Identifying method of brain cognitive states based on tensor locality preserving projection

Abstract

The invention discloses an identifying method of brain cognitive states based on tensor locality preserving projection (Tensor Locality Preserving Projection, TLPP). The method comprises the following steps: 1) pretreating and grouping of fMRI (functional Magnetic Resonance Imaging) data of the brain cognitive states; 2) constructing a neighbor graph G and a corresponding incidence matrix S; 3) calculating characteristic decomposition of a training sample set, solving corresponding characteristic transformation matrix and calculating low dimensional imbedding of training samples; 4) classifying and identifying: calculating low dimensional imbedding of the training sample sets, and distinguishing and classifying the training sample sets by a tensor distance-based neighbor classifier. According to the method, dimensionality reduction and characteristic extraction are directly carried out on multidimensional tensors by TLPP algorithm, and characteristic dimensionality reduction is carried out on collected brain cognitive fMRI data, so that the brain cognitive states are effectively identified and classified. By combining the tensor distance-based neighbor classifier, the classifying accuracy is improved. The method not only inherits advantages of conventional methods, but also greatly reduces complex of time and space and overcomes curse of dimensionality. The method is less in calculated amount, less in memory consumption and shorter in time consumed.

Description

technical field [0001] The invention belongs to the technical fields of medical image processing, biological feature extraction and pattern recognition, and relates to the preprocessing of fMRI data, the construction of neighbor graphs, the calculation of transformation matrices and low-dimensional embedding, and in particular to a brain recognition system based on tensor local projection. The cognitive state identification method can be used to process fMRI data of the cognitive state of the brain and carry out discrimination and classification. Background technique [0002] Informatics, computer science, and neurology, the three disciplines are gradually integrated with the advancement of technology and new developments in science. Neuroinformatics is an interdisciplinary scientific research field. In recent years, the research and exploration of brain images has led to the continuous generation of large amounts of data in this field. How to reasonably use data mining algo...

AI Technical Summary

Problems solved by technology

[0009] Aiming at the problems of dimensionality disaster existing in the fields of biological feature extraction and classification and discrimination, the present invention provides a way to directly reduce the dimensionality of data i...

Images