Neuron action potential feature extraction method based on singular spectrum entropy

Abstract

The invention relates to a neuron action potential feature extraction method based on singular spectrum entropy. The conventional method has incomplete extraction of information and low calculation efficiency. The method comprises the following steps of: firstly sampling an action potential signal and forming a time sequence X in the set time window width; setting values of embedding dimension K and delay time T and carrying out multi-dimensional phase space reconstruction on the time sequence X to obtain a phase space matrix Y; carrying out singular value decomposition on the phase space matrix Y to obtain a singular value of the phase space matrix Y, respectively calculating the ratio between each nonzero singular value and the sum of all singular values to obtain a probability, and calculating a singular spectrum entropy value of the time sequence X by utilizing an information entropy calculation method; and finally moving a time window and calculating all singular entropy values according to the information entropy calculation method to obtain the neuron action potential feature. The invention has complete information amount and fast calculation speed in the calculation process.

Description

technical field [0001] The invention belongs to the field of biomedical engineering, and relates to a neuron action potential feature extraction method, in particular to a neuron action potential feature extraction method based on singular spectrum entropy. Background technique [0002] The feature extraction technology of neuron action potential is the early foundation of neuroinformatics research such as action potential pattern classification technology and action potential sequence decoding, and due to the development of implantable multi-electrode array technology, it is possible to acquire a large number of neuron action potentials , so extracting the effective features of action potentials and dividing them into corresponding neurons according to the features plays a key role in understanding the correlation between neuron responses and external stimuli. [0003] Currently, neuron action potential feature extraction and pattern classification methods mainly include te...

AI Technical Summary

Problems solved by technology

The action potential singular spectrum entropy feature extracted by this method can be effectively used for the classification of later action potentials, and it can solve the problem that the features extracted by traditional methods cannot reflect the complete information of the action potential or cannot reflect the nonlinear and non-stationary dynamic characteristics of the action potential. question

Images