CN109567818B - Hemoglobin information-based method for identifying multiple walking gait adjustment intents - Google Patents
Hemoglobin information-based method for identifying multiple walking gait adjustment intents Download PDFInfo
- Publication number
- CN109567818B CN109567818B CN201811383174.5A CN201811383174A CN109567818B CN 109567818 B CN109567818 B CN 109567818B CN 201811383174 A CN201811383174 A CN 201811383174A CN 109567818 B CN109567818 B CN 109567818B
- Authority
- CN
- China
- Prior art keywords
- brain
- walking gait
- hemoglobin
- adjustment
- gait adjustment
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
-
- 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
Abstract
The invention discloses a method for identifying multiple walking gait adjustment intents based on hemoglobin information. The invention discloses a method for identifying multiple walking gait adjustment intentions based on hemoglobin information, which is characterized by comprising the following steps of: preprocessing data of the recorded brain cortex hemoglobin concentration at the walking gait adjusting moment; the recorded brain cortex hemoglobin concentration at the walking gait adjusting moment is that a subject completes a corresponding walking gait adjusting task in a fixed area by applying a near infrared spectroscopy brain imaging technology (NIRS) to perform a test experiment; "obtained; for the preprocessed cerebral cortex hemoglobin information, carrying out corresponding channel division according to the distribution of the brain functional regions, and calculating and extracting relevant parameters as features; and applying a pattern recognition algorithm to establish four detection models of gait adjustment intentions. Has the advantages that: the invention is simple and convenient to test by applying the near infrared spectrum brain imaging technology.
Description
Technical Field
The invention relates to the field of intelligent walking aid and rehabilitation training, in particular to a method for identifying multiple walking gait adjustment intentions based on hemoglobin information.
Background
In recent years, more and more people suffer from the suffering of motor dysfunction. These people are the old with inconvenient legs and feet, or the disabled after accidents, diseases and natural disasters. Therefore, more and more researchers are working on developing walking aids or rehabilitation training devices to help these people recover their mobility. The brain-computer interface is a technology with a prospect and plays a wide and profound role in the field of rehabilitation. Through brain-computer interface technology, the spontaneous movement intentions of the brain of a user can be decoded, and then the spontaneous movement intentions are used for controlling external equipment to help the user train and recover the motor ability. Therefore, for the specific groups with lower limb movement dysfunction, the walking aid equipment developed based on the brain-computer interface technology can better make up the defects of the walking aid equipment in the current market and meet the urgent needs of the lower limb movement dysfunction people.
Lower limb movements tend to have greater amplitude of movement relative to upper limb movements and are subject to more environmental factors, particularly the walking movement of the lower limbs. Such a movement may make the brain signals acquired by some techniques unstable or even fail, and cannot be applied to practical situations. Such as electroencephalogram (EEG), Magnetoencephalography (MEG), functional magnetic resonance imaging (fMRI), etc. These techniques often require a stable testing environment and the equipment is too bulky to move in response to the user walking. Although some studies have been made to study the state of the brain while walking using the above-mentioned techniques, these studies are performed on a treadmill, which is not in accordance with the actual daily situation. Fortunately, this can be effectively applied by near infrared brain imaging (fNIRS). Due to the portability of fNIRS and its low sensitivity to the environment, in practical applications, users can walk long distances in the natural environment, carrying the fNIRS device, and simultaneously acquire their brain hemoglobin information while exercising. Therefore, the brain-computer interface technology based on fN irs is the best choice for studying the spontaneous gait adjustment intention during walking.
The efforts of spontaneous intention adjustment based on brain-computer interface technology research on the global scale are not much at present, and most of the efforts are based on preliminary stages. And in many studies, the main focus is on studying the spontaneous adjustment intentions from the resting state to the moving state, such as from rest to reaching, from rest to stepping down, etc. Although these studies have achieved some success, in real-life everyday situations, the user's voluntary adjustment intent is often not from rest to motion, but from one state of motion to another. Therefore, in order to pay attention to its utility, the spontaneous gait adjustment intention studied is a spontaneous adjustment intention from one gait to another.
The traditional technology has the following technical problems:
however, there is another practical difficulty in how to put the established detection model of spontaneous modulation intention into practice. In practical application, a user needs to perform a corresponding test in advance to acquire brain signals for decoding and modeling. This requires a lot of preparation time and can cause discontent mood for use. Therefore, decoding modeling based on existing user data and then testing directly for new users gives results, which is the best solution. Such a method is called Inter-BCI. However, the model established in this way is often less accurate than the former.
Disclosure of Invention
The invention aims to provide a method for identifying various walking gait adjustment intents based on hemoglobin information so as to achieve identification of walking gait adjustment, wherein the method comprises four gait adjustment states of pace increase, pace decrease, step length increase and step length decrease respectively, and the purpose of laying a foundation for realizing an intelligent rehabilitation medical auxiliary means based on a brain-computer interface technology is achieved.
In order to solve the above technical problem, the present invention provides a method for identifying a plurality of walking gait adjustment intents based on hemoglobin information, comprising:
preprocessing data of the recorded brain cortex hemoglobin concentration at the walking gait adjusting moment; the recorded brain cortex hemoglobin concentration at the walking gait adjusting moment is that a subject completes a corresponding walking gait adjusting task in a fixed area by applying a near infrared spectroscopy brain imaging technology (NIRS) to perform a test experiment; "obtained;
for the preprocessed cerebral cortex hemoglobin information, carrying out corresponding channel division according to the distribution of the brain functional regions, and calculating and extracting relevant parameters as features;
and applying a pattern recognition algorithm to establish four detection models of gait adjustment intentions.
In one embodiment, the test experiment is performed by using near infrared spectroscopy brain imaging (NIRS), and the subject completes the corresponding walking gait adjustment task in a fixed area; "the four gait adjustments of pace increase, pace decrease, stride increase and stride decrease were each performed 2 consecutive times with approximately 40 seconds of rest time from task to task.
In one embodiment, preprocessing data is performed on the recorded brain cortex hemoglobin concentration at the walking gait adjusting moment; the pretreatment method is specifically as follows:
a Chebyshev low-pass filter is adopted, the filtering cut-off frequency is 0.145Hz, high-frequency components in the signal are filtered, and frequency components of neuron activity are reserved;
and correcting the base line of the signal by adopting a morphological filtering method and combining a closed-open filtering method and a closed-open filtering method, and removing null shift.
In one embodiment, for preprocessed cerebral cortex hemoglobin information, corresponding channel division is carried out according to distribution of brain functional regions, and related parameters are calculated and extracted as features; and in the step III, performing related operations of characteristic engineering on the preprocessed cerebral cortex hemoglobin information.
In one embodiment, for preprocessed cerebral cortex hemoglobin information, corresponding channel division is carried out according to distribution of brain functional regions, and related parameters are calculated and extracted as features; the method specifically comprises the following steps:
firstly, calculating the information entropy of each channel, secondly, calculating the weight of each channel on the basis of the information entropy, and finally obtaining the blood oxygen concentration value of the corresponding region according to a weighted average method;
and calculating corresponding parameters of hemoglobin for each brain region, wherein the parameters comprise three major characteristics such as statistical characteristics, entropy characteristics and related characteristics of blood oxygen content, including mean value, energy, variance, range, information entropy and Pearson correlation coefficient, and the three major characteristics are used as original characteristic space.
In one embodiment, a pattern recognition algorithm is applied to establish four gait adjustment intention detection models. The method specifically comprises the following steps:
the Kolmogorov-Smirnov test is adopted to test whether the characteristics in different states are in the same distribution, if the characteristics are in the same distribution, the characteristics are in the state without the capability of distinguishing and should be removed, and the preliminary screening is carried out by the filtering type characteristic selection mode to obtain a characteristic subspace;
performing principal component analysis on the feature subspace, performing dimension reduction on the feature, and selecting principal components with the first 95% contribution rate as a feature dimension reduction space;
a stacking support vector machine model (stacking-SVMs) with two layers is realized by adopting a stacking ensemble learning algorithm (stacking); for the SVM model of the first layer, adopting an annealing genetic algorithm for a dimensionality reduction space, selecting 15 optimal groups of feature combinations, and constructing 15 groups of SVM models according to the 15 optimal groups of feature combinations; for the SVM model of the second layer, integrating the 15 SVM models of the previous layer by using an SVM as a base classifier Stacking algorithm, and still adopting an annealing genetic algorithm to optimize the hyperparameters of the SVM, such as penalty coefficients;
and detecting according to the established model to obtain a detection result.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods when executing the program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of any of the methods.
A processor for running a program, wherein the program when running performs any of the methods.
The invention has the beneficial effects that:
the invention uses near infrared spectrum brain imaging technology to carry out test experiment, has simple operation, easy carrying, low requirement on external environment, low sensitivity to environmental noise and no side effect on a subject. In the whole test process, a subject carries on the NIRS equipment, completes the corresponding gait adjustment task in a natural environment and collects corresponding brain hemoglobin information, so that the obtained state identification result is more favorable for being used for walking aid/rehabilitation equipment; the autonomous control of gait adjustment enables the biological information of the cerebral cortex to be acquired under the natural scene of cognitive activities, increases the actual application value of the recognition algorithm, and lays a foundation for realizing practical and feasible walking aid equipment based on the brain-computer interface technology;
the method of combining mathematical form filtering with Chebyshev low-pass filtering is adopted, so that the noise component of the low-frequency interesting frequency band can be effectively removed, the form characteristic of a low-frequency signal is kept, and the redundant ineffective high-frequency component can be filtered, so that the stability and effectiveness of the signal can be better ensured, and the subsequent identification can be well ensured;
the method adopts an entropy weight method to replace the traditional averaging method to calculate the hemoglobin concentration of the brain area, and the hemoglobin concentration value of the brain area calculated by the method has higher robustness and can effectively weaken the influence of individual difference;
the invention provides a two-layer SVM model based on a stacking integration algorithm, and the model has better generalization performance and higher recognition effect compared with a single SVM model, and can be effectively applied to the practical application of Inter-BCI.
Drawings
Fig. 1 is a timing chart of four gait adjustment states in the method for recognizing multiple walking gait adjustment intentions based on brain hemoglobin information according to the embodiment of the present invention.
Fig. 2 is a diagram showing brain cortex movement-related regions and test channel distribution in the method for identifying multiple walking gait adjustment intents based on cerebral hemoglobin information according to the embodiment of the present invention.
Fig. 3 is an effect diagram of a mathematical morphology filtering combined with chebyshev low-pass filtering method in the method for identifying multiple walking gait adjustment intents based on cerebral hemoglobin information disclosed in the embodiment of the present invention.
Fig. 4 is a pattern recognition frame diagram of a recognition method for multiple walking gait adjustment intents based on brain hemoglobin information according to an embodiment of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
Referring to fig. 1 to 4 and tables 1 to 3, a method for recognizing various gait adjustment intentions based on cerebral hemoglobin information includes the following steps:
(1) applying near infrared brain imaging (NIRS) technology to perform a test experiment, wherein the subject completes a corresponding walking gait adjustment task in a fixed area;
(2) preprocessing data of the recorded brain cortex hemoglobin concentration at the walking gait adjusting moment;
(3) for the preprocessed cerebral cortex hemoglobin information, carrying out corresponding channel division according to the distribution of the brain functional regions, and calculating and extracting relevant parameters as features;
(4) applying a pattern recognition algorithm to establish four detection models of gait adjustment intentions.
The invention applies near infrared spectrum brain imaging technology (NIRS) to carry out test experiments, has the advantages of simple and convenient operation, portability, low requirements on external environment, low sensitivity on environmental noise and no side effect on a test subject. In the whole test process, the subject carries the NIRS equipment and completes the corresponding gait adjustment task in a natural environment, so that the obtained state identification result is more favorable for being used for walking aid/rehabilitation equipment; the autonomous control of gait adjustment enables the biological information of the cerebral cortex to be acquired under the natural scene of cognitive activities, increases the actual application value of the recognition algorithm, and lays a foundation for realizing practical and feasible walking aid equipment based on the brain-computer interface technology.
Preferably, the four gait adjustments of pace increase, pace decrease, stride increase and stride decrease of step (1) are each performed 2 consecutive times with a task-to-task rest time of about 40 seconds.
Preferably, in the step (2), the acquired oxygenated hemoglobin parameters are preprocessed by a method of combining morphological filtering and Chebyshev filtering. Firstly, a Chebyshev low-pass filter is adopted, the filtering cut-off frequency is 0.145Hz, high-frequency components in signals are filtered, and frequency components of neuron activity are reserved. Then, a morphological filtering method and a closed-open filtering and closed-open filtering method are combined to correct the base line of the signal and remove the null shift. The method can better ensure the morphological characteristics of the low-frequency signal, effectively remove the noise component of the low-frequency interested frequency band, and simultaneously filter the redundant ineffective high-frequency component.
Preferably, the step (3) performs a correlation operation of feature engineering on the preprocessed brain cortex hemoglobin information.
Preferably, step (3) is carried out as follows:
and (3-1) performing corresponding channel division according to the distribution of the brain function areas, and calculating the blood oxygen concentration value of the corresponding area according to the channels contained in the brain function areas, wherein the value is calculated by an entropy weight method. The calculation steps are as follows, firstly, the information entropy of each channel is calculated, secondly, the weight of each channel is calculated on the basis of the information entropy, and finally, the blood oxygen concentration value of the corresponding area is obtained according to a weighted average method;
and (3-2) calculating corresponding parameters of hemoglobin for each brain region, wherein the parameters comprise three main characteristics such as statistical characteristics, entropy characteristics and related characteristics of blood oxygen content, including mean value, energy, variance, range, information entropy, Pearson correlation coefficient and the like. This is used as the original feature space.
Preferably, step (4) is carried out as follows:
(4-1) adopting Kolmogorov-Smirnov to test whether the characteristics in different states are in the same distribution, if the characteristics are in the same distribution, indicating that the characteristics are in a state of no ability to distinguish, and rejecting the characteristics, and carrying out primary screening by the filtering type characteristic selection mode to obtain a characteristic subspace.
And (4-2) carrying out principal component analysis on the feature subspace, carrying out dimension reduction on the features, and selecting principal components with the first 95% contribution rate as a dimension reduction space of the features.
And (4-3) realizing a two-layer stacking support vector machine model (stacking-SVMs) by adopting a stacking ensemble learning algorithm (stacking). For the SVM model of the first layer, for the dimensionality reduction space, an annealing genetic algorithm is adopted to select the optimal 15 groups of feature combinations, and 15 groups of SVM models are constructed according to the optimal 15 groups of feature combinations. And for the SVM model of the second layer, integrating the 15 SVM models of the previous layer by using an SVM as a base classifier Stacking algorithm, and still adopting an annealing genetic algorithm to optimize the hyperparameter, such as a penalty coefficient, of the SVM.
And (4-4) detecting according to the established model to obtain a detection result.
TABLE 1 sub-region channel numbering for further partitioning
| Name of subregion | Channel numbering | Name of subregion | Channel numbering |
| PFClu | (1，4，5) | PFClw | (3，5，8) |
| PFCll | (1，3，8) | PFCmw | (5，6，9) |
| PFClr | (1，5，8) | PFCwl1 | (5，8，9) |
| PFCul | (1，2，5) | PRFrw | (6，7，10) |
| PFCmu | (2，5，6) | PFCwr | (6，9，10) |
| PFCml | (2，5，9) | PMCll | (11，14，18) |
| PFCmr | (2，6，9) | SMAuu | (12，15，16) |
| PFCur | (2，3，6) | SMAll | (12，15，19) |
| PFCru | (2，6，7) | SMArr | (12，16，19) |
| PFCrl | (2，6，10) | PMCrr | (13，17，20) |
| PFCrr | (2，7，10) | SMAww | (15，16，19) |
Table 2 calculation of the sub-area values equation 1. data normalization, using the maximum-minimum normalization equation:
for j 1 to M channels:
2. calculating the weight of each channel in the region:
2.1 calculate the probability of each sample:
2.2 calculate the information entropy of each channel:
2.3 calculate the weight of each channel.
3. Calculating regional blood oxygen values:
TABLE 3 calculation formula of three major characteristics
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods when executing the program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of any of the methods.
A processor for running a program, wherein the program when running performs any of the methods.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (6)
1. A hemoglobin information-based method for recognizing multiple walking gait adjustment intents is characterized by comprising the following steps:
preprocessing data of the recorded brain cortex hemoglobin concentration at the walking gait adjusting moment; the recorded brain cortex hemoglobin concentration at the walking gait adjusting moment is that a test experiment is carried out by applying a near infrared spectrum brain imaging technology, and a subject completes a corresponding task of walking gait adjustment in a fixed area; "obtained;
for the preprocessed cerebral cortex hemoglobin information, carrying out corresponding channel division according to the distribution of the brain functional regions, and calculating and extracting relevant parameters as features;
applying a pattern recognition algorithm to establish four detection models of gait adjustment intentions;
the method for establishing the detection models of the four gait adjustment intentions by applying the pattern recognition algorithm specifically comprises the following steps:
the Kolmogorov-Smirnov test is adopted to test whether the characteristics in different states are in the same distribution, if the characteristics are in the same distribution, the characteristics are in the state of no ability to distinguish and should be removed, and the preliminary screening is carried out through the filtering type characteristic selection mode to obtain a characteristic subspace;
performing principal component analysis on the feature subspace, performing dimension reduction on the feature, and selecting principal components with the first 95% contribution rate as a feature dimension reduction space;
a stacked integrated learning algorithm is adopted to realize a two-layer stacked support vector machine model; for the SVM model of the first layer, adopting an annealing genetic algorithm for a dimensionality reduction space, selecting 15 optimal groups of feature combinations, and constructing 15 groups of SVM models according to the 15 optimal groups of feature combinations; for the SVM model of the second layer, integrating 15 SVM models of the previous layer by using an SVM as a base classifier and adopting an integrated learning algorithm, and still adopting an annealing genetic algorithm to optimize the hyperparameter of the SVM;
and detecting according to the established model to obtain a detection result.
2. The method for recognizing walking gait adjustment intents according to claim 1, wherein the preprocessing of the data is performed on the cortical hemoglobin concentration recorded at the time of walking gait adjustment; the pretreatment method is specifically as follows:
a Chebyshev low-pass filter is adopted, the filtering cut-off frequency is 0.145Hz, high-frequency components in the signal are filtered, and frequency components of neuron activity are reserved;
and correcting the base line of the signal by adopting a morphological filtering method and combining a closed-open filtering method and a closed-open filtering method, and removing null shift.
3. The method according to claim 1, wherein the preprocessed brain cortex hemoglobin information is divided into channels according to the distribution of brain function regions, and the related parameters are calculated and extracted as features; the method specifically comprises the following steps:
firstly, calculating the information entropy of each channel, secondly, calculating the weight of each channel on the basis of the information entropy, and finally obtaining the blood oxygen concentration value of the corresponding region according to a weighted average method;
and calculating corresponding parameters of hemoglobin for each brain area, wherein the corresponding parameters comprise three main characteristics including statistical characteristics, entropy characteristics and related characteristics of blood oxygen content, including mean value, energy, variance, range, information entropy and Pearson correlation coefficient, and the three main characteristics are used as original characteristic space.
4. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 3 are implemented when the program is executed by the processor.
5. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 3.
6. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the method of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811383174.5A CN109567818B (en) | 2018-11-20 | 2018-11-20 | Hemoglobin information-based method for identifying multiple walking gait adjustment intents |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811383174.5A CN109567818B (en) | 2018-11-20 | 2018-11-20 | Hemoglobin information-based method for identifying multiple walking gait adjustment intents |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109567818A CN109567818A (en) | 2019-04-05 |
| CN109567818B true CN109567818B (en) | 2021-06-01 |
Family
ID=65923005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811383174.5A Active CN109567818B (en) | 2018-11-20 | 2018-11-20 | Hemoglobin information-based method for identifying multiple walking gait adjustment intents |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109567818B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109710065B (en) * | 2018-12-18 | 2021-12-28 | 苏州大学 | Method for recognizing walking regulation intention based on brain hemoglobin information |
| CN110384506A (en) * | 2019-06-06 | 2019-10-29 | 苏州布芮恩智能科技有限公司 | The recognition methods that walking based on brain hemoglobin information is intended to |
| JP7262658B2 (en) * | 2019-07-16 | 2023-04-21 | ニューラロジックス コーポレイション | Systems and methods for camera-based quantification of blood biomarkers |
| CN112274145A (en) * | 2019-07-22 | 2021-01-29 | 苏州布芮恩智能科技有限公司 | Method and device for processing near-infrared brain function imaging data and storage medium |
| CN112274144A (en) * | 2019-07-22 | 2021-01-29 | 苏州布芮恩智能科技有限公司 | Method and device for processing near-infrared brain function imaging data and storage medium |
| CN111950441A (en) * | 2020-08-10 | 2020-11-17 | 苏州大学 | FNIRS real-time decoding method and system for upper limb movement intention |
| CN112022136A (en) * | 2020-09-11 | 2020-12-04 | 国家康复辅具研究中心 | Near-infrared brain function and gait parameter based assessment method and system |
| CN112370049B (en) * | 2020-11-16 | 2022-07-29 | 天津市环湖医院(天津市神经外科研究所、天津市脑系科中心医院) | Freezing gait acquisition and analysis system and method based on multi-mode signal synchronization |
| CN112656372B (en) * | 2020-12-17 | 2022-02-15 | 苏州大学 | Brain network topological rule-based mental fatigue detection method and system |
| CN112656373B (en) * | 2020-12-17 | 2022-12-16 | 苏州大学 | Physical fatigue detection method and system based on brain network topological law |
| CN113017622A (en) * | 2021-03-03 | 2021-06-25 | 苏州大学 | fNIRS-based imaginary object displacement direction decoding method |
| CN112884079A (en) * | 2021-03-30 | 2021-06-01 | 河南大学 | Method for estimating near-surface nitrogen dioxide concentration based on Stacking integrated model |
| CN113647938A (en) * | 2021-08-18 | 2021-11-16 | 苏州大学 | Method and system for advanced detection of motion state change based on physiological signals |
| CN115687898B (en) * | 2022-12-30 | 2023-07-11 | 苏州大学 | Gait parameter self-adaptive fitting method based on multi-mode signals |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8195593B2 (en) * | 2007-12-20 | 2012-06-05 | The Invention Science Fund I | Methods and systems for indicating behavior in a population cohort |
| WO2012135068A1 (en) * | 2011-03-25 | 2012-10-04 | Drexel University | Functional near infrared spectrocopy based brain computer interface |
| CN102973279A (en) * | 2012-12-18 | 2013-03-20 | 哈尔滨工业大学 | Near-infrared brain-machine interface signal detection method integrating independent component analysis and least square method |
| CN104182645A (en) * | 2014-09-01 | 2014-12-03 | 黑龙江省计算中心 | Empirical mode decomposition and sliding time window weighted least square method based brain-computer interface extraction method |
| CN107563298A (en) * | 2017-08-08 | 2018-01-09 | 苏州大学 | The recognition methods for squatting up away state of imagination motion stage based on brain hemoglobin information |
| CN108309318A (en) * | 2018-01-30 | 2018-07-24 | 苏州大学 | Cerebral function state evaluation device based on brain hemoglobin information |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5531237B2 (en) * | 2009-02-24 | 2014-06-25 | 本田技研工業株式会社 | Brain information output device, robot, and brain information output method |
-
2018
- 2018-11-20 CN CN201811383174.5A patent/CN109567818B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8195593B2 (en) * | 2007-12-20 | 2012-06-05 | The Invention Science Fund I | Methods and systems for indicating behavior in a population cohort |
| WO2012135068A1 (en) * | 2011-03-25 | 2012-10-04 | Drexel University | Functional near infrared spectrocopy based brain computer interface |
| CN102973279A (en) * | 2012-12-18 | 2013-03-20 | 哈尔滨工业大学 | Near-infrared brain-machine interface signal detection method integrating independent component analysis and least square method |
| CN104182645A (en) * | 2014-09-01 | 2014-12-03 | 黑龙江省计算中心 | Empirical mode decomposition and sliding time window weighted least square method based brain-computer interface extraction method |
| CN107563298A (en) * | 2017-08-08 | 2018-01-09 | 苏州大学 | The recognition methods for squatting up away state of imagination motion stage based on brain hemoglobin information |
| CN108309318A (en) * | 2018-01-30 | 2018-07-24 | 苏州大学 | Cerebral function state evaluation device based on brain hemoglobin information |
Non-Patent Citations (2)
| Title |
|---|
| 《一种基于fMRI数据的脑功能网络构建方法》;薛绍伟 等;《计算机应用研究》;20101130;第27卷(第11期);第4055-4057页 * |
| 《基于近红外脑功能成像技术的脑卒中研究现状》;眭演祥 等;《中国康复》;20161031;第31卷(第5期);第387-389页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109567818A (en) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109567818B (en) | Hemoglobin information-based method for identifying multiple walking gait adjustment intents | |
| Naik et al. | Nonnegative matrix factorization for the identification of EMG finger movements: Evaluation using matrix analysis | |
| He et al. | Common Bayesian network for classification of EEG-based multiclass motor imagery BCI | |
| Butkevičiūtė et al. | Removal of movement artefact for mobile EEG analysis in sports exercises | |
| US9149719B2 (en) | Device and method for generating a representation of a subject's attention level | |
| CN110353702A (en) | A kind of emotion identification method and system based on shallow-layer convolutional neural networks | |
| Zhao et al. | Deep learning in the EEG diagnosis of Alzheimer’s disease | |
| WO2019148557A1 (en) | Cerebral function state evaluation device based on cerebral hemoglobin information | |
| CN109710065B (en) | Method for recognizing walking regulation intention based on brain hemoglobin information | |
| CN111091074A (en) | Motor imagery electroencephalogram signal classification method based on optimal region common space mode | |
| Lahiri et al. | Evolutionary perspective for optimal selection of EEG electrodes and features | |
| Naik et al. | Dependence independence measure for posterior and anterior EMG sensors used in simple and complex finger flexion movements: Evaluation using SDICA | |
| CN114533086A (en) | Motor imagery electroencephalogram decoding method based on spatial domain characteristic time-frequency transformation | |
| Li et al. | A between-subject fNIRS-BCI study on detecting self-regulated intention during walking | |
| KR20190030611A (en) | Method for integrated signal processing of bci system | |
| Sadiq et al. | Evaluation of power spectral and machine learning techniques for the development of subject-specific BCI | |
| CN113143261B (en) | Myoelectric signal-based identity recognition system, method and equipment | |
| CN114305453A (en) | Multi-source manifold electroencephalogram feature transfer learning method | |
| Monica et al. | RETRACTED ARTICLE: Hybrid FOW—a novel whale optimized firefly feature selector for gait analysis | |
| Coyle et al. | Extracting features for a brain-computer interface by self-organising fuzzy neural network-based time series prediction | |
| CN113128384A (en) | Brain-computer interface software key technical method of stroke rehabilitation system based on deep learning | |
| CN112599245A (en) | Mental health index evaluation method and system | |
| CN106333681A (en) | Sleep state monitoring method and system based on self learning | |
| CN111671421B (en) | Electroencephalogram-based children demand sensing method | |
| CN108932403A (en) | Leave and the dynamic recognition methods of fortune based on brain hemoglobin information |
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 |