Traditional Chinese medicine clinical big data storage method based on multi-mark feature selection and classification

Abstract

The invention, which relates to the cross technology application field of big data mining and traditional Chinese medicine digitalization, provides a traditional Chinese medicine clinical big data storage method based on multi-mark feature selection and classification. Information acquisition is carried out on a patient, quantified grading is carried out based on symptoms of different patients, and corresponding multi-type labels are given; the collected patient data are normalized, vectorization processing is carried out on a marking data set to obtain a standard multi-mark data set, and themulti-mark data set is divided into a training set and a testing set to verify the effectiveness of algorithm; a needed related matrix for feature selection of the training set is calculated and global optimal feature weight distribution is calculated by using a penalty function method; and first K feature sub sets with the largest weights are selected, a testing set prediction result is obtainedbased on an MLkNN method, and an optimal feature sub set is selected to carry out new patient disease prediction.

Description

technical field [0001] The present invention relates to the cross-technical application field of big data mining and digitization of traditional Chinese medicine, especially relates to the use of information entropy and global optimization technology, combined with the development system of clinical digitization of traditional Chinese medicine, to compress and store data according to the characteristics of high redundancy of clinical data of traditional Chinese medicine TCM clinical big data storage method based on multi-marker feature selection and classification. Background technique [0002] The research on multi-label learning (Multi-label Learning) was originally germinated in the document classification problem (Zhang Minling. Multi-label learning: problems, algorithms and data [J]. 2011). Compared with traditional supervised learning, the category label has changed from single to multiple. A subset composed of two, using the traditional single-label classification met...

AI Technical Summary

Problems solved by technology

[0005] TCM diagnostics and multi-label problems include: 1) TCM digital big data storage problem is a natural multi-label problem, a patient may be diagnosed as different diseases according to different diagnosis and treatment characteristics; 2) In the process of TCM data storage, in order to ensure data selection And the robustness of subsequent use, there are more redundant information in its diagnostic features, so feature selection is very necessary; 3) At present, it is relatively rare to solve the digital big data storage problem of traditional Chinese medicine from the perspective of multi-label feature selection

Images