The invention provides an unbalanced learning-based
abnormal cell remote transfer classification method and
system, and the method comprises the steps: obtaining a plurality of
data sequences with a certain
cell remote transfer and a plurality of
data sequences without a certain
cell remote transfer, dividing the
data set into a
training set and a
test set, enabling the
training set to be used fortraining a model, and enabling the
test set to be used for testing the model; firstly, a
training set is input into a
feature selection algorithm to be compared with a
classification result of an original situation
data set, and p features with the best result are selected; Using an
oversampling algorithm to obtain a training set of which the ratio of positive and negative samples is 1: 1, respectively inputting the training set into a classification
algorithm, testing by using a data sequence of a
test set, and selecting to obtain an
oversampling algorithm i of a training set Pi with an optimal
evaluation result; By adjusting the proportion of the positive and negative samples, the training set is input into an
oversampling algorithm for obtaining a training set Pi, the proportion of thepositive and negative samples is gradually increased to a set proportion, and the optimal proportion of the positive and negative samples is classified and evaluated. According to the technical scheme, an oversampling algorithm is used for attempting to increase the proportion of the positive samples, and better model evaluation indexes and the
recall rate of a few positive samples are obtained.