Classification method and system for cerebral apoplexy unbalanced data set

The invention discloses a cerebral apoplexy unbalanced data set-oriented classification method and system, and relates to the technical field of data processing, and the method comprises the steps: dividing a cerebral apoplexy unbalanced data set into a training sample set and a test sample set; determining a positive/negative sample adaptive adjustment radius according to the distance between the sample points so as to determine a positive/negative sample adaptive adjustment factor, and further constructing a difference matrix; counting the number of positive samples and the number of negative samples in the effective range of the sample points according to the difference matrix so as to determine the positive/negative information content contained in the sample points, and further constructing an information content fuzzy membership function; determining a positive/negative fuzzy membership function based on the distance between samples; an improved positive/negative class fuzzy membership function is deter