Research on Monitoring Topping Time of Cotton Based on AdaBoost+Decision Tree

Algorithm 2

AdaBoost algorithm.

	Input: training dataset , where sample , , is the instance space, and is the set of tokens.
	Output: final regression algorithm: G(x).
(1)	Initialize the weight distribution of the training data, weight value for each data.
(2)	For . represents the total amount of the simple regression model.
(a)	Perform learning using the training dataset with weight distribution to obtain the base regression model .
(b)	Calculate the error rate of on the training dataset, where represents the distance between and , this paper chooses the mean square error distance.
(c)	Calculate the coefficient of .
(d)	Update the weight distribution of the training dataset
	,
	Where is the normalization factor
	Which makes a probability distribution.
(3)	Construct a linear combination of the basic regression model
	To obtain the final regression model.