ELECTROCARDIO PARAMETER CALCULATION METHOD BASED ON DEEP LEARNING

摘要

An electrocardio parameter calculation method based on deep learning, which method belongs to the technical field of medical data. The method comprises the following steps: S1, constructing a data set; S2, pre-processing a label; S3, performing standardization and expansion on the data set; S4, training a model; and S5, verifying the model, which involves predicting, according to a second label, a wave band to which a point position belongs, and comparing a predicted wave band with a wave band of a first label, so as to calculate a corresponding Dice index. The technical problems to be solved by the present method are: the strong subjectivity, great variability and great influence of an acquisition environment of wave band division of electrocardio data in actual use, and the poor adaptability and a to-be-improved accuracy rate of a traditional method, etc., and provided is an electrocardio parameter calculation method based on deep learning.