Naive Bayes data processing system and method based on minority-class sample synthesis

Abstract

The invention discloses a naive Bayes data processing system and method based on minority-class sample synthesis. The system includes a medical information database, a data preprocessing module and adata analysis module which are connected through network equipment, wherein the medical information database is used for storing medical information data packets; the data preprocessing module is usedfor performing vacant value filling of data, and the data analysis module includes a data balance compression module, a Wrapper feature selection module and a naive Bayes analysis and prediction module which perform communication connection through a data bus and perform missing filling, smoothing processing, redundancy removal and accurate analysis and prediction of medical data, thereby achieving the purposes of ensuring integrity of medical data and enabling interpretation of the medical data to be more accurate.

Description

technical field [0001] The invention relates to the field of computer medical applications, in particular to a naive Bayesian data processing system and method based on minority class sample synthesis. Background technique [0002] The Internet of Things Medical Diagnosis System (MIoT) aims to realize the interaction between patients and medical staff, medical institutions, and medical equipment by creating a regional medical information platform for health records and using the most advanced Internet of Things technology, and gradually achieve informatization. In recent years, intelligent medical technology, which combines artificial intelligence, medical robots and digital assisted medical technology, is leading a new round of medical reform. Intelligent medical technology begins to run through all aspects of medical care such as diagnosis, surgery, nursing and rehabilitation. Hospitals have relied on medical staff to check breast cell activity during the clinical diagnos...

AI Technical Summary

Problems solved by technology

Wrapper uses the training accuracy of the follow-up learning algorithm to evaluate the feature subset, which has a small deviation and a large amount of calculation, so it is not suitable for large data sets.

[0009] (3) Data imbalance

[0010] The existing SMOTE data balance method only balances the data on the original basis. The result of this will only increase the amount of data, which will have a negative impact on the time efficiency of the follow-up Wrapper method to screen redundant features.

[0011] (4) Naive Bayes' feature assumption independence defect

However, the Naive Bayesian method assumes that the data features are equally important and conditionally independent when estimating the conditional probability. This assumption is difficult to satisfy in actual situations, and there is often a correlation between the data features.

Images