Sorting method based on non-supervision feature selection

Abstract

The invention discloses a sorting method based on non-supervision feature selection. By means of the method, high dimensional data are expressed in similar diagrams, distances between sample points are obtained through the ITML, and a similar matrix of the original high dimensional data is set up; then the SM algorithm is executed on the similar matrix and a diagonal matrix corresponding to the similar matrix to achieve mapping of original sample sets to feather vector space; then through learning of sparse coefficient vectors and MCFS scores, weight coefficients of all attributes in the original sample set are obtained, and the attribute which can best express the original sample information is selected out; finally a support vector machine is used for setting up a sorting model of the selected data to predict fatigue states of a driver. The method selects features of the high dimensional data under the condition of maintaining data aggregate structures before the sorting model is set up, and the negative effect of curse of dimensionality on data sorting is avoided.

Description

technical field [0001] The present invention relates to the fields of data processing such as signal processing, data mining, and cluster analysis, and in particular to a method of using an unsupervised feature selection method based on information metric learning to reduce the dimension of high-dimensional data, and then using a support vector machine to establish a classification model. . Background technique [0002] With the continuous development of the Internet and the information industry, data information in many fields such as economy, electronic information, medicine, and meteorology has also ushered in a stage of explosive growth, and there is no shortage of massive high-dimensional data. How to classify high-dimensional data to better discover potential useful information is a research hotspot in the field of data mining. [0003] Classification is the process of predicting data class labels by establishing a classifier that describes a pre-defined data class or...

AI Technical Summary

Problems solved by technology

However, in feature selection, the importance of the features of high-dimensional data is usually sorted by some evaluation criteria, ignoring the possible associations between different features, so the optimal feature subset cannot be generated, and thus cannot be obtained. best classification result

Images