CN116304563A - Construction worker fatigue degree calculation method and system - Google Patents
Construction worker fatigue degree calculation method and system Download PDFInfo
- Publication number
- CN116304563A CN116304563A CN202310143622.9A CN202310143622A CN116304563A CN 116304563 A CN116304563 A CN 116304563A CN 202310143622 A CN202310143622 A CN 202310143622A CN 116304563 A CN116304563 A CN 116304563A
- Authority
- CN
- China
- Prior art keywords
- fatigue
- electroencephalogram
- preset
- site
- signal
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 65
- 238000004364 calculation method Methods 0.000 title claims description 24
- 210000004556 brain Anatomy 0.000 claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 230000009467 reduction Effects 0.000 claims description 79
- JYGXADMDTFJGBT-VWUMJDOOSA-N hydrocortisone Chemical compound O=C1CC[C@]2(C)[C@H]3[C@@H](O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 JYGXADMDTFJGBT-VWUMJDOOSA-N 0.000 claims description 30
- 238000001228 spectrum Methods 0.000 claims description 18
- 229960000890 hydrocortisone Drugs 0.000 claims description 15
- 238000003062 neural network model Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 239000003973 paint Substances 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 210000001061 forehead Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003296 saliva Anatomy 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Heart & Thoracic Surgery (AREA)
- Psychiatry (AREA)
- Surgery (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Psychology (AREA)
- Evolutionary Computation (AREA)
- Developmental Disabilities (AREA)
- Fuzzy Systems (AREA)
- Child & Adolescent Psychology (AREA)
- Social Psychology (AREA)
- Educational Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Hospice & Palliative Care (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of safety monitoring, in particular to a method and a system for calculating the fatigue degree of construction workers, wherein the method comprises the following steps: acquiring an electroencephalogram signal of a preset site of a constructor through an intelligent safety helmet with a brain-computer interface, wherein the preset site comprises a first site, a second site, a third site and a fourth site; preprocessing the electroencephalogram signals of the preset sites to obtain processed electroencephalogram signals; extracting target brain electrical characteristics from the processed brain electrical signals according to a preset time interval; determining and outputting the fatigue degree of the construction worker according to the target brain electrical characteristics and a pre-trained fatigue recognition model, wherein the fatigue degree comprises: high fatigue, medium fatigue and low fatigue. Through this scheme, in case detect that constructor is in fatigue state, can send the signal through brain-computer interface safety helmet and remind to guarantee constructor's safety.
Description
Technical Field
The disclosure relates to the technical field of safety monitoring of construction sites, in particular to a fatigue degree calculation method and system for construction workers.
Background
With the great development of national capital construction and the guarantee of civilians, production safety problems are the current concern of governments and various large manufacturers. In each production accident cause, the fatigue factor becomes a main factor. In the construction scene of the foundation, construction workers wear the safety helmet to avoid potential safety problems, but the traditional safety helmet only provides a physical anti-collision function and cannot monitor physical signs of the construction workers. Therefore, LEN et al propose a wearable sign monitoring system that places a plurality of EEG monitoring electrodes on the cerebral cortex, enabling detection of human brain signals. The wearable sign monitoring system only provides a monitoring method of EEG, but does not calculate fatigue of workers, and can not effectively identify the fatigue degree of the workers in the production activity scene.
Disclosure of Invention
In order to overcome the problems in the related art, the present disclosure provides a method and system for calculating the fatigue degree of a construction worker.
According to a first aspect of embodiments of the present disclosure, there is provided a method for calculating a fatigue degree of a construction worker, including:
acquiring an electroencephalogram signal of a preset site of a constructor through an intelligent safety helmet with a brain-computer interface, wherein the preset site comprises a first site, a second site, a third site and a fourth site;
preprocessing the electroencephalogram signals of the preset sites to obtain processed electroencephalogram signals;
extracting target brain electrical characteristics from the processed brain electrical signals according to a preset time interval;
determining and outputting the fatigue degree of the construction worker according to the target brain electrical characteristics and a pre-trained fatigue recognition model, wherein the fatigue degree comprises: high fatigue, medium fatigue and low fatigue.
In one embodiment, preferably, preprocessing the electroencephalogram signal at the preset site to obtain a processed electroencephalogram signal includes:
performing data noise reduction processing on the electroencephalogram signals corresponding to the first position and the second position by using the electroencephalogram signals corresponding to the third position and the fourth position so as to obtain a first noise reduction signal corresponding to the first position and a second noise reduction signal corresponding to the second position;
wherein the first noise reduction signal is calculated using the following first calculation formula:
V fp1, noise reduction signal ＝V Fp1, original signal -(V T5 +V T6 )/2；
Wherein V is Fp1, noise reduction signal Representing the first noise reduction signal, V Fp1, original signal Representing the brain electrical signal corresponding to the first locus, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
calculating the second noise reduction signal using a second calculation formula:
V fp2, noise reduction signal ＝V Fp2, original signal -(V T5 +V T6 )/2；
Wherein V is Fp2, noise reduction signal Representing the second noise reduction signal, V Fp2, original signal Representing the brain electrical signal corresponding to the second position, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
in one embodiment, preferably, extracting the target electroencephalogram feature from the processed electroencephalogram signal according to a preset time interval includes:
downsampling the processed electroencephalogram signal, and reducing the frequency of the processed electroencephalogram signal from the original frequency to the target frequency to obtain an electroencephalogram signal with the target frequency;
performing continuous wavelet transformation on the electroencephalogram signals of the target frequency, extracting electroencephalogram signal power spectrum energy values in each frequency range at each time point in a preset frequency interval in preset time according to preset time and preset frequency step length to obtain target electroencephalogram characteristics of preset number, wherein the electroencephalogram signal power spectrum energy values are calculated by adopting the following third calculation formula:
wherein a, b represent parameter dimensions, ω 0 Represents the wavelet center frequency, f (t) represents the first noise reduction signal and the second noise reduction signal, t represents the time t, i is
P f，t The power spectrum energy value of the brain electrical signal with frequency f and time t is shown.
In one embodiment, preferably, the training process of the fatigue recognition model includes:
collecting fatigue data of a target number, wherein the fatigue data comprises electroencephalogram characteristic data and corresponding cortisol data;
dividing the fatigue data into high fatigue degree, medium fatigue degree and low fatigue degree according to the cortisol content, and obtaining the divided fatigue data;
training the divided fatigue data and a preset deep neural network model to obtain the fatigue identification model.
In one embodiment, preferably, the preset depth neural network model includes a first convolution layer, a second convolution layer, a third convolution layer, a first partial acceptance, a second partial acceptance, a third partial acceptance, a discard layer, and a full connection layer;
wherein the convolution kernel of the first convolution layer is 7*7, and the step length is 1; the convolution kernel of the second convolution layer is 1*1, and the step length is 1; the convolution kernel of the third convolution layer is 3*3, and the step length is 1;
the first partial acceptance comprises a first acceptance layer and a second acceptance layer, the second partial acceptance comprises a third acceptance layer, a fourth acceptance layer, a fifth acceptance layer, a sixth acceptance layer and a seventh acceptance layer, and the third partial acceptance comprises an eighth acceptance layer and a ninth acceptance layer;
the ninth acceptance layer is connected to the discarding layer, and the paint layer performs data discarding according to a preset discarding rate;
the fully connected layer is connected to the discard layer.
In one embodiment, preferably, the method further comprises:
the output mode of the fatigue degree of the construction worker comprises at least one of the following steps: graphic presentation and voice prompt.
In one embodiment, preferably, the method further comprises:
when the fatigue degree of the construction worker is detected to be high, and the duration reaches the preset duration, reminding information is sent to the intelligent safety helmet of the brain-computer interface, so that the intelligent safety helmet of the brain-computer interface carries out alarm prompt according to the reminding information to prompt the construction worker to rest.
According to a second aspect of the embodiments of the present disclosure, there is provided a fatigue degree calculating device for construction workers, including:
the acquisition module is used for acquiring brain-electrical signals of a preset site of a construction worker through the brain-computer interface intelligent safety helmet, wherein the preset site comprises a first site, a second site, a third site and a fourth site;
the preprocessing module is used for preprocessing the electroencephalogram signals of the preset sites to obtain processed electroencephalogram signals;
the extraction module is used for extracting target electroencephalogram characteristics from the processed electroencephalogram signals according to a preset time interval;
the determining module is used for determining and outputting the fatigue degree of the construction worker according to the target electroencephalogram characteristics and the pre-trained fatigue recognition model, wherein the fatigue degree comprises the following steps: high fatigue, medium fatigue and low fatigue.
In one embodiment, preferably, the preprocessing module is configured to:
performing data noise reduction processing on the electroencephalogram signals corresponding to the first position and the second position by using the electroencephalogram signals corresponding to the third position and the fourth position so as to obtain a first noise reduction signal corresponding to the first position and a second noise reduction signal corresponding to the second position;
wherein the first noise reduction signal is calculated using the following first calculation formula:
V fp1, noise reduction signal ＝V Fp1, original signal -(V T5 +V T6 )/2；
Wherein V is Fp1, noise reduction signal Representing the first noise reduction signal, V Fp1, original signal Representing the brain electrical signal corresponding to the first locus, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
calculating the second noise reduction signal using a second calculation formula:
V fp2, noise reduction signal ＝V Fp2, original signal -(V T5 +V T6 )/2；
Wherein V is Fp2, noise reduction signal Representing the second noise reduction signal, V Fp2, original signal Representing the brain electrical signal corresponding to the second position, V T5 And V T6 Respectively represent the electroencephalogram corresponding to the third site and the fourth siteA signal;
in one embodiment, preferably, the extraction module is configured to:
downsampling the processed electroencephalogram signal, and reducing the frequency of the processed electroencephalogram signal from the original frequency to the target frequency to obtain an electroencephalogram signal with the target frequency;
performing continuous wavelet transformation on the electroencephalogram signals of the target frequency, extracting electroencephalogram signal power spectrum energy values in each frequency range at each time point in a preset frequency interval in preset time according to preset time and preset frequency step length to obtain target electroencephalogram characteristics of preset number, wherein the electroencephalogram signal power spectrum energy values are calculated by adopting the following third calculation formula:
wherein a, b represent parameter dimensions, ω 0 Represents the wavelet center frequency, f (t) represents the first noise reduction signal and the second noise reduction signal, t represents the time t, i is
P f，t The power spectrum energy value of the brain electrical signal with frequency f and time t is shown.
In one embodiment, preferably, the training process of the fatigue recognition model includes:
collecting fatigue data of a target number, wherein the fatigue data comprises electroencephalogram characteristic data and corresponding cortisol data;
dividing the fatigue data into high fatigue degree, medium fatigue degree and low fatigue degree according to the cortisol content, and obtaining the divided fatigue data;
training the divided fatigue data and a preset deep neural network model to obtain the fatigue identification model.
In one embodiment, preferably, the preset depth neural network model includes a first convolution layer, a second convolution layer, a third convolution layer, a first partial acceptance, a second partial acceptance, a third partial acceptance, a discard layer, and a full connection layer;
wherein the convolution kernel of the first convolution layer is 7*7, and the step length is 1; the convolution kernel of the second convolution layer is 1*1, and the step length is 1; the convolution kernel of the third convolution layer is 3*3, and the step length is 1;
the first partial acceptance comprises a first acceptance layer and a second acceptance layer, the second partial acceptance comprises a third acceptance layer, a fourth acceptance layer, a fifth acceptance layer, a sixth acceptance layer and a seventh acceptance layer, and the third partial acceptance comprises an eighth acceptance layer and a ninth acceptance layer;
the ninth acceptance layer is connected to the discarding layer, and the discarding layer performs data discarding according to a preset discarding rate;
the fully connected layer is connected to the discard layer.
In one embodiment, preferably, the output mode of the fatigue degree of the construction worker includes at least one of the following: graphic presentation and voice prompt.
In one embodiment, preferably, the apparatus further comprises:
and the sending module is used for sending reminding information to the intelligent safety helmet of the brain-computer interface when the fatigue degree of the construction worker is detected to be high, and the duration reaches the preset duration, so that the intelligent safety helmet of the brain-computer interface carries out alarm prompt according to the reminding information to prompt the construction worker to rest.
In one embodiment, the preprocessing module 42 is preferably configured to:
performing data noise reduction processing on the electroencephalogram signals corresponding to the first position and the second position by using the electroencephalogram signals corresponding to the third position and the fourth position so as to obtain a first noise reduction signal corresponding to the first position and a second noise reduction signal corresponding to the second position;
wherein the first noise reduction signal is calculated using the following first calculation formula:
V fp1, noise reduction signal ＝V Fp1, original signal -(V T5 +V T6 )/2；
Wherein V is Fp1, noise reduction signal Representing the first noise reduction signal, V Fp1, original signal Representing the brain electrical signal corresponding to the first locus, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
calculating the second noise reduction signal using a second calculation formula:
V fp2, noise reduction signal ＝V Fp2, original signal -(V T5 +V T6 )/2；
Wherein V is Fp2, noise reduction signal Representing the second noise reduction signal, V Fp2, original signal Representing the brain electrical signal corresponding to the second position, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
in one embodiment, preferably, the extraction module 43 is configured to:
downsampling the processed electroencephalogram signal, and reducing the frequency of the processed electroencephalogram signal from the original frequency to the target frequency to obtain an electroencephalogram signal with the target frequency;
performing continuous wavelet transformation on the electroencephalogram signals of the target frequency, extracting electroencephalogram signal power spectrum energy values in each frequency range at each time point in a preset frequency interval in preset time according to preset time and preset frequency step length to obtain target electroencephalogram characteristics of preset number, wherein the electroencephalogram signal power spectrum energy values are calculated by adopting the following third calculation formula:
wherein a, b represent parameter dimensions, ω 0 Represents the wavelet center frequency, f (t) represents the first noise reduction signal and the second noise reduction signal, t represents the time t, i is
P f，t Indicating the frequency f, timeIs the brain electrical signal power spectrum energy value at t.
In one embodiment, preferably, the training process of the fatigue recognition model includes:
collecting fatigue data of a target number, wherein the fatigue data comprises electroencephalogram characteristic data and corresponding cortisol data;
dividing the fatigue data into high fatigue degree, medium fatigue degree and low fatigue degree according to the cortisol content, and obtaining the divided fatigue data;
training the divided fatigue data and a preset deep neural network model to obtain the fatigue identification model.
In one embodiment, preferably, the preset depth neural network model includes a first convolution layer, a second convolution layer, a third convolution layer, a first partial acceptance, a second partial acceptance, a third partial acceptance, a discard layer, and a full connection layer;
wherein the convolution kernel of the first convolution layer is 7*7, and the step length is 1; the convolution kernel of the second convolution layer is 1*1, and the step length is 1; the convolution kernel of the third convolution layer is 3*3, and the step length is 1;
the first partial acceptance comprises a first acceptance layer and a second acceptance layer, the second partial acceptance comprises a third acceptance layer, a fourth acceptance layer, a fifth acceptance layer, a sixth acceptance layer and a seventh acceptance layer, and the third partial acceptance comprises an eighth acceptance layer and a ninth acceptance layer;
the ninth acceptance layer is connected to the discarding layer, and the discarding layer performs data discarding according to a preset discarding rate;
the fully connected layer is connected to the discard layer.
In one embodiment, preferably, the output mode of the fatigue degree of the construction worker includes at least one of the following: graphic presentation and voice prompt.
In one embodiment, preferably, the apparatus further comprises:
and the sending module is used for sending reminding information to the intelligent safety helmet of the brain-computer interface when the fatigue degree of the construction worker is detected to be high, and the duration reaches the preset duration, so that the intelligent safety helmet of the brain-computer interface carries out alarm prompt according to the reminding information to prompt the construction worker to rest.
According to a third aspect of embodiments of the present disclosure, there is provided a safety monitoring and early warning device for a construction site, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to:
acquiring an electroencephalogram signal of a preset site of a constructor through an intelligent safety helmet with a brain-computer interface, wherein the preset site comprises a first site, a second site, a third site and a fourth site;
preprocessing the electroencephalogram signals of the preset sites to obtain processed electroencephalogram signals;
extracting target brain electrical characteristics from the processed brain electrical signals according to a preset time interval;
determining and outputting the fatigue degree of the construction worker according to the target brain electrical characteristics and a pre-trained fatigue recognition model, wherein the fatigue degree comprises: high fatigue, medium fatigue and low fatigue.
According to a fourth aspect of the present invention there is provided a computer readable storage medium having stored thereon computer instructions which when executed by a processor perform the steps of the method of any of the embodiments of the first aspect.
The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:
in the embodiment of the invention, the brain-computer interface safety helmet is used for realizing the real-time acquisition of brain-computer signals and the background transmission through a network, and the characteristics extraction, fatigue degree classification, data transmission feedback and safety helmet information reminding are realized on the signals through an algorithm in the background. If the construction worker is in a fatigue state once detected, a signal prompt is sent out through the brain-computer interface safety helmet, so that the safety of the construction worker is ensured.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a flowchart illustrating a method of calculating a fatigue degree of a construction worker according to an exemplary embodiment.
Fig. 2 is a schematic diagram illustrating an electroencephalogram signal acquisition site according to an exemplary embodiment.
Fig. 3 is a schematic structural view showing step S103 in a fatigue degree calculation method of a construction worker according to an exemplary embodiment.
Fig. 4 is a block diagram illustrating a fatigue degree calculating apparatus of a construction worker according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
Fig. 1 is a flowchart illustrating a method of calculating a fatigue degree of a construction worker according to an exemplary embodiment.
As shown in fig. 1, the fatigue degree calculating method of a construction worker includes:
step S101, acquiring an electroencephalogram signal of a preset site of a construction worker through an intelligent safety helmet with a brain-computer interface, wherein the preset site comprises a first site, a second site, a third site and a fourth site; as shown in FIG. 2, the invention mainly collects the electroencephalogram signals of four sites of a first site Fp1, a second site Fp2, a third site T5 and a fourth site T6, and the collection frequency is 250Hz. Since the mental state (whether tired) of the user mainly activates the forehead lobe, the main signal acquisition electrodes are symmetrically distributed on the forehead lobe of the brain, and the electrode points are symmetrically distributed (Fp 1, fp 2) left and right. The brain electrical signals acquired by the T5 and T6 are used as reference sites for data noise reduction processing.
Performing data noise reduction processing on the electroencephalogram signals corresponding to the first position and the second position by using the electroencephalogram signals corresponding to the third position and the fourth position so as to obtain a first noise reduction signal corresponding to the first position and a second noise reduction signal corresponding to the second position;
wherein the first noise reduction signal is calculated using the following first calculation formula:
V fp1, noise reduction signal ＝V Fp1, original signal -(V T5 +V T6 )/2；
Wherein V is Fp1, noise reduction signal Representing the first noise reduction signal, V Fp1, original signal Representing the brain electrical signal corresponding to the first locus, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
calculating the second noise reduction signal using a second calculation formula:
V Fp2 ， noise reduction signal ＝V Fp2, original signal -(V T5 +V T6 )/2；
Wherein V is Fp2, noise reduction signal Representing the second noise reduction signal, V Fp2, original signal Representing the brain electrical signal corresponding to the second position, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
the data sample length is typically set to 10 seconds. And transmitting the acquired electroencephalogram signals to the human-computer interaction device every 10 seconds through the network connection module. The network connection module is not limited to bluetooth, data traffic, wiFi, etc. The man-machine interaction device has a relatively far data transmission capability, and data is transmitted to the background in a data flow (4G or 5G) mode. The data traffic mode can realize remote data transmission, and mainly uses the data traffic to realize data transmission to the background.
Step S102, preprocessing the brain electrical signals of the preset sites to obtain processed brain electrical signals;
the frequency range of the effective electroencephalogram signal is 0.4hz to 45hz, the amplitude is 0.5uV to 100uV, and the preprocessing of the electroencephalogram signal mainly comprises the steps of filtering the frequency range and the amplitude of the ineffective electroencephalogram signal, so that the elimination of noise is realized, and the method mainly comprises the operations of coding, amplifying, filtering and the like. The signal processing device implementing the above-described series of operations includes, but is not limited to, a microprocessor MPU, a central processing unit CPU, a graphics processing unit GPU, and the like.
Step S103, extracting target brain electrical characteristics from the processed brain electrical signals according to a preset time interval;
as shown in fig. 3, in one embodiment, preferably, step S103 includes:
step S301, downsampling the processed electroencephalogram signal, and reducing the frequency of the processed electroencephalogram signal from the original frequency to the target frequency to obtain an electroencephalogram signal with the target frequency;
step S302, performing continuous wavelet transformation on the electroencephalogram signals of the target frequency, extracting electroencephalogram signal power spectrum energy values in each frequency range at each time point in a preset frequency interval in preset time according to preset time and preset frequency step length to obtain target electroencephalogram characteristics of preset number, wherein the electroencephalogram signal power spectrum energy values are calculated by adopting the following third calculation formula:
wherein a, b represent parameter dimensions, ω 0 Represents the wavelet center frequency, f (t) represents the first noise reduction signal and the second noise reduction signal, t represents the time t, i is
P f，t The power spectrum energy value of the brain electrical signal with frequency f and time t is shown.
In this embodiment, the brain electrical signal is first downsampled to relieve the computational pressure, and the original signal at 250Hz can be resampled to 125Hz. A Continuous Wavelet Transform (CWT) is then performed, for example using a Morlet wavelet, to extract EEG signal power spectral energy values in various frequency ranges at various time points within 10s, 1-40Hz in frequency steps in time of 10s, 0.1Hz, resulting in 2 (channel) ×1250 (time) ×400 (frequency) entry-labeled electroencephalographic features.
Step S104, determining and outputting the fatigue degree of the construction worker according to the target electroencephalogram characteristics and a pre-trained fatigue recognition model, wherein the fatigue degree comprises the following steps: high fatigue, medium fatigue and low fatigue.
In the embodiment of the invention, the brain-computer interface safety helmet is used for realizing the real-time acquisition of brain-computer signals and the background transmission through a network, and the characteristics extraction, fatigue degree classification, data transmission feedback and safety helmet information reminding are realized on the signals through an algorithm in the background. If the construction worker is in a fatigue state once detected, a signal prompt is sent out through the brain-computer interface safety helmet, so that the safety of the construction worker is ensured.
In one embodiment, preferably, the training process of the fatigue recognition model includes:
collecting fatigue data of a target number, wherein the fatigue data comprises electroencephalogram characteristic data and corresponding cortisol data; electroencephalogram signals of 20 subjects over 5 workdays can be continuously collected, saliva of subjects collected every 2 hours on each workday and cortisol content determined for determining true fatigue levels. Total 400 cortisol data were collected and divided into three groups of high, medium and low fatigue, denoted y, based on cortisol content i 。
Dividing the fatigue data into high fatigue degree, medium fatigue degree and low fatigue degree according to the cortisol content, and obtaining the divided fatigue data;
training the divided fatigue data and a preset deep neural network model to obtain the fatigue identification model.
In one embodiment, preferably, the preset depth neural network model includes a first convolution layer, a second convolution layer, a third convolution layer, a first partial acceptance, a second partial acceptance, a third partial acceptance, a discard layer, and a full connection layer;
wherein the convolution kernel of the first convolution layer is 7*7, and the step length is 1; the convolution kernel of the second convolution layer is 1*1, and the step length is 1; the convolution kernel of the third convolution layer is 3*3, and the step length is 1;
the first partial acceptance comprises a first acceptance layer and a second acceptance layer, the second partial acceptance comprises a third acceptance layer, a fourth acceptance layer, a fifth acceptance layer, a sixth acceptance layer and a seventh acceptance layer, and the third partial acceptance comprises an eighth acceptance layer and a ninth acceptance layer;
the ninth acceptance layer is connected to the discarding layer, and the paint layer performs data discarding according to a preset discarding rate;
the fully connected layer is connected to the discard layer.
In one embodiment, preferably, the output mode of the fatigue degree of the construction worker includes at least one of the following: graphic presentation and voice prompt.
In this embodiment, the background transmits the predicted result value to the man-machine interaction device to output and display data to the user, and the feedback mode to the user may be a graphic context or a voice prompt, and preferably, the feedback mode is a graphic context mode.
In one embodiment, preferably, the method further comprises:
when the fatigue degree of the construction worker is detected to be high, and the duration reaches the preset duration, reminding information is sent to the intelligent safety helmet of the brain-computer interface, so that the intelligent safety helmet of the brain-computer interface carries out alarm prompt according to the reminding information to prompt the construction worker to rest.
The intelligent safety helmet with the brain-computer interface receives the current high fatigue degree signal of the user, and the signal reminding module of the intelligent safety helmet with the brain-computer interface can apply buzzing reminding to the user to remind the user to carry out proper rest adjustment.
Fig. 4 is a block diagram illustrating a fatigue degree calculating apparatus of a construction worker according to an exemplary embodiment.
As shown in fig. 4, according to a second aspect of the embodiment of the present disclosure, there is provided a fatigue degree calculating device for construction workers, including:
an acquisition module 41, configured to acquire an electroencephalogram signal of a preset site of a construction worker through a brain-computer interface intelligent safety helmet, where the preset site includes a first site, a second site, a third site and a fourth site;
the preprocessing module 42 is configured to preprocess the electroencephalogram signal at the preset site to obtain a processed electroencephalogram signal;
an extracting module 43, configured to extract a target electroencephalogram feature from the processed electroencephalogram signal according to a preset time interval;
a determining module 44, configured to determine and output a fatigue degree of the construction worker according to the target electroencephalogram feature and a pre-trained fatigue recognition model, where the fatigue degree includes: high fatigue, medium fatigue and low fatigue.
In one embodiment, the preprocessing module 42 is preferably configured to:
performing data noise reduction processing on the electroencephalogram signals corresponding to the first position and the second position by using the electroencephalogram signals corresponding to the third position and the fourth position so as to obtain a first noise reduction signal corresponding to the first position and a second noise reduction signal corresponding to the second position;
wherein the first noise reduction signal is calculated using the following first calculation formula:
V fp1, noise reduction signal ＝V Fp1, original signal -(V T5 +V T6 )/2；
Wherein V is Fp1, noise reduction signal Representing the first noise reduction signal, V Fp1, original signal Representing the brain electrical signal corresponding to the first locus, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
calculating the second noise reduction signal using a second calculation formula:
V fp2, noise reduction signal ＝V Fp2, original signal -(V T5 +V T6 )/2；
Wherein V is Fp2, noise reduction signal Representing the second noise reduction signal, V Fp2, original signal Representing the brain electrical signal corresponding to the second position, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
in one embodiment, preferably, the extraction module 43 is configured to:
downsampling the processed electroencephalogram signal, and reducing the frequency of the processed electroencephalogram signal from the original frequency to the target frequency to obtain an electroencephalogram signal with the target frequency;
performing continuous wavelet transformation on the electroencephalogram signals of the target frequency, extracting electroencephalogram signal power spectrum energy values in each frequency range at each time point in a preset frequency interval in preset time according to preset time and preset frequency step length to obtain target electroencephalogram characteristics of preset number, wherein the electroencephalogram signal power spectrum energy values are calculated by adopting the following third calculation formula:
wherein a, b represent parameter dimensions, ω 0 Represents the wavelet center frequency, f (t) represents the first noise reduction signal and the second noise reduction signal, t represents the time t, i is
P f，t The power spectrum energy value of the brain electrical signal with frequency f and time t is shown.
In one embodiment, preferably, the training process of the fatigue recognition model includes:
collecting fatigue data of a target number, wherein the fatigue data comprises electroencephalogram characteristic data and corresponding cortisol data;
dividing the fatigue data into high fatigue degree, medium fatigue degree and low fatigue degree according to the cortisol content, and obtaining the divided fatigue data;
training the divided fatigue data and a preset deep neural network model to obtain the fatigue identification model.
In one embodiment, preferably, the preset depth neural network model includes a first convolution layer, a second convolution layer, a third convolution layer, a first partial acceptance, a second partial acceptance, a third partial acceptance, a discard layer, and a full connection layer;
wherein the convolution kernel of the first convolution layer is 7*7, and the step length is 1; the convolution kernel of the second convolution layer is 1*1, and the step length is 1; the convolution kernel of the third convolution layer is 3*3, and the step length is 1;
the first partial acceptance comprises a first acceptance layer and a second acceptance layer, the second partial acceptance comprises a third acceptance layer, a fourth acceptance layer, a fifth acceptance layer, a sixth acceptance layer and a seventh acceptance layer, and the third partial acceptance comprises an eighth acceptance layer and a ninth acceptance layer;
the ninth acceptance layer is connected to the discarding layer, and the discarding layer performs data discarding according to a preset discarding rate;
the fully connected layer is connected to the discard layer.
In one embodiment, preferably, the output mode of the fatigue degree of the construction worker includes at least one of the following: graphic presentation and voice prompt.
In one embodiment, preferably, the apparatus further comprises:
and the sending module is used for sending reminding information to the intelligent safety helmet of the brain-computer interface when the fatigue degree of the construction worker is detected to be high, and the duration reaches the preset duration, so that the intelligent safety helmet of the brain-computer interface carries out alarm prompt according to the reminding information to prompt the construction worker to rest.
According to a third aspect of embodiments of the present disclosure, there is provided a safety monitoring and early warning device for a construction site, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to:
acquiring an electroencephalogram signal of a preset site of a constructor through an intelligent safety helmet with a brain-computer interface, wherein the preset site comprises a first site, a second site, a third site and a fourth site;
preprocessing the electroencephalogram signals of the preset sites to obtain processed electroencephalogram signals;
extracting target brain electrical characteristics from the processed brain electrical signals according to a preset time interval;
determining and outputting the fatigue degree of the construction worker according to the target brain electrical characteristics and a pre-trained fatigue recognition model, wherein the fatigue degree comprises: high fatigue, medium fatigue and low fatigue.
According to a fourth aspect of the present invention there is provided a computer readable storage medium having stored thereon computer instructions which when executed by a processor perform the steps of the method of any of the embodiments of the first aspect.
It is further understood that the term "plurality" in this disclosure means two or more, and other adjectives are similar thereto. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. The singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It is further understood that the terms "first," "second," and the like are used to describe various information, but such information should not be limited to these terms. These terms are only used to distinguish one type of information from another and do not denote a particular order or importance. Indeed, the expressions "first", "second", etc. may be used entirely interchangeably. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure.
It will be further understood that although operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A method for calculating a fatigue degree of a construction worker, comprising:
acquiring an electroencephalogram signal of a preset site of a constructor through an intelligent safety helmet with a brain-computer interface, wherein the preset site comprises a first site, a second site, a third site and a fourth site;
preprocessing the electroencephalogram signals of the preset sites to obtain processed electroencephalogram signals;
extracting target brain electrical characteristics from the processed brain electrical signals according to a preset time interval;
determining and outputting the fatigue degree of the construction worker according to the target brain electrical characteristics and a pre-trained fatigue recognition model, wherein the fatigue degree comprises: high fatigue, medium fatigue and low fatigue.
2. The method for calculating the fatigue degree of the construction worker according to claim 1, wherein preprocessing the electroencephalogram signal at the preset site to obtain a processed electroencephalogram signal, comprises:
performing data noise reduction processing on the electroencephalogram signals corresponding to the first position and the second position by using the electroencephalogram signals corresponding to the third position and the fourth position so as to obtain a first noise reduction signal corresponding to the first position and a second noise reduction signal corresponding to the second position;
wherein the first noise reduction signal is calculated using the following first calculation formula:
V fp1, noise reduction signal ＝V Fp1, original signal -（V T5 +V T6 ）/2；
Wherein V is Fp1, noise reduction signal Representing the first noise reduction signal, V Fp1, original signal Representing the brain electrical signal corresponding to the first locus, V T5 And V T6 Respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus;
calculating the second noise reduction signal using a second calculation formula:
V fp2, noise reduction signal ＝V Fp2, original signal -(V T5 +V T6 )/2；
Wherein V is Fp2, noise reduction signal Representing the second noise reduction signal, V Fp2, original signal Representing the brain electrical signal corresponding to the second position, V T5 And V T6 And respectively representing the electroencephalogram signals corresponding to the third locus and the fourth locus.
3. The method for calculating the fatigue degree of the construction worker according to claim 1, wherein extracting the target electroencephalogram feature from the processed electroencephalogram signal at a preset time interval comprises:
downsampling the processed electroencephalogram signal, and reducing the frequency of the processed electroencephalogram signal from the original frequency to the target frequency to obtain an electroencephalogram signal with the target frequency;
performing continuous wavelet transformation on the electroencephalogram signals of the target frequency, extracting electroencephalogram signal power spectrum energy values in each frequency range at each time point in a preset frequency interval in preset time according to preset time and preset frequency step length to obtain target electroencephalogram characteristics of preset number, wherein the electroencephalogram signal power spectrum energy values are calculated by adopting the following third calculation formula:
wherein a, b represent parameter dimensions, ω 0 Represents the wavelet center frequency, f (t) represents the first noise reduction signal and the second noise reduction signal, t represents the time t, i is
P f，t The power spectrum energy value of the brain electrical signal with frequency f and time t is shown.
4. The method for calculating the fatigue degree of the construction worker according to claim 1, wherein the training process of the fatigue recognition model includes:
collecting fatigue data of a target number, wherein the fatigue data comprises electroencephalogram characteristic data and corresponding cortisol data;
dividing the fatigue data into high fatigue degree, medium fatigue degree and low fatigue degree according to the cortisol content, and obtaining the divided fatigue data;
training the divided fatigue data and a preset deep neural network model to obtain the fatigue identification model.
5. The method for calculating the fatigue degree of the constructor according to claim 4, wherein the preset depth neural network model comprises a first convolution layer, a second convolution layer and a third convolution layer, a first partial indication, a second partial indication, a third partial indication, a discarding layer and a full connection layer;
wherein the convolution kernel of the first convolution layer is 7*7, and the step length is 1; the convolution kernel of the second convolution layer is 1*1, and the step length is 1; the convolution kernel of the third convolution layer is 3*3, and the step length is 1;
the first partial acceptance comprises a first acceptance layer and a second acceptance layer, the second partial acceptance comprises a third acceptance layer, a fourth acceptance layer, a fifth acceptance layer, a sixth acceptance layer and a seventh acceptance layer, and the third partial acceptance comprises an eighth acceptance layer and a ninth acceptance layer;
the ninth acceptance layer is connected to the discarding layer, and the paint layer performs data discarding according to a preset discarding rate;
the fully connected layer is connected to the discard layer.
6. The method for calculating the fatigue degree of a construction worker according to claim 1, characterized in that the method further comprises:
the output mode of the fatigue degree of the construction worker comprises at least one of the following steps: graphic presentation and voice prompt.
7. The method for calculating the fatigue degree of a construction worker according to claim 1, characterized in that the method further comprises:
when the fatigue degree of the construction worker is detected to be high, and the duration reaches the preset duration, reminding information is sent to the intelligent safety helmet of the brain-computer interface, so that the intelligent safety helmet of the brain-computer interface carries out alarm prompt according to the reminding information to prompt the construction worker to rest.
8. A construction worker's fatigue degree calculation device, characterized by comprising:
the acquisition module is used for acquiring brain-electrical signals of a preset site of a construction worker through the brain-computer interface intelligent safety helmet, wherein the preset site comprises a first site, a second site, a third site and a fourth site;
the preprocessing module is used for preprocessing the electroencephalogram signals of the preset sites to obtain processed electroencephalogram signals;
the extraction module is used for extracting target electroencephalogram characteristics from the processed electroencephalogram signals according to a preset time interval;
the determining module is used for determining and outputting the fatigue degree of the construction worker according to the target electroencephalogram characteristics and the pre-trained fatigue recognition model, wherein the fatigue degree comprises the following steps: high fatigue, medium fatigue and low fatigue.
9. A construction worker fatigue degree calculation device, characterized by comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to:
acquiring an electroencephalogram signal of a preset site of a constructor through an intelligent safety helmet with a brain-computer interface, wherein the preset site comprises a first site, a second site, a third site and a fourth site;
preprocessing the electroencephalogram signals of the preset sites to obtain processed electroencephalogram signals;
extracting target brain electrical characteristics from the processed brain electrical signals according to a preset time interval;
determining and outputting the fatigue degree of the construction worker according to the target brain electrical characteristics and a pre-trained fatigue recognition model, wherein the fatigue degree comprises: high fatigue, medium fatigue and low fatigue.
10. A computer readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310143622.9A CN116304563B (en) | 2023-02-09 | 2023-02-09 | Construction worker fatigue degree calculation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310143622.9A CN116304563B (en) | 2023-02-09 | 2023-02-09 | Construction worker fatigue degree calculation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116304563A true CN116304563A (en) | 2023-06-23 |
| CN116304563B CN116304563B (en) | 2024-02-06 |
Family
ID=86823220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310143622.9A Active CN116304563B (en) | 2023-02-09 | 2023-02-09 | Construction worker fatigue degree calculation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116304563B (en) |
Citations (6)
| 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 |
| CN110215206A (en) * | 2019-06-12 | 2019-09-10 | 中国科学院自动化研究所 | Stereoscopic display visual fatigue evaluation method, system, device based on EEG signals |
| CN110772268A (en) * | 2019-11-01 | 2020-02-11 | 哈尔滨理工大学 | Multimode electroencephalogram signal and 1DCNN migration driving fatigue state identification method |
| CN111329497A (en) * | 2020-02-21 | 2020-06-26 | 华南理工大学 | Wearable fatigue driving monitoring system and method based on forehead electroencephalogram signals |
| CN113679396A (en) * | 2021-08-13 | 2021-11-23 | 北京脑陆科技有限公司 | Training method, device, terminal and medium for fatigue recognition model |
| US20220015685A1 (en) * | 2020-07-14 | 2022-01-20 | Dhiraj JEYANANDARAJAN | Systems and methods for brain state capture and referencing |
-
2023
- 2023-02-09 CN CN202310143622.9A patent/CN116304563B/en active Active
Patent Citations (6)
| 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 |
| CN110215206A (en) * | 2019-06-12 | 2019-09-10 | 中国科学院自动化研究所 | Stereoscopic display visual fatigue evaluation method, system, device based on EEG signals |
| CN110772268A (en) * | 2019-11-01 | 2020-02-11 | 哈尔滨理工大学 | Multimode electroencephalogram signal and 1DCNN migration driving fatigue state identification method |
| CN111329497A (en) * | 2020-02-21 | 2020-06-26 | 华南理工大学 | Wearable fatigue driving monitoring system and method based on forehead electroencephalogram signals |
| US20220015685A1 (en) * | 2020-07-14 | 2022-01-20 | Dhiraj JEYANANDARAJAN | Systems and methods for brain state capture and referencing |
| CN113679396A (en) * | 2021-08-13 | 2021-11-23 | 北京脑陆科技有限公司 | Training method, device, terminal and medium for fatigue recognition model |
Non-Patent Citations (3)
| Title |
|---|
| XIAOWEI LI ET AL.: "EEG-based mild depressive detection using feature selection methods and classifiers", COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, vol. 136, pages 151 - 161, XP029753508, DOI: 10.1016/j.cmpb.2016.08.010 * |
| 姚迪: "基于卷积神经网络的高铁司机脑电疲劳检测研究", 中国优秀硕士学位论文全文数据库工程科技Ⅱ辑, vol. 2021, no. 07, pages 033 - 525 * |
| 杜云梅 等: "基于深度卷积神经网络的脑电图异常检测", 华南师范大学学报(自然科学版), no. 02, pages 122 - 128 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116304563B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fu et al. | Dynamic driver fatigue detection using hidden Markov model in real driving condition | |
| Begum | Intelligent driver monitoring systems based on physiological sensor signals: A review | |
| Kumar et al. | Characterization of coronary artery disease using flexible analytic wavelet transform applied on ECG signals | |
| CA3003765C (en) | Drowsiness onset detection | |
| Rigas et al. | Towards Driver's State Recognition on Real Driving Conditions. | |
| Sahayadhas et al. | Physiological signal based detection of driver hypovigilance using higher order spectra | |
| CN106691474A (en) | Brain electrical signal and physiological signal fused fatigue detection system | |
| CN110151203B (en) | Fatigue driving identification method based on multistage avalanche convolution recursive network EEG analysis | |
| CN110123314A (en) | Judge that brain is absorbed in the method for relaxation state based on EEG signals | |
| Yu et al. | Epileptic seizure prediction based on local mean decomposition and deep convolutional neural network | |
| Anilkumar et al. | Design of drowsiness, heart beat detection system and alertness indicator for driver safety | |
| US10877444B1 (en) | System and method for biofeedback including relevance assessment | |
| Hayawi et al. | Driver's drowsiness monitoring and alarming auto-system based on EOG signals | |
| CN106913333B (en) | Method for selecting sensitivity characteristic index of continuous attention level | |
| Dehzangi et al. | Towards multi-modal wearable driver monitoring: Impact of road condition on driver distraction | |
| CN116138745B (en) | Sleep respiration monitoring method and device integrating millimeter wave radar and blood oxygen data | |
| Ke et al. | Drowsiness detection system using heartbeat rate in android-based handheld devices | |
| JP6468637B2 (en) | Sleepiness estimation apparatus and sleepiness estimation program | |
| Sahayadhas et al. | Electromyogram signal based hypovigilance detection | |
| CN116304563B (en) | Construction worker fatigue degree calculation method and system | |
| CN113576495A (en) | Motor imagery evaluation method combined with EEG data quality | |
| Albalawi et al. | Single-channel real-time drowsiness detection based on electroencephalography | |
| CN115713754B (en) | Staged hierarchical intervention method and system based on driver fear emotion recognition | |
| Krishnan et al. | Drowsiness detection using band power and log energy entropy features based on EEG signals | |
| JP6468635B2 (en) | Sleepiness estimation apparatus and sleepiness estimation program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |