Brain function network classification method based on deep forest

Abstract

The invention discloses a brain function network classification method based on a deep forest, and belongs to the field of non-neural network deep learning theory and application research. The methodspecifically comprises the following steps: initializing parameters, performing multi-granularity scanning to generate a multi-granularity cascade feature vector, generating a cascade forest structure, extracting advanced features, and finally calculating a prediction result. According to the method, deep learning and integrated learning are combined, so that the method has a strong feature learning capability of a deep model and a strong generalization capability of the integrated learning; the brain function network classification method has the advantages that when brain network data of high-dimensional small samples are oriented, rapid and accurate brain function network classification is achieved, hyper-parameters are few, the training time is short, the model generalization capacityis high, and the over-fitting problem of previous brain function network classification can be effectively solved.

Description

technical field [0001] The invention belongs to the field of non-neural network deep learning theory and application research, and specifically relates to a method for classifying brain function networks based on deep forests. Background technique [0002] Human connectome research attempts to establish a multi-level brain network map that depicts different living human brain functions and structures, and to explore the correlation between neuropsychiatric diseases and abnormal topological changes in brain networks. This research can not only provide a new perspective for the understanding of the pathological mechanism of neurological and psychiatric diseases, but also provide new biomarkers for the early diagnosis and treatment evaluation of these diseases. [0003] A brain network is a graph model composed of nodes and edges, where nodes are usually defined as neurons, neural clusters, or regions of interest (ROIs), and edges correspond to the connection patterns between t...

AI Technical Summary

Problems solved by technology

However, this type of method has many training parameters, difficulty in adjusting hyperparameters, and prone to overfitting when faced with high-dimensional and small-sample brain network data, which are the main bottlenecks that restrict its further development and wider application.

Images