CN111084617A - Bioelectric signal processing system - Google Patents
Bioelectric signal processing system Download PDFInfo
- Publication number
- CN111084617A CN111084617A CN201911358199.4A CN201911358199A CN111084617A CN 111084617 A CN111084617 A CN 111084617A CN 201911358199 A CN201911358199 A CN 201911358199A CN 111084617 A CN111084617 A CN 111084617A
- Authority
- CN
- China
- Prior art keywords
- chip
- processing system
- signal processing
- bioelectrical signal
- processed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/30—Input circuits therefor
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a bioelectrical signal processing system, which belongs to the technical field of data processing and comprises: embedded chip, ESP32 chip and signal acquisition equipment. Through the cooperation of the embedded chip, the ESP32 chip and the signal acquisition equipment, the bioelectric signal processing device can realize bioelectric signal processing on the premise of not increasing too many hardware equipment, is convenient to carry and wear, and has low cost.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a bioelectrical signal processing system.
Background
Brain Computer Interface (BCI) is also called Brain-Computer Interface, which is an interactive mode for connecting human Brain with Computer and mechanical equipment. The brain-computer interface generally recognizes a person's intention/idea/command by recognizing a mental/psychological/physiological state of the person by analyzing a bio-electric signal such as EEG (brain wave)/EMG (electromyogram) using an algorithm. The BCI technology has important significance in the fields of assistance for disabled people, rehabilitation systems, man-machine interaction and the like. However, the current brain-computer interface system is generally divided into two parts, namely software and hardware, which are separated. Independent of each other and connected through a certain data interface.
There are many schemes in the market, such as Epoc helmet of Emotive corporation, Mindset head-mounted detector of NeuroSky corporation, gssbamp series electroencephalogram amplifier of g.tec corporation, hardware OpenBCI gaplion Board helmet developed by OpenBCI of open source community, etc. According to the technical scheme, the bioelectricity signals acquired by hardware are transmitted to a computer through wireless transmission such as Bluetooth or WiFi or wired transmission such as USB connecting lines, matched software and algorithms are operated at the computer end, and data are analyzed, but the devices generally have the problems of large and heavy hardware devices, inconvenience in carrying, incapability of wearing, high cost and the like.
Disclosure of Invention
In order to solve all or part of the above technical problems, the present invention provides a bioelectrical signal processing system, comprising: the device comprises an embedded chip, an ESP32 chip and signal acquisition equipment;
the signal acquisition equipment is used for acquiring a bioelectricity signal to be processed and amplifying the bioelectricity signal to be processed;
the ESP32 chip is used for reading and buffering the amplified bioelectrical signal to be processed, and transmitting the buffered bioelectrical signal to be processed to the embedded chip at one time;
the embedded chip is used for extracting time domain features and frequency domain features of the bioelectricity signal to be processed sent by the ESP32 chip to obtain the time domain features and the frequency domain features;
the embedded chip is also used for carrying out pattern recognition on the time domain characteristics and the frequency domain characteristics through a neural network model to obtain a pattern recognition result.
Preferably, the time-domain feature extraction includes: at least one of root mean square, impulse factor, peak factor, margin, kurtosis, skewness, covariance, autocorrelation function, upper and lower envelope lines, parkinsonian tremor coefficient, stiffness coefficient, motion coefficient, brain psychomotor, and concentration.
Preferably, the frequency domain feature extraction includes: at least one of a fast Fourier transform, a short-time Fourier transform, a wavelet packet transform, an empirical mode decomposition, and a Hilbert-Huang transform.
Preferably, the embedded chip is also used for preprocessing the bioelectrical signal to be processed sent by the ESP32 chip.
Preferably, the pre-treatment comprises: at least one of baseline rectification, artifact removal, noise reduction, notching, band pass filtering, and smoothing.
Preferably, the bioelectrical signal processing system further comprises: the SPI screen is connected with the embedded chip;
and the SPI screen is used for displaying the bioelectricity signal to be processed and the pattern recognition result.
Preferably, the embedded chip is a multi-processing core chip;
the embedded chip is also used for distributing the tasks which need to be executed currently to different processing cores, and the processing cores execute the corresponding tasks in parallel.
Preferably, the embedded chip is further configured to establish a local data stream through the python lab streaming media layer, so as to implement inter-process data sharing.
Preferably, the neural network model is built by Tensorflow.
Preferably, the bioelectrical signal processing system further comprises: the WiFi driving chip is connected with the embedded chip;
and the WiFi driving chip is used for sending the pattern recognition result to external equipment.
Through the cooperation of the embedded chip, the ESP32 chip and the signal acquisition equipment, the bioelectric signal processing device can realize bioelectric signal processing on the premise of not increasing too many hardware equipment, is convenient to carry and wear, and has low cost.
Drawings
Fig. 1 is a block diagram showing a configuration of a bioelectrical signal processing system according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
FIG. 1 is a block diagram showing the structure of a bioelectrical signal processing system according to an embodiment of the present invention; referring to fig. 1, the bioelectric signal processing system includes: embedded chip 100, ESP32 chip 200, and signal acquisition device 300.
The signal collecting device 300 is configured to collect a bioelectric signal to be processed and amplify the bioelectric signal to be processed.
It should be noted that the bioelectric signal to be processed is an EEG (brain wave) signal and/or an EMG (electromyography) signal, and of course, other information with similar characteristics may also be used, which is not limited in this embodiment.
It can be understood that the signal acquisition device can acquire signals through a sensor in an implanted brain computer Interface (EmBCI), and a software part of the signal acquisition device is supported by a part of C language bottom layer, so that the operation speed is improved.
The ESP32 chip 200 is configured to read and buffer the amplified bioelectrical signal to be processed, and transmit the buffered bioelectrical signal to be processed to the embedded chip at one time.
In a specific implementation, the ESP32 chip 200 has a precision clock high sampling rate, so that the to-be-processed bioelectrical signal after amplification can be read by the precision clock high sampling rate, and the embedded chip 100 performs data preprocessing on the to-be-processed bioelectrical signal after amplification, and then buffers the processed bioelectrical signal in the buffer, that is, the embedded chip 100 is further configured to preprocess the to-be-processed bioelectrical signal sent by the ESP32 chip, and in a specific implementation, the preprocessing includes: at least one of baseline correction, artifact removal, noise reduction, notching, band pass filtering, and smoothing.
The embedded chip 100 is configured to perform time domain feature extraction and frequency domain feature extraction on the to-be-processed bioelectrical signal sent by the ESP32 chip to obtain a time domain feature and a frequency domain feature.
In a specific implementation, the time domain feature extraction includes: at least one of root mean square, impulse factor, peak factor, margin, kurtosis, skewness, covariance, autocorrelation function, upper and lower envelope lines, parkinsonian tremor coefficient, stiffness coefficient, motion coefficient, brain psychomotor, and concentration.
It should be noted that the frequency domain feature extraction includes: at least one of a fast Fourier transform, a short-time Fourier transform, a wavelet transform (discrete and continuous), a wavelet packet transform, an empirical mode decomposition, and a Hilbert-yellow transform.
The embedded chip 100 is further configured to perform pattern recognition on the time domain feature and the frequency domain feature through a neural network model, so as to obtain a pattern recognition result.
In order to show the pattern recognition result, in this embodiment, the bioelectrical signal processing system further includes: a Serial Peripheral Interface (SPI) screen connected to the embedded chip;
the SPI screen is used for right the bioelectricity signal to be processed and the pattern recognition result are shown, specifically, the SPI screen can be selected for use by 2.3 cun SPI screens, so that the equipment is easier to use, and the SPI screen is convenient to drive, in the embodiment, the ILI9341 chip can be selected for driving.
For embedded chips, it is often necessary to perform a number of tasks, such as: tasks such as data acquisition, interface display, model training and the like, which all need to occupy system resources and are supposed to be executed in sequence to cause too low recognition efficiency, so that the embedded chip 100 is a multi-core chip, specifically, a full-log high-computing four-core 64-bit chip H5 (specifically, a four-core 64-bit ARM Cortex a53 CPU) can be selected, and a Python program is run to read data sent by the ESP32 chip 200;
the embedded chip 100 is further configured to allocate the tasks that need to be executed currently to different processing cores, and each processing core concurrently executes the corresponding tasks, that is, allocates the tasks such as data acquisition, interface display, model training, and the like to different processing cores, so that the tasks are concurrently executed, and the real-time online recognition delay is short.
In a specific implementation, the embedded chip 100 is further configured to establish a local data stream through a python lab stream media layer (Pylsl), where one end sends data to multiple ends for receiving and data multiplexing, so as to implement inter-process data sharing.
In the specific implementation, the neural network model is built by Tensorflow, and the later layers of the neural network are retrained in real time by a transfer learning method, so that the characteristic classification with better mobility, namely pattern recognition, is realized.
In order to facilitate interaction with an external device and achieve output of a recognition result, in this embodiment, the bioelectrical signal processing system further includes: the WiFi driving chip is connected with the embedded chip;
the WiFi driving chip is used for sending the pattern recognition result to external equipment, and specifically, the AP6212 chip can be selected as the WiFi driving chip.
The embodiment can realize the bioelectricity signal processing on the premise of not increasing too many hardware devices through the matching of the embedded chip, the ESP32 chip and the signal acquisition device, is convenient to carry, can be worn and has low cost.
For the prior art, the interfaces are numerous, and the separation of software and hardware means that communication between the two must be through a certain wired or wireless interface. The bioelectrical signal data transmission of the real-time system has a high requirement on the stability of the transmission mode, and if the wired connection is in poor contact or the wireless connection signal is interfered, packet loss is likely to occur, which also limits the data transmission speed. A plurality of interfaces have different standards, data cannot be shared, exclusive driving is needed, and the system is overstaffed and redundant.
In addition, for the prior art, the development of the algorithm and the software is difficult, and the maintenance and the update of the software require higher time cost and labor cost for being compatible with different architectures, different platforms and different systems, but the system of the embodiment can keep better compatibility, and avoid wasting the time cost and the labor cost.
The technical scheme of the invention is explained in detail in aspects of system composition, structure, coefficient calculation principle, upper computer display interface, use flow and the like through the drawings and the description of the specific embodiment. The above-described modes are only preferred embodiments of the present invention, and it will be apparent to those skilled in the art that modifications or equivalent substitutions can be made on the basis of the present disclosure to apply to various medical instrument systems, not limited to the system structure described in the embodiments of the present invention, and thus the above-described modes are only preferred and not intended to be limiting.
The above embodiments are only some specific embodiments of the present invention, and the above embodiments are only used for illustrating the technical solutions and concepts of the present invention and not for limiting the scope of the claims of the present invention. Other technical solutions which can be obtained by logical analysis, reasoning or limited experiments based on the concepts of the patent and the prior art should also be considered to fall within the scope of the claims of the present invention.
The above embodiments are only for illustrating the invention and are not to be construed as limiting the invention, and those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention, therefore, all equivalent technical solutions also belong to the scope of the invention, and the scope of the invention is defined by the claims.
Claims (10)
1. A bioelectrical signal processing system, characterized in that the bioelectrical signal processing system comprises: the device comprises an embedded chip, an ESP32 chip and signal acquisition equipment;
the signal acquisition equipment is used for acquiring a bioelectricity signal to be processed and amplifying the bioelectricity signal to be processed;
the ESP32 chip is used for reading and buffering the amplified bioelectrical signal to be processed, and transmitting the buffered bioelectrical signal to be processed to the embedded chip at one time;
the embedded chip is used for extracting time domain features and frequency domain features of the bioelectricity signal to be processed sent by the ESP32 chip to obtain the time domain features and the frequency domain features;
the embedded chip is also used for carrying out pattern recognition on the time domain characteristics and the frequency domain characteristics through a neural network model to obtain a pattern recognition result.
2. The bioelectrical signal processing system according to claim 1, wherein the time domain feature extraction comprises: at least one of root mean square, impulse factor, peak factor, margin, kurtosis, skewness, covariance, autocorrelation function, upper and lower envelope lines, parkinsonian tremor coefficient, stiffness coefficient, motion coefficient, brain psychomotor, and concentration.
3. The bioelectrical signal processing system according to claim 1, wherein the frequency domain feature extraction comprises: at least one of a fast Fourier transform, a short-time Fourier transform, a wavelet packet transform, an empirical mode decomposition, and a Hilbert-Huang transform.
4. The bioelectrical signal processing system according to claim 1, wherein the embedded chip is further configured to preprocess the bioelectrical signal to be processed transmitted from the ESP32 chip.
5. The bioelectrical signal processing system according to claim 4, wherein the preprocessing comprises: at least one of baseline rectification, artifact removal, noise reduction, notching, band pass filtering, and smoothing.
6. The bioelectrical signal processing system according to claim 1, further comprising: the SPI screen is connected with the embedded chip;
and the SPI screen is used for displaying the bioelectricity signal to be processed and the pattern recognition result.
7. The bioelectrical signal processing system according to any one of claims 1 to 6, wherein the embedded chip is a multi-processing core chip;
the embedded chip is also used for distributing the tasks which need to be executed currently to different processing cores, and the processing cores execute the corresponding tasks in parallel.
8. The bioelectrical signal processing system according to any one of claims 1 to 6, wherein the embedded chip is further configured to establish a local data stream through a python lab streaming media layer, thereby enabling inter-process sharing of data.
9. The bioelectrical signal processing system according to any one of claims 1 to 6, wherein the neural network model is constructed by Tensorflow.
10. The bioelectrical signal processing system according to any one of claims 1 to 6, further comprising: the WiFi driving chip is connected with the embedded chip;
and the WiFi driving chip is used for sending the pattern recognition result to external equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911358199.4A CN111084617A (en) | 2019-12-25 | 2019-12-25 | Bioelectric signal processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911358199.4A CN111084617A (en) | 2019-12-25 | 2019-12-25 | Bioelectric signal processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111084617A true CN111084617A (en) | 2020-05-01 |
Family
ID=70397148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911358199.4A Pending CN111084617A (en) | 2019-12-25 | 2019-12-25 | Bioelectric signal processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111084617A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101716079A (en) * | 2009-12-23 | 2010-06-02 | 江西蓝天学院 | Brainprint identity identification authentication method based on multi-characteristics algorithm |
| CN102512159A (en) * | 2011-12-08 | 2012-06-27 | 西安交通大学 | Portable wireless electroencephalogram acquisition device |
| CN106990406A (en) * | 2017-03-01 | 2017-07-28 | 浙江大学 | A kind of three-dimensional acoustics imaging real time signal processing device based on embeded processor |
| CN208689417U (en) * | 2018-09-17 | 2019-04-02 | 海口丰润动漫单片机微控科技开发有限公司 | A kind of embedded integrated development platform |
| CN110058691A (en) * | 2019-04-18 | 2019-07-26 | 西安交通大学 | Based on Embedded wearable wireless dry electrode brain wave acquisition processing system and method |
| CN212698896U (en) * | 2019-12-25 | 2021-03-16 | 杭州航弈生物科技有限责任公司 | Bioelectric signal processing system |
-
2019
- 2019-12-25 CN CN201911358199.4A patent/CN111084617A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101716079A (en) * | 2009-12-23 | 2010-06-02 | 江西蓝天学院 | Brainprint identity identification authentication method based on multi-characteristics algorithm |
| CN102512159A (en) * | 2011-12-08 | 2012-06-27 | 西安交通大学 | Portable wireless electroencephalogram acquisition device |
| CN106990406A (en) * | 2017-03-01 | 2017-07-28 | 浙江大学 | A kind of three-dimensional acoustics imaging real time signal processing device based on embeded processor |
| CN208689417U (en) * | 2018-09-17 | 2019-04-02 | 海口丰润动漫单片机微控科技开发有限公司 | A kind of embedded integrated development platform |
| CN110058691A (en) * | 2019-04-18 | 2019-07-26 | 西安交通大学 | Based on Embedded wearable wireless dry electrode brain wave acquisition processing system and method |
| CN212698896U (en) * | 2019-12-25 | 2021-03-16 | 杭州航弈生物科技有限责任公司 | Bioelectric signal processing system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khan et al. | Multiclass EEG motor-imagery classification with sub-band common spatial patterns | |
| Gohel et al. | Review on electromyography signal acquisition and processing | |
| Jiang et al. | IoT-based remote facial expression monitoring system with sEMG signal | |
| US20210217419A1 (en) | Lip-language recognition aac system based on surface electromyography | |
| CN212698896U (en) | Bioelectric signal processing system | |
| CN108968952A (en) | A kind of brain myoelectricity and Inertia information synchronous acquisition device | |
| Norani et al. | A review of signal processing in brain computer interface system | |
| Hamedi et al. | Human facial neural activities and gesture recognition for machine-interfacing applications | |
| Khalid et al. | Towards a brain computer interface using wavelet transform with averaged and time segmented adapted wavelets | |
| CN104267807A (en) | Hand action mechanomyography based man-machine interaction method and interaction system | |
| CN105892676A (en) | Human-machine interaction device, system and method of vascular intervention operation wire feeder | |
| Salvaro et al. | A minimally invasive low-power platform for real-time brain computer interaction based on canonical correlation analysis | |
| KR101527273B1 (en) | Method and Apparatus for Brainwave Detection Device Attached onto Frontal Lobe and Concentration Analysis Method based on Brainwave | |
| Tripathi et al. | SurfMyoAiR: A surface electromyography-based framework for airwriting recognition | |
| Rajashekhar et al. | Electroencephalogram (EEG) signal classification for brain–computer interface using discrete wavelet transform (DWT) | |
| CN106725463B (en) | Method and system for positioning cerebral cortex hand functional area by applying cortical electroencephalogram signals | |
| CN111084617A (en) | Bioelectric signal processing system | |
| CN105686827B (en) | A kind of electromyography signal processing and feature extracting method based on microcontroller | |
| Li et al. | A wearable wireless device designed for surface electromyography acquisition | |
| Rosli et al. | Electrocardiographic (ECG) and Electromyographic (EMG) signals fusion for physiological device in rehab application | |
| CN206627909U (en) | A kind of brain machine interface system | |
| Turnip et al. | Application of support vector machine classifier on developed wireless ECG system | |
| CN204158401U (en) | Brain cognition and mental status checkout gear | |
| Bandara et al. | Differentiation of signals generated by eye blinks and mouth clenching in a portable brain computer interface system | |
| CN209515202U (en) | A kind of first aid information transmission system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |