CN108888280B - Student class attending attention evaluation method based on electroencephalogram signal analysis - Google Patents
Student class attending attention evaluation method based on electroencephalogram signal analysis Download PDFInfo
- Publication number
- CN108888280B CN108888280B CN201810507554.9A CN201810507554A CN108888280B CN 108888280 B CN108888280 B CN 108888280B CN 201810507554 A CN201810507554 A CN 201810507554A CN 108888280 B CN108888280 B CN 108888280B
- Authority
- CN
- China
- Prior art keywords
- signal
- electroencephalogram
- attention
- component
- analysis
- 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.)
- Active
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
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/168—Evaluating attention deficit, hyperactivity
-
- 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
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
Abstract
The invention discloses a student attendance attention evaluation method based on electroencephalogram signal analysis, which aims to solve the problem that the student attendance attention concentration is difficult to characterize, and comprises the following steps of: 1. collecting electroencephalogram signals of students, namely 1) collecting original electroencephalogram signals; 2) carrying out pre-stage amplification processing on the original electroencephalogram signals; 3) amplifying the electroencephalogram signals subjected to the primary amplification treatment again; 4) converting the amplified electroencephalogram signal into a digital signal; 2. analyzing the electroencephalogram signals: 1) removing power frequency interference of the electroencephalogram signal; 2) carrying out low-pass filtering processing on the electroencephalogram signals; 3) removing ocular artifacts; 4) extracting and quantifying the features; 6) quantifying sample entropy as concentration of attention; 3. transmitting the quantified concentration of attention through a wireless transmitting device; 4. receiving, by a wireless receiving device, attention concentration data; 5. storing concentration data over a period of time; 6. presented through a visual interface.
Description
Technical Field
The invention relates to an evaluation method belonging to the technical field of cognitive neuroscience and information, in particular to a student class attendance evaluation method based on electroencephalogram signal analysis.
Background
The change of human emotion and state is associated with the change of the electroencephalogram signal of the human to a certain degree. In class, the more concentrated the attention of the students, the more clearly the content of the teacher can be mastered, and the change of the concentration degree of the attention is really related to the change of the electroencephalogram signal.
The brain cell population, when active, produces rhythmic electric field fluctuations. The electroencephalogram (EEG), which is a general reflection of such electric field fluctuations on the surface of the cerebral cortex or scalp, records changes in electrical signals during brain activity. The electroencephalogram signal is a random signal, has the characteristics of non-stability and non-linearity, and can reflect the state and the change of a human nervous system. Brain Computer Interface (BCI) is a technique of collecting electroencephalogram signals in cerebral cortex, sensing electrical signal patterns of cerebral neurons, converting the signals into interpretable signals through steps of amplification, filtering, feature extraction and the like, and distinguishing states, emotions, ideas, moods and the like of a human body from the interpretable signals.
The frequency range of the electroencephalogram signals is 0-30Hz, and the electroencephalogram signals can be divided into four wave bands of delta, theta, alpha and beta according to different frequencies, wherein the frequency range of the delta wave is 0.5-4Hz, the amplitude is 20-200 mu V, and the frequency range mainly reflects that a human is in a deep sleep state or has serious organic brain diseases; the frequency range of the theta wave is 4-8Hz, the amplitude is 10-50 muV, and the theta wave mainly reflects the light sleeping state and the drowsiness state of a person; the frequency range of the alpha wave is 8-13Hz, the amplitude is about 50 muV, and the alpha wave mainly reflects that a person is in a relaxed, eye-closed and clear state; the frequency range of the beta wave is 13-30Hz, the amplitude is 5-20 muV, the complexity degree of the beta wave has great correlation with the mental stress degree, and the higher complexity degree generally means that the brain of a human is more clear and nervous, and has higher concentration.
Therefore, the attention of students can be evaluated by analyzing the change of the complexity of the beta wave in the electroencephalogram signals.
The brain-computer interface patent in the prior art does not apply the electroencephalogram signal analysis attention concentration to student attention assessment, the prior patent technology relates to attention assessment under a driving environment (for example, the application number is CN201410381256), an attention training system (for example, the application number is CN201611106017.0) and an attention testing system (for example, the application number is CN201710164162.2), and the evaluation of student attention to class by analyzing the change of a brain wave specific frequency band in the class process of a student is a novel and efficient method, and no related patent is disclosed yet.
Disclosure of Invention
The invention provides a student class attendance attention evaluation method based on electroencephalogram signal analysis, aiming at solving the problem that the class attendance attention concentration degree of a student is difficult to characterize.
In order to solve the technical problems, the invention is realized by adopting the following technical scheme: the student class attending attention evaluation method based on electroencephalogram signal analysis comprises the following steps:
1) collecting electroencephalogram signals of students;
2) filtering, independently extracting a beta frequency band, calculating sample entropy, and quantizing the sample entropy into attention concentration;
3) transmitting the quantified concentration of attention through a wireless transmitting device;
4) receiving, by a wireless receiving device, attention concentration data;
5) storing concentration data over a period of time;
6) presented through a visual interface.
The technical scheme is that the acquisition of the electroencephalogram signals of students comprises the following steps:
(1) collecting original brain electrical signals;
a wet electrode single-channel acquisition mode is selected, the wet electrode single-channel acquisition mode comprises a data electrode and two reference electrodes, the data electrode is placed at the Fpz position in a 10-20 standard electrode placement method specified by the International electroencephalogram institute, namely the center of the frontal pole to acquire data, and the reference electrode A1 and the reference electrode A2 are placed at the left and right ear papillae;
(2) the primary electroencephalogram signal is subjected to pre-stage amplification processing
Because the acquired original electroencephalogram signal is very weak, the amplitude range is 5-100 muV, the original electroencephalogram signal needs to be amplified, the amplification gain of the original electroencephalogram signal is much higher than that of a common signal, and the original electroencephalogram signal is generally amplified by about 20000 times;
(3) amplifying the EEG signal subjected to the primary amplification treatment again
In order to prevent the amplifier from being saturated by introduced noise caused by overhigh amplification factor, the amplification process is divided into two stages, a simple equidirectional amplification circuit is adopted in the step, the signal amplified by the preamplifier is amplified again, and the amplification factor is 100;
(4) converting the amplified EEG signal into digital signal
The amplified analog EEG signal is converted by an A/D converter, the sampling frequency is set to 512 sample points per second, and the converted digital signal is sent to an EEG signal analysis unit.
The filtering processing and the independent extraction of the beta frequency band to calculate the sample entropy and the quantization of the sample entropy into the attention concentration ratio in the technical scheme refer to the following steps:
(1) removing power frequency interference of electroencephalogram signals
Under the common environment, the acquisition of the electroencephalogram signals is interfered by the power frequency environment brought by the mains supply voltage with the frequency of 50Hz, so that the analysis of the electroencephalogram signals is influenced; in the step, the invention adopts an FIR notch filter to eliminate power frequency interference, and the stop band is set to be 45-55 Hz;
(2) low-pass filtering treatment of brain electrical signal
Because the useful EEG signal frequency is small, a Chebyshev I type low-pass filter is adopted to remove high-frequency interference, and the cut-off frequency of a pass band is 50 Hz;
(3) removing ocular artifacts;
(4) extracting beta frequency band electroencephalogram signals;
(5) computing sample entropy
Adding a sliding time window to the electroencephalogram signal, calculating the sample entropy of the electroencephalogram signal by taking the length of 1s as the sliding time window, namely 512 points, moving 64 sampling points in the window each time, calculating the sample entropy of the electroencephalogram signal of the next 1s time window until the sample entropy of the electroencephalogram signal of the last 1s time window of the signal in one minute is calculated, and thus obtaining the time sequence of the sample entropy of the electroencephalogram signal in the sample data;
the group of sample entropy sequences are superposed and averaged to obtain the sample entropy of the signal within 1 min;
(6) quantifying sample entropy as concentration of attention
Calibrating the attention concentration ratio of the time period by calculating the values of the beta wave sample entropies of different time periods; the quantization process quantizes the sample entropy values according to (0-0.5], (0.5-1.0], (1.0-1.5], (1.5-2.0] and more than 2.0 into five grades of label1, label2, label3, label4 and label5, which respectively represent a low value, a normal level, a high value and a high value, and the concentration degree is gradually improved.
The method for removing the ocular artifacts in the technical scheme comprises the following steps:
a. overall empirical mode decomposition;
b. rapid independent component analysis
The adopted rapid independent component analysis algorithm is an independent component analysis method based on negative entropy, each eigenmode component obtained in the step a is respectively input into an independent component analysis system for blind source separation, and the obtained source signals comprise an electroencephalogram component source signal and an opthalmic component source signal;
c. threshold value judgment, selecting pure electroencephalogram component
Setting a threshold value aiming at the approximate entropy of each component in the source signal, judging the component as an electro-oculogram component when the entropy value is greater than 0.6, judging the component as an electro-encephalography component when the entropy value is less than or equal to 0.6, and simultaneously setting the electro-oculogram component to be 0 to obtain an electro-encephalography signal source;
d. fast independent component analysis inverse transform
Converting the electroencephalogram signal source obtained in the step c into a relatively pure electroencephalogram signal extracted from a single intrinsic mode component through rapid independent component analysis inverse transformation;
e. d, adding all the pure electroencephalogram signals obtained in the step d
And d, adding the plurality of pure signal components extracted in the step d, and then preprocessing the electroencephalogram signal.
The overall empirical mode decomposition in the technical scheme is as follows:
decomposing the electroencephalogram signal subjected to A/D conversion into a plurality of intrinsic mode components by overall empirical mode decomposition, wherein the intrinsic mode components need to meet two conditions that the number of signal extreme points is equal to the number of zero points or the difference value is 1, and the local mean value of an upper envelope defined by the maximum value of the signal and a lower envelope defined by the minimum value of the signal is 0;
the decomposition process is as follows:
a) white Gaussian noise N with zero mean and constant standard deviationi(t) adding to the input signal S (t) such that
Si(t)＝S(t)+Ni(t)
Wherein: n is a radical ofi(t) represents the ith added noise;
b) find Si(t) all extreme points, including maxima and minima;
c) fitting the extreme points by adopting a cubic spline to obtain an upper envelope curve and a lower envelope curve, calculating a mean value, and further obtaining a difference value h between an original signal and the mean value;
d) judging whether the difference h between the original signal and the mean value can meet two conditions of the intrinsic mode component, and if so, taking the difference h between the original signal and the mean value as a first intrinsic mode component; otherwise, the previous two steps of operation are carried out on the difference value h between the original signal and the average value, the process is repeated until the kth step meets the condition of the intrinsic mode component, the first intrinsic mode component is obtained, and the difference value r between the original signal and the intrinsic mode component is obtained;
e) taking the difference r as a signal to be decomposed, and performing the decomposition process until the final difference r is a monotonous signal or only one pole exists;
the final decomposition results are:
wherein: cj(t) decomposing the jth eigenmode component, and R (t) is the rest obtained by decomposition.
The extraction of the beta-band electroencephalogram signal in the technical scheme is as follows:
a. fast Fourier transform
Performing fast Fourier transform on the preprocessed signal to obtain a frequency domain signal;
b. frequency band screening
Reserving a 13-30Hz frequency band signal, namely a beta wave frequency range, and setting other frequency range to be 0;
c. inverse fast Fourier transform
And c, performing fast Fourier inverse transformation on the result obtained in the step b to obtain a time domain signal only containing a beta wave frequency band.
Compared with the prior art, the invention has the beneficial effects that:
the student attendance attention evaluation method based on electroencephalogram signal analysis extracts electroencephalogram signal characteristics related to attention concentration degree by analyzing cerebral cortex electrical information of a specific frequency band of a student in class, and feeds back the student attendance attention in different time periods through computer software, so that the problem that the student attendance concentration degree is difficult to quantify and represent is solved, and a suggestion is provided for a teacher to give lessons.
Drawings
FIG. 1 is a schematic block diagram of the structural components of a student class attendance attention evaluation system based on electroencephalogram analysis according to the present invention;
FIG. 2 is a block diagram of a flow chart of a student attendance attention evaluation method based on electroencephalogram analysis according to the present invention;
FIG. 3 is a block diagram of a flow chart of a method for acquiring electroencephalogram signals in the method for evaluating student attendance attention based on electroencephalogram signal analysis according to the present invention;
FIG. 4 is a block diagram of a process of a electroencephalogram signal analysis method in the method for evaluating attention of students attending classes based on electroencephalogram signal analysis according to the present invention;
FIG. 5 is a block diagram of a flow chart of a method for removing ocular artifacts in the step of analyzing electroencephalogram signals according to the electroencephalogram signal analysis-based student attending attention evaluation method of the present invention;
FIG. 6 is a flow chart of a feature extraction and quantification method in the step of analyzing electroencephalogram signals according to the electroencephalogram signal analysis-based student attending attention evaluation method of the present invention;
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the present invention will be further described with reference to the accompanying drawings and specific embodiments.
The invention provides a student class attendance attention evaluation method and system based on electroencephalogram signal analysis, aiming at the problem that the student class attendance attention concentration ratio is difficult to characterize.
Referring to fig. 1, the system for evaluating the attention of students on class based on electroencephalogram analysis comprises a student end and a teacher end.
The student end is integrated into a single-channel electroencephalogram head ring, the rechargeable battery supplies power, and the student end/single-channel electroencephalogram head ring is integrated with an electroencephalogram signal acquisition unit, an electroencephalogram signal analysis unit and a Bluetooth wireless transmission unit.
The electroencephalogram signal acquisition unit acquires electrical signals of cerebral cortex, amplifies the electrical signals and performs analog-to-digital conversion, and comprises four parts, namely an acquisition electrode, a preposed primary amplifier, a secondary amplification circuit and an A/D converter, wherein the converted signals are transmitted into an electroencephalogram signal analysis unit;
the collecting electrodes in the electroencephalogram signal collecting unit adopt a single-channel collecting mode, the wet electrodes are used for better realizing circuit communication, the electroencephalogram signal collecting unit comprises a data electrode and two reference electrodes, the data electrode is placed at the Fpz position (namely the center of the frontal pole) in a 10-20 standard electrode placing method specified by the International electroencephalogram institute, and the reference electrodes A1 and A2 are respectively positioned at the left and right auricular papillae positions;
the preposed first-stage amplifier in the electroencephalogram signal acquisition unit selects an instrument amplifier INA128 of TI company, a pin 5 is grounded, a pin 3 and a pin 2 are connected with differential input, a pin 8 and a pin 1 are connected with a resistance for adjusting gain, and the maximum gain in the step can reach 10000 times;
the secondary amplification circuit in the electroencephalogram signal acquisition unit adopts a simple homodromous amplification circuit, and the amplification factor is 100 times;
the A/D converter in the electroencephalogram signal acquisition unit adopts a MAX548A low-power consumption 8-bit voltage type 2-path analog-to-digital converter of American signal company, and the sampling frequency is set to 512 sample points per second;
the electroencephalogram signal analysis unit carries out power frequency interference removal, low-pass filtering processing and ocular artifact removal on an incoming electroencephalogram signal, extracts and quantifies characteristics of related frequency band signals into 5 attention concentration levels, and the steps are executed by a TMS320LF2407 DSP microcontroller through a preset program, so that the electroencephalogram signal analysis unit has better digital signal processing capability and high operation speed, can expand a plurality of parallel external devices, and can reliably process the electroencephalogram signal;
the 10 pins of the TMS320LF2407 DSP microcontroller in the electroencephalogram signal analysis unit are connected with the output of the A/D converter;
the Bluetooth wireless transmitting unit adopts a BT-06 Bluetooth serial port communication module produced by Shenzhen Shangtai micro-technology Limited company, is connected with a synchronous Serial Port (SPI) embedded in a DSP microcontroller, and transmits a quantitative result of student attention concentration to a teacher end in real time;
the teacher end is embedded in the computer and comprises a Bluetooth wireless receiving unit, a database and a visual interface; the student end and the teacher end are in wireless communication connection.
The Bluetooth wireless receiving unit is a Bluetooth adapter 4.0 produced by Shenzhen Lulian science and technology Limited, is connected with a teacher computer through a USB universal serial interface and receives attention concentration data transmitted by the student end Bluetooth wireless transmitting unit;
the database is stored in a computer hard disk, a Redis key value is adopted to store the database, a record file is adopted to ensure the persistence of the record of the database, and the attention concentration condition of a certain period of time in a certain class is allowed to be inquired or deleted at any time;
the visual interface is displayed through a computer display screen, written by VC + +, calls data in the database and draws a student attention concentration curve.
Referring to fig. 2, the student attending lesson attention evaluation method based on electroencephalogram analysis according to the present invention comprises the following steps:
1. collecting electroencephalogram signals of students
Referring to fig. 3, the acquisition of the electroencephalogram signals of the students is completed by an electroencephalogram signal acquisition unit integrated in a brain loop, and the steps are as follows:
(1) collecting original EEG signals
A wet electrode single-channel acquisition mode is selected, the wet electrode single-channel acquisition mode comprises a data electrode and two reference electrodes, the data electrode is placed at an Fpz position (namely the center point of a forehead) in a 10-20 standard electrode placement method specified by the International electroencephalogram society to acquire data, and the reference electrodes A1 and A2 are placed at the left and right ear papillae;
(2) carrying out pre-stage amplification processing on the original electroencephalogram signals;
because the acquired original electroencephalogram signal is very weak, the amplitude range is 5-100 muV, the original electroencephalogram signal needs to be subjected to multi-stage amplification treatment, the amplification gain of the original electroencephalogram signal is much higher than that of a common signal, and the original electroencephalogram signal is generally amplified by about 20000 times;
(3) amplifying the electroencephalogram signals subjected to the primary amplification treatment again;
in order to prevent the amplifier from being saturated by introduced noise caused by overhigh amplification factor, the amplification process is divided into two stages, a simple equidirectional amplification circuit is adopted in the step, the signal amplified by the preamplifier is amplified again, and the amplification factor is 100;
(4) converting the amplified EEG signal into digital signal
The amplified analog electroencephalogram signal is converted through the A/D converter, the sampling frequency is set to 512 sample points per second, and the converted digital signal is sent to an electroencephalogram signal analysis unit;
2. analysis of brain electrical signals
Referring to fig. 4, the step is completed by a brain electrical signal analysis unit integrated in the brain electrical head loop, and is executed by a program preset in the DSP microcontroller, and the steps are as follows:
(1) removing power frequency interference of electroencephalogram signals
Under the common environment, the acquisition of the electroencephalogram signals is interfered by the power frequency environment brought by the mains supply voltage with the frequency of 50Hz, and the analysis of the electroencephalogram activity signals is influenced; in the step, the invention adopts an FIR notch filter to eliminate power frequency interference, and the stop band is set to be 45-55 Hz;
(2) low-pass filtering treatment of brain electrical signal
Because the useful EEG signal frequency is small, a Chebyshev I type low-pass filter is adopted to remove high-frequency interference, and the cut-off frequency of a pass band is 50 Hz;
(3) removing ocular artifacts
Referring to fig. 5, ocular artifacts caused by eye movement and the like are very common noises in the electroencephalogram signals and seriously affect the extraction of useful information; in the step, a method combining ensemble empirical mode decomposition and rapid independent component analysis is adopted to eliminate ocular artifacts to obtain a relatively pure electroencephalogram signal; the steps for removing the ocular artifacts are as follows:
a. ensemble empirical mode decomposition
Decomposing the electroencephalogram signal subjected to A/D conversion into a plurality of intrinsic mode components by overall empirical mode decomposition, wherein the intrinsic mode components need to meet two conditions that the number of signal extreme points is equal to the number of zero points or the difference value is one, and the local mean value of an upper envelope defined by the maximum value of the signal and a lower envelope defined by the minimum value of the signal is 0;
the decomposition process is as follows:
a) white Gaussian noise N with zero mean and constant standard deviationi(t) adding to the input signal S (t) such that
Si(t)＝S(t)+Ni(t)
Wherein: n is a radical ofi(t) represents the ith added noise;
b) find Si(t) all extreme points, including maxima and minima;
c) fitting the extreme points by adopting a cubic spline to obtain an upper envelope curve and a lower envelope curve, calculating a mean value, and further obtaining a difference value h between an original signal and the mean value;
d) judging whether the difference h between the original signal and the mean value can meet two conditions of the intrinsic mode component, and if so, taking the difference h between the original signal and the mean value as a first intrinsic mode component; otherwise, the previous two steps of operation are carried out on the difference value h between the original signal and the average value, the process is repeated until the kth step meets the condition of the intrinsic mode component, the first intrinsic mode component is obtained, and the difference value r between the original signal and the intrinsic mode component is obtained;
e) taking the difference r as a signal to be decomposed, and performing the decomposition process until the final difference r is a monotonous signal or only one pole exists;
the final decomposition results are:
wherein: cj(t) decomposing the jth eigenmode component, and R (t) is the rest obtained by decomposition.
b. Rapid independent component analysis
The fast independent component analysis algorithm is an independent component analysis method based on negative entropy, each eigenmode component obtained in the step a is respectively input into an independent component analysis system for blind source separation, and the obtained source signals comprise an electroencephalogram component source signal and an opthalmic component source signal;
c. threshold value judgment, selecting pure electroencephalogram component
Setting a threshold value aiming at the approximate entropy of each component in the source signal, judging the component as an electro-oculogram component when the entropy value is greater than 0.6, judging the component as an electro-encephalography component when the entropy value is less than or equal to 0.6, and simultaneously setting the electro-oculogram component to be 0 to obtain an electro-encephalography signal source;
d. fast independent component analysis inverse transform
Converting the electroencephalogram signal source obtained in the step c into a relatively pure electroencephalogram signal extracted from a single intrinsic mode component through rapid independent component analysis inverse transformation;
e. d, adding all the pure electroencephalogram signals obtained in the step d
D, adding the plurality of pure signal components extracted in the step d, and then preprocessing the electroencephalogram signals;
(4) extracting and quantifying the features;
referring to fig. 6, the electroencephalogram feature extraction process of the student attention concentration is still performed in the DSP microcontroller, and signal processing is realized by a built-in program; the invention extracts beta wave (namely 13-30Hz) electroencephalogram signals related to attention concentration ratio through fast Fourier transform, and comprises the following steps:
a. fast Fourier transform;
performing fast Fourier transform on the preprocessed signal to obtain a frequency domain signal;
b. screening frequency bands;
reserving a 13-30Hz frequency band signal, namely a beta wave frequency range, and setting other frequency range to be 0;
c. performing fast Fourier inverse transformation;
performing fast Fourier inverse transformation on the result obtained in the step b to obtain a time domain signal only containing a beta wave frequency band;
(5) computing sample entropy
Adding a sliding time window to the electroencephalogram signal, calculating the sample entropy of the electroencephalogram signal by taking the length of 1s as the sliding time window (512 points), moving the window by 64 sampling points each time, calculating the sample entropy of the electroencephalogram signal of the next 1s time window until calculating the sample entropy of the electroencephalogram signal of the last 1s time window of the signal in one minute, and thus obtaining the time sequence of the sample entropy of the electroencephalogram signal in the sample data;
the group of sample sequences are superposed and averaged, namely the sample entropy of the signal within 1min is obtained;
(6) quantifying sample entropy as concentration of attention
Calibrating the attention concentration ratio of the time period by calculating the values of the beta wave sample entropies of different time periods; the quantization process quantizes the sample entropy values according to (0-0.5], (0.5-1.0], (1.0-1.5], (1.5-2.0] and more than 2.0 into five grades of label1, label2, label3, label4 and label5, which respectively represent a low value, a normal level, a high value and a high value, and the concentration degree is gradually improved;
3. transmitting quantified concentration of attention through a wireless transmitting device
In the step, a BT-06 Bluetooth module is used as an external device of the DSP microcontroller in the step 2, so that the wireless transmission of attention concentration is realized;
4. receiving attention concentration data by a wireless receiving device
The teacher end's bluetooth wireless receiving unit is bluetooth adapter 4.0, links to each other through the USB serial ports between it and the computer, waits that student end bluetooth wireless sending module pairs the back with teacher end computer male bluetooth wireless receiving unit, and the quantization result of concentration is transmitted by wireless real time.
5. Storing concentration data over a period of time
The data are stored in a key value storage database built in a computer in real time, the key value storage database adopts a record file to ensure the persistence of the records of the database, the attention concentration condition of a certain period of time in a class is allowed to be inquired at any time, the key in the database is 1, 2.
6. Presenting through a visual interface
The visual interface of the teacher end of the student attendance attention evaluation method based on electroencephalogram signal analysis is compiled by VC + +, data in a database is called, and a student attention concentration curve is drawn. The interface functions as follows: the visual software draws a student attention concentration curve from data stored in a database in one class (45 minutes), and feeds back the attention of students in different time periods through computer software, wherein the time period curve with high and high attention concentrations is green, and the time period curve with low and low attention concentrations is marked with red and is represented by bold color, so as to remind teachers to think about contents and methods taught in the red time periods.
The invention provides a student lecture attending attention evaluation method based on electroencephalogram signal analysis, which extracts electroencephalogram characteristics related to attention concentration degree by analyzing electroencephalogram information of a specific frequency band of a student in class, feeds back the lecture attending attention of the student at different time intervals through computer software, solves the problem that the lecture attending attention concentration degree of the student is difficult to quantify and represent, and provides suggestions for teachers.
Claims (6)
1. A student class attendance attention evaluation method based on electroencephalogram signal analysis is characterized by comprising the following steps:
1) collecting electroencephalogram signals of students;
2) filtering, independently extracting a beta frequency band, calculating sample entropy, and quantizing the sample entropy into attention concentration;
3) transmitting the quantified concentration of attention through a wireless transmitting device;
4) receiving, by a wireless receiving device, attention concentration data;
5) storing concentration data over a period of time;
6) presented through a visual interface.
2. The method for evaluating the attention of a student attending lesson based on electroencephalogram analysis according to claim 1, wherein the step of collecting the electroencephalogram signals of the student is as follows:
(1) collecting original EEG signals
A wet electrode single-channel acquisition mode is selected, the wet electrode single-channel acquisition mode comprises a data electrode and two reference electrodes, the data electrode is placed at the Fpz position in a 10-20 standard electrode placement method specified by the International electroencephalogram institute, namely the center of the frontal pole to acquire data, and the reference electrode A1 and the reference electrode A2 are placed at the left and right ear papillae;
(2) the primary electroencephalogram signal is subjected to pre-stage amplification processing
Because the acquired original electroencephalogram signal is very weak, the amplitude range is 5-100 muV, the original electroencephalogram signal needs to be amplified, the amplification gain of the original electroencephalogram signal is much higher than that of a common signal, and the original electroencephalogram signal is generally amplified by about 20000 times;
(3) amplifying the EEG signal subjected to the primary amplification treatment again
In order to prevent the amplifier from being saturated by introduced noise caused by overhigh amplification factor, the amplification process is divided into two stages, a simple equidirectional amplification circuit is adopted in the step, the signal amplified by the preamplifier is amplified again, and the amplification factor is 100;
(4) converting the amplified EEG signal into digital signal
The amplified analog EEG signal is converted by an A/D converter, the sampling frequency is set to 512 sample points per second, and the converted digital signal is sent to an EEG signal analysis unit.
3. The electroencephalogram signal analysis-based student lecture attention evaluation method as claimed in claim 1, wherein the filtering, the independent extraction of the beta frequency band, the calculation of the sample entropy, and the quantization of the sample entropy into the attention concentration ratio refer to:
(1) removing power frequency interference of electroencephalogram signals
Under the common environment, the acquisition of the electroencephalogram signals is interfered by the power frequency environment brought by the mains supply voltage with the frequency of 50Hz, so that the analysis of the electroencephalogram signals is influenced; in the step, the invention adopts an FIR notch filter to eliminate power frequency interference, and the stop band is set to be 45-55 Hz;
(2) low-pass filtering treatment of brain electrical signal
Because the useful EEG signal frequency is small, a Chebyshev I type low-pass filter is adopted to remove high-frequency interference, and the cut-off frequency of a pass band is 50 Hz;
(3) removing ocular artifacts;
(4) extracting beta frequency band electroencephalogram signals;
(5) computing sample entropy
Adding a sliding time window to the electroencephalogram signal, calculating the sample entropy of the electroencephalogram signal by taking the length of 1s as the sliding time window, namely 512 points, moving 64 sampling points in the window each time, calculating the sample entropy of the electroencephalogram signal of the next 1s time window until the sample entropy of the electroencephalogram signal of the last 1s time window of the signal in one minute is calculated, and thus obtaining the time sequence of the sample entropy of the electroencephalogram signal in the sample data;
the group of sample entropy sequences are superposed and averaged to obtain the sample entropy of the signal within 1 min;
(6) quantifying sample entropy as concentration of attention
Calibrating the attention concentration ratio of the time period by calculating the values of the beta wave sample entropies of different time periods; the quantization process quantizes the sample entropy values according to (0-0.5], (0.5-1.0], (1.0-1.5], (1.5-2.0] and more than 2.0 into five grades of label1, label2, label3, label4 and label5, which respectively represent a low value, a normal level, a high value and a high value, and the concentration degree is gradually improved.
4. The electroencephalogram signal analysis-based student lecture attention evaluation method according to claim 3, wherein the removing of ocular artifacts is:
a. overall empirical mode decomposition;
b. rapid independent component analysis
The adopted rapid independent component analysis algorithm is an independent component analysis method based on negative entropy, each eigenmode component obtained in the step a is respectively input into an independent component analysis system for blind source separation, and the obtained source signals comprise an electroencephalogram component source signal and an opthalmic component source signal;
c. threshold value judgment, selecting pure electroencephalogram component
Setting a threshold value aiming at the approximate entropy of each component in the source signal, judging the component as an electro-oculogram component when the entropy value is greater than 0.6, judging the component as an electro-encephalography component when the entropy value is less than or equal to 0.6, and simultaneously setting the electro-oculogram component to be 0 to obtain an electro-encephalography signal source;
d. fast independent component analysis inverse transform
Converting the electroencephalogram signal source obtained in the step c into a relatively pure electroencephalogram signal extracted from a single intrinsic mode component through rapid independent component analysis inverse transformation;
e. d, adding all the pure electroencephalogram signals obtained in the step d
And d, adding the plurality of pure signal components extracted in the step d, and then preprocessing the electroencephalogram signal.
5. The electroencephalogram signal analysis-based student attendance attention evaluation method according to claim 4, wherein the ensemble empirical mode decomposition means:
decomposing the electroencephalogram signal subjected to A/D conversion into a plurality of intrinsic mode components by overall empirical mode decomposition, wherein the intrinsic mode components need to meet two conditions that the number of signal extreme points is equal to the number of zero points or the difference value is 1, and the local mean value of an upper envelope defined by the maximum value of the signal and a lower envelope defined by the minimum value of the signal is 0;
the decomposition process is as follows:
a) white Gaussian noise N with zero mean and constant standard deviationi(t) adding to the input signal S (t) such that
Si(t)＝S(t)+Ni(t)
Wherein: n is a radical ofi(t) represents the ith added noise;
b) find Si(t) all extreme points, including maxima and minima;
c) fitting the extreme points by adopting a cubic spline to obtain an upper envelope curve and a lower envelope curve, calculating a mean value, and further obtaining a difference value h between an original signal and the mean value;
d) judging whether the difference h between the original signal and the mean value can meet two conditions of the intrinsic mode component, and if so, taking the difference h between the original signal and the mean value as a first intrinsic mode component; otherwise, the previous two steps of operation are carried out on the difference value h between the original signal and the average value, the process is repeated until the kth step meets the condition of the intrinsic mode component, the first intrinsic mode component is obtained, and the difference value r between the original signal and the intrinsic mode component is obtained;
e) taking the difference r as a signal to be decomposed, and performing the decomposition process until the final difference r is a monotonous signal or only one pole exists;
the final decomposition results are:
wherein: cj(t) decomposing the jth eigenmode component, and R (t) is the rest obtained by decomposition.
6. The method for evaluating the attention of students attending classes based on electroencephalogram signal analysis according to claim 3, wherein the extraction of the beta-band electroencephalogram signal is as follows:
a. fast Fourier transform
Performing fast Fourier transform on the preprocessed signal to obtain a frequency domain signal;
b. frequency band screening
Reserving a 13-30Hz frequency band signal, namely a beta wave frequency range, and setting other frequency range to be 0;
c. inverse fast Fourier transform
And c, performing fast Fourier inverse transformation on the result obtained in the step b to obtain a time domain signal only containing a beta wave frequency band.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810507554.9A CN108888280B (en) | 2018-05-24 | 2018-05-24 | Student class attending attention evaluation method based on electroencephalogram signal analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810507554.9A CN108888280B (en) | 2018-05-24 | 2018-05-24 | Student class attending attention evaluation method based on electroencephalogram signal analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108888280A CN108888280A (en) | 2018-11-27 |
| CN108888280B true CN108888280B (en) | 2021-07-13 |
Family
ID=64343335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810507554.9A Active CN108888280B (en) | 2018-05-24 | 2018-05-24 | Student class attending attention evaluation method based on electroencephalogram signal analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108888280B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109646022B (en) * | 2019-01-10 | 2021-06-01 | 杭州电子科技大学 | Child attention assessment system and method thereof |
| CN109846477B (en) * | 2019-01-29 | 2021-08-06 | 北京工业大学 | Electroencephalogram classification method based on frequency band attention residual error network |
| CN110595603B (en) * | 2019-04-26 | 2022-04-19 | 深圳市豪视智能科技有限公司 | Video-based vibration analysis method and related product |
| CN112472106A (en) * | 2019-09-10 | 2021-03-12 | 西安慧脑智能科技有限公司 | Method, chip, storage medium and device for analyzing electroencephalogram signals |
| CN110897639A (en) * | 2020-01-02 | 2020-03-24 | 清华大学深圳国际研究生院 | Electroencephalogram sleep staging method based on deep convolutional neural network |
| CN111258428B (en) * | 2020-01-20 | 2023-10-24 | 西安臻泰智能科技有限公司 | Brain electricity control system and method |
| CN112185191B (en) * | 2020-09-21 | 2022-08-16 | 信阳职业技术学院 | Intelligent digital teaching model |
| CN112245756A (en) * | 2020-10-16 | 2021-01-22 | 郑州大学 | Attention training method based on single-channel electroencephalogram |
| CN112494774A (en) * | 2020-10-16 | 2021-03-16 | 杭州师范大学 | Continuous attention regulation and control system based on delayed electroencephalogram feedback |
| CN113080998B (en) * | 2021-03-16 | 2022-06-03 | 北京交通大学 | Electroencephalogram-based concentration state grade assessment method and system |
| CN113476057B (en) * | 2021-07-08 | 2023-04-07 | 先端智能科技(天津)有限公司 | Content evaluation method and device, electronic device and storage medium |
| CN116757524B (en) * | 2023-05-08 | 2024-02-06 | 广东保伦电子股份有限公司 | Teacher teaching quality evaluation method and device |
| CN117158972B (en) * | 2023-11-04 | 2024-03-15 | 北京视友科技有限责任公司 | Attention transfer capability evaluation method, system, device and storage medium |
Family Cites Families (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060257834A1 (en) * | 2005-05-10 | 2006-11-16 | Lee Linda M | Quantitative EEG as an identifier of learning modality |
| CN100573622C (en) * | 2008-05-09 | 2009-12-23 | 杨杰 | Multimedia brainwave feedback children learning and training method and instrument for training |
| US20110015536A1 (en) * | 2009-07-17 | 2011-01-20 | Michael Milgramm | EEG-based method for determining a subject's compatibility with a work environment |
| US20150073294A1 (en) * | 2012-03-30 | 2015-03-12 | Agency for Science, Technology Research | Method for assessing the treatment of attention-deficit/hyperactivity disorder |
| CN102920453A (en) * | 2012-10-29 | 2013-02-13 | 泰好康电子科技（福建）有限公司 | Electroencephalogram signal processing method and device |
| CN203885496U (en) * | 2013-12-24 | 2014-10-22 | 天津师范大学 | Wearing-type electrocerebral attention training instrument |
| CN103656833B (en) * | 2013-12-24 | 2015-12-30 | 天津师范大学 | A kind of Wearable brain electricity attention instrument for training |
| CN103989485A (en) * | 2014-05-07 | 2014-08-20 | 朱晓斐 | Human body fatigue evaluation method based on brain waves |
| CN104182995B (en) * | 2014-08-08 | 2017-02-15 | 吉林大学 | Highway roadside landscape color evaluation method based on driving fatigue |
| CN104644165B (en) * | 2015-02-11 | 2017-05-17 | 电子科技大学 | Wearable electroencephalogram acquisition device |
| CN104700119B (en) * | 2015-03-24 | 2018-02-13 | 北京机械设备研究所 | A kind of EEG signals isolated component extracting method based on convolution blind source separating |
| CN106175799A (en) * | 2015-04-30 | 2016-12-07 | 深圳市前海览岳科技有限公司 | Based on brain wave assessment human body emotion and the method and system of fatigue state |
| CN105139695A (en) * | 2015-09-28 | 2015-12-09 | 南通大学 | EEG collection-based method and system for monitoring classroom teaching process |
| CN106066697A (en) * | 2016-06-13 | 2016-11-02 | 吉林大学 | The control device of a kind of brain control handset dialing and control method |
| CN105943207B (en) * | 2016-06-24 | 2017-12-05 | 吉林大学 | One kind is based on idiodynamic intelligent artificial limb kinematic system and its control method |
| CN106691474A (en) * | 2016-11-25 | 2017-05-24 | 中原电子技术研究所（中国电子科技集团公司第二十七研究所） | Brain electrical signal and physiological signal fused fatigue detection system |
| CN107174262B (en) * | 2017-05-27 | 2021-02-02 | 西南交通大学 | Attention evaluation method and system |
| CN107463792B (en) * | 2017-09-21 | 2023-11-21 | 北京大智商医疗器械有限公司 | Nerve feedback device, system and method |
| CN107657868A (en) * | 2017-10-19 | 2018-02-02 | 重庆邮电大学 | A kind of teaching tracking accessory system based on brain wave |
-
2018
- 2018-05-24 CN CN201810507554.9A patent/CN108888280B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108888280A (en) | 2018-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108888280B (en) | Student class attending attention evaluation method based on electroencephalogram signal analysis | |
| CN107024987B (en) | Real-time human brain attention testing and training system based on EEG | |
| CN108236464B (en) | Feature extraction method based on electroencephalogram signals and detection extraction system thereof | |
| CN106725462B (en) | Acousto-optic Sleep intervention system and method based on EEG signals | |
| CN110765920A (en) | Motor imagery classification method based on convolutional neural network | |
| CA2480798A1 (en) | Fast estimation of weak bio-signals using novel algorithms for generating multiple additional data frames | |
| CN108113660B (en) | Portable multi-biological signal amplifier | |
| CN110262658B (en) | Brain-computer interface character input system based on enhanced attention and implementation method | |
| CN110916652A (en) | Data acquisition device and method for controlling robot movement based on motor imagery through electroencephalogram and application of data acquisition device and method | |
| CN109091141A (en) | A kind of sleep quality monitor and its monitoring method based on brain electricity and eye electricity | |
| CN111616681A (en) | Anesthesia state monitoring system based on portable electroencephalogram acquisition equipment and deep learning | |
| Sulaiman et al. | Offline labview-based EEG signals analysis for human stress monitoring | |
| CN114601476A (en) | EEG signal emotion recognition method based on video stimulation | |
| CN114403896A (en) | Method for removing ocular artifacts in single-channel electroencephalogram signal | |
| CN111012345A (en) | Eye fatigue degree detection system and method | |
| CN113197583A (en) | Electrocardiogram waveform segmentation method based on time-frequency analysis and recurrent neural network | |
| CN106843509B (en) | Brain-computer interface system | |
| CN109002798B (en) | Single-lead visual evoked potential extraction method based on convolutional neural network | |
| Demir et al. | Bio-inspired filter banks for frequency recognition of SSVEP-based brain–computer interfaces | |
| Radhakrishnan et al. | Investigating EEG Signals of Autistic Individuals Using Detrended Fluctuation Analysis. | |
| CN115686208A (en) | Music induced emotion recognition method and system based on EEG | |
| CN115192907A (en) | Real-time biofeedback percutaneous vagus nerve electronic acupuncture device | |
| Bandara et al. | Differentiation of signals generated by eye blinks and mouth clenching in a portable brain computer interface system | |
| CN204745287U (en) | Therapeutical depression evaluation system of hypnotizeing based on rhythm of heart variability | |
| Chowdhury et al. | Stress Detection Through Single Channel Real-Time EEG Signal from Temporal Lobe Using Machine Learning Model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |