CN108932403A - Leave and the dynamic recognition methods of fortune based on brain hemoglobin information - Google Patents
Leave and the dynamic recognition methods of fortune based on brain hemoglobin information Download PDFInfo
- Publication number
- CN108932403A CN108932403A CN201810707382.XA CN201810707382A CN108932403A CN 108932403 A CN108932403 A CN 108932403A CN 201810707382 A CN201810707382 A CN 201810707382A CN 108932403 A CN108932403 A CN 108932403A
- Authority
- CN
- China
- Prior art keywords
- window
- standard deviation
- leave
- sum
- test
- 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
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention relates to the leave based on brain hemoglobin information and transport dynamic recognition methods, the resting state and motion state of subject are differentiated by collected data, the maximum value of the respective standard deviation of all parameters is calculated using the method for sliding window, as the benchmark for differentiating first motion, the standard deviation for acquiring data later is determined into initial position compared with its benchmark, the recognition accuracy of final movement state and leave is 89.4%, and the False Rate for section of resting is only 1.23%.
Description
Technical field
The present invention relates to brain hemoglobin information, more particularly to leave and fortune based on brain hemoglobin information
Dynamic recognition methods.
Background technique
Aging of population has been a conspicuousness problem of today's society.Data show, 2016, the generation more than 60 years old
Boundary's size of population accounts for about the 12% of total number of persons, and according to the discovery trend prediction of today's society, to the year two thousand fifty, this ratio is big
Appointment rises to 21%.Aging results in the increase of the elderly's body kinematics function being remarkably decreased with body fragility, significantly
It increases such old man's fracture or the probability of other accidents occurs, cause its serious dyskinesia, it is normal to influence it
Quality of life.It is shown according to data, the annual whole world has more than 15,000,000 people's apoplexy, and it is second largest dead former that apoplexy has become the whole world
Cause.There is 6,000,000 patients with cerebrovascular disease in China, average every 21s just has a people to die of apoplexy.Moreover, global apoplexy
Crowd has the tendency that greatly rejuvenation, and the apoplexy probability of 20 years old to 64 years old this age level has improved 25%, accounted for apoplexy sufferer
One third.It will lead to patient after apoplexy and occur that muscle inability, spasm, sensorimotor control are impaired and cognitive function is lost
Phenomena such as, this also means that patient will appear serious energy loss in normal walking, a possibility that increasing patient falls.And
It may cause it along with cognitive function of patients decline and severe motion dysfunction occur.Simultaneously as the rapid development of society,
Cause the to disable number of patient such as incident spinal cord injury, traffic accident, industrial injury, unexpected injury and disease also constantly increases
Greatly.Therefore, for above-mentioned dyskinesia patient, normal walking has been its main challenge, is gone on a journey for a long time by wheelchair
Or positive motion intention is not got enough athletic exercise and reduces caused by bed, it not only results in cerebral function and adds with advancing age
Speed decline, a possibility that also further resulting in the appearance of other complication, body function is accelerated to degenerate.These problems will be serious
The rehabilitation process of patient is influenced, and brings heavy financial burden to society.For such patient, restoring its walking ability is also
The hope of their most originals.Therefore training appropriate is provided for these patients, helping early stage patient to restore walking ability has weight
Big meaning.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of leave based on brain hemoglobin information and
Dynamic recognition methods is transported, motor pattern can further be differentiated later by determining movement state, to realize brain-computer interface movement control
System differentiates the resting state and motion state of subject by collected data, and it is each to calculate all parameters using the method for sliding window
From the maximum value of standard deviation the standard deviation of data will be acquired later compared with its benchmark as the benchmark for differentiating first motion
To determine initial position.
A kind of leave based on brain hemoglobin information and the dynamic recognition methods of fortune, comprising:
Obtain three kinds of blood oxygen hemoglobin information in multiple channels of the test zone of acquisition, the blood red egg of three kinds of blood oxygens
White information, that is, deoxyhemoglobin signal, total oxygen hemoglobin signal and oxygen-containing hemoglobin information signal；
It is filtered using Chebyshev's first-order bandpass filter；
It include 8 sampled points in each window using the method for sliding window, it is primary every three sampled point slidings, and calculate this
The standard deviation of a window；
It is compared for the standard deviation size of data points all in baseline, for 22 channels of experiment test, respectively
Calculate the maximum standard deviation in each channel；
The calculating of standard deviation, the standard deviation in each channel after having been calculated base corresponding with its are carried out to this window function
Quasi- value is compared, poor if more than above-mentioned standard, then 8 sampled points to this window and before it and previous window and it before
8 each sampled points carry out single factor test method analysis respectively.
The above-mentioned leave based on brain hemoglobin information and the dynamic recognition methods of fortune, are sentenced by collected data
The resting state and motion state not being tested calculate the maximum value of the respective standard deviation of all parameters using the method for sliding window, as
The standard deviation for acquiring data later is determined initial position compared with its benchmark by the benchmark for differentiating first motion, final to transport
The recognition accuracy of dynamic and leave is 89.4%, and the False Rate for section of resting is only 1.23%.
Detailed description of the invention
Fig. 1 is experiment flow figure provided by the embodiments of the present application.
Fig. 2 is experiment headgear layout provided by the embodiments of the present application.
Fig. 3 is that curve is illustrated after leave to fortune dynamic filter under certain a certain state of subject provided by the embodiments of the present application
Figure.
Fig. 4 is real-time sliding window schematic diagram provided by the embodiments of the present application.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
A kind of leave based on brain hemoglobin information and the dynamic recognition methods of fortune, comprising:
Obtain three kinds of blood oxygen hemoglobin information in multiple channels of the test zone of acquisition, the blood red egg of three kinds of blood oxygens
White information, that is, deoxyhemoglobin signal, total oxygen hemoglobin signal and oxygen-containing hemoglobin information signal；
It is filtered using Chebyshev's first-order bandpass filter；
It include 8 sampled points in each window using the method for sliding window, it is primary every three sampled point slidings, and calculate this
The standard deviation of a window；
It is compared for the standard deviation size of data points all in baseline, for 22 channels of experiment test, respectively
Calculate the maximum standard deviation in each channel；
The calculating of standard deviation, the standard deviation in each channel after having been calculated base corresponding with its are carried out to this window function
Quasi- value is compared, poor if more than above-mentioned standard, then 8 sampled points to this window and before it and previous window and it before
8 each sampled points carry out single factor test method analysis respectively.
The above-mentioned leave based on brain hemoglobin information and the dynamic recognition methods of fortune, are sentenced by collected data
The resting state and motion state not being tested calculate the maximum value of the respective standard deviation of all parameters using the method for sliding window, as
The standard deviation for acquiring data later is determined initial position compared with its benchmark by the benchmark for differentiating first motion, final to transport
The recognition accuracy of dynamic and leave is 89.4%, and the False Rate for section of resting is only 1.23%.
In other one embodiment, " it is filtered using Chebyshev's first-order bandpass filter；" in filter range
For 0.01Hz-0.1Hz.
In other one embodiment, step " is filtered using Chebyshev's first-order bandpass filter；" after and
Step " it include 8 sampled points in each window using the method for sliding window, it is primary every three sampled point slidings, and calculate this window
Standard deviation；" before, filtered data is handled using following formula:
Tatal (i)=2 × tatal (i)-tatal (i-1)+tatal (i+1)
Oxyhb (i)=2 × oxyhb (i)-oxyhb (i-1)+oxyhb (i+1)
Deoxyhb (i)=2 × deoxyhb (i)-deoxyhb (i-1)+deoxyhb (i+1)
In other one embodiment, and step " calculating of standard deviation is carried out to this window function, it is every after having been calculated
The standard deviation in a channel a reference value corresponding with its is compared, poor if more than above-mentioned standard, then 8 to this window and before it
Sampled point and previous window and 8 each sampled points before it carry out single factor test method analysis respectively." specifically include:
Sample average is calculated first
Wherein xijIt is i-th of value in the case of jth arranges, njFor jth column total number, to continue to calculate its total sum of squares of deviations
(SST), sum of squares of deviations (SSA) between sum of squares of deviations (SSE) and group in organizing:
WhereinIndicate sample average,Indicate sample variance.Later in calculating group sum of squares of deviations mean square
(MSE) between group sum of squares of deviations mean square (MSA) and its test value p
N is the sum in every columns in formula, and m is overall number.P is the statistical test value acquired, is used to define number
Column whether there is significant difference, its general value range is between 0.01-0.05.It provides herein, if single factor test side at above-mentioned two
Poor comparison result when there is p < 0.05 at one if it exists, then remembers that the value in this channel under this parameter is " 1 ", is otherwise denoted as " 0 ",
It is all made of such method for three kinds of time blood oxygen time serieses in all channels and is handled, finally by 20 subjects of observation
In the feature of task initial phase, to determine Rule of judgment, for moving the differentiation of start-stop state.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
Computer program, which is characterized in that the step of processor realizes the method when executing described program.
A kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The step of the method is realized when execution.
A kind of processor, which is characterized in that the processor is for running program, wherein described program executes when running
The method.
Gait rehabilitation training is carried out based on the dyskinesia patient that the Preparatory work of experiment stage seeks advice to rehabilitation department doctor
As a result, the present invention designs small step low speed, small step middling speed, middle step low speed, middle step middling speed, middle step high speed and big this 6 kinds of middling speed of step are not
Same gait parameter.Whole experiment process can all have an experimenter, and and then subject is walked, it is ensured that subject, which is expert at, passes by
It is not influenced by data line weight and length in journey.
Whole experiment process starts to walk the difference of foot according to the starting stage, and subject is divided into 2 groups, first group of 16 people of subject,
It first steps right crus of diaphragm, second group of 15 people of subject under each gait parameter, and the starting stage first steps left foot.For some gait
Parameter, it is desirable that the subject station time specified in initial position rest, then according to the spontaneous walking of specified gait position to terminal
It sets, starting point is retracted after guarantee rest specified time and continues the next gait of rest preparation.Before real experiment starts, to set
The experimental program of meter is simulated test, and discovery is with the increase for being tested the testing time, it may appear that fatigue and head are uncomfortable
Situation, and it is inadaptable in view of take that headgear tested, therefore be modified for the time of having a rest of subject.Regulation:
All gait parameters are walked 2 times, when a certain gait parameter carries out first pass walking, it is desirable that subject is before task starts and task
After time of having a rest be held at 10s or so, using this subtask as subject laundering period, grinding after being not used in
Study carefully；When carrying out second time walking, the time of having a rest before and after task is maintained at 40s or so, this is all over the depth tested after being used for
Enter research.In the experiment initial stage, in order to guarantee that subject is able to know that the time of about 40s and later to leave and movement state
It is differentiated, subject can be allowed to be familiar with the time span of 40s or so in incipient stage rest 40s, and with this time span work
For the baseline of subject rest.The flow chart entirely tested is as shown in Figure 1.The gait start-stop of whole experiment process is spontaneous by being tested
Control, experimenter do not give any prompt.
To avoid the spot on head from having an impact the signal-to-noise ratio of signal, all subjects must clear up head before participating in test
Skin simultaneously guarantees dry scalp.Before experiment starts, experimenter can be trained subject, it is ensured that subject can accurately remember whole
Body experimental procedure and accurately walk out all gaits.Due to the length limitation of device data transmission line, guaranteeing not pull data
Under the premise of transmission line, it is desirable that subject is walked in a fixed area, length 4.4m, and the starting moved and end
Stop bit is set all to be indicated in advance.According to the observation before experiment for different gaits, it is specified that in the length of this 4.4m, small walking is used
Whole process about step number is covered as 8-9 step, the step number that middle step-length covers whole process is about 6 steps, and big step-length covers entirely mistake
The step number of journey is about 4 steps.Concrete condition can be adjusted slightly according to subject height.Leg speed is carried out according to the speed of walking of subject usually
Adjustment, low speed is about the 50% of middling speed, and high speed is about middling speed 150%, has experimenter to carry out time note in whole experiment process
Record, to ensure that the leg speed being tested is implicitly present in gap.Since extraneous natural light and light can have an impact experimental data,
Indoor all light can be closed when testing and carrying out.
This project data acquisition equipment is the FORIE-3000 equipment of Japanese Shimadzu Corporation.It is equipped with 8 emitters and 8 connects
Pole is received, as shown in Figure 2.The wavelength that test phase emitter issues 780nm, 805nm and 830nm is tested, it is de- to be respectively intended to test
Oxygen hemoglobin, total oxygen hemoglobin and oxygen-containing hemoglobin information.The acquisition equipment sampling time is 0.13s.
The present invention is selected headgear region using Broadman (Bordmann) subregion as foundation, it is dissected by Germany
Scholar Bryant Buddhist nun pacifies Broadman (KorbinianBrodmann) and proposes cortex anatomical area based on the difference of brain cell structure
Domain system.And it is sent out according to mechanism study result of each function brain area in speed and step-length is carried out using fNIRS before
It is existing, in walking phase, as long as the region for playing adjustment effect for speed is PFC, PMC, the region SMA, in addition, the region PFC for
An important role is also played in identification motor mindedness.Determining therefrom that this tests main test zone is PFC, SMA and PMC
These three regions, 9th area of Broadman subregion, 8th area and 6th area in corresponding diagram.
For experiment equipment used in the present invention, determines and be laid out using 3 × 5 channel headgear, used 8 in this headgear
A emitter and 7 receiving poles test 22 channels altogether.In order to enable headgear to navigate to required measured zone, using 10-
20 systems position brain region.In this system diagram, by being distributed in antinion on the front and back sagittal line of the nasion to rear convex pillow bone
Point (Fpz), metopion (Fz), central point (Cz), vertex (Pz) and pillow point (Oz).Wherein antinion midpoint to the nasion distance and
Pillow point to occipital bone distance respectively account for this front and back sagittal line length 10%, remaining point between distance be its 20%.Therefore Cz point exists
The center of this front and back sagittal line.Left and right sagittal line is left preauricular point to the line of right preauricular point, is distributed in left temporo thereon
(T3) point, left centre (C3) point, (T4) point in right temporo, right median (C4) point.T3 point is to left preauricular point, T4 point to right preauricular point
The 10% of this occupied left and right sagittal line of distance point, remaining each point accounts for 20%.This experiment Cz point position be selected in front and back sagittal line with
The point of intersection of left and right sagittal line, according to Broadman Zone system, it is specified that Cz point is 30mm at a distance from receiving pole 7, and it is each
The distance between emitter and receiving pole are also fixed as 30mm.In figure, corresponding channel 1 frontal lobe area (PFC) to channel 7, eye movement
The corresponding channel 8 to 12 in area (frontal eye cortex, FEC), left front motor area (PMCL) corresponding channel 13 and channel 18,
Right preceding motor area (PMCR) corresponding channel 15 and channel 20, movement auxiliary region (SMA) is to channel 14,16,1719.21 and 22.
Since in practical operation, the head of each subject is not of uniform size, the area in each brain function region is had differences, therefore is herein
The concept for proposing an opposed area will use corresponding mathematical measure and weaken this difference in subsequent data handling procedure
It is different.
It is tested using the acquisition that near infrared gear carries out brain information, three kinds of test moulds can be divided into according to the difference of triggering mode
Formula is Block mode, Event-related mode and Continuous mode respectively.Block mode is using fixed rest
It is the specific difference being usually used between two kinds of different tasks of comparison with fixed task time；Event-related mode is common
In trigger-type task, when external condition changes, corresponding is made by vision or the method for sound prompt subject
Business.Continuous mode is a kind of by being tested spontaneous continuous motor pattern, the start-stop of task by being tested spontaneous control, and
The stimulation that will not carry out vision or the sense of hearing in whole experiment process to subject, is conducive to the research of autogenic movement.Therefore this hair
It is bright that data are acquired using Continuous mode, when subject carries out movement or stop motion, use test circle
Mark button on face is marked.
Data judgement subject leave and movement state based on acquisition, are that the present invention first has to solve the problems, such as.In this hair
In bright, start-stop state is differentiated using three kinds of blood oxygen hemoglobin information.In the data processing stage for differentiating movement start-stop state, appoint
What, which calculates the data before being based on current sample time, is realized.
For each experiment, it is required to the time of having a rest that subject carries out 40s before its task starts, is stopped with this
Cease the differentiation of state and task state.Therefore, the baseline that the time of this 40s or so is tested thus, for leave and task state
Differentiate.And because between subject difference it is excessive, differentiate the feature being in addition tested with the feature of other subjects, it is ineffective, because
This, the differentiation that leave and task state are directed in the present invention is differentiated using the benchmark for being tested itself.It is directed to list
It is illustrated for a subject.
By observation original number it has been found that will start in the task incipient stage and incipient stage, blood oxygen concentration can go out
An existing apparent variation.Therefore for some subject, three kinds of different blood oxygen parameters of its reference line are extracted first, are used
Chebyshev's first-order bandpass filter is filtered, filter range 0.01Hz-0.1Hz.To be sentenced after guarantee using standard deviation
Disconnected data fluctuations situation, is handled filtered data that (this treating method has used one after judgement point using following formula
The sampled point of a point, causes the delay of 0.13s):
Tatal (i)=2 × tatal (i)-tatal (i-1)+tatal (i+1) (3.1)
Oxyhb (i)=2 × oxyhb (i)-oxyhb (i-1)+oxyhb (i+1) (3.2)
Deoxyhb (i)=2 × deoxyhb (i)-deoxyhb (i-1)+deoxyhb (i+1) (3.3)
The method for using sliding window later includes 8 sampled points in each window, primary every three sampled points slidings, and is counted
The standard deviation of this window is calculated, as shown in Figure 3.It is compared later for the standard deviation size of all data points in baseline, for
22 channels for testing test, calculate separately the maximum standard deviation in each channel, due to being used herein as being tested the data pair of itself
The judgement of its leave and task state, there is no the errors of head zone, therefore processing later is carried out directly against single channel
Research.
After subject respectively establishes the benchmark of its leave, start subsequent judgement, since the filtering of data exists
The requirement of points, therefore the present invention 180 points of selection are filtered and (meet WAVELET PACKET DECOMPOSITION requirement, and later in real time discriminating
Without reconnaissance again), it carries out selecting last 8 points as window function after the calculating of formula 3.1,3.2 and 3.3 after filtering
It is studied.
The calculating of standard deviation, the standard deviation in each channel after having been calculated base corresponding with its are carried out to this window function
Quasi- value is compared, poor if more than above-mentioned standard, then 8 sampled points to this window and before it and previous window and it before
8 each sampled points carry out the analysis of single factor test method (one-way ANOVA) respectively, the specific steps of which are as follows:
Sample average is calculated first
Wherein xijIt is i-th of value in the case of jth arranges, njFor jth column total number, to continue to calculate its total sum of squares of deviations
(SST), sum of squares of deviations (SSA) between sum of squares of deviations (SSE) and group in organizing:
WhereinIndicate sample average,Indicate sample variance.Later in calculating group sum of squares of deviations mean square
(MSE) between group sum of squares of deviations mean square (MSA) and its test value p
N is the sum in every columns in formula, and m is overall number.P is the statistical test value acquired, is used to define number
Column whether there is significant difference, its general value range is between 0.01-0.05.It provides herein, if single factor test side at above-mentioned two
Poor comparison result when there is p < 0.05 at one if it exists, then remembers that the value in this channel under this parameter is " 1 ", is otherwise denoted as " 0 ",
It is all made of such method for three kinds of time blood oxygen time serieses in all channels and is handled, finally by 20 subjects of observation
In the feature of task initial phase, to determine Rule of judgment, for moving the differentiation of start-stop state.
For the differentiation of different motion state, total oxygen hemoglobin is used only in the present invention and the oxygen-containing deoxyhemoglobin that subtracts is joined
Several pairs of data are studied, therefore analysis methods all later is de- only for subtracting in total oxygen hemoglobin and oxygen-containing hemoglobin
The difference of oxygen hemoglobin, and all analyses are all first to extract the two blood oxygen parameters of data.The first step is will test
The oxygen-containing Hemoglobin Value of data directly subtracts the value of deoxyhemoglobin, the research after being used for as poor oxygen.
The present invention mainly describes the method for differentiating the data processing of movement start-stop state and different motion state recognition.It is first
The 40s time of having a rest before first being started according to experiment calculates under each parameter each channel most by the method that standard deviation compares
Benchmark of the big standard deviation as judgement movement start-stop state.Then the data acquired later are carried out with the calculating of standard deviation, if
Value of standard deviation is greater than a reference value at this, and the one-way analysis of variance result of its former and later two window meets the p < for having one
When 0.05, that is, it is considered as one and meets condition, be overlapped result after calculating the value of all parameters, to finds out movement start-stop
Rule of judgment.
When carrying out the differentiation of leave and task state, treating method herein is carried out afterwards to acquired data
It analyzes, 240 sampled points after 200 sampled points and Mark point before being extracted task status Mark point, totally 340 samplings
Point is used as research object, but calculating process is not carried out according further to the requirement of real-time Transmission using the point after current data
It calculates.A sliding window is carried out using every three points to calculate, and when seeking the standard deviation of a window, is still extracted this first 172 of point and is adopted
Sampling point, 8 sampled points of adding window, totally 180 sampled points are filtered, and treatment process is identical with chapter 3.
By 22 channels under the obtained three kinds of parameters of test are asked respectively each of which window standard deviation and the window with
After the single factor test variation decomposition comparison result of previous window, all results under a certain parameter are overlapped, some is obtained
It is tested the respective total value of the lower three kinds of parameters of 6 states.
Feature of 20 subjects before and after task segment is summarized according to the observation later, sets following Rule of judgment to define
There is following situation and be considered as movement initial phase:
One, meeting in respective 22 channels under three kinds of blood oxygen parameters there are two kinds of blood oxygen parameters has more than at 3 or at 3
Digital " 1 " situation occur is considered as motion state；
Two, in the case where there is not motion state in subject 20s, if occurring it simultaneously under three of them blood oxygen parameter later
In a parameter 22 channels summation be significantly greater than before maximum value, then be considered as motion state.
In conclusion the starting of subject motion state can be judged in time and effectively using such method,
And its during the break between the False Rate of section be also not especially high, this carries out rising for Large Amplitude Motion using brain blood oxygenation information for after
A basis has been established in the judgement of beginning position.But the method mainly studies the fluctuation situation of blood oxygen, terminates in short-term in task
The interior fluctuation that still will appear brain blood oxygenation information may generate certain error to result is differentiated, therefore movement is stopped
The judgement at moment also needs to improve.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (7)
1. a kind of leave based on brain hemoglobin information and the dynamic recognition methods of fortune characterized by comprising
Obtain three kinds of blood oxygen hemoglobin information in multiple channels of the test zone of acquisition, the blood red egg of three kinds of blood oxygens
White information, that is, deoxyhemoglobin signal, total oxygen hemoglobin signal and oxygen-containing hemoglobin information signal；
It is filtered using Chebyshev's first-order bandpass filter；
It include 8 sampled points in each window using the method for sliding window, it is primary every three sampled point slidings, and calculate this window
Standard deviation；
It is compared for the standard deviation size of data points all in baseline, for 22 channels of experiment test, calculates separately
The maximum standard deviation in each channel；
The calculating of standard deviation, the standard deviation in each channel after having been calculated a reference value corresponding with its are carried out to this window function
Be compared, it is poor if more than above-mentioned standard, then 8 sampled points to this window and before it and previous window and before it 8
Each sampled point carries out single factor test method analysis respectively.
2. the leave according to claim 1 based on brain hemoglobin information and the dynamic recognition methods of fortune, special
Sign is, " is filtered using Chebyshev's first-order bandpass filter；" in filter range be 0.01Hz-0.1Hz.
3. the leave according to claim 1 based on brain hemoglobin information and the dynamic recognition methods of fortune, special
Sign is that step " is filtered using Chebyshev's first-order bandpass filter；" after and step " using the method for sliding window, often
It include 8 sampled points in a window, it is primary every three sampled point slidings, and calculate the standard deviation of this window；" before, using such as
Lower formula handles filtered data:
Tatal (i)=2 × tatal (i)-tatal (i-1)+tatal (i+1)
Oxyhb (i)=2 × oxyhb (i)-oxyhb (i-1)+oxyhb (i+1)
Deoxyhb (i)=2 × deoxyhb (i)-deoxyhb (i-1)+deoxyhb (i+1).
4. the leave according to claim 1 based on brain hemoglobin information and the dynamic recognition methods of fortune, special
Sign is that step " carries out the calculating of standard deviation, the standard deviation in each channel after having been calculated and its correspondence to this window function
A reference value be compared, it is poor if more than above-mentioned standard, then 8 sampled points to this window and before it and previous window and it
Each sampled point in 8 before carries out single factor test method analysis respectively." specifically include:
Sample average is calculated first
Wherein xijIt is i-th of value in the case of jth arranges, njFor jth column total number, to continue to calculate its total sum of squares of deviations
(SST), sum of squares of deviations (SSA) between sum of squares of deviations (SSE) and group in organizing:
WhereinIndicate sample average,Indicate sample variance.Later in calculating group sum of squares of deviations mean square (MSE) and group
Between sum of squares of deviations mean square (MSA) and its test value p
N is the sum in every columns in formula, and m is overall number.P is the statistical test value acquired, and being used to define ordered series of numbers is
No there are significant differences, its general value range is between 0.01-0.05.It provides herein, if single factor test variance ratio at above-mentioned two
Compared with as a result, then remember that the value in this channel under this parameter is " 1 " when there is p < 0.05 at one if it exists, be otherwise denoted as " 0 ", for
Three kinds of time blood oxygen time serieses in all channels are all made of such method and are handled, in office finally by 20 subjects of observation
The feature of business initial phase, to determine Rule of judgment, for moving the differentiation of start-stop state.
5. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any one of claims 1 to 4 the method when executing described program
Step.
6. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claims 1 to 4 the method is realized when row.
7. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit requires 1 to 4 described in any item methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810707382.XA CN108932403B (en) | 2018-07-02 | 2018-07-02 | Brain hemoglobin information-based resting state and movement state identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810707382.XA CN108932403B (en) | 2018-07-02 | 2018-07-02 | Brain hemoglobin information-based resting state and movement state identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108932403A true CN108932403A (en) | 2018-12-04 |
| CN108932403B CN108932403B (en) | 2021-09-14 |
Family
ID=64447180
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810707382.XA Active CN108932403B (en) | 2018-07-02 | 2018-07-02 | Brain hemoglobin information-based resting state and movement state identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108932403B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109710065A (en) * | 2018-12-18 | 2019-05-03 | 苏州大学 | Walking based on brain hemoglobin information adjusts the recognition methods being intended to |
| 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 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104771255A (en) * | 2015-01-06 | 2015-07-15 | 苏州大学 | Implementation method for identifying motion models based on cerebral-cortex hemoglobin information |
| CN106901749A (en) * | 2017-01-06 | 2017-06-30 | 苏州大学 | A kind of extracting method of cortex hemoglobin information representation locomitivity parameter |
| CN106901751A (en) * | 2017-01-06 | 2017-06-30 | 苏州大学 | A kind of recognition methods of the speed movement status based on brain hemoglobin information |
-
2018
- 2018-07-02 CN CN201810707382.XA patent/CN108932403B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104771255A (en) * | 2015-01-06 | 2015-07-15 | 苏州大学 | Implementation method for identifying motion models based on cerebral-cortex hemoglobin information |
| CN106901749A (en) * | 2017-01-06 | 2017-06-30 | 苏州大学 | A kind of extracting method of cortex hemoglobin information representation locomitivity parameter |
| CN106901751A (en) * | 2017-01-06 | 2017-06-30 | 苏州大学 | A kind of recognition methods of the speed movement status based on brain hemoglobin information |
Non-Patent Citations (1)
| Title |
|---|
| JIACHENG XU等: "Classification of desired motion speed — A study based on cerebral hemoglobin information", 《2017 2ND INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS AND MECHATRONICS (ICARM)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109710065A (en) * | 2018-12-18 | 2019-05-03 | 苏州大学 | Walking based on brain hemoglobin information adjusts the recognition methods being intended to |
| CN109710065B (en) * | 2018-12-18 | 2021-12-28 | 苏州大学 | Method for recognizing walking regulation intention based on brain hemoglobin information |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108932403B (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200367800A1 (en) | Method for identifying driving fatigue based on cnn-lstm deep learning model | |
| Hamadicharef et al. | Learning EEG-based spectral-spatial patterns for attention level measurement | |
| CN110353673B (en) | Electroencephalogram channel selection method based on standard mutual information | |
| CN112617772B (en) | Driving fatigue identification method and system based on pulse wave signals | |
| CN108932403A (en) | Leave and the dynamic recognition methods of fortune based on brain hemoglobin information | |
| CN114358194A (en) | Gesture tracking based detection method for abnormal limb behaviors of autism spectrum disorder | |
| CN113768471A (en) | Parkinson disease auxiliary diagnosis system based on gait analysis | |
| Li et al. | Multi-modal emotion recognition based on deep learning of EEG and audio signals | |
| Kaur et al. | Using virtual reality to examine the neural and physiological anxiety-related responses to balance-demanding target-reaching leaning tasks | |
| Zhang et al. | Research on Dyslexia Detection based on Eye Tracking | |
| Gasparini et al. | Age-related walkability assessment: A preliminary study based on the emg | |
| CN111671421B (en) | Electroencephalogram-based children demand sensing method | |
| Bulygin et al. | Image-Based Fatigue Detection of Vehicle Driver: State-of-the-Art and Reference Model | |
| CN116712075A (en) | Driving fatigue identification method and device based on wrist multi-axial acceleration entropy | |
| Karimi et al. | Designing an intelligent system to detect stress levels during driving. | |
| Buscema et al. | The Implicit Function as Squashing Time Model: A Novel Parallel Nonlinear EEG Analysis Technique Distinguishing Mild Cognitive Impairment and Alzheimer′ s Disease Subjects with High Degree of Accuracy | |
| CN104644173B (en) | A kind of depressed risk three-level early warning system | |
| Fu et al. | Detecting drowsiness in driving simulation based on EEG | |
| CN107595295A (en) | A kind of recognition methods of the lower extremity movement resistive state based on brain hemoglobin information | |
| CN110363242B (en) | Brain consciousness multi-classification method and system based on support vector machine | |
| Zaeni et al. | Classification of the Stride Length based on IMU Sensor using the Decision Tree | |
| Gasparini et al. | EMG for Walkability Assessment: A Comparison between Elderly and Young Adults. | |
| CN112656430A (en) | Stroke balance rehabilitation assessment method based on standing position unbalance induced electroencephalogram | |
| CN118098507B (en) | Self-adaptive upper limb rehabilitation training control method and system based on multi-source data | |
| Zucco et al. | Resting-State EEG Classification for PNES Diagnosis |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Chunguang Inventor after: Jin Hedian Inventor after: Qu Wei Inventor after: Li Weida Inventor after: Li Juan Inventor after: Zhang Hongmiao Inventor before: Li Chunguang Inventor before: Qu Wei Inventor before: Li Weida Inventor before: Li Juan Inventor before: Zhang Hongmiao |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |