SSVEP EEG classification method based on convolutional neural model augmented with EMD data

A technology of convolutional neural and classification methods, applied in the fields of SSVEP EEG classification, artificial intelligence and pattern recognition, and brain-computer interface, to achieve the effect of optimizing models and inputs, high application prospects, and increasing ease of use

CN109299751BActive Publication Date: 2022-05-31NANKAI UNIV
3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2022-05-31

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The present invention relates to the algorithm of brain-computer interface, artificial intelligence and pattern recognition, more specifically, relates to the SSVEP EEG classification method based on the convolutional neural model enhanced by EMD data, which can be applied to the fields of medical equipment, human-computer interaction, robot control, etc. . This method first preprocesses the original EEG data. After preprocessing, the empirical mode decomposition method is used to decompose the original EEG data, and a large number of artificial EEG data that conform to the time-frequency domain characteristics of the original EEG signal are generated by mixing. The original EEG data is merged and used for parameter training of the neural network, so as to achieve the effect of effectively training network parameters with a small amount of EEG data. Finally, the complex Morlet wavelet transform is used to generate the EEG tensor, and the original time domain data is converted into a tensor dictionary integrating time domain, frequency domain and spatial information as the input of the neural network, and the convolutional neural network model is used to enhance the data. EEG training set for classification.
Need to check novelty before this filing date? Find Prior Art

Description

SSVEP EEG Classification Method Based on EMD Data Augmented Convolutional Neural Model technical field The present invention relates to the algorithm of brain-computer interface, artificial intelligence and pattern recognition, more particularly, relate to based on EMD data The SSVEP EEG classification method of the enhanced convolutional neural model can be applied to medical devices, human-computer interaction, robot control, etc. field. Background technique In recent years, with the development of computer science and artificial intelligence technology, brain-computer interface technology (BCI) as a new It has important application value in the field of rehabilitation science and control. BCI uses EEG signals to realize the human brain Communication or control with a computer or other electronic device, so it can help physically disabled patients to Improve the ability to communicate with the outside world. Steady-state visual evoked potentials are currently a...

Examples

Embodiment Construction

[0030] For the original EEG data, the preprocessing is mainly to filter out the DC component and band-pass filtering operations. first of all

[0036]

[0038] A large amount of artificial data is generated by randomly extracting and mixing different sequences of IMFs to train the network.

[0045] Referring to Figure 2, it is a structural diagram of a convolutional neural network model. The structure of the convolutional network is as follows, the first layer of convolution

[0048]

[0051] Results: As shown in Figure 5, the average correct rate of 5 subjects exceeded 95%, and the original training set was expanded to 2 times the original maximum.

[0053] Although the above-mentioned embodiments have been described, once those skilled in the art know the basic innovation