CN107967942B - Children autism spectrum disorder analysis system based on near-infrared brain imaging map features - Google Patents
Children autism spectrum disorder analysis system based on near-infrared brain imaging map features Download PDFInfo
- Publication number
- CN107967942B CN107967942B CN201711330861.6A CN201711330861A CN107967942B CN 107967942 B CN107967942 B CN 107967942B CN 201711330861 A CN201711330861 A CN 201711330861A CN 107967942 B CN107967942 B CN 107967942B
- Authority
- CN
- China
- Prior art keywords
- autism spectrum
- spectrum disorder
- children
- brain imaging
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000002610 neuroimaging Methods 0.000 title claims abstract description 41
- 208000029560 autism spectrum disease Diseases 0.000 title claims abstract description 40
- 238000004458 analytical method Methods 0.000 title claims description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 13
- 230000000284 resting effect Effects 0.000 claims abstract description 13
- 238000001228 spectrum Methods 0.000 claims abstract description 13
- 206010003805 Autism Diseases 0.000 claims abstract description 12
- 208000020706 Autistic disease Diseases 0.000 claims abstract description 12
- 238000005516 engineering process Methods 0.000 claims abstract description 12
- 238000012360 testing method Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 12
- 102000001554 Hemoglobins Human genes 0.000 claims abstract description 9
- 108010054147 Hemoglobins Proteins 0.000 claims abstract description 9
- 238000003745 diagnosis Methods 0.000 claims abstract description 8
- 238000013528 artificial neural network Methods 0.000 claims abstract description 7
- 238000013461 design Methods 0.000 claims abstract description 7
- 230000008859 change Effects 0.000 claims abstract description 3
- 210000004556 brain Anatomy 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 10
- 238000007405 data analysis Methods 0.000 claims description 9
- 210000001652 frontal lobe Anatomy 0.000 claims description 8
- 210000000869 occipital lobe Anatomy 0.000 claims description 8
- 210000003478 temporal lobe Anatomy 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 3
- 230000005284 excitation Effects 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 5
- 238000002329 infrared spectrum Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000004886 head movement Effects 0.000 description 2
- 230000004630 mental health Effects 0.000 description 2
- 238000003012 network analysis Methods 0.000 description 2
- 230000001123 neurodevelopmental effect Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 208000012239 Developmental disease Diseases 0.000 description 1
- 238000004497 NIR spectroscopy Methods 0.000 description 1
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 208000030251 communication disease Diseases 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002599 functional magnetic resonance imaging Methods 0.000 description 1
- 230000013016 learning Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000926 neurological effect Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000003997 social interaction Effects 0.000 description 1
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a system for analyzing childhood autism spectrum disorder based on near-infrared brain imaging atlas characteristics, which comprises: the method comprises the following steps that firstly, through an annular near-infrared brain imaging acquisition scheme, resting state near-infrared brain imaging data of large-scale normal children and autism spectrum disorder children are respectively acquired; step two, calculating phase synchronization coefficients of hemoglobin change horizontal time sequences of any two channels, and establishing a synchronization network; thirdly, calculating network characteristic parameters of the complex networks of the normal children and the autism spectrum disorder children, and further obtaining a training data sample set and a test sample set; a fourth step, obtaining a pattern classifier according to a standard forward neural network structure design technology for a training data sample set and a test sample set of normal children and autism spectrum disorder children; and fifthly, finally realizing a diagnosis result of the risk of the child suffering from the autism spectrum disorder by using the pattern classifier obtained in the fourth step.
Description
Technical Field
The invention relates to a system for analyzing childhood autism spectrum disorder based on near-infrared brain imaging atlas characteristics, and belongs to the technical field of medical diagnosis.
Background
Autism Spectrum Disorder (ASD) is a group of neurological developmental disorders characterized primarily by social disorders, language communication disorders, a narrow range of interest or activity, and repetitive stereotypical behavior. ASD has become a serious challenge in the world public health and education fields, seriously harms physical and mental health of children, can cause lifelong disability if recovery cannot be obtained, affects physical and mental health, social interaction, learning, living and employment of patients throughout the life, and also causes serious burden to families and society.
Revealing neurodevelopmental characteristics of autism spectrum disorder children is a great challenge for researchers because: first, these children are often reluctant to lie in a claustrophobic space to receive brain image scans, and thus can experience excessive head movements that can result in data acquisition failures; second, such children often have varying degrees of language, cognitive, and social skills deficits such that they cannot effectively coordinate and complete the testing tasks designed by the experimenter, and are further affected by performance scores and therefore cannot match normal control groups.
In the last two decades, the emergence of a new imaging technology, namely a near infrared spectrum imaging technology, provides a new opportunity for researchers to explore clinical neurodevelopmental mechanisms. The near infrared spectrum imaging technology is a non-invasive brain imaging technology for detecting the change of the cerebral cortex hemoglobin concentration by means of near infrared light, is not very sensitive to the head movement of an experimental participant, can acquire data under the motion condition and in an open space, and has higher time resolution, lower cost and safe and portable use compared with functional nuclear magnetic resonance (fMRI), and has better space resolution compared with electroencephalogram (EEG). Therefore, the near infrared spectrum imaging technology is considered to be an effective brain imaging technology for studying children and clinical population. Therefore, some researchers have recently begun exploring the use of near infrared spectroscopy imaging techniques to analyze features of the brain functional network of autistic patients. However, even so, the identification of childhood autism spectrum disorders is still currently in the theoretical analysis stage and no conclusion is available for clinical application.
The invention is established on the basis of brain network analysis and pattern recognition theory, utilizes a near-infrared brain imaging technology suitable for autism spectrum disorder children, obtains large-scale normal children and autism spectrum disorder children to respectively acquire resting state near-infrared brain imaging data through an annular near-infrared brain imaging acquisition scheme covering 44 channels of six brain areas of frontal lobe, temporal lobe and occipital lobe on two sides, establishes a network characteristic parameter and a pattern classifier suitable for autism spectrum disorder children identification, and assists medical workers to complete primary diagnosis of the autism spectrum disorder of the children.
Disclosure of Invention
The invention provides a children autism spectrum disorder analysis system based on near-infrared brain imaging atlas characteristics, which assists medical workers in completing primary diagnosis of children autism spectrum disorder.
Specifically, in order to achieve the purpose, the invention discloses a system for analyzing the childhood autism spectrum disorder based on the near-infrared brain imaging spectrum characteristics, which comprises the following modules:
a data acquisition module: specifically, as follows, the following description will be given,
the method comprises the following steps that firstly, through an annular near-infrared brain imaging acquisition scheme, resting state near-infrared brain imaging data of large-scale normal children and autism spectrum disorder children are respectively acquired;
secondly, establishing a complex network for resting state image data of normal children and autism spectrum disorder children;
a data analysis module: the third step, respectively calculating network characteristic parameters of the complex networks of the two groups of normal children and autism spectrum disorder children, and further obtaining a training data sample set and a test sample set;
a fourth step, obtaining a pattern classifier according to a standard forward neural network structure design technology for a training data sample set and a test sample set of normal children and autism spectrum disorder children;
a data judgment module: and in the fifth step, the pattern classifier obtained in the third step is utilized to finally realize the diagnosis result of the risk of the child suffering from the autism spectrum disorder.
Furthermore, in the first step of the data acquisition module, the annular near-infrared brain imaging acquisition scheme is that the positions of a light source and a detector of the measuring cap are in annular layout in comparison with the position of an international 10-20 system, and six brain areas of the frontal lobe, the temporal lobe and the occipital lobe on two sides are respectively covered; measuring the forward most light source and receiver of the cap at a position adjacent to FP1 and FP2, the rearward most light source and receiver at a position adjacent to PO7 and PO8, the left most light source and receiver at a position adjacent to T3, and the right most light source and receiver at a position adjacent to T4; the distance between each pair of adjacent light sources and receivers is about 3 cm.
Further, the resting state near-infrared brain imaging data in the first step in the data acquisition module is obtained by the annular near-infrared brain imaging acquisition scheme, and a time sequence of 44 channel hemoglobin variation levels of six brain areas, namely, frontal lobe, temporal lobe and occipital lobe, of the two sides of the tested subject in the resting state is obtained.
Further, the complex network in the second step is a phase synchronization network.
Further, the phase synchronization network is constructed by calculating a phase synchronization coefficient of any two-channel time series of hemoglobin variation levels.
Further, the complex network characteristic parameters in the third step in the data analysis module mainly include global network efficiency, local network efficiency, average clustering coefficient, average path length, betweenness, centrality, and modularization attributes.
Further, the input vector of the training data sample set and the test sample set in the third step is composed of seven variables of global network efficiency, local network efficiency, average clustering coefficient, average path length, betweenness, centrality and modularization attribute, and the output result is {0, 1} data, where 0 represents data of a normal child and 1 represents data of a child with autism spectrum disorder.
Further, the mode classifier in the fourth step of the data judgment module adopts a standardized forward neural network structure design algorithm to determine structural information such as the number of hidden layer neurons, the weight and the threshold of the input layer, the weight and the threshold of the hidden layer, the weight and the threshold of the output layer and the like.
Further, the hidden excitation function of the pattern classifier is a Sigmoid function
The output layer activation function is a linear function f (x) ═ x; the functional mapping of the pattern classifier can thus be expressed as: out is W2*f(W1*in+B1)+B2Where out is the output of the functional mapping of the pattern classifier, in is the input of the functional mapping of the pattern classifier, W1Is hidden layer weight value W2Is the weight of the output layer, B1Is hidden layer threshold value, B2Is the output layer threshold.
The invention has the beneficial effects that: the invention is established on the basis of brain network analysis and pattern recognition theory, utilizes a near-infrared brain imaging technology suitable for autism spectrum disorder children, obtains large-scale normal children and autism spectrum disorder children to respectively acquire resting state near-infrared brain imaging data through an annular near-infrared brain imaging acquisition scheme covering 44 channels of six brain areas of frontal lobe, temporal lobe and occipital lobe on two sides, establishes a network characteristic parameter and a pattern classifier suitable for autism spectrum disorder children identification, and can provide more objective image indexes and assist medical workers to finish primary diagnosis of autism spectrum disorder of children compared with the existing method mainly depending on questionnaires or behavior observation.
Drawings
FIG. 1 is a flow chart of the steps of the overall system implementation of the present invention;
FIG. 2 is a position diagram of an annular near-infrared brain imaging acquisition light source and detector of the present invention;
FIG. 3 is a flow chart of the construction of the phase synchronization network according to the present invention;
FIG. 4 is a block diagram of a training architecture of the pattern classifier of the present invention.
Detailed Description
The technical solution proposed by the present invention is further explained in detail below with reference to the accompanying drawings. As shown in fig. 1, the system for analyzing childhood autism spectrum disorder based on near-infrared brain imaging profile features provided by the invention comprises the following modules:
a data acquisition module: specifically, as follows, the following description will be given,
the first step S1, collecting resting state near-infrared brain imaging data of large-scale normal children and autism spectrum disorder children respectively through a ring-shaped near-infrared brain imaging collection scheme;
a second step S2, establishing a complex network for the resting state image data of normal children and autism spectrum disorder children;
a data analysis module: specifically, as follows, the following description will be given,
step S3, respectively calculating network characteristic parameters of the complex networks of the normal children and the autism spectrum disorder children, and further obtaining a training data sample set and a test sample set;
a fourth step S4, obtaining a pattern classifier for the training data sample set and the test sample set of the normal children and the autism spectrum disorder children according to a standard forward neural network structure design technology;
a data judgment module: specifically, as follows, the following description will be given,
in the fifth step S5, the pattern classifier obtained in the fourth step S4 is used to finally realize the diagnosis result of the risk of the childhood suffering from autism spectrum disorder.
In the first step S1 in the data acquisition module, the annular near-infrared brain imaging acquisition scheme is that the positions of the light source and the detector of the measurement cap are in an annular layout (as shown in fig. 2) in comparison with the position of the international 10-20 system, and the six brain areas of the frontal lobe, the temporal lobe and the occipital lobe on two sides are covered respectively; measuring the forward most light source and receiver of the cap at a position adjacent to FP1 and FP2, the rearward most light source and receiver at a position adjacent to PO7 and PO8, the left most light source and receiver at a position adjacent to T3, and the right most light source and receiver at a position adjacent to T4; the distance between each pair of adjacent light sources and receivers is about 3 cm.
In the first step S1 in the data acquisition module, the resting-state near-infrared brain imaging data is obtained by the annular near-infrared brain imaging acquisition scheme, and a time series of 44 channel hemoglobin variation levels of the six brain areas, namely the frontal lobe, the temporal lobe and the occipital lobe, of the two sides of the tested subject in the resting state is obtained.
The complex network in the second step S2 is a phase synchronization network.
The phase synchronization network is constructed according to the principle shown in fig. 3, i.e. by calculating the phase synchronization coefficient of any two-channel time series of hemoglobin variation levels.
The complex network characteristic parameters in the third step S3 in the data analysis module mainly include global network efficiency, local network efficiency, average clustering coefficient, average path length, betweenness, centrality, and modularization attribute.
In the third step S3 in the data analysis module, the input vector of the training data sample set and the test sample set is composed of seven variables, i.e., global network efficiency, local network efficiency, average clustering coefficient, average path length, betweenness, centrality, and modularization property, and the output result is {0, 1} data, where 0 represents data of a normal child and 1 represents data of a child with autism spectrum disorder.
The mode classifier in the fourth step S4 determines structural information such as the number of hidden layer neurons, the weight and threshold of the input layer, the weight and threshold of the hidden layer, the weight and threshold of the output layer, and the like, by using a standardized forward neural network structural design algorithm according to the principle shown in fig. 4.
The hidden excitation function of the pattern classifier is a Sigmoid function
The output layer activation function is a linear function f (x) ═ x; the functional mapping of the pattern classifier can thus be expressed as: out is W2*f(W1*in+B1)+B2Wherein out is the output of the function mapping relation of the pattern classifier (the output result of the invention is {0, 1} data, where 0 represents the data of normal children and 1 represents the data of autism spectrum disorder children), in is the input of the function mapping relation of the pattern classifier (the invention is composed of seven variables of global network efficiency, local network efficiency, average clustering coefficient, average path length, betweenness, centrality and modularization property), and W is the input of the function mapping relation of the pattern classifier1Is hidden layer weight value W2Is the weight of the output layer, B1Is hidden layer threshold value, B2Is the output layer threshold.
The present invention can be realized in light of the above.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A children autism spectrum disorder analysis system based on near-infrared brain imaging atlas characteristics is characterized by comprising the following modules: a data acquisition module, a data analysis module and a data judgment module,
a data acquisition module: the first step is that resting state near-infrared brain imaging data of large-scale normal children and autism spectrum disorder children are respectively acquired through a ring-shaped near-infrared brain imaging acquisition scheme; secondly, establishing a complex network for resting state image data of normal children and autism spectrum disorder children;
a data analysis module: the third step is used for calculating network characteristic parameters of complex networks of two groups of normal children and autism spectrum disorder children respectively and further obtaining a training data sample set and a test sample set; a fourth step, obtaining a pattern classifier according to a standard forward neural network structure design technology for a training data sample set and a test sample set of normal children and autism spectrum disorder children;
a data judgment module: for executing a fifth step of finally obtaining a diagnosis result of the child's risk of suffering from autism spectrum disorder using the pattern classifier obtained in the third step;
the annular near-infrared brain imaging acquisition scheme in the first step of the data acquisition module is that the positions of a light source and a detector of a measuring cap are in annular layout in comparison with the position of an international 10-20 system, and six brain areas of the frontal lobe, the temporal lobe and the occipital lobe on two sides are covered respectively; measuring the forward most light source and receiver of the cap at a position adjacent to FP1 and FP2, the rearward most light source and receiver at a position adjacent to PO7 and PO8, the left most light source and receiver at a position adjacent to T3, and the right most light source and receiver at a position adjacent to T4; the distance between each pair of adjacent light sources and receivers is about 3 cm.
2. The system for analyzing the childhood autism spectrum disorder based on the near-infrared brain imaging profile characteristics of claim 1, wherein: in the first step of the data acquisition module, the resting-state near-infrared brain imaging data is obtained by the annular near-infrared brain imaging acquisition scheme, and a time sequence of 44 channel hemoglobin change levels of six brain areas, namely the frontal lobe, the temporal lobe and the occipital lobe, of the tested child in the resting state is obtained.
3. The system for analyzing the childhood autism spectrum disorder based on the near-infrared brain imaging profile characteristics according to claim 2, wherein: the complex network in the second step in the data acquisition module is a phase synchronization network.
4. The system for analyzing the childhood autism spectrum disorder based on the near-infrared brain imaging profile characteristics of claim 3, wherein: the phase synchronization network is constructed by calculating the phase synchronization coefficient of any two-channel hemoglobin variation level time sequence, and the problems that the current common complex network construction method based on the correlation coefficient is easily influenced by the amplitude of the channel hemoglobin variation level and a negative correlation coefficient possibly exists are overcome.
5. The system for analyzing the childhood autism spectrum disorder based on the near-infrared brain imaging profile characteristics according to claim 4, wherein: the complex network characteristic parameters in the third step in the data analysis module mainly comprise global network efficiency, local network efficiency, average clustering coefficient, average path length, betweenness, centrality and modularization attributes.
6. The system for analyzing the childhood autism spectrum disorder based on the near-infrared brain imaging profile characteristics of claim 5, wherein: in the third step of the data analysis module, input vectors of the training data sample set and the testing sample set are composed of seven variables of global network efficiency, local network efficiency, average clustering coefficient, average path length, betweenness, centrality and modularization attribute, and output results are {0, 1} data, wherein 0 represents data of normal children and 1 represents data of autism spectrum disorder children.
7. The system for analyzing the childhood autism spectrum disorder based on the near-infrared brain imaging profile characteristics of claim 6, wherein: and in the fourth step, the mode classifier adopts a standardized forward neural network structure design algorithm to determine the number of hidden layer neurons, the input layer weight and threshold, the hidden layer weight and threshold and the output layer weight and threshold.
8. The system for analyzing the childhood autism spectrum disorder based on the near-infrared brain imaging profile characteristics of claim 7, wherein: the hidden excitation function of the pattern classifier is a Sigmoid function
The output layer activation function is a linear function f (x) ═ x; the functional mapping of the pattern classifier can thus be expressed as: out is W2*f(W1*in+B1)+B2Where out is the output of the functional mapping of the pattern classifier, in is the input of the functional mapping of the pattern classifier, W1Is hidden layer weight value W2Is the weight of the output layer, B1Is hidden layer threshold, B2Is the output layer threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711330861.6A CN107967942B (en) | 2017-12-13 | 2017-12-13 | Children autism spectrum disorder analysis system based on near-infrared brain imaging map features |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711330861.6A CN107967942B (en) | 2017-12-13 | 2017-12-13 | Children autism spectrum disorder analysis system based on near-infrared brain imaging map features |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107967942A CN107967942A (en) | 2018-04-27 |
| CN107967942B true CN107967942B (en) | 2021-10-01 |
Family
ID=61995137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711330861.6A Active CN107967942B (en) | 2017-12-13 | 2017-12-13 | Children autism spectrum disorder analysis system based on near-infrared brain imaging map features |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107967942B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111009321A (en) * | 2019-08-14 | 2020-04-14 | 电子科技大学 | Application method of machine learning classification model in juvenile autism auxiliary diagnosis |
| CN110473635B (en) * | 2019-08-14 | 2023-02-28 | 电子科技大学 | Analysis method of relation model of teenager brain structure network and brain function network |
| CN111084610A (en) * | 2019-12-20 | 2020-05-01 | 东南大学 | Time-space characteristic analysis method for near-infrared brain imaging signals of autism children |
| CN112545503B (en) * | 2020-12-09 | 2021-09-07 | 中南民族大学 | Ice drug addict detection method and system based on multichannel fNIRS signals |
| CN113889274B (en) * | 2021-10-11 | 2022-09-13 | 中山大学 | Method and device for constructing risk prediction model of autism spectrum disorder |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318253A (en) * | 2014-11-11 | 2015-01-28 | 东南大学 | MOOC online learning pattern recognition system and method |
| CN105559805A (en) * | 2015-12-31 | 2016-05-11 | 四川大学 | Diagnosis assessment system for post-traumatic stress disorder |
-
2017
- 2017-12-13 CN CN201711330861.6A patent/CN107967942B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318253A (en) * | 2014-11-11 | 2015-01-28 | 东南大学 | MOOC online learning pattern recognition system and method |
| CN105559805A (en) * | 2015-12-31 | 2016-05-11 | 四川大学 | Diagnosis assessment system for post-traumatic stress disorder |
Non-Patent Citations (1)
| Title |
|---|
| 孤独症谱系障碍儿童近红外信号的空间复杂性分析;贾会宾等;《第二十届全国心理学学术会议--心理学与国民心理健康摘要集》;20171103;660-661 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107967942A (en) | 2018-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107967942B (en) | Children autism spectrum disorder analysis system based on near-infrared brain imaging map features | |
| Gao et al. | Complex networks and deep learning for EEG signal analysis | |
| CN106886792B (en) | Electroencephalogram emotion recognition method for constructing multi-classifier fusion model based on layering mechanism | |
| Kropotov | Functional neuromarkers for psychiatry: Applications for diagnosis and treatment | |
| Yang et al. | A complex network-based broad learning system for detecting driver fatigue from EEG signals | |
| KR20190128978A (en) | Method for estimating human emotions using deep psychological affect network and system therefor | |
| Miller et al. | Higher dimensional analysis shows reduced dynamism of time-varying network connectivity in schizophrenia patients | |
| Lu et al. | XGBoost algorithm-based monitoring model for urban driving stress: Combining driving behaviour, driving environment, and route familiarity | |
| Peng et al. | 3D-STCNN: Spatiotemporal Convolutional Neural Network based on EEG 3D features for detecting driving fatigue | |
| CN115553752A (en) | Brain dysfunction auxiliary evaluation method based on multi-modal data fusion | |
| Wang et al. | Detection of driver stress in real-world driving environment using physiological signals | |
| Arif et al. | Vector phase analysis approach for sleep stage classification: A functional near-infrared spectroscopy-based passive brain–computer interface | |
| Tan et al. | Motion sickness detection for intelligent vehicles: A wearable-device-based approach | |
| Dhanapal et al. | Electroencephalogram classification using various artificial neural networks | |
| CN115659207A (en) | Electroencephalogram emotion recognition method and system | |
| Wang et al. | Taking a deeper look at the brain: predicting visual perceptual and working memory load from high-density fNIRS data | |
| Ardito et al. | Brain computer interface: Deep learning approach to predict human emotion recognition | |
| Zhang et al. | Predicting the symptom severity in autism spectrum disorder based on EEG metrics | |
| Manganas et al. | A comparative survey on simultaneous EEG-fMRI methodologies | |
| Yang et al. | Three-Stream Convolutional Neural Network for Depression Detection with Ocular Imaging | |
| Liu et al. | fNIRS feature extraction and classification in grip-force tasks | |
| CN110363242B (en) | Brain consciousness multi-classification method and system based on support vector machine | |
| Menagadevi et al. | Resting‐State fMRI: Large Data Analysis in Neuroimaging | |
| Li et al. | An EEG-based Brain Cognitive Dynamic Recognition Network for representations of brain fatigue | |
| Zhang et al. | Construction of the brain-inspired computing model verified by spatiotemporal correspondence between the hierarchical computation of the model and the complex multi-stage processing of the human brain during facial expression recognition |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231016 Address after: Room 802-23024, Information Building, No. 13 Linyin North Street, Pinggu District, Beijing, 101299 Patentee after: Beijing Hongsu Cultural Development Co.,Ltd. Address before: 210096, No. four archway, Xuanwu District, Jiangsu, Nanjing 2 Patentee before: SOUTHEAST University |