CN114403897A - Human body fatigue detection method and system based on electroencephalogram signals - Google Patents
Human body fatigue detection method and system based on electroencephalogram signals Download PDFInfo
- Publication number
- CN114403897A CN114403897A CN202210049232.0A CN202210049232A CN114403897A CN 114403897 A CN114403897 A CN 114403897A CN 202210049232 A CN202210049232 A CN 202210049232A CN 114403897 A CN114403897 A CN 114403897A
- Authority
- CN
- China
- Prior art keywords
- electroencephalogram signal
- energy
- wave
- wavelet
- electroencephalogram
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—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
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/164—Lie detection
-
- 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]
- A61B5/372—Analysis of electroencephalograms
- A61B5/374—Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Psychiatry (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Psychology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Social Psychology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a human body fatigue detection method and system based on electroencephalogram signals, which belong to the technical field of digital signal processing and comprise the following steps: acquiring a noise-containing electroencephalogram signal and preprocessing the noise-containing electroencephalogram signal to obtain a clean electroencephalogram signal; carrying out wavelet packet transformation decomposition on the clean electroencephalogram signal to obtain a rhythm wave; calculating the energy of the rhythm wave, and calculating an energy ratio according to the energy of the rhythm wave; inputting the energy ratio into a pre-trained artificial neural network to obtain the probability of fatigue and non-fatigue, wherein the probability is the detection result; interference information contained in the electroencephalogram signals is eliminated, the accuracy of fatigue detection is improved, and reliable and accurate human body fatigue detection independent of individual difference is achieved.
Description
Technical Field
The invention relates to a human body fatigue detection method and system based on electroencephalogram signals, and belongs to the technical field of digital signal processing.
Background
Long-term high-intensity monotonous mental work can cause mental fatigue to people, but if the mental fatigue is not adjusted and recovered in time, the mental fatigue can reduce the working and learning efficiency and even threaten the life health of people; the current method for detecting human fatigue mainly comprises the following steps: the human behavior characteristics, the human facial characteristics and the human physiological indexes are analyzed through images, wherein the human behavior characteristics and the human facial characteristics have differences among human bodies, so that whether fatigue is caused or not cannot be accurately identified, and the human physiological indexes have certain deception; the electroencephalogram can directly reflect the electrical activity of brain tissues, and the evaluation of mental fatigue by the electroencephalogram becomes a hot spot of mental fatigue detection research.
At present, some meaningful achievements are obtained by utilizing brain waves to detect human fatigue at home and abroad; korean and the like combine the nonlinear characteristics of electroencephalogram signals and use multi-scale entropy combined support vector machine for fatigue detection; in addition, the prior art has the problems of low detection accuracy, low reliability, low expandability and the like.
Disclosure of Invention
The invention aims to provide a human body fatigue detection method and system based on electroencephalogram signals, which are used for eliminating interference information contained in the electroencephalogram signals, improving the accuracy of fatigue detection and realizing reliable and accurate human body fatigue detection independent of individual difference.
In order to realize the purpose, the invention is realized by adopting the following technical scheme:
in a first aspect, the invention provides a human body fatigue detection method based on electroencephalogram signals, which comprises the following steps:
acquiring a noise-containing electroencephalogram signal and preprocessing the noise-containing electroencephalogram signal to obtain a clean electroencephalogram signal;
carrying out wavelet packet transformation decomposition on the clean electroencephalogram signal to obtain a rhythm wave;
calculating the energy of the rhythm wave, and calculating an energy ratio according to the energy of the rhythm wave;
and inputting the energy ratio into a pre-trained artificial neural network to obtain the probability of fatigue and non-fatigue, wherein the probability is the detection result.
With reference to the first aspect, the method for obtaining the clean electroencephalogram signal by obtaining the electroencephalogram signal containing the noise and preprocessing the electroencephalogram signal containing the noise further comprises the following steps of preprocessing the electroencephalogram signal containing the noise by utilizing wavelet transform:
carrying out multi-scale decomposition on the noise-containing electroencephalogram signal by using a wavelet function to obtain a one-level wavelet decomposition structure;
performing threshold quantization processing on the wavelet coefficients on all scales through the compressed detail vectors and the threshold vectors to obtain a secondary wavelet decomposition structure;
and performing inverse transformation on the secondary wavelet decomposition structure through the wavelet function to obtain a clean electroencephalogram signal.
With reference to the first aspect, further, the compressed detail vector and the threshold vector are preset.
With reference to the first aspect, further, wavelet packet transform decomposition is performed on the clean electroencephalogram signal to obtain a rhythm wave, wherein the number of layers of the wavelet packet transform decomposition is six.
With reference to the first aspect, further, the method of calculating the energy of the rhythm wave includes:
the delta wave energy is:
the theta wave energy is:
the alpha wave energy is:
the beta wave energy is:
wherein, x (delta)n(n＝1，2...，N)、x(θ)n(n＝1，2...，N)、x(α)n(N ═ 1, 2.., N) and x (β)nN denotes the amplitude of each rhythm wave, and N is the number of sampling points.
With reference to the first aspect, further, the method for calculating the energy ratio value according to the rhythmic wave energy includes:
R＝(E(α)+E(θ))/E(β)
wherein E (alpha), E (theta) and E (beta) are alpha wave energy, theta wave energy and beta wave energy respectively.
In a second aspect, the present invention further provides a human fatigue detection system based on electroencephalogram signals, including:
a preprocessing module: the method is used for acquiring the electroencephalogram signal containing the noise and preprocessing the electroencephalogram signal to obtain a clean electroencephalogram signal;
wavelet packet transform decomposition module: the device is used for carrying out wavelet packet transformation decomposition on the clean electroencephalogram signal to obtain a rhythm wave;
an energy ratio acquisition module: the energy ratio is calculated according to the energy of the rhythm wave;
a detection module: and inputting the energy ratio into the pre-trained artificial neural network to obtain the probability of fatigue and non-fatigue, wherein the probability is the detection result.
Compared with the prior art, the invention has the following beneficial effects:
according to the method and the system for detecting the human body fatigue based on the electroencephalogram signals, the electroencephalogram signals containing noise are preprocessed to obtain clean electroencephalogram signals, interference information contained in the electroencephalogram signals is eliminated, and the accuracy of subsequent fatigue detection is improved; transforming and decomposing the clean electroencephalogram signals by using wavelet packets to obtain rhythm waves, wherein the wavelet packets can further subdivide high-frequency signals relative to wavelet transformation, and decompose the signals according to any time-frequency resolution; calculating the energy and the energy ratio of the rhythm wave according to the rhythm wave, further inputting the energy and the energy ratio into a trained artificial neural network to realize the detection of whether the human body is tired or not, taking the energy ratio as the input of fatigue detection according to the rhythm characteristics of the electroencephalogram signal, constructing a fatigue detection classifier, and realizing reliable and accurate human body fatigue detection independent of individual difference;
the method has the advantages that the noise-containing electroencephalogram signals are preprocessed through wavelet transformation, the wavelet transformation is time-frequency analysis of the signals, some local noises can be processed in a targeted mode, the effect is good, the original electroencephalogram signals can be well extracted, and the clean electroencephalogram signals are obtained.
Drawings
FIG. 1 is a flowchart of a human fatigue detection method based on electroencephalogram signals according to an embodiment of the present invention;
fig. 2 is a test result diagram of a human fatigue detection method based on electroencephalogram signals provided by the embodiment of the invention.
Detailed Description
The present invention is further described with reference to the accompanying drawings, and the following examples are only for clearly illustrating the technical solutions of the present invention, and should not be taken as limiting the scope of the present invention.
Example 1
As shown in fig. 1, a method for detecting human fatigue based on electroencephalogram signals provided by an embodiment of the present invention includes the following steps:
and S1, acquiring the electroencephalogram signal containing the noise and preprocessing the electroencephalogram signal to obtain a clean electroencephalogram signal.
In the present embodiment, first, 60 sets of data (noisy electroencephalograms) are acquired as training samples, and 20 sets of data (noisy electroencephalograms) are acquired as test samples.
Preprocessing the acquired noise-containing electroencephalogram signals by utilizing wavelet transformation:
carrying out multi-scale decomposition on the noise-containing electroencephalogram signals by using a wavelet function to obtain a first-level wavelet decomposition structure [ C, L ];
performing threshold quantization processing on wavelet coefficients on all scales through a customized compressed detail vector M and a customized threshold vector P to obtain a secondary wavelet decomposition structure [ MC, L ];
and performing inverse transformation (signal reconstruction) on the secondary wavelet decomposition structure through the same wavelet function to obtain a clean electroencephalogram signal.
In this embodiment, a d5 wavelet function is selected to perform 3-layer decomposition on a noisy electroencephalogram signal, a high-frequency coefficient is subjected to threshold processing, and finally, a d5 wavelet function is used to perform signal reconstruction to obtain a clean electroencephalogram signal.
And S2, carrying out wavelet packet transformation decomposition on the clean electroencephalogram signal to obtain a rhythm wave.
Carrying out feature extraction on the denoised clean electroencephalogram signal through wavelet packet transform decomposition, and extracting four rhythm waves which are delta waves, theta waves, alpha waves and beta waves respectively; delta waves appear when a human body is extremely tired or falls asleep, theta waves appear when the human body is frustrated or depressed, alpha waves appear when the human body is in a clear state or thought intensively, and beta waves appear when the human body is nervous, emotional or excited.
And S3, calculating the energy of the rhythm wave, and calculating the energy ratio according to the energy of the rhythm wave.
According to the sampling frequency of the brain wave and the frequency division of the brain wave, the number of the decomposition layers of the wavelet packet is determined to be six, and the energy of each rhythm is obtained by taking the coefficient of decomposition of the wavelet packet as the characteristic.
The method for calculating the energy of the rhythm wave comprises the following steps:
the delta wave energy is:
the theta wave energy is:
the alpha wave energy is:
the beta wave energy is:
wherein, x (delta)n(n＝1，2...，N)、x(θ)n(n＝1，2...，N)、x(α)n(N ═ 1, 2.., N) and x (β)nN is the number of sampling points, and each represents the amplitude of each rhythm wave after wavelet packet transformation decomposition.
The method for calculating the energy ratio comprises the following steps:
R＝(E(α)+E(θ))/E(β)
wherein E (alpha), E (theta) and E (beta) are alpha wave energy, theta wave energy and beta wave energy respectively.
And S4, inputting the energy ratio into the pre-trained artificial neural network to obtain the probability of fatigue and non-fatigue, wherein the probability is the detection result.
The method includes the steps that an Artificial Neural Network (ANN) is trained by using a MATLAB neural network tool, input sample data are normalized before the artificial neural network is trained, in order to prevent the problem that the range of the sample data is large, and therefore the convergence speed of the neural network is slow or the training time is long, the range of the sample data needs to be controlled between-1 and 1, the still neural network training function constructed in the embodiment is set to be a trailing dx function, the weight and the threshold are updated according to the gradient descent momentum and the self-adaptive learning rate, the training speed is high, the precision is high, the maximum iteration number of the network is set to be 500, the learning rate is 0.01, and the target error is 0.01.
Training the ANN artificial neural network, defining two outputs which respectively correspond to the probability that a test sample belongs to fatigue and non-fatigue, wherein the probability is the detection result, the non-fatigue is represented by [10] and the fatigue is represented by [01] according to the probability; and classifying and identifying the test result, wherein the identification 1 is non-fatigue, and the identification 2 is fatigue.
In this embodiment, the data obtained in S1 after processing 60 sets of data is used as a training sample, and after the training is completed, the data obtained after processing another 20 sets of data is used as a test sample, so as to obtain a test result chart as shown in fig. 2.
As can be seen from fig. 2, the training error obtained after the training for 138 times is 0.0092598, and since the military error can express the relationship between the output of the artificial neural network and its expected output, the accuracy of the final test sample is 87.5%.
According to the human body fatigue detection method based on the electroencephalogram signals, the noise-containing signals are preprocessed through wavelet transformation, the wavelet transformation is developed continuously based on Fourier transformation, and the Fourier transformation is global transformation, so that the local ratio of the wavelet transformation is poor, the wavelet transformation is usually used for processing steady signals, and the wavelet transformation is not suitable for denoising the non-steady signals such as the electroencephalogram signals; the wavelet transform is a time-frequency analysis of signals, can be used for pertinently removing some local noises, has a good effect, and can be used for well extracting original electroencephalogram signals.
The wavelet transformation mainly selects a proper wavelet function for the noise-containing electroencephalogram signal to carry out discrete wavelet decomposition to obtain wavelet coefficients on all scales, then carries out threshold denoising processing on a frequency band containing noise, and finally reconstructs a denoised signal to obtain a clean electroencephalogram signal.
Wavelet packet transformation is adopted to decompose the signals, wavelet packets further subdivide high-frequency signals relative to wavelet transformation energy conversion, and the signals are decomposed according to any time-frequency resolution.
And according to the rhythm characteristics of the electroencephalogram signal, the energy ratio is used as a fatigue detection index, a fatigue detection classifier is constructed, and reliable and accurate fatigue detection independent of individual difference is realized.
Example 2
The embodiment of the invention provides a human body fatigue detection system based on electroencephalogram signals, which comprises:
a preprocessing module: the method is used for acquiring the electroencephalogram signal containing the noise and preprocessing the electroencephalogram signal to obtain a clean electroencephalogram signal;
wavelet packet transform decomposition module: the device is used for carrying out wavelet packet transformation decomposition on the clean electroencephalogram signal to obtain a rhythm wave;
an energy ratio acquisition module: the energy ratio is calculated according to the energy of the rhythm wave;
a detection module: and inputting the energy ratio into the pre-trained artificial neural network to obtain the probability of fatigue and non-fatigue, wherein the probability is the detection result.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (7)
1. A human body fatigue detection method based on electroencephalogram signals is characterized by comprising the following steps:
acquiring a noise-containing electroencephalogram signal and preprocessing the noise-containing electroencephalogram signal to obtain a clean electroencephalogram signal;
carrying out wavelet packet transformation decomposition on the clean electroencephalogram signal to obtain a rhythm wave;
calculating the energy of the rhythm wave, and calculating an energy ratio according to the energy of the rhythm wave;
and inputting the energy ratio into a pre-trained artificial neural network to obtain the probability of fatigue and non-fatigue, wherein the probability is the detection result.
2. The electroencephalogram signal-based human body fatigue detection method according to claim 1, wherein the step of obtaining the electroencephalogram signal containing noise and preprocessing the electroencephalogram signal containing noise to obtain a clean electroencephalogram signal comprises the step of preprocessing the electroencephalogram signal containing noise by utilizing wavelet transform:
carrying out multi-scale decomposition on the noise-containing electroencephalogram signal by using a wavelet function to obtain a one-level wavelet decomposition structure;
performing threshold quantization processing on the wavelet coefficients on all scales through the compressed detail vectors and the threshold vectors to obtain a secondary wavelet decomposition structure;
and performing inverse transformation on the secondary wavelet decomposition structure through the wavelet function to obtain a clean electroencephalogram signal.
3. The electroencephalogram signal-based human body fatigue detection method according to claim 2, wherein the compressed detail vector and the threshold vector are preset.
4. The electroencephalogram signal-based human body fatigue detection method according to claim 1, characterized in that wavelet packet transform decomposition is performed on clean electroencephalogram signals to obtain rhythm waves, wherein the number of layers of wavelet packet transform decomposition is six.
5. The electroencephalogram signal-based human body fatigue detection method according to claim 1, wherein the method for calculating the energy of the rhythmic wave comprises:
the delta wave energy is:
the theta wave energy is:
the alpha wave energy is:
the beta wave energy is:
wherein, x (delta)n(n＝1，2...，N)、x(θ)n(n＝1，2...，N)、x(α)n(N ═ 1, 2.., N) and x (β)nN denotes the amplitude of each rhythm wave, and N is the number of sampling points.
6. The electroencephalogram signal-based human body fatigue detection method according to claim 1, wherein the method for calculating the energy ratio from the rhythmic wave energy comprises:
R＝(E(α)+E(θ))/E(β)
wherein E (alpha), E (theta) and E (beta) are alpha wave energy, theta wave energy and beta wave energy respectively.
7. A human fatigue detection system based on electroencephalogram signals is characterized by comprising:
a preprocessing module: the method is used for acquiring the electroencephalogram signal containing the noise and preprocessing the electroencephalogram signal to obtain a clean electroencephalogram signal;
wavelet packet transform decomposition module: the device is used for carrying out wavelet packet transformation decomposition on the clean electroencephalogram signal to obtain a rhythm wave;
an energy ratio acquisition module: the energy ratio is calculated according to the energy of the rhythm wave;
a detection module: and inputting the energy ratio into the pre-trained artificial neural network to obtain the probability of fatigue and non-fatigue, wherein the probability is the detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210049232.0A CN114403897A (en) | 2022-01-17 | 2022-01-17 | Human body fatigue detection method and system based on electroencephalogram signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210049232.0A CN114403897A (en) | 2022-01-17 | 2022-01-17 | Human body fatigue detection method and system based on electroencephalogram signals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114403897A true CN114403897A (en) | 2022-04-29 |
Family
ID=81272880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210049232.0A Pending CN114403897A (en) | 2022-01-17 | 2022-01-17 | Human body fatigue detection method and system based on electroencephalogram signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114403897A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115281676A (en) * | 2022-10-08 | 2022-11-04 | 齐鲁工业大学 | Fatigue detection method based on GRU neural network and ECG signal |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107714037A (en) * | 2017-10-12 | 2018-02-23 | 西安科技大学 | A kind of miner's fatigue identification method based on the mining helmet of brain-computer interface |
| CN111631697A (en) * | 2020-06-15 | 2020-09-08 | 电子科技大学 | Intelligent sleep and fatigue state information monitoring control system and method and monitor |
-
2022
- 2022-01-17 CN CN202210049232.0A patent/CN114403897A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107714037A (en) * | 2017-10-12 | 2018-02-23 | 西安科技大学 | A kind of miner's fatigue identification method based on the mining helmet of brain-computer interface |
| CN111631697A (en) * | 2020-06-15 | 2020-09-08 | 电子科技大学 | Intelligent sleep and fatigue state information monitoring control system and method and monitor |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115281676A (en) * | 2022-10-08 | 2022-11-04 | 齐鲁工业大学 | Fatigue detection method based on GRU neural network and ECG signal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108714026B (en) | Fine-grained electrocardiosignal classification method based on deep convolutional neural network and online decision fusion | |
| Hsieh et al. | Feature selection framework for xgboost based on electrodermal activity in stress detection | |
| CN111310570B (en) | Electroencephalogram signal emotion recognition method and system based on VMD and WPD | |
| Chang et al. | DeepHeart: a deep learning approach for accurate heart rate estimation from PPG signals | |
| CN114533086B (en) | Motor imagery brain electrolysis code method based on airspace characteristic time-frequency transformation | |
| Yuan et al. | A novel wavelet-based model for eeg epileptic seizure detection using multi-context learning | |
| CN109480835B (en) | Mental fatigue detection method based on long-term and short-term memory neural network | |
| CN108567418A (en) | A kind of pulse signal inferior health detection method and detecting system based on PCANet | |
| CN112200016A (en) | Electroencephalogram signal emotion recognition based on ensemble learning method AdaBoost | |
| Azar et al. | Deep recurrent neural network-based autoencoder for photoplethysmogram artifacts filtering | |
| CN112603332A (en) | Emotion cognition method based on electroencephalogram signal characteristic analysis | |
| CN112580486B (en) | Human behavior classification method based on radar micro-Doppler signal separation | |
| CN110543831A (en) | brain print identification method based on convolutional neural network | |
| CN112754502A (en) | Automatic music switching method based on electroencephalogram signals | |
| CN115414051A (en) | Emotion classification and recognition method of electroencephalogram signal self-adaptive window | |
| CN114403897A (en) | Human body fatigue detection method and system based on electroencephalogram signals | |
| CN114662524A (en) | Plug-and-play type domain adaptation method based on electroencephalogram signals | |
| CN116350233A (en) | Electrocardiosignal quality assessment method based on self-encoder | |
| CN116304815A (en) | Motor imagery electroencephalogram signal classification method based on self-attention mechanism and parallel convolution | |
| Degirmenci et al. | Synchrosqueezing transform in biomedical applications: A mini review | |
| Nibhanupudi | Signal denoising using wavelets | |
| Blumensath et al. | Shift-invariant sparse coding for single channel blind source separation | |
| CN111493864B (en) | EEG signal mixed noise processing method, equipment and storage medium | |
| CN114091529A (en) | Electroencephalogram emotion recognition method based on generation countermeasure network data enhancement | |
| Chen et al. | Heart Sound Classification Based on Mel-Frequency Cepstrum Coefficient Features and Multi-Scale Residual Recurrent Neural Networks |
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 |