CN103989485A - Human body fatigue evaluation method based on brain waves - Google Patents
Human body fatigue evaluation method based on brain waves Download PDFInfo
- Publication number
- CN103989485A CN103989485A CN201410190155.6A CN201410190155A CN103989485A CN 103989485 A CN103989485 A CN 103989485A CN 201410190155 A CN201410190155 A CN 201410190155A CN 103989485 A CN103989485 A CN 103989485A
- Authority
- CN
- China
- Prior art keywords
- ripple
- waves
- brain wave
- brain
- complexity
- 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
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a human body fatigue evaluation method based on brain waves. According to the method, a ThinkGearAM electroencephalogram chip is used for acquiring original brain wave signals, an built-in algorithm is used for analyzing and processing the original brain wave signals, and four kinds of parameters are given through calculation according to processed brain wave data; the four kinds of parameters include variable coefficients of five brain wave signals of original delta waves, original theta waves, original alpha waves, original beta waves and original gamma waves, two nonlinear parameters of complexity and power spectral entropy, a fatigue index F worked out through energy of four basic rhythms of the delta waves, the theta waves, the alpha waves and the beta waves in the brain waves, and two parameters of relaxation degree and attention degree extracted through the brain wave signals, and the four kinds of parameters serve as input of a probabilistic neural network (PPN), the output of the PNN serves as a human body fatigue evaluation basis, and therefore the human body fatigue can be judged according to the brain waves of people.
Description
Technical field
The present invention relates to health engineering, neuro physiology, biomedicine, Digital Signal Processing, pattern extraction and pattern classification, soft project, particularly a kind of human-body fatigue degree evaluation methodology based on brain wave.
Background technology
Fatigue refers to that body is under certain environment condition, the state that the labor efficiency trend causing due to long-time or overwrought muscle power or mental work declines.Medically, by tired character, fatigue can be divided into physiological fatigue and psychological fatigue, to the evaluation of fatigue state, can be undertaken by the method for subjectivity and objectivity.The subjectss' that test and assess such as the method Main Basis subjective survey table of subjective evaluation and test, self-log, sleep habit application form and Stamford sleep yardstick table degree of fatigue.The method of objective evaluation is mainly from medical angle, borrows the aid test subjectss' such as medical apparatus, equipment human body behavior, physiology, the variation of some index of biochemical aspect, thereby determines its degree of fatigue.
Although subjective evaluation method is simple to operate, direct, expense is cheap, in addition to task complete noiseless, easily the advantage such as be accepted, it is a kind of method of the evaluation fatigue widely being adopted, but this method is difficult to quantize tired grade and degree, understanding because of everyone has obvious difference again, and its result often can not be satisfactory.In recent years, the detections such as electroencephalogram, electro-oculogram, electrocardiogram and analytical technology have been made significant headway, and in mental fatigue research, brain electricity has now become one of index of evaluating the most widely central nervous system's variation, is described as and detects tired " goldstandard ".
At present, utilize brain electricity to carry out fatigue strength research at home and abroad and obtained some significant achievements.As aspect nonlinear kinetics, the people such as Wu Xiangbao are the analysis for brain electric fatigue by Lempel-Ziv complexity, the Sample Entropy complexity that the people such as the people such as Pincus have proposed approximate entropy complexity and have been applied in fatigue detecting research, Richman propose has also had application more widely in fatigue detecting.Aspect power spectrumanalysis, Murata etc. utilize the amplitude of event related potential P300 and preclinical length to analyze mental fatigue, find the increase along with mental fatigue degree, prolongation of latency, and amplitude reduces; Jung etc. analyze brain Vigilance level by EEG power spectrum, find that EEG power spectrum can reflect the fatigue conditions of brain.
Although brain wave has been used to tired detection, this metering system part that still comes with some shortcomings:
The first, measure tired degree of accuracy not high, not strong to individual specific aim, often there will be false positive phenomenon;
The second, to the degree of fatigue of human body, can not judge accurately, the error rate of judgement is excessive.
Summary of the invention
In order to overcome above-mentioned the deficiencies in the prior art, the invention provides a kind of human-body fatigue degree evaluation methodology based on brain wave.The method has solved in traditional method not strong to individual specific aim, and False Rate is excessive, the problem that grade decision errors is excessive.
The technical solution adopted in the present invention is: by adopting the multiple tired method of measuring, and the input using brain electrical feature parameter as PNN neutral net (probabilistic neural network), and by the output of PNN neutral net, judge current tester's degree of fatigue.PNN neutral net is a kind of neutral net that is usually used in pattern classification, and it need to carry out with BP algorithm the calculating of back-propagation unlike traditional Multilayer Feedforward Neural Networks, but the computational process of complete forward direction.Short, the difficult local optimum that produces of its training time, and its classification accuracy rate is higher, as long as no matter classification problem how complicated has abundant training data, can guarantee to obtain the optimal solution under bayesian criterion, compared with prior art, the present invention has improved the degree of accuracy that fatigue strength is evaluated to a certain extent, and versatility strengthens, the error rate that grade is judged diminishes, and evaluation result has accuracy, credibility.
Accompanying drawing explanation
Fig. 1 is system framework figure, and Fig. 2 is test result figure.
The specific embodiment
1. by dry-type electrode, contact brain forehead and gather EEG signals, the initial data obtaining can be passed in ThinkGear AM brain electrical chip in real time, and processed by the algorithm that chip itself is built-in, obtain digitized original brain wave data, comprise δ, θ, slow α, fast α, slow β, fast β, slow γ, 8 EEG parameters of middle γ ripple, and " focus ", " allowance " two eSense parameters, brain electrical chip sends in one's hands machine with the form of packet by bluetooth by the data after processing, and by corresponding software by data parsing out, deposit in Microsoft Excel.
2. by brain wave initial data, calculate following four class signals,
(1) complexity based on α ripple, two kinds of nonlinear parameters of Power Spectral Entropy;
(2) energy spectrum by calculating δ ripple, θ ripple, α ripple and 4 basilic rhythms of β ripple in brain wave is to obtain fatigue exponent F;
(3) according to the value of the resulting allowance of brain electrical chip built-in algorithms and focus all at 1-100, record multi-group data and ask its meansigma methods;
(4) by brain electrical chip, obtained δ ripple, θ ripple, α ripple, β ripple, the γ ripple of original EEG signals, obtain the coefficient of variation of 5 kinds of ripples in Measuring Time.
3. utilize the neutral net instrument of MATLAB to carry out the training of network,
(1) above-mentioned four kinds of characteristic parameters are made to normalized, we incite somebody to action wherein 50 groups of data and, as training sample, remain 30 groups of data as test sample book;
(2) by fatigue level of human body people for being divided into 5 grades, and replaced by 1 ~ 5 these five numerical value, corresponding relation as shown in Table 1:
(3) produce after training set and test set, the threshold value of each node of hidden layer obtaining through training and with the weights that are connected of input layer, and be connected weights between hidden layer and output layer;
(4) utilize test group to test to the network of setting up, obtain result as shown in accompanying drawing one.Have 30 groups of test datas, according to test result, find to only have the 4th, 8,12,17,23 groups, this test result of 5 groups and expected results are different, and result and the expected results of all the other 25 groups of data fit like a glove, and the accuracy of prediction is 83.3%;
(5) conclusion: according to the result of above test, can prove that this human-body fatigue degree evaluation methodology based on brain wave is truly feasible, but because the sample number of this test is less, make to a certain extent the undertrained comprehensive of neutral net, cause result can have certain error, if increase the sample of training, the error of this evaluation methodology will further reduce.
The tired grade classification of table 1
Degree of fatigue | Not tired | Slight tired | Moderate is tired | Severe is tired | Extremely tired |
Represent numerical value | 1 | 2 | 3 | 4 | 5 |
Claims (3)
1. the human-body fatigue degree evaluation methodology based on brain wave, the realization of the method comprises the following steps successively:
The first step, utilize ThinkGear AM brain wave chip to obtain training sample, and therefrom extract brain wave characteristic parameter, pre-input parameter using it as neutral net, the subjective survey table of filling according to measurand obtains evaluation result simultaneously, as the output of neutral net, and the sample collecting is divided into training group and test group;
Second step, the characteristic parameter extracting is made to normalized, direct input as neutral net, and corresponding fatigue strength evaluation result regulation is replaced by 1 ~ 5 these five numerical value, as the direct output of network, utilize set according to training, according to the difference of reality output and desired output, constantly adjust each node and connect weights and threshold value, tentatively complete the foundation of network;
Can the 3rd step, utilizes the data of test group to test the network of setting up, check this network get a desired effect, and thus network is carried out to repetition training, improves constantly the correctness of its evaluation, finally completes the foundation of network,
It is characterized in that, the brain wave characteristic parameter extracting in the first step is divided into four classes:
The first kind, the coefficient of variation of original δ ripple, θ ripple, α ripple, β ripple, 5 kinds of eeg signals of γ ripple,
δ ripple is after adult falls asleep, or adult occurs when sleepy, θ ripple, occurs when teenager or adult are sleepy, α ripple is clear-headed people, quiet, close one's eyes and euglycemia scope situation under occur, β ripple is opened eyes and (brain wave there will be when normal person works by day) appears while being in nervous active state in cerebral cortex people, γ ripple occurs when people enters S sleep, the coefficient of variation is to weigh a statistic of each observation degree of variation in data, when carrying out the comparison of two or more data degrees of variation, if the linear module of data is identical with average, can directly utilize standard deviation to carry out comparison, when if the unit of data and (or) average are different, relatively its degree of variation just can not adopt standard deviation, and need to adopt the ratio of standard deviation and average to carry out comparison, the ratio of standard deviation and average is called the coefficient of variation, therefore utilize the coefficient of variation, observe the degree of variation of each EEG signals, its computing formula is:
The coefficient of variation=(standard deviation/meansigma methods) * 100% (1)
Equations of The Second Kind, complexity based on α ripple, two kinds of nonlinear parameters of Power Spectral Entropy, complexity is with the growth of its length, to occur the speed of new model from the angle reflection data sequence of one dimension, reflected data complexity structurally, include a lot of information, the complexity of regular motion (stable state and periodic movement) equals 0, random motion (desirable white noise) is 1, mixed noisy regular motion, the complexity of coloured noise and chaos is between 0 and 1, according to Lempel-Ziv complexity calculating method, first will be by data sequence symbolization, symbol sebolic addressing complexity computational process is as follows:
Making c (n) is a certain given symbol sebolic addressing S=(s
1, s
2..., s
n) complexity, s wherein
irepresent a character, make respectively S, Q represents two character strings, SQ represents by S, total character string that two character strings of Q form, SQP represents the character string that last character of SQ is deleted, wherein, P represents to delete the operation of last character, make the set of all different word strings of V (SQP) expression SQP, c (n), S, Q is initialized as c (n)=1, S=s
1, Q=s
2, can obtain SPQ=s
1, suppose S=s
1, s
2..., s
r, Q=s
r+1if Q ∈ V (SQP), represents s
r+1s=s
1, s
2..., s
ra substring, S is constant, only Q need be updated to Q=s
r+1s
r+2, and then judge whether Q belongs to V (SQP), and said process loops, until Q V (SQP) supposes now Q=s
r+1, s
r+2..., s
r+i, i.e. s
r+1, s
r+2..., s
r+inot s
1, s
2..., s
r+i-1substring, so the value of c (n) will increase by 1, then Q will be combined in S, make S be updated to s
1, s
2..., s
r, s
r+1, s
r+2..., s
r+i, getting Q is s
r+i+1, repeat above step, until Q gets last position, so just S=(s
1, s
2..., s
n) be divided into the individual different substring of c (n), and according to research, disassembly in the binary system represented sequence corresponding to x interval to nearly all belonging to [0,1] all can tend to a definite value
Lim
n->∞c(n)=b(n)=n/log
2 n (2)
Wherein b (n) is the asymptotic behavior of random sequence, can make c (n) normalization with it, is called " normalization complexity ",
C
LZN(n)=c(n)/b(n) (3)
Power Spectral Entropy is a kind of index of brain electricity complexity analyzing, angular surveying seasonal effect in time series complexity from frequency-domain analysis and nonlinear dynamic analysis, its spectrum entropy rule shows as has the obvious vibration rhythm and pace of moving things in signal, be that signal waveform is regular, when signal waveform is comparatively during rule, the spectrum peak existing in brain wave power spectrum is narrower, and spectrum entropy is less; Otherwise when signal waveform is irregular stochastic signal, power spectrum is more smooth, spectrum entropy is larger, and by the sampled data of α ripple, according to FFT, conversion can obtain power spectral density P (x), suppose that seasonal effect in time series discrete Fourier transform is X (x), its power spectral density is
P(x)= |X(x)|
2 /N (4)
Power spectrum P (x) is normalized to the probability density function P of available power spectrum according to the power of total spectrum by ψ
w. define corresponding power spectrum comentropy, be called for short Power Spectral Entropy,
H
w=-∑P
wlog(P
w) (5)
The 3rd class, the fatigue exponent F that the energy meter of δ ripple, θ ripple, α ripple and 4 basilic rhythms of β ripple is calculated in brain wave,
F=(E
δ+E
θ)/(E
α+E
β) (6)
Wherein δ ripple, θ ripple, α ripple, four signal waves of β ripple are stochastic signal, and by Parseval theorem, energy spectral density area under a curve equals the area under signal amplitude square, and total energy is:
∫
-∞ ∞|f(t)|
2dt= ∫
-∞ ∞|ψ(w)|
2dw (7)
For discrete-time series, Parseval theorem is still set up, and utilizes the discrete-time series data that measure in time domain, and energy can calculate by quadratic sum;
The 4th class, the meansigma methods of the allowance extracting by means of eeg signal and two parameters of focus, focus and allowance are the comprehensive embodiments of various brain waves, wherein focus can be thought the repressed degree of eegαwave simply, allowance is α ripple, outward manifestation when particularly intermediate frequency α ripple enlivens, focus can reflect the intensity of human body attention; Allowance mainly reflects the mental status of human body, and they are concentrated expressions of the various different brainwave activities of brain, and both values all can directly be obtained by brain electrical chip built-in algorithms.
2. the human-body fatigue degree evaluation methodology based on brain wave according to claim 1, is characterized in that having adopted PNN neutral net to pass judgment on degree of fatigue.
3. the human-body fatigue evaluation methodology based on brain wave according to claim 1, it is characterized in that having adopted human body under various fatigue states, using after every brain wave characteristic parameter normalized as input, and after fatigue strength is classified, by a numerical value, replaced as output, PNN neutral net being trained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410190155.6A CN103989485A (en) | 2014-05-07 | 2014-05-07 | Human body fatigue evaluation method based on brain waves |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410190155.6A CN103989485A (en) | 2014-05-07 | 2014-05-07 | Human body fatigue evaluation method based on brain waves |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103989485A true CN103989485A (en) | 2014-08-20 |
Family
ID=51304006
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410190155.6A Pending CN103989485A (en) | 2014-05-07 | 2014-05-07 | Human body fatigue evaluation method based on brain waves |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103989485A (en) |
Cited By (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104305964A (en) * | 2014-11-11 | 2015-01-28 | 东南大学 | Head mounted fatigue detector and method |
CN104503588A (en) * | 2014-12-31 | 2015-04-08 | 北京奇艺世纪科技有限公司 | Terminal control method and device |
CN104605866A (en) * | 2015-01-21 | 2015-05-13 | 中煤科工集团西安研究院有限公司 | Miner physiological and psychological fatigue monitoring method based on electroencephalogram detection |
CN104814735A (en) * | 2015-05-22 | 2015-08-05 | 京东方科技集团股份有限公司 | Method and device for judging whether brain is tired |
CN105266801A (en) * | 2015-09-10 | 2016-01-27 | 太原理工大学 | J wave detection and classification method based on probabilistic neural network (PNN) |
CN105467807A (en) * | 2015-11-19 | 2016-04-06 | 西安交通大学 | Holographic-display-oriented multichannel man-machine interaction work efficiency evaluation system and evaluation method |
CN105701973A (en) * | 2016-04-26 | 2016-06-22 | 成都远控科技有限公司 | Fatigue detection and early warning method based on brain wave acquisition and system thereof |
CN105809156A (en) * | 2016-05-17 | 2016-07-27 | 中山衡思健康科技有限公司 | Meditation detecting system for calculating meditation scores based on electroencephalograms |
CN105929966A (en) * | 2016-05-18 | 2016-09-07 | 王之腾 | Peripheral device brain wave control method capable of learning adaptively |
CN105975942A (en) * | 2016-05-17 | 2016-09-28 | 中山衡思健康科技有限公司 | Meditation detection method for calculating meditation score by concept density based on EEG |
CN106377251A (en) * | 2016-09-21 | 2017-02-08 | 广州视源电子科技股份有限公司 | Sleep state identification model training method and sleep state identification model training system based on electroencephalogram |
CN106504475A (en) * | 2016-10-15 | 2017-03-15 | 北海益生源农贸有限责任公司 | Method for detecting fatigue driving based on EEG signals |
CN106618560A (en) * | 2016-12-23 | 2017-05-10 | 北京怡和嘉业医疗科技股份有限公司 | Method and device for processing brain wave signals |
CN106923824A (en) * | 2017-03-27 | 2017-07-07 | 广州视源电子科技股份有限公司 | Brain electricity allowance recognition methods and device based on many spatial signal properties |
CN106943150A (en) * | 2017-03-22 | 2017-07-14 | 新乡医学院 | Mental fatigue detecting system and its method for use |
CN108241431A (en) * | 2016-12-26 | 2018-07-03 | 中国移动通信有限公司研究院 | A kind of task adjusting method and device |
CN108324272A (en) * | 2018-03-13 | 2018-07-27 | 天津大学 | A kind of device for checking and examining anxiety degree based on LZC complexities |
CN108388340A (en) * | 2018-02-11 | 2018-08-10 | 广东欧珀移动通信有限公司 | Control method of electronic device and Related product |
CN108836320A (en) * | 2018-04-02 | 2018-11-20 | 东北电力大学 | A method of organoleptic substances classification is carried out based on smell brain wave |
CN108888280A (en) * | 2018-05-24 | 2018-11-27 | 吉林大学 | Student based on electroencephalogramsignal signal analyzing listens to the teacher attention evaluation method |
CN108903936A (en) * | 2018-07-03 | 2018-11-30 | 西安科技大学 | The Intelligent mining helmet control method merged based on human body information and environmental information |
CN109620263A (en) * | 2018-12-13 | 2019-04-16 | 湖南仪峰安安网络科技股份有限公司 | A kind of enterprises and institutions are on duty personnel's sign safety analytical method |
CN109843158A (en) * | 2016-07-13 | 2019-06-04 | 悦享趋势科技(北京)有限责任公司 | Judge the whether effective method and device of pulse wave |
CN109993180A (en) * | 2017-12-29 | 2019-07-09 | 新华网股份有限公司 | Human biological electricity data processing method and device, storage medium and processor |
CN110123314A (en) * | 2019-04-24 | 2019-08-16 | 华南理工大学 | Judge that brain is absorbed in the method for relaxation state based on EEG signals |
CN110164091A (en) * | 2019-06-13 | 2019-08-23 | 华东师范大学 | A kind of fatigue driving monitoring device based on brain wave |
CN110267585A (en) * | 2016-12-08 | 2019-09-20 | 皇家飞利浦有限公司 | Determine the corrected timing that the stimulation of object is supplied to during sleep |
CN111528839A (en) * | 2020-05-29 | 2020-08-14 | 北京京东方健康科技有限公司 | Sleep detection method and device, sleep aid equipment and method |
CN112329802A (en) * | 2019-08-01 | 2021-02-05 | 实践大学 | AI grouping integration system for gas quality meter and special attention and relaxation measurement |
CN112353391A (en) * | 2020-10-22 | 2021-02-12 | 武汉理工大学 | Electroencephalogram signal-based method and device for recognizing sound quality in automobile |
CN112888366A (en) * | 2018-10-15 | 2021-06-01 | 田边三菱制药株式会社 | Electroencephalogram analysis device, electroencephalogram analysis system, and electroencephalogram analysis program |
CN112911136A (en) * | 2021-01-11 | 2021-06-04 | 深圳市宏智力科技有限公司 | Video recording control method based on brain waves |
CN113261974A (en) * | 2021-06-07 | 2021-08-17 | 吉林大学 | Sports fatigue monitoring method based on multiple physiological signals |
CN113679386A (en) * | 2021-08-13 | 2021-11-23 | 北京脑陆科技有限公司 | Method, device, terminal and medium for recognizing attention |
CN114041796A (en) * | 2022-01-13 | 2022-02-15 | 深圳市心流科技有限公司 | Concentration assessment method and device based on brain wave signal and storage medium |
CN114224359A (en) * | 2021-12-18 | 2022-03-25 | 西南交通大学 | Electroencephalogram fatigue index determination method for high-speed rail dispatcher |
CN114569075A (en) * | 2022-02-28 | 2022-06-03 | 浙江柔灵科技有限公司 | Energy judgment-based real-time falling asleep point detection method and system and sleep-assisting device |
CN115067945A (en) * | 2022-08-22 | 2022-09-20 | 深圳市海清视讯科技有限公司 | Fatigue detection method, device, equipment and storage medium |
-
2014
- 2014-05-07 CN CN201410190155.6A patent/CN103989485A/en active Pending
Cited By (49)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104305964A (en) * | 2014-11-11 | 2015-01-28 | 东南大学 | Head mounted fatigue detector and method |
CN104503588A (en) * | 2014-12-31 | 2015-04-08 | 北京奇艺世纪科技有限公司 | Terminal control method and device |
CN104605866A (en) * | 2015-01-21 | 2015-05-13 | 中煤科工集团西安研究院有限公司 | Miner physiological and psychological fatigue monitoring method based on electroencephalogram detection |
CN104814735A (en) * | 2015-05-22 | 2015-08-05 | 京东方科技集团股份有限公司 | Method and device for judging whether brain is tired |
US10772526B2 (en) | 2015-05-22 | 2020-09-15 | Boe Technology Group Co., Ltd. | Apparatus and method for determining whether the brain is fatigued |
CN105266801A (en) * | 2015-09-10 | 2016-01-27 | 太原理工大学 | J wave detection and classification method based on probabilistic neural network (PNN) |
CN105467807A (en) * | 2015-11-19 | 2016-04-06 | 西安交通大学 | Holographic-display-oriented multichannel man-machine interaction work efficiency evaluation system and evaluation method |
CN105467807B (en) * | 2015-11-19 | 2018-10-30 | 西安交通大学 | Multimodal human-computer interaction work efficiency evaluation system towards hologram display and assessment method |
CN105701973A (en) * | 2016-04-26 | 2016-06-22 | 成都远控科技有限公司 | Fatigue detection and early warning method based on brain wave acquisition and system thereof |
CN105809156A (en) * | 2016-05-17 | 2016-07-27 | 中山衡思健康科技有限公司 | Meditation detecting system for calculating meditation scores based on electroencephalograms |
CN105975942A (en) * | 2016-05-17 | 2016-09-28 | 中山衡思健康科技有限公司 | Meditation detection method for calculating meditation score by concept density based on EEG |
CN105929966A (en) * | 2016-05-18 | 2016-09-07 | 王之腾 | Peripheral device brain wave control method capable of learning adaptively |
CN109843158A (en) * | 2016-07-13 | 2019-06-04 | 悦享趋势科技(北京)有限责任公司 | Judge the whether effective method and device of pulse wave |
CN106377251A (en) * | 2016-09-21 | 2017-02-08 | 广州视源电子科技股份有限公司 | Sleep state identification model training method and sleep state identification model training system based on electroencephalogram |
CN106504475A (en) * | 2016-10-15 | 2017-03-15 | 北海益生源农贸有限责任公司 | Method for detecting fatigue driving based on EEG signals |
CN106504475B (en) * | 2016-10-15 | 2019-05-10 | 北海益生源农贸有限责任公司 | Method for detecting fatigue driving based on EEG signals |
CN110267585B (en) * | 2016-12-08 | 2022-05-31 | 皇家飞利浦有限公司 | Determining corrected timing of stimulation provided to a subject during sleep |
CN110267585A (en) * | 2016-12-08 | 2019-09-20 | 皇家飞利浦有限公司 | Determine the corrected timing that the stimulation of object is supplied to during sleep |
CN106618560A (en) * | 2016-12-23 | 2017-05-10 | 北京怡和嘉业医疗科技股份有限公司 | Method and device for processing brain wave signals |
CN108241431B (en) * | 2016-12-26 | 2020-10-30 | 中国移动通信有限公司研究院 | Task adjusting method and device |
CN108241431A (en) * | 2016-12-26 | 2018-07-03 | 中国移动通信有限公司研究院 | A kind of task adjusting method and device |
CN106943150A (en) * | 2017-03-22 | 2017-07-14 | 新乡医学院 | Mental fatigue detecting system and its method for use |
CN106923824A (en) * | 2017-03-27 | 2017-07-07 | 广州视源电子科技股份有限公司 | Brain electricity allowance recognition methods and device based on many spatial signal properties |
CN106923824B (en) * | 2017-03-27 | 2019-12-20 | 广州视源电子科技股份有限公司 | Electroencephalogram relaxation degree identification method and device based on multi-space signal characteristics |
CN109993180A (en) * | 2017-12-29 | 2019-07-09 | 新华网股份有限公司 | Human biological electricity data processing method and device, storage medium and processor |
CN108388340A (en) * | 2018-02-11 | 2018-08-10 | 广东欧珀移动通信有限公司 | Control method of electronic device and Related product |
CN108324272A (en) * | 2018-03-13 | 2018-07-27 | 天津大学 | A kind of device for checking and examining anxiety degree based on LZC complexities |
CN108836320A (en) * | 2018-04-02 | 2018-11-20 | 东北电力大学 | A method of organoleptic substances classification is carried out based on smell brain wave |
CN108888280A (en) * | 2018-05-24 | 2018-11-27 | 吉林大学 | Student based on electroencephalogramsignal signal analyzing listens to the teacher attention evaluation method |
CN108903936B (en) * | 2018-07-03 | 2021-01-26 | 西安科技大学 | Intelligent mining helmet control method based on human body information and environment information fusion |
CN108903936A (en) * | 2018-07-03 | 2018-11-30 | 西安科技大学 | The Intelligent mining helmet control method merged based on human body information and environmental information |
CN112888366A (en) * | 2018-10-15 | 2021-06-01 | 田边三菱制药株式会社 | Electroencephalogram analysis device, electroencephalogram analysis system, and electroencephalogram analysis program |
CN109620263A (en) * | 2018-12-13 | 2019-04-16 | 湖南仪峰安安网络科技股份有限公司 | A kind of enterprises and institutions are on duty personnel's sign safety analytical method |
CN110123314B (en) * | 2019-04-24 | 2020-12-22 | 华南理工大学 | Method for judging brain concentration and relaxation state based on electroencephalogram signals |
CN110123314A (en) * | 2019-04-24 | 2019-08-16 | 华南理工大学 | Judge that brain is absorbed in the method for relaxation state based on EEG signals |
CN110164091A (en) * | 2019-06-13 | 2019-08-23 | 华东师范大学 | A kind of fatigue driving monitoring device based on brain wave |
CN112329802A (en) * | 2019-08-01 | 2021-02-05 | 实践大学 | AI grouping integration system for gas quality meter and special attention and relaxation measurement |
CN111528839A (en) * | 2020-05-29 | 2020-08-14 | 北京京东方健康科技有限公司 | Sleep detection method and device, sleep aid equipment and method |
WO2021238457A1 (en) * | 2020-05-29 | 2021-12-02 | 京东方科技集团股份有限公司 | Sleep testing method and apparatus, and sleep-aiding device and method |
CN111528839B (en) * | 2020-05-29 | 2023-06-23 | 北京京东方健康科技有限公司 | Sleep detection method and device, sleep assisting equipment and method |
CN112353391A (en) * | 2020-10-22 | 2021-02-12 | 武汉理工大学 | Electroencephalogram signal-based method and device for recognizing sound quality in automobile |
CN112911136A (en) * | 2021-01-11 | 2021-06-04 | 深圳市宏智力科技有限公司 | Video recording control method based on brain waves |
CN113261974A (en) * | 2021-06-07 | 2021-08-17 | 吉林大学 | Sports fatigue monitoring method based on multiple physiological signals |
CN113679386A (en) * | 2021-08-13 | 2021-11-23 | 北京脑陆科技有限公司 | Method, device, terminal and medium for recognizing attention |
CN114224359A (en) * | 2021-12-18 | 2022-03-25 | 西南交通大学 | Electroencephalogram fatigue index determination method for high-speed rail dispatcher |
CN114041796B (en) * | 2022-01-13 | 2022-05-17 | 深圳市心流科技有限公司 | Concentration assessment method and device based on brain wave signal and storage medium |
CN114041796A (en) * | 2022-01-13 | 2022-02-15 | 深圳市心流科技有限公司 | Concentration assessment method and device based on brain wave signal and storage medium |
CN114569075A (en) * | 2022-02-28 | 2022-06-03 | 浙江柔灵科技有限公司 | Energy judgment-based real-time falling asleep point detection method and system and sleep-assisting device |
CN115067945A (en) * | 2022-08-22 | 2022-09-20 | 深圳市海清视讯科技有限公司 | Fatigue detection method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103989485A (en) | Human body fatigue evaluation method based on brain waves | |
Webber Jr et al. | Recurrence quantification analysis of nonlinear dynamical systems | |
CN105877766A (en) | Mental state detection system and method based on multiple physiological signal fusion | |
CN109674468A (en) | It is a kind of singly to lead brain electricity sleep mode automatically method by stages | |
Kołodziej et al. | A new method of EEG classification for BCI with feature extraction based on higher order statistics of wavelet components and selection with genetic algorithms | |
CN105147248A (en) | Physiological information-based depressive disorder evaluation system and evaluation method thereof | |
CN204931634U (en) | Based on the depression evaluating system of physiologic information | |
CN102274022A (en) | Sleep state monitoring method based on electroencephalogram signals | |
CN101049236A (en) | Instant detection system and detection method for state of attention based on interaction between brain and computer | |
Kalaivani et al. | Prediction of biomedical signals using deep learning techniques | |
WO2019140047A1 (en) | System and method for smart, secure, energy-efficient iot sensors | |
Somani et al. | classification of motor unit action potential using transfer learning for the diagnosis of neuromuscular diseases | |
CN112842279B (en) | Sleep quality evaluation method and device based on multi-dimensional characteristic parameters | |
Lim et al. | Artificial intelligence classification methods of atrial fibrillation with implementation technology | |
CN106781283A (en) | A kind of method for detecting fatigue driving based on soft set | |
CN114052744A (en) | Electrocardiosignal classification method based on pulse neural network | |
Esmaeilpour et al. | Analyzing the EEG signals in order to estimate the depth of anesthesia using wavelet and fuzzy neural networks | |
Meng et al. | Evaluation of decomposition parameters for high-density surface electromyogram using fast independent component analysis algorithm | |
Dzitac et al. | Identification of ERD using fuzzy inference systems for brain-computer interface | |
CN110473631A (en) | Intelligent sleep monitoring method and system based on real world research | |
CN111110268B (en) | Human body muscle sound signal prediction method based on random vector function connection network technology | |
Veer | A flexible approach for segregating physiological signals | |
Siuly et al. | Exploring Rhythms and Channels-Based EEG Biomarkers for Early Detection of Alzheimer's Disease | |
Mumtaz et al. | EEG classification of physiological conditions in 2D/3D environments using neural network | |
Zhang et al. | Non-uniform sample assignment in training set improving recognition of hand gestures dominated with similar muscle activities |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140820 |
|
WD01 | Invention patent application deemed withdrawn after publication |