Biological information recognition method based on dynamic sample selection integration

Abstract

The invention discloses a biological information recognition method based on dynamic sample selection integration, mainly solving the problem of low correct recognition rate of subclass samples caused by data imbalance. The realizing process for solving the problem comprises the following steps: (1) a training set is divided into a series of balanced sub data sets by adopting a training set dividing method; (2) the obtained balanced sub data sets are divided into respective matrix classifiers as initial training sets; (3) on the matrix classifiers, cyclic training is carried out by adopting adynamic sample selecting method; (4) a testing set is tested by decision functions obtained in each training, thus obtaining decision results; (5) weight of the decision results is calculated by adopting a cost-sensitive idea; and (6) the decision results of each time are weighted and integrated, thus obtaining the final recognition result. Compared with the prior art, the method has the advantages of high accuracy and low calculation complexity, the size relation between a correct ratio and a recall ratio can be regulated as required, and the method is used for recognizing biological information, network intrusion and financial fraud and detecting anti-spam.

Description

technical field [0001] The invention belongs to the technical field of information processing, relates to biological information identification, and is used for snoRNA identification, microRNA precursor identification, and authenticity identification of SNP sites in bioinformatics, and can also be used for network intrusion, financial fraud, and anti-spam detection. Background technique [0002] In bioinformatics research, there are a large number of classification problems with class imbalance. For example: non-coding RNA gene mining, especially microRNA mining. In addition, such problems are often encountered in SNP site discrimination, snoRNA identification, and microArray data analysis. Since the positive examples in most problems come from experimental verification, and the negative examples usually do not require experimental verification, the cost of obtaining negative examples is low and the cost of positive examples is high, so there are usually far more negative ...

AI Technical Summary

Problems solved by technology

This method has the advantages of using less training data and fast execution speed, but it starts from a set of balanced data sets and will be affected by the selection of the initial balanced data set

[0009] In short, the various methods in the past are difficult to identify small-class samples, and they cannot adjust the size relationship between the total recognition rate and the recognition rate of small-class samples according to the needs.

Images