Unlock instant, AI-driven research and patent intelligence for your innovation.

Spatial filtering method and device based on Lp/q-mixed norm

A technology of spatial filtering and norm, which is applied in the input/output of user/computer interaction, electrical digital data processing, and pattern recognition in signals, etc. It can solve the problem that the method of diagonalizing the matrix to solve the spatial filtering vector is infeasible and so on. , to achieve the effect of good classification rate, good robustness and stability

Inactive Publication Date: 2020-01-24
SOUTHEAST UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Since the objective function of the proposed method is in the form of a quotient and contains an absolute value operator, this makes the traditional method of matrix diagonalization to solve the spatial filter vector unfeasible

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Spatial filtering method and device based on Lp/q-mixed norm
  • Spatial filtering method and device based on Lp/q-mixed norm
  • Spatial filtering method and device based on Lp/q-mixed norm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] like figure 1 Shown is the flow chart of a kind of spatial filtering method based on Lp / q-norm disclosed according to the present invention, below in conjunction with figure 1 A spatial filtering method based on the Lp / q-norm according to the embodiments disclosed in the present invention will be described.

[0051] The present invention proposes a spatial filtering method based on the Lp / q-norm, specifically comprising the following steps:

[0052] Step 1, signal preprocessing, performing bandpass filtering on the collected EEG signal data, and selecting data in a suitable time period as the data to be processed;

[0053] Step 2, using the Lp / q-mixed norm to redefine the objective function;

[0054] Step 3, based on the Lp / q-mixed norm objective function, the EEG data matrix is ​​iterated to the optimal spatial filter vector to obtain the iterated EEG data;

[0055] Step 4, performing feature extraction on the EEG data obtained through iteration;

[0056] Step 5, u...

Embodiment 2

[0089] like Figure 5 Shown is a diagram of a spatial filtering device based on the Lp / q-mixing norm disclosed in the present invention, and a spatial filtering device based on the Lp / q-mixing norm of this embodiment includes: a processor, a memory, and a memory stored in The computer program in the memory and operable on the processor, when the processor executes the computer program, implements the steps in the embodiment of the above-mentioned Lp / q-mixed norm-based spatial filtering device.

[0090] The device includes: a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor executes the computer program to run in the following units of the device:

[0091] The processor includes the following units:

[0092] A data preprocessing unit, configured to preprocess the raw data;

[0093] The filter acquisition unit is used to obtain the optimal spatial filter vector from the preprocessed data matrix with the objective...

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

No PUM Login to View More

Abstract

The invention discloses a spatial filtering method and device based on an Lp / q-mixed norm. Two types of electroencephalogram signals are modeled by using an Lp-norm and an Lq-norm respectively; basedon the Lp / q-mixed norm, an objective function is constructed, and an iterative algorithm for solving an optimal spatial filtering vector is provided, so that fine discrimination information is extracted, a beneficial classification method is provided for a brain-computer interface system, features with discrimination capability are sought, and electroencephalogram signal classification is furthercarried out. The method has the effect of resisting the influence of abnormal values on the classification performance, and compared with a traditional method, the provided method has better classification performance, robustness and stability.

Description

technical field [0001] The present invention relates to the field of robust modeling based on Lp / q-mixed norm, and the field of feature extraction and classification of EEG signals in brain-computer interface systems. Specifically, it relates to the common The spatial pattern method, the iterative algorithm for solving the optimal spatial filter, and its electroencephalogram signal classification method specifically relate to a spatial filtering method and device based on the Lp / q-mixed norm. Background technique [0002] Since the objective functions of common algorithms in the field of machine learning and pattern recognition are expressions based on the L2-norm, but from the perspective of statistical modeling, the use of the L2-norm will lead to overfitting and outliers Sensitivity and other issues; and the data collected from sensors are often inevitably polluted by outliers and noise, so the robust modeling of algorithms has attracted extensive attention of researchers...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06F3/01
CPCG06F3/015G06F2203/011G06F2218/02G06F2218/12
Inventor 王海贤邓玥
Owner SOUTHEAST UNIV