model
(xiii)	M is the current time, which is an integer.