Structure sparse multi-kernel learning-based multi-modal data feature screening and classification method

Abstract

The invention discloses a Structure sparse multi-kernel learning-based multi-modal data feature screening and classification method. The method comprises the following steps of: extracting data features and normalizing the features; constructing a kernel matrix for each data feature by utilizing a kernel function; grouping all the data features and the corresponding kernel functions according to the data features; training a Structure sparse multi-kernel classification model by utilizing training data with class labels, and optimizing parameters of the model; and classifying test data by using the trained Structure sparse multi-kernel classification model. According to the method, the data feature selection and data modal fusion are modeled in the uniform structure sparse multi-modal classification model, and the structure sparse feature selection and classifier learning expressed on the basis of an optimal kernel are carried out at the same time, so that a multi-modal data feature screening, fusion and classification method is provided.

Description

technical field [0001] The invention relates to a method for screening and classifying multimodal data features, in particular to a method for screening and classifying multimodal data features based on structural sparse multi-kernel learning, which belongs to the fields of machine learning and biomedicine, and is specifically applied to image and and / or in the field of disease understanding and diagnosis from genetic data. Background technique [0002] Many problems in our actual production and application can be attributed to classification problems. With the rapid increase of various data acquisition methods, we can often have data from multiple data sources (or called multi-modal). These different data describe different aspects of specific problems, but different modal data are heterogeneous, and how to effectively utilize multi-modal data to enhance classification becomes a major challenge. For example, old age is a neurodegenerative disease with insidious onset and ...

AI Technical Summary

Problems solved by technology

[0004] The key technical problem to be solved by the present invention is: in the face of feature selection and classification of high-dimensional and multi-modal data, how to effectively reduce the data dimension so as to overcome the adverse effects of insufficient samples, and at the same time facilitate the establishment of a robust model that is easy to explain ; How to overcome the heterogeneous characteristics of different modal data, and how to use the different information of different modal data and

Images