Characteristic representation and extraction method and device of a physiological time sequence, and a storage medium
A physiological time and sequence technology, applied in biometric identification, biometric identification mode based on physiological signals, instruments, etc., can solve problems such as data misinterpretation, and achieve effective extraction, simple algorithm implementation, and efficient algorithm operation.
Active Publication Date: 2019-04-19
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF15 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, these methods may suffer from some limitations in practical applications
For example, finding the correlation dimension or Lyapunov index requires that the time series have sufficient length; approximate entropy and sample entropy are affected by factors such as local trends in the time series, which may lead to misinterpretation of the data
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0104] In order to further illustrate the physiological time-series feature extraction method proposed by the present invention, a kind of electroencephalogram signal is specifically used to illustrate the implementation process of the present invention.
[0105] EEG signal is the overall reflection of the electrophysiological activity of brain nerve cells on the surface of the cerebral cortex or scalp. EEG signals contain a large amount of physiological and disease information. In terms of engineering applications, people also try to use EEG signals to realize brain-computer interfaces, and use people's different EEG signals for different sensations, movements or cognitive activities. The effective extraction and classification of EEG signals can achieve certain control purposes. Since the EEG signal is a non-stationary random signal without ergodicity, and its background noise is also very strong, the feature extraction of the EEG signal has always been a very attractive but...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a characteristic representation and extraction method and device of a physiological time sequence based on singular spectrum decomposition and a co-spatial mode, and a storagemedium. The method comprises the following steps: acquiring a physiological time sequence and preprocessing the physiological time sequence to obtain a preprocessed physiological time sequence; Performing singular spectrum decomposition on the physiological time sequence to obtain singular spectrum components of each order of the physiological time sequence; And carrying out common spatial patternalgorithm processing by utilizing the singular spectrum components of each order of the physiological time sequence, and extracting to obtain feature information of the physiological time sequence corresponding to different physiological states. Compared with a traditional feature extraction method, the method is an automatic feature extraction method based on self data driving, basically does not need algorithm parameter presetting, has the advantages of being simple in algorithm implementation, efficient in algorithm operation and the like, and can effectively extract feature information ofphysiological signals.
Description
technical field [0001] The present invention relates to the technical field of physiological signal processing and feature extraction, in particular to a method, device and storage medium for feature representation and extraction of physiological time series based on singular spectrum decomposition and co-space mode. Background technique [0002] Physiological time series is a data set of physiological signals changing with time. It is characterized by the fact that it contains not only a lot of information, but also is relatively complex, reflecting the activity state of the physiological system and containing rich physiological state characteristics. It is of great importance in medical research. It can provide a basis for doctors to analyze and diagnose patients' diseases. [0003] Most of the existing feature extraction methods for physiological time series are suitable for stationary physiological time series, and cannot effectively extract nonlinear and non-stationary ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/10G06V40/15G06F2218/12G06F2218/08
Inventor 陆云王明江韩宇菲张啟权
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL