CN219266900U - Portable brain-computer interface system based on raspberry group - Google Patents

Abstract

The utility model discloses a portable brain-computer interface system based on a raspberry group, which is characterized by comprising the raspberry group, an electroencephalogram signal acquisition device and a visual stimulator, wherein the raspberry group is connected with the visual stimulator in a wired mode and is used for driving the visual stimulator to generate stimulation flicker, the electroencephalogram signal acquisition device is connected with the raspberry group and is used for feeding back acquired electroencephalogram signals of a user to the raspberry group, and the raspberry group decodes the received electroencephalogram signals and converts the decoded electroencephalogram signals into corresponding control instructions. The utility model adopts the raspberry pie as a data receiving, analyzing and executing unit, the raspberry pie is based on an open source system, has strong compatibility, and can realize a brain-computer interface system by matching with an electroencephalogram signal acquisition device; the raspberry pie has good data processing capability and can run a complex brain electrolysis code algorithm; the raspberry pie has rich GPIO interfaces and strong expansibility, so that the brain-computer interface system can be used in different use scenes to realize different functions.

Description

A portable brain-computer interface system based on Raspberry Pi

technical field

The utility model belongs to the technical field of brain-computer interface, in particular to a portable brain-computer interface system based on raspberry pie.

Background technique

Brain-computer interface technology is used to create a direct connection between the human or animal brain and external devices, thereby realizing information exchange between the brain and external devices. Its workflow mainly includes EEG signal collection, signal processing, and signal output. and execute. Currently, the use of BCIs is limited to laboratory settings, mainly due to the limitations of EEG signal acquisition devices and decoding devices. The collection of EEG signals needs to rely on professional equipment, and the analysis of EEG signals has certain requirements for computer computing power. The current brain-computer interface system has shortcomings in miniaturization, portability, and wearability, and it is difficult to promote brain-computer interface technology to daily life.

Utility model content

Aiming at the deficiencies of the prior art, the purpose of this utility model is to provide a portable brain-computer interface system based on the Raspberry Pi, which solves the problems of the prior art that it is not easy to carry and has poor ductility.

The purpose of this utility model is also to provide a kind of portable brain-computer interface system based on raspberry pie, comprising raspberry pie, EEG signal acquisition device and visual stimulator, described raspberry pie is connected with visual stimulator by wired mode, For driving the visual stimulator to generate stimulation flicker, the EEG signal acquisition device is connected with the Raspberry Pi, and is used to feed back the collected user's EEG signal to the Raspberry Pi, and the Raspberry Pi receives The EEG signals are decoded and converted into corresponding control instructions.

Preferably, the raspberry pie is provided with a stimulation drive module, a wireless receiving module and an EEG decoding module, the stimulation drive module drives the visual stimulator to generate stimulation flashes, and the EEG signal acquisition device collects The user's EEG signal is fed back to the Raspberry Pi. When the wireless receiving module in the Raspberry Pi receives the EEG signal, it is transmitted to the EEG decoding module. The EEG decoding module performs decoding through preprocessing and FBCCA algorithm. And convert the decoding result into corresponding control instructions.

Preferably, an EEG collector OpenBCI and a wireless transmission module for collecting EEG signals are provided in the EEG signal acquisition device, and the EEG collector OpenBCI passes the collected user's EEG signals through the wireless transmission module Feedback to Raspberry Pi.

Preferably, the visual stimulator includes four blinking blocks, each of which flashes at a different frequency.

Preferably, the size and frequency of each said block is associated with said stimulus drive module.

Compared with the prior art, the portable brain-computer interface system based on the Raspberry Pi described in the utility model adopts the Raspberry Pi as the data receiving, analysis and execution unit. The combination of electrical signal acquisition devices can realize the brain-computer interface system; the Raspberry Pi has good data processing capabilities and can run complex EEG decoding algorithms; the Raspberry Pi has rich GPIO interfaces and strong scalability, so that the brain-computer interface system can be It can be used in different usage scenarios to achieve different functions; Raspberry Pi is small in size, light in weight, and low in power consumption, which is conducive to the development of wearable devices.

Description of drawings

Fig. 1 is a schematic structural diagram of the portable brain-computer interface system based on the Raspberry Pi of the present invention.

Detailed ways

In order to make the purpose, technical solution and advantages of the utility model clearer, the utility model will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the utility model, and are not intended to limit the utility model.

As shown in Figure 1, a portable brain-computer interface system based on Raspberry Pi provided by the embodiment of the present invention includes Raspberry Pi, an EEG signal acquisition device and a visual stimulator. The Raspberry Pi includes a stimulus driver module, a wireless receiving module and an EEG decoding module, and the EEG signal acquisition device includes an EEG collector OpenBCI and a wireless transmitting module. The Raspberry Pi is connected to the visual stimulator by wire, and the stimulus driver module drives the visual stimulator to generate stimulus flashes. According to the user's needs, the user watches the relevant stimulus flickering, and the EEG signal collector OpenBCI collects the user's EEG signal at this time, and sends it to the Raspberry Pi through the wireless transmission module. After receiving the EEG signal, the wireless receiving module of the Raspberry Pi transmits it to the EEG decoding module, and decodes it through preprocessing and filter bank canonical correlation analysis FBCCA algorithm, and converts the decoding result into corresponding control instructions.

In a specific implementation process, the visual stimulator includes four flashing blocks, and each block flashes at a different frequency. Four blocks represent 4 instructions, and the size and frequency of the blocks are determined by the stimulation drive module. In this embodiment, the optional range of stimulation frequency is 8-12 Hz.

In a specific implementation process, the EEG signal collector OpenBCI includes 8 measuring electrodes, 1 reference electrode and 1 ground electrode.

In this embodiment, the measurement electrodes are placed on PO5, PO3, POz, PO4, PO6, O1, Oz and O2 of the 10/20 international standard leads, and the reference electrode and ground electrode are placed on the left and right ears respectively.

In a specific implementation process, the wireless transmitting module is connected with the wireless receiving module of the Raspberry Pi based on Bluetooth or WIFI.

In a specific implementation process, the EEG decoding module performs pre-filtering on the user's EEG signal, and then uses filter bank canonical correlation analysis (FBCCA) to finally decode and identify the instruction that the user wants to send.

In a specific implementation process, the filter preprocessing includes the following steps: 1) performing 50Hz notch wave processing; 2) performing 1-50Hz bandpass filtering.

In a specific implementation process, the filter bank canonical correlation analysis FBCCA includes the following steps: 1) carry out filter bank analysis, using a plurality of different bandpass filters to decompose the EEG signal into a plurality of sub-band signals; 2 ) Correlation analysis is performed between each sub-band component obtained by filtering and the standard sine-cosine reference signal, and the frequency corresponding to the maximum correlation is the identification result.

In summary, the portable brain-computer interface system based on the Raspberry Pi described in the utility model adopts the Raspberry Pi as the data receiving, analysis and execution unit. The Raspberry Pi is based on an open source system and has strong compatibility. The brain-computer interface system can be realized with OpenBCI; the Raspberry Pi has good data processing capabilities and can run complex EEG decoding algorithms; the Raspberry Pi has rich GPIO interfaces and strong scalability, making this brain-computer interface system applicable to different Different usage scenarios can be used to achieve different functions; Raspberry Pi is small in size, light in weight, and low in power consumption, which is conducive to the development of wearable devices.

The above is only a preferred embodiment of the utility model, but the scope of protection of the present invention is not limited thereto, and any person familiar with the technical field can easily think of the technical scope disclosed in the utility model Changes or replacements should fall within the protection scope of the present utility model. Therefore, the protection scope of the present utility model should be based on the protection scope of the claims.

Claims (5)

1. A portable brain-computer interface system based on raspberry group, is characterized in that, comprises raspberry group, EEG signal acquisition device and visual stimulator, described raspberry group is connected with visual stimulator by wired mode, for The visual stimulator is driven to stimulate flickering, and the EEG signal acquisition device is connected with the Raspberry Pi, and is used to feed back the collected user's EEG signal to the Raspberry Pi, and the brain wave received by the Raspberry Pi The electrical signals are decoded and converted into corresponding control commands. 2. a kind of portable brain-computer interface system based on raspberry pie according to claim 1, is characterized in that, is provided with stimulation drive module, wireless receiving module and EEG decoding module in described raspberry pie, and described stimulation The driving module drives the visual stimulator to generate stimulation flickering, and the EEG signal acquisition device feeds back the collected user's EEG signal to the Raspberry Pi. After the wireless receiving module in the Raspberry Pi receives the EEG signal , transmitted to the EEG decoding module, the EEG decoding module performs decoding through preprocessing and FBCCA algorithm, and converts the decoding result into corresponding control instructions. 3. a kind of portable brain-computer interface system based on raspberry pie according to claim 2, is characterized in that, is provided with the EEG collector and the wireless transmission module for collecting EEG signal in the described EEG signal acquisition device , the EEG collector feeds back the collected user's EEG signal to the Raspberry Pi through the wireless transmission module. 4. A kind of portable brain-computer interface system based on Raspberry Pi according to claim 2 or 3, is characterized in that, described visual stimulator comprises four flicker blocks, and each block adopts different frequency flicker. 5. A kind of portable brain-computer interface system based on Raspberry Pi according to claim 4, is characterized in that, the size and the frequency of each described block are associated with described stimulation driving module.

Images