Cross verification method based on LOO-CV verification

Abstract

The invention discloses a cross verification method based on LOO-CV verification, and the method comprises an elimination module, a simplification module, a verification module and a storage module; the elimination module is connected with the simplification module, the simplification module is connected with the verification module, the verification module is connected with the storage module, and the storage module is connected with the elimination module at the same time. The elimination module comprises to-be-verified data and eliminated data provided by a user, the simplification module comprises relatively simplified to-be-verified data and a grouping data set, the verification module comprises simplified data, verification data and sub-samples, and the storage module comprises target data and eliminated data. According to the cross validation method based on LOO-CV validation, various cross validation modes are adopted, so that the cross validation method can adapt to validationof large and small samples at the same time, the validation flexibility is improved, the validation accuracy is improved, rejected data can be utilized, and the influence on the validation efficiencywhen the rejected data reappear is avoided.

Description

technical field [0001] The invention relates to the technical field of information verification, in particular to a cross verification method based on LOO-CV verification. Background technique [0002] In the prior art, when it comes to data verification, various methods are used. There is the simplest verification, the safest and most accurate, but the efficiency is low. Co-validation, cross-validation, etc., and the cross-validation method is mainly used in modeling applications. The basic idea of ​​​​the cross-validation method is to group the original data, one part is used as a training set to train the model, and the other part is used as a test set. The evaluation model can obtain highly reliable data, but there are still some problems in the cross-validation method adopted by most existing technologies, such as: [0003] When a cross-validation method is used alone, for example, when Cross Validation is used alone, there may be a situation: the data set has 5 catego...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a cross-validation method based on LOO-CV verification, to solve the cross-validation method adopted by most of the prior art proposed in the above-mentioned background technology, which adopts a single cross-validation method and is difficult to eliminate The use of data will easily affect the verification efficiency when the rejected data reappears

Images