CN103584856A - Algorithm for identifying blinking force by processing brain waves - Google Patents
Algorithm for identifying blinking force by processing brain waves Download PDFInfo
- Publication number
- CN103584856A CN103584856A CN201310632391.4A CN201310632391A CN103584856A CN 103584856 A CN103584856 A CN 103584856A CN 201310632391 A CN201310632391 A CN 201310632391A CN 103584856 A CN103584856 A CN 103584856A
- Authority
- CN
- China
- Prior art keywords
- brain wave
- amplitude
- formula
- var
- value
- 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.)
- Granted
Links
Images
Abstract
The invention discloses an algorithm for identifying blinking force by processing brain waves. Within each working period, firstly, the amplitude x of the brain waves is measured, an approximate mean value Y and a mean square value Z are obtained by calculation through the iterative formula of Yn=(1-k)Yn-1+kxn and the iterative formula of Zn=(1-k)Zn-1+kxn<2>, the variance Var(x) is calculated on the basis of the formula Var(x)=E(x<2>)-[E(x)]<2>, and then the amplitude S of the x after standardization is calculated according to the formula of or the formula of . The amplitude S is compared with the set positive threshold value and the set negative threshold value, and whether an event A or an event B happens is judged. If the event A happens, it is considered that the blinking motion happens, at the moment the blinking force is the amplitude obtained when the event A happens. The algorithm for identifying the blinking force by processing the brain waves has the advantages of being capable of identifying rapid and continuous blinks and the blink force, small in calculated amount, good in adaptability and the like.
Description
Technical field
The present invention relates to a kind of by processing the algorithm of brain wave identification dynamics nictation.
Background technology
By observing the original magnitude image of brain wave, we find, for anyone, when his health transfixion, nictation, action all can cause the fluctuation of forehead EEG ripple, and fluctuation size and nictation dynamics be directly proportional.But because everyone brain wave image has nuance, if process brain wave by setting threshold values, this will cause the product designing to lack universality.If but directly average and variance, will cause huge amount of calculation and computer memory.
In prior art, use the TGAM module of NeuroSky company can measure original brain wave data and nictation dynamics, but the response speed of this TGAM Module recognition dynamics nictation is very slow, and None-identified continuous nictation rapidly.
Summary of the invention
The present invention is the weak point existing in above-mentioned prior art for avoiding, provide a kind of operand little and can fast recognition continuously nictation by processing the algorithm of brain wave identification dynamics nictation, with can fast recognition continuously nictation and nictation dynamics.
The present invention be technical solution problem by the following technical solutions.
By processing an algorithm for brain wave identification dynamics nictation, it comprises the steps:
Step 1: using ear-lobe as with reference to ground connection, measure the voltage of forehead, observe the oscillogram of brain wave;
Step 2: set a forward threshold values value and a negative sense threshold values; The amplitude of brain wave is called to event A higher than forward threshold values, the amplitude of brain wave is called to event B lower than negative sense threshold values;
Step 3: within each working cycle of the oscillogram of brain wave, first brain wave amplitude x;
Step 4: carry out iteration by formula (1), obtain the approximation Yn of the average of brain wave amplitude x
Iterative formula (1) is: Y
n=(1-k) Y
n-1+ kx
n(1)
In formula (1), x
nit is the amplitude that n measures brain wave constantly; Y
nwhile being the n time iteration, the approximation of the average of amplitude x; K is constant, and n is natural number; If (k is less, Y
njust approach the approximation of real x average, but adaptive speed is just slower.Conventionally k gets 0.005.）
Step 5: carry out iteration by formula (2), obtain the mean-square value Z of brain wave amplitude x
napproximation;
Iterative formula (2) is: Z
n=(1-k) Z
n-1+ kx
n 2(2)
In formula (2), x
nit is the amplitude that n measures brain wave constantly; Z
nwhile being the n time iteration, the approximation of the mean-square value of amplitude x; K is constant, and n is natural number; If (k is less, Z
njust approach the approximation of real x mean-square value, but adaptive speed is just slower.Conventionally k gets 0.005.）
Step 6: the variance Var(x that asks for the approximation of x by formula (3));
Var（x）=E(x
2)-[E(x)]
2 （3）；
Formula (3), the amplitude that x is brain wave, E (x) is the average of brain wave amplitude, E (x
2) mean-square value of brain wave amplitude, Var(x) be the variance of brain wave amplitude;
Step 7: by formula (4), x is carried out to standardization;
Formula (4), the amplitude that x is brain wave, E (x) is the average of brain wave amplitude, Var(x) is the variance of brain wave amplitude; S is the value after x standardization.
A kind of feature of identifying the algorithm of dynamics nictation by processing brain wave of the present invention is also:
In described step 7, adopt formula (5), x is carried out to standardization;
Wherein, the amplitude that x is brain wave, E (x) is the average of brain wave amplitude, Var(x) is the variance of brain wave amplitude; S is the value after x standardization; Function sgn(x) represent: when x is more than or equal to 0, its value is 1; When x is less than or equal to 0, its value is for-1.
Compared with the prior art, beneficial effect of the present invention is embodied in:
Of the present invention a kind of by processing the algorithm of brain wave identification dynamics nictation, within each working cycle, first brain wave amplitude x, by iterative formula (1) and (2), calculate approximate average Y and mean-square value Z, according to formula (3), calculate variance, then according to the amplitude S of x after formula (4) or formula (5) normalized.And amplitude S is compared with forward threshold values value and the negative sense threshold values of setting, decision event A or B.If what occur be A event, and there is time difference constantly and surpass preset value in two events, thinking action nictation has occurred, and the maximum that rounds S in individual nictation of process is dynamics nictation.
Of the present invention a kind of by processing the algorithm of brain wave identification dynamics nictation, have can fast recognition continuously nictation and nictation dynamics, the advantage such as amount of calculation is smaller, algorithm adaptivity is good.
Accompanying drawing explanation
Fig. 1 is of the present invention a kind of by processing the flow chart of the algorithm of brain wave identification dynamics nictation.
Fig. 2 is the span marked graph of parameter i in Fig. 1.
Fig. 3 is of the present invention a kind of by processing the Matlab analog result figure of the algorithm of brain wave identification dynamics nictation.
Below pass through the specific embodiment, and the invention will be further described by reference to the accompanying drawings.
The specific embodiment
By processing an algorithm for brain wave identification dynamics nictation, it is characterized in that, comprise the steps:
Step 1: using ear-lobe as with reference to ground connection, measure the voltage of forehead, observe the oscillogram of brain wave;
Step 2: set a forward threshold values value and a negative sense threshold values; The amplitude of brain wave is called to event A higher than forward threshold values, the amplitude of brain wave is called to event B lower than negative sense threshold values;
Step 3: within each working cycle of the oscillogram of brain wave, first brain wave amplitude x;
Step 4: carry out iteration by formula (1), obtain the approximation Yn of the average of brain wave amplitude x
Iterative formula (1) is: Y
n=(1-k) Y
n-1+ kx
n(1)
In formula (1), x
nit is the amplitude that n measures brain wave constantly; Y
nwhile being the n time iteration, the approximation of the average of amplitude x; K is constant, and n is natural number; If (k is less, Y
njust approach the approximation of real x average, but adaptive speed is just slower.Conventionally k gets 0.005.）
Step 5: carry out iteration by formula (2), obtain the mean-square value Z of brain wave amplitude x
napproximation;
Iterative formula (2) is: Z
n=(1-k) Z
n-1+ kx
n 2(2)
In formula (2), x
nit is the amplitude that n measures brain wave constantly; Z
nwhile being the n time iteration, the approximation of the mean-square value of amplitude x; K is constant, and n is natural number; If (k is less, Z
njust approach the approximation of real x mean-square value, but adaptive speed is just slower.Conventionally k gets 0.005.）
Step 6: the variance Var(x that asks for the approximation of x by formula (3));
Var（x）=E(x
2)-[E(x)]
2 （3）；
Formula (3), the amplitude that x is brain wave, E (x) is the average of brain wave amplitude, E (x
2) mean-square value of brain wave amplitude, Var(x) be the variance of brain wave amplitude;
Step 7: by formula (4), x is carried out to standardization;
Formula (4), the amplitude that x is brain wave, E (x) is the average of brain wave amplitude, Var(x) is the variance of brain wave amplitude; S is the value after x standardization.
As the flow chart of Fig. 1 specific embodiment that is algorithm of the present invention.During initialization, the value of each parameter is: Y=0; Z=10000; K=0.005; MaxI=100; I=maxI; MaxS=0; Wherein: i is A, B two interval of events number of cycles; As above, maximum wait period constant maxI is 100.Concrete algorithm computational process is participated in Fig. 1.
As Fig. 2, it is the span marked graph of parameter i in Fig. 1.The brain wave waveform of a nictation in Fig. 2 of take is example, and time i can not be long, because if i is long, just do not become continuous process nictation, therefore upper limit maxI need to be set.This method, through test, can well be identified nictation and dynamics thereof in the situation that health is static.But in the process of people's motion, muscle electricity can disturb eeg signal, causes calculated distortion, so also should adopt the algorithm of filtering, realize in the process of motion identification nictation and dynamics thereof.
Try to achieve the variance Var(x of the approximation of x) after, the variance Var(x of the approximation by x), x is carried out to standardization.In prior art, directly calculate average and the variance of n brain wave data, calculate n average constantly and need to have n+1 computing (addition and multiplication) altogether, variance needs 2n+3 computing.Adopted after algorithm of the present invention, computation of mean values and variance are all to need to calculate for 3 times, and this has reduced the amount of calculation of whole computational process greatly, are convenient to by the blink identification of dynamics of brain wave.
Experiment finds, the amplitude of brain wave and nictation dynamics be approximate proportional relationship, so can represent by the amplitude of brain wave dynamics nictation.But due to everyone the waviness amplitude of brain wave and scope neither with, so need the algorithm can self adaptation.And the amount of calculation of this algorithm is necessary little, so that realize in real time, processes.Algorithm of the present invention, operand is little and can fast recognition blink continuously.
The action that found through experiments, can blink is divided into two stages: close one's eyes, open eyes.Using ear-lobe as with reference to ground connection, measure the voltage of forehead, observe the oscillogram of brain wave.Be used as the action time of closing one's eyes, can produce a pulse identical with the image longitudinal axis positive direction of oscillogram, the amplitude peak of pulse with become to be similar to proportional relationship with the dynamics of closing one's eyes.Be used as the action time of opening eyes, can produce a pulse contrary with the image longitudinal axis positive direction of oscillogram, the amplitude peak of pulse with become to be similar to proportional relationship with the eyesight degree of opening eyes.
Set a forward threshold values value and a negative sense threshold values, the amplitude of brain wave is called to event A higher than forward threshold values, the amplitude of brain wave is called to event B lower than negative sense threshold values.After only having A event, event B occurs, and there is difference constantly and be less than preset value in two events, just thinking that occurred nictation moves.If there is A event after A event or B event directly occurs, do not think and having produced action nictation.
Owing to having adopted, brain wave amplitude is carried out to standardized method, so forward threshold values and negative sense threshold values are all constant.Through experimental verification, forward threshold values gets 3, and negative sense threshold values gets-2.
Need explanation a bit, because people is deliberately almost to close one's eyes firmly when nictation entirely, open eyes and do not exert oneself, thus dynamics that should be when closing one's eyes, as dynamics nictation.
In described step 7, adopt formula (5), x is carried out to standardization;
Wherein, the amplitude that x is brain wave, E (x) is the average of brain wave amplitude, Var(x) is the variance of brain wave amplitude; S is the value after x standardization; Function sgn(x) represent: when x is more than or equal to 0, its value is 1; When x is less than or equal to 0, its value is for-1.
In formula (4), need to open radical sign.And very large owing to opening this amount of calculation of radical sign, if be not while using this algorithm on good equipment in computing capability, be easy to affect computational speed.And adopt formula (5), and do not open the process that radical sign calculates, computational speed is than very fast.Can greatly reduce amount of calculation like this.When being that amplitude compares, only need be by S
2with square comparing of amplitude x.Due to what compare, be the square value of amplitude, when comparing numerical values recited, it is also to be noted that amplitude need to retain original sign simultaneously.
By matlab, algorithm is simulated.Following Fig. 3 of result (eeg signal all gathers by TGAM module) of simulation, value k gets 0.00015 here.Black zone in figure represents brain wave figure, and the some representative of brain wave figure middle white is carved at this moment and recognized action nictation.Corresponding straight line and the other numeral of straight line of point of white, is illustrated in dynamics nictation that this measures constantly.
The computational process of the algorithm in each working cycle is as follows: within each working cycle, first brain wave amplitude x, by iterative formula (1) and (2), calculate approximate average Y and mean-square value Z, according to formula (3), calculate variance, then according to the amplitude S of x after formula (4) or formula (5) normalized.And S is compared with forward threshold values value and the negative sense threshold values of setting, decision event A or B.
By S, judge event A or B have occurred, if there is the B time, while seeing last generation event, occur what, if what occur is A event, and there is difference constantly and be less than preset value in two events, thinking action nictation has occurred, the maximum that rounds S in process nictation is dynamics nictation.
Algorithm of the present invention, by measuring forehead EEG ripple, identifies the algorithm of dynamics nictation.This algorithm entered test, had adaptivity, and algorithm is simple, was convenient to realize.Dynamics nictation obtaining through algorithm process, has enough precision.
Of the present invention by processing the algorithm of brain wave identification dynamics nictation, comprise the standardized method of digitized brain wave amplitude data and data after cleanup standard how, provide that a kind of real-time operand is little, fast operation can identify continuously nictation and nictation dynamics algorithm, can distinguish intentional nictation and unconscious nictation.
Algorithm of the present invention, through test, can well be identified nictation and dynamics thereof in the situation that health is static.
Claims (2)
1. by processing an algorithm for brain wave identification dynamics nictation, it is characterized in that, comprise the steps:
Step 1: using ear-lobe as with reference to ground connection, measure the voltage of forehead, observe the oscillogram of brain wave;
Step 2: set a forward threshold values value and a negative sense threshold values; The amplitude of brain wave is called to event A higher than forward threshold values, the amplitude of brain wave is called to event B lower than negative sense threshold values;
Step 3: within each working cycle of the oscillogram of brain wave, first brain wave amplitude x;
Step 4: carry out iteration by formula (1), obtain the approximation Yn of the average of brain wave amplitude x
Iterative formula (1) is: Y
n=(1-k) Y
n-1+ kx
n(1)
In formula (1), x
nit is the amplitude that n measures brain wave constantly; Y
nwhile being the n time iteration, the approximation of the average of amplitude x; K is constant, and n is natural number; If (k is less, and Yn just approaches the approximation of real x average, but adaptive speed is just slower.Conventionally k gets 0.005.）
Step 5: carry out iteration by formula (2), obtain the mean-square value Z of brain wave amplitude x
napproximation;
Iterative formula (2) is: Z
n=(1-k) Z
n-1+ kx
n 2(2)
In formula (2), x
nit is the amplitude that n measures brain wave constantly; Z
nwhile being the n time iteration, the approximation of the mean-square value of amplitude x; K is constant, and n is natural number.
Step 6: the variance Var(x that asks for the approximation of x by formula (3));
Var（x）=E(x
2)-[E(x)]
2 （3）；
Formula (3), the amplitude that x is brain wave, E (x) is the average of brain wave amplitude, E (x
2) mean-square value of brain wave amplitude, Var(x) be the variance of brain wave amplitude;
Step 7: by formula (4), x is carried out to standardization;
Formula (4), the amplitude that x is brain wave, E (x) is the average of brain wave amplitude, Var(x) is the variance of brain wave amplitude; S is the value after x standardization.
2. a kind of algorithm of identifying dynamics nictation by processing brain wave according to claim 1, is characterized in that, in described step 7, adopts formula (5), and x is carried out to standardization;
Wherein, the amplitude that x is brain wave, E (x) is the average of brain wave amplitude, Var(x) is the variance of brain wave amplitude; S is the value after x standardization; Function sgn(x) represent: when x is more than or equal to 0, its value is 1; When x is less than or equal to 0, its value is for-1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310632391.4A CN103584856B (en) | 2013-11-29 | 2013-11-29 | A kind of method by process brain wave identification dynamics nictation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310632391.4A CN103584856B (en) | 2013-11-29 | 2013-11-29 | A kind of method by process brain wave identification dynamics nictation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103584856A true CN103584856A (en) | 2014-02-19 |
| CN103584856B CN103584856B (en) | 2015-09-30 |
Family
ID=50075334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310632391.4A Active CN103584856B (en) | 2013-11-29 | 2013-11-29 | A kind of method by process brain wave identification dynamics nictation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103584856B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105011951A (en) * | 2014-04-24 | 2015-11-04 | 闽南师范大学 | Device for extracting eye blinking times by brain waves and method |
| CN105988569A (en) * | 2015-02-13 | 2016-10-05 | 北京智谷睿拓技术服务有限公司 | Method and device for determining control information |
| CN107440714A (en) * | 2017-09-07 | 2017-12-08 | 哈尔滨理工大学 | A kind of focus and blink action extraction element and method |
| CN107582051A (en) * | 2017-10-12 | 2018-01-16 | 公安部南昌警犬基地 | A kind of animal mood brain electricity analytical equipment |
| CN107714038A (en) * | 2017-10-12 | 2018-02-23 | 北京翼石科技有限公司 | The feature extracting method and device of a kind of EEG signals |
| CN108245154A (en) * | 2018-01-24 | 2018-07-06 | 福州大学 | The method that blink section in brain electricity or eye electricity is accurately determined using rejecting outliers |
| CN113080971A (en) * | 2021-04-12 | 2021-07-09 | 北京交通大学 | Method and system for judging fatigue state by detecting blink signals |
| CN114288520A (en) * | 2021-12-31 | 2022-04-08 | 广州酷狗计算机科技有限公司 | Sleep assisting method, device, equipment and storage medium based on brain waves |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5649061A (en) * | 1995-05-11 | 1997-07-15 | The United States Of America As Represented By The Secretary Of The Army | Device and method for estimating a mental decision |
| JPH10155759A (en) * | 1996-11-28 | 1998-06-16 | Kanazawa Kogyo Univ | Magnetism measuring apparatus and cryogenic container |
| JP2011133548A (en) * | 2009-12-22 | 2011-07-07 | Toyota Motor Corp | Visual field-specifying device and display position-adjusting device |
| CN102133099A (en) * | 2011-01-27 | 2011-07-27 | 中国医学科学院生物医学工程研究所 | Device and method for estimating discomfort in watching 3D images by bioelectricity |
| WO2011105000A1 (en) * | 2010-02-25 | 2011-09-01 | パナソニック株式会社 | Brain wave interface system, brain wave interface provision device, execution method of brain wave interface, and program |
-
2013
- 2013-11-29 CN CN201310632391.4A patent/CN103584856B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5649061A (en) * | 1995-05-11 | 1997-07-15 | The United States Of America As Represented By The Secretary Of The Army | Device and method for estimating a mental decision |
| JPH10155759A (en) * | 1996-11-28 | 1998-06-16 | Kanazawa Kogyo Univ | Magnetism measuring apparatus and cryogenic container |
| JP2011133548A (en) * | 2009-12-22 | 2011-07-07 | Toyota Motor Corp | Visual field-specifying device and display position-adjusting device |
| WO2011105000A1 (en) * | 2010-02-25 | 2011-09-01 | パナソニック株式会社 | Brain wave interface system, brain wave interface provision device, execution method of brain wave interface, and program |
| CN102133099A (en) * | 2011-01-27 | 2011-07-27 | 中国医学科学院生物医学工程研究所 | Device and method for estimating discomfort in watching 3D images by bioelectricity |
Non-Patent Citations (1)
| Title |
|---|
| 范郑丽: "《眨眼条件反射过程中PFC事件相关电位变化即860MHz电磁辐射对其影响》", 《第三军医大学硕士学位论文》, 31 December 2010 (2010-12-31), pages 29 - 50 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105011951A (en) * | 2014-04-24 | 2015-11-04 | 闽南师范大学 | Device for extracting eye blinking times by brain waves and method |
| CN105988569A (en) * | 2015-02-13 | 2016-10-05 | 北京智谷睿拓技术服务有限公司 | Method and device for determining control information |
| CN107440714A (en) * | 2017-09-07 | 2017-12-08 | 哈尔滨理工大学 | A kind of focus and blink action extraction element and method |
| CN107582051A (en) * | 2017-10-12 | 2018-01-16 | 公安部南昌警犬基地 | A kind of animal mood brain electricity analytical equipment |
| CN107714038A (en) * | 2017-10-12 | 2018-02-23 | 北京翼石科技有限公司 | The feature extracting method and device of a kind of EEG signals |
| CN108245154A (en) * | 2018-01-24 | 2018-07-06 | 福州大学 | The method that blink section in brain electricity or eye electricity is accurately determined using rejecting outliers |
| CN108245154B (en) * | 2018-01-24 | 2020-10-09 | 福州大学 | Method for accurately determining blink interval in electroencephalogram or electrooculogram by using abnormal value detection |
| CN113080971A (en) * | 2021-04-12 | 2021-07-09 | 北京交通大学 | Method and system for judging fatigue state by detecting blink signals |
| CN114288520A (en) * | 2021-12-31 | 2022-04-08 | 广州酷狗计算机科技有限公司 | Sleep assisting method, device, equipment and storage medium based on brain waves |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103584856B (en) | 2015-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103584856A (en) | Algorithm for identifying blinking force by processing brain waves | |
| WO2022012364A1 (en) | Electromyographic signal processing method and apparatus, and exoskeleton robot control method and apparatus | |
| CN110974212A (en) | Electrocardio and myoelectric characteristic fused rehabilitation training motion state monitoring method and system | |
| Pancholi et al. | Advanced energy kernel-based feature extraction scheme for improved EMG-PR-based prosthesis control against force variation | |
| Anderson et al. | Nonlinear dynamic modeling of isometric force production in primate eye muscle | |
| CN103955270A (en) | Character high-speed input method of brain-computer interface system based on P300 | |
| CN111207875A (en) | Electromyographic signal-torque matching method based on multi-granularity parallel CNN model | |
| CN106127191A (en) | Brain electricity sorting technique based on WAVELET PACKET DECOMPOSITION and logistic regression | |
| Zou et al. | A multimodal fusion model for estimating human hand force: Comparing surface electromyography and ultrasound signals | |
| Veer | Experimental study and characterization of SEMG signals for upper limbs | |
| CN106901732A (en) | The measuring method and measurement apparatus of muscular strength and Muscle tensility under mutation status | |
| Hasan et al. | Human hand gesture detection based on EMG signal using ANN | |
| Abbasi-Asl et al. | Estimation of muscle force with emg signals using hammerstein-wiener model | |
| CN116473556A (en) | Emotion calculation method and system based on multi-site skin physiological response | |
| Hayashi et al. | Acquisition of logicality in living neuronal networks and its operation to fuzzy bio-robot system | |
| Krell et al. | Memory and processing efficient formula for moving variance calculation in EEG and EMG signal processing | |
| CN112370039A (en) | Classroom quality detection method and device based on intelligent classroom | |
| CN103197668B (en) | Data drive type control performance detection device and method | |
| Tahtirvanci et al. | Classification of EEG signals using spiking neural networks | |
| Alias et al. | Parallel artificial neural network approaches for detecting the behaviour of eye movement using cuda software on heterogeneous cpu-gpu systems | |
| CN106709467A (en) | Real-time spike potential detection and classification method suitable for hardware realization | |
| CN106580320A (en) | EEG signal feature analysis method and system based on visual inducement | |
| Xue et al. | SEMG based intention identification of complex hand motion using nonlinear time series analysis | |
| CN113143275A (en) | Electroencephalogram fatigue detection method for quantitative evaluation of sample and characteristic quality in combined manner | |
| Fang et al. | Research on gesture recognition based on sEMG and inertial sensor fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |