Motor imagery identification method and system fusing CNN-BiLSTM model and probability cooperation
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of motor imagery and recognition methods, applied in character and pattern recognition, neural learning methods, biological neural network models, etc.
Pending Publication Date: 2019-10-08
QILU UNIV OF TECH
View PDF5 Cites 23 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
LSTM is improved on the basis of the traditional RNN model. By adding mechanisms such as forgetting gate, memory gate and output gate, it can effectively avoid the occurrence of gradient disappearance and blasting, and then learn more ancient information. However, simply Sometimes it is not enough to deduce the information from the previous information to the latter information. How to better use the LSTM model to extract the timing characteristics of the EEG signal in order to achieve better results is an urgent need to solve the technology in the current technology question
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0076] as attached figure 1 As shown, the motion imagery recognition method of the fusion CNN-BiLSTM model and probability cooperation of the present invention, this method captures and extracts the spatio-temporal depth feature in the EEG signal by the CNN model of fusion BiLSTM network, and the time of capturing and extracting - Input the empty depth feature to the ProCRC classifier for classification, and use the test set data to evaluate the performance of the built CNN-BiLSTM model to realize the user's intention recognition; the specific steps are as follows:
[0077] S1. Collecting EEG signals; wherein, the EEG signal is a non-invasive EEG signal with weak signal amplitude, low signal-to-noise ratio, non-stationarity, nonlinearity, and great processing difficulty;
[0078] Dataset III (DatasetIVa) in the international BCI Competition III competition database was used in the experiment. Dataset IVa is a two-type motor imagery task involving the right hand and feet, and E...
Embodiment 2
[0131] as attached Image 6 As shown, the fusion CNN-BiLSTM model of the present invention and the motion imagery recognition system of probability cooperation, this system comprises,
[0132] The EEG signal acquisition unit is used to collect EEG signals; among them, the EEG signal is a non-invasive EEG signal, which has weak signal amplitude, low signal-to-noise ratio, non-stationarity, and nonlinearity, and is difficult to process ;
[0133] The deep neural network construction unit is used to extract the spatio-temporal depth features of the EEG signal through the convolutional neural network (CNN) in deep learning combined with the bidirectional long-short-term memory model network (BiLSTM);
[0134] Among them, the deep neural network construction unit includes,
[0135] The CNN model constructs a subunit for extracting spatial features in the EEG signal through a convolutional neural network;
[0136] The BiLSTM model construction subunit is used to construct a two-w...
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 motor imagery identification method and system fusing a CNN-BiLSTM model and probability cooperation, belonging to the field of man-machine interfaces. The invention aims tosolve the technical problem of how to effectively extract features and how to quickly realize classification, and the method adopts the technical scheme that (1) the method captures and extracts time-space depth features in an EEG signal by merging a CNN model of a BiLSTM network, and inputs captured and extracted time-space depth features into a ProCRC classifier for classification, and uses testset data pairs to construct the CNN-BiLSTM model for performance evaluation to achieve intent recognition. The method comprises the following specific steps: S1, acquiring an electroencephalogram signal; S2, constructing a deep neural network; S3, establishing a classifier; and S4, testing and evaluating the model. The system comprises an electroencephalogram signal acquisition unit, a deep neural network construction unit, a classifier construction unit and a model test and evaluation unit.
Description
technical field [0001] The present invention relates to the field of brain-computer interface, and more to the field of classification and recognition of electroencephalogram signals based on motor imagery, which combines a convolutional neural network and a bidirectional long-short-term memory model with a probabilistic cooperative representation classifier. A motion imagery recognition method and system integrating CNN-BiLSTM model and probabilistic collaboration. Background technique [0002] Brain-computer interface (Brain-Computer Interface, BCI) is a special communication system, it does not rely on the peripheral nerves and muscle tissue of the human body, it can realize the communication between the human brain and external equipment, this kind of communication does not require language or action control The communication method belongs to the category of brain control technology. In recent years, BCI technology has attracted the attention of many scholars at home a...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more