CN108008821A - Performance estimating method, device, terminal and the storage medium of artificial limb classification of motion device - Google Patents
Performance estimating method, device, terminal and the storage medium of artificial limb classification of motion device Download PDFInfo
- Publication number
- CN108008821A CN108008821A CN201711336803.4A CN201711336803A CN108008821A CN 108008821 A CN108008821 A CN 108008821A CN 201711336803 A CN201711336803 A CN 201711336803A CN 108008821 A CN108008821 A CN 108008821A
- Authority
- CN
- China
- Prior art keywords
- test
- current
- artificial limb
- motion device
- event
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention discloses a kind of performance estimating method, device, terminal and the storage medium of artificial limb classification of motion device.This method includes：It is current test event to determine a test event in default multiple test events；The starting point and test target in the current test event are shown in reference axis, and continuously acquire the electromyography signal of subject, the electromyography signal is identified by artificial limb classification of motion device to obtain result action, the corresponding movement locus of the result action, and recording test time are drawn since the starting point；According to the movement locus of current test event and the testing time, test value of the current test event for test evaluation index is determined；Comprehensive the multiple test event obtains the assessed value that artificial limb classification of motion device is directed to total evaluation index for the test value of test evaluation index.The present invention realizes the real-time assessment to artificial limb classification of motion device performance, and the assessment result quantified, assessment result are more accurate.
Description
Technical field
The present embodiments relate to prosthesis control technology, more particularly to a kind of Performance Evaluation side of artificial limb classification of motion device
Method, device, terminal and storage medium.
Background technology
Disabled population of China sample investigation data were calculated in 2006 according to State Statistics Bureau, in all kinds of disabled persons in the whole nation,
Physical disabilities population is most, is 24,120,000 people, and the 29.07% of Zhan Zong disabled populations.Due to contingency, birth defect, disease,
The reasons such as natural calamity, physical disabilities population are also being continuously increased.Only in the Wenchuan County in Sichuan violent earthquake in May, 2008, just there is 2
People loses limbs more than ten thousand.These amputation personage is, it is necessary to dress artificial limbs to aid in its daily life and work.According to artificial limb
Control mode, at present, domestic and international commercialized artificial limbs have mechanical cable-operated prosthesis, myoelectric limb and the myoelectricity rope control mixing false
Limb.
There is the problems such as function is single, manipulation is slow, clumsy in one's movement, difficult in maintenance for traditional mechanical cable-operated prosthesis.Closely
Since more than ten years, the control of artificial limb has been widely used in it from the electromyography signal (Electromyogram, EMG) of limbs surface recording
In system.Most important component is electrode and classification of motion device in myoelectric limb.Electrode is used for the muscle electric signal for gathering amputee,
Electric signal reaches in trained classification of motion device and judgement is identified, and then classification of motion device exports one it considers that most connecing
Near action, last motor drive artificial limb to complete the action.Method of the myoelectric limb as intuitive control, amputee can pictures
The hand for manipulating oneself equally manipulates artificial limb, it is not necessary to extra learning burden, therefore be current most promising control artificial limb
Method.
Amputee, because everyone muscle feature is different, is needed to myoelectric limb after myoelectric limb is worn
In artificial limb classification of motion device be trained and can just it is agreed with wearer.But myoelectric limb currently on the market, it is only capable of making
With off line data analysis, to assess sorting technique and training effect, lack quantifiable real-time evaluation measures, therefore amputee
It is only capable of, by the myoelectric limb control effect after data prediction and subjective observation training, judging control situation.Off line data analysis
Although objective data can be provided, the concrete condition in real-time myoelectric limb control can not be reacted completely.In actual flesh
Electric artificial limb is in use, the action and the intention performance of a different dive of amputee made there may be myoelectric limb even will completely can not be complete
The action for wanting to complete into amputee.This can be that amputee brings certain accident and risk.To sum up, current myoelectric limb needs
Want a kind of model and means that artificial limb classification of motion device training can be effectively assessed with real-time objective.
The content of the invention
In view of this, the embodiment of the present invention provide a kind of performance estimating method of artificial limb classification of motion device, device, terminal and
Storage medium, to realize the real-time assessment to artificial limb classification of motion device performance.
In a first aspect, an embodiment of the present invention provides a kind of performance estimating method of artificial limb classification of motion device, the method
Including：
It is current test event to determine a test event in default multiple test events；
The starting point and test target in the current test event are shown in reference axis, and continuously acquires subject's
Electromyography signal, identifies that the electromyography signal to obtain result action, is painted since the starting point by artificial limb classification of motion device
Make the corresponding movement locus of the result action, and recording test time；
According to the movement locus of current test event and the testing time, determine that current test event is assessed for test
The test value of index；
Comprehensive the multiple test event obtains artificial limb classification of motion device for whole for the test value of test evaluation index
The assessed value of body evaluation index.
Second aspect, the embodiment of the present invention additionally provide a kind of capability evaluating device of artificial limb classification of motion device, the dress
Put including：
Test event chooses module, for determining a test event in default multiple test events for current test
Project；
Movement locus drafting module, for showing starting point and test mesh in the current test event in reference axis
Mark, and the electromyography signal of subject is continuously acquired, identify that the electromyography signal is moved to obtain result by artificial limb classification of motion device
Make, the corresponding movement locus of the result action, and recording test time are drawn since the starting point；
Test value determining module, for the movement locus according to current test event and the testing time, determines current
Test value of the test event for test evaluation index；
Assessed value determining module, for integrating test value of the multiple test event for test evaluation index, obtains
Artificial limb classification of motion device is directed to the assessed value of total evaluation index.
The third aspect, the embodiment of the present invention additionally provide a kind of terminal, and the terminal includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processing
Device realizes the performance estimating method of the artificial limb classification of motion device described in any embodiment of the present invention.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer-readable storage medium, are stored thereon with computer program,
The performance estimating method of the artificial limb classification of motion device described in any embodiment of the present invention is realized when the program is executed by processor.
The technical solution of the embodiment of the present invention, by showing starting point and test target in current test event, and even
The continuous electromyography signal for obtaining subject, identifies that the electromyography signal obtains result action, and draw knot by artificial limb classification of motion device
Fruit acts corresponding movement locus, and recording test time, according to movement locus and testing time, determines that current test event is directed to
The test value of evaluation index is tested, the test value of comprehensive multiple test events, obtains the assessed value of artificial limb classification of motion device, realize
Real-time assessment to artificial limb classification of motion device performance, and the assessment result quantified, assessment result are more accurate.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the performance estimating method for artificial limb classification of motion device that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow chart of the performance estimating method of artificial limb classification of motion device provided by Embodiment 2 of the present invention；
Fig. 3 is the exemplary plot of correspondence of the default result action with treating track drafting in the embodiment of the present invention；
Fig. 4 is a kind of structural representation of the capability evaluating device for artificial limb classification of motion device that the embodiment of the present invention three provides
Figure；
Fig. 5 is a kind of structure diagram for terminal that the embodiment of the present invention four provides.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
It illustrate only part related to the present invention rather than full content in description, attached drawing.
Embodiment one
Fig. 1 is a kind of flow chart of the performance estimating method for artificial limb classification of motion device that the embodiment of the present invention one provides, this
Embodiment is applicable to be controlled the artificial limb classification of motion device in myoelectric limb the situation of Performance Evaluation, and this method can be by
The capability evaluating device of artificial limb classification of motion device performs, which can be realized by software and/or hardware, can generally integrate
In the terminals such as computer, this method specifically comprises the following steps：
Step 110, it is current test event to determine a test event in default multiple test events.
When amputee installs myoelectric limb first, in order to make myoelectric limb adapt to the muscle feature of the amputee itself,
Need to carry out action training to the artificial limb classification of motion device in myoelectric limb.The application is exactly the artificial limb action point completed to training
The assessment of the control performance of class device.
When the control performance to artificial limb classification of motion device is assessed, multiple test events can be set, each in advance
The size and location of test target in test event can be set in advance, can also be determined at random in specific test, and pin
Each test event respectively tests subject, to obtain the test result of the artificial limb classification of motion device of training completion,
The test result of each test event is finally integrated to obtain the assessment performance of artificial limb classification of motion device.Multiple test items therein
Mesh is at least two test events.
When the artificial limb classification of motion device completed to training is controlled the assessment of performance, first from default multiple tests
A test event is chosen in project, as current test event.When specifically choosing test event, can randomly select,
It can be chosen according to the order of test event.
Step 120, the starting point and test target in the current test event are shown in reference axis, and is continuously acquired
The electromyography signal of subject, identifies the electromyography signal to obtain result action, from the starting by artificial limb classification of motion device
Point starts to draw the corresponding movement locus of the result action, and recording test time.
The application assesses the performance of artificial limb classification of motion device based on Fitts' law.Wherein, Fitts' law is
In the model of the human behavior activity proposed in 1954, the basic concept of the law is Paul Fitts：Any point is moved to
Related with the range-to-go and size the time required to target's center position, the distance bigger time is longer, when target is bigger
Between it is shorter, meanwhile, Fitts' law given multiple parameters be used for weigh mobile efficiency.
Wherein, reference axis can be one-dimensional coordinate axis though, two-dimensional coordinate axis or 3-D walls and floor etc..Specifically can be according to training
The quantity of the identifiable action of artificial limb classification of motion device of completion is determined, and when such as can recognize that two actions, determines reference axis
For one-dimensional coordinate axis though；During recognizable four actions, it is two-dimensional coordinate axis to determine reference axis；During recognizable six actions, determine to sit
Parameter is 3-D walls and floor, it is only for citing, is not specifically limited.Myoelectric limb includes electrode, artificial limb classification of motion device, drives
Dynamic motor and mechanical system；Wherein, electrode is located on the deformed limb of amputee, for gathering the electromyography signal of amputee；Artificial limb moves
Make grader to be used to identify the electromyography signal on the deformed limb that electrode collects, obtain corresponding result action；Drive motor driving
Mechanical system completes the result action.When amputee wants to make an intention action, if driving motor drive machinery system
System completes the action, then artificial limb classification of motion device identifies successfully；If driving motor drive machinery system is completed and is intended to
Different malfunctions is acted, then artificial limb classification of motion device recognition failures.Wherein, electromyography signal is that list is moved in numerous muscle fibres
The superposition of metaaction current potential over time and space, surface electromyogram signal are electrical activities on superficial muscular electromyography signal and nerve cord
In the comprehensive effect of skin surface, it can reflect nervimuscular activity to a certain extent.Electromyography signal in the application can be with
For surface electromyogram signal.
Wherein, artificial limb classification of motion device is a software, can run in myoelectric limb, can also run on computer
Etc. in terminal, so as to fulfill the assessment of the control performance to myoelectric limb classification of motion device.Carried out to artificial limb classification of motion device
During assessment, subject can be the complete people of limbs, can also amputee, certainly, artificial limb classification of motion device must be directed to by
The grader that examination person is trained.
The result action that artificial limb classification of motion device identifies is mapped as a corresponding track.In current test event
During beginning, the position of the starting point and test target in current test event is shown in reference axis first, due to from starting point
It can include the corresponding track of multiple actions to test target to get to, so needing to continuously acquire multiple myoelectricities letter of subject
Number, get electrode collection subject an electromyography signal when, by the electromyography signal input artificial limb classification of motion device into
Row identification, obtains corresponding result action, determines that the result action is corresponding and treat track drafting, drawn since the starting point
This treats track drafting, the movement locus completed, then identifies that next electromyography signal obtains corresponding result action, and
Determine that this treats track drafting as starting point-rendering for the terminal of the corresponding movement locus treated track drafting, completed using last time,
The movement locus drawn twice before obtaining is completed, the result action drawn and identify that follow-up electromyography signal obtains of taking this as the standard
It is corresponding to treat track drafting, obtain final movement locus.In the test process of current test event, it can also record current
The testing time of test event.Wherein, test target can be shown round or square etc., be not specifically limited here.By
The movement locus of examination person may be along reference axis and with round-trip to a certain degree.Starting point can be any in reference axis
A bit, can be coordinate origin for convenience of calculation.In multiple test events, the size of test target can be different.
Step 130, according to the movement locus of current test event and the testing time, determine that current test event is directed to
Test the test value of evaluation index.
Wherein, test evaluation index is the index for each individual test event, is set in advance, and in advance
There is provided corresponding computation rule.It can be one to test evaluation index, or multiple.Test evaluation index can include
Throughput, path effective percentage, test result, overshoot at least one of number and reaction time.Throughput is used for quantifying to test
The performance of project, calculates, unit according to the distance of starting point to test target, the width of test target and testing time
For bits per second；In current test event, the distance of the central point of starting point to test target is beeline, the beeline
Divided by the length of actual movement locus is efficient for the test item destination path；Test result includes being successfully tested or testing mistake
Lose；In current test event, movement locus, which is moved in test target, not to stop the second preset time and removes test target again
It is defined as once overshooting；In current test event, from starting to show that test target treats that track drafting is completed to first
The required time is the reaction time.
After the movement locus of current test event is obtained, according to the movement locus of current test event and testing time,
According to the computation rule of test evaluation index, the value of the test evaluation index is calculated, as test value.
Step 140, comprehensive the multiple test event obtains the artificial limb classification of motion for the test value of test evaluation index
Device is directed to the assessed value of total evaluation index.
Wherein, total evaluation index is the overall target of artificial limb classification of motion device, the total evaluation of artificial limb classification of motion device
Index includes at least one of throughput, path effective percentage, completion rate, overshoot rate and reaction time.Each total evaluation refers to
Mark is corresponded with the index in test evaluation index respectively.
It is comprehensive according to the synthesis rule to the multiple test event for the test value of test evaluation index set in advance
Test value of the multiple test event for test evaluation index is closed, artificial limb classification of motion device is obtained and is directed to total evaluation index
Assessed value.Such as test value of multiple test events for test evaluation index is averaged, obtains artificial limb classification of motion device pin
To the assessed value of corresponding total evaluation index.
Exemplary, for the throughput in total evaluation index, path effective percentage and reaction time, in the multiple surveys of synthesis
During the test value of examination project, corresponding evaluation index can be averaged respectively, obtain artificial limb classification of motion device and be directed to respectively
The assessed value of these three total evaluation indexs.Completion rate is after the multiple test event is equal, is tested in test result
The result that the number of successful number divided by total test event obtains；Overshoot rate is to terminate in the multiple test event
Afterwards, the total degree of overshoot divided by the result that the number of total test event obtains be will appear from.
The technical solution of the present embodiment, by showing starting point and test target in current test event, and is continuously obtained
The electromyography signal of subject is taken, identifies that the electromyography signal obtains result action by artificial limb classification of motion device, and drawing result is moved
Make corresponding movement locus, recording test time, according to movement locus and testing time, determines current test event for test
The test value of evaluation index, the test value of comprehensive multiple test events, obtains the assessed value of artificial limb classification of motion device, realizes pair
The real-time assessment of artificial limb classification of motion device performance, and the assessment result quantified, assessment result is more accurate, compared to traditional
Subjective judgement method, there is the advantages of direct, objective, accurate.
On the basis of above-described embodiment, it is also optional including：
Test value of the current test event of real-time display for test evaluation index；
Obtain artificial limb classification of motion device be directed to total evaluation index assessed value when, show the assessed value.
It can include the display interface for drawing interface and evaluation index of track, certainly, rail in one display interface at the same time
The drafting interface of mark and the display interface of evaluation index can also be shown respectively in different display interfaces.In current test item
In purpose test process, virtual reality interface can also be included in display interface, a void is included in the virtual display interface
The upper limb of anthropomorphic body, after amputee makes intention action, result that the upper limb in the interface can be identified according to grader
Action, makes corresponding action, which may be identical with intention action, it is also possible to and it is different, so as to intuitively reflect this
The identification correctness of action.
In current test event test process, when obtaining current test event for the test value for testing evaluation index,
Can be with the current test event of real-time display for the test value for testing evaluation index.After the completion of multiple test events are equal, obtain
When artificial limb classification of motion device is directed to the assessed value of total evaluation index, display artificial limb classification of motion device is for total evaluation index
Assessed value, for subject refer to so as to its in follow-up training it is more targeted.
Embodiment two
Fig. 2 is a kind of flow chart of the performance estimating method of artificial limb classification of motion device provided by Embodiment 2 of the present invention, this
Embodiment is optimized on the basis of above-described embodiment, specifically current test event is tested to obtain movement locus
Detailed process is optimized, and this method specifically comprises the following steps：
Step 201, it is current test event to determine a test event in default multiple test events.
Step 202, the starting point and test target in current test event are shown in reference axis, by light when starting to test
Mark rests on the starting point, and starts timing.
Artificial limb classification of motion device is come out by limited a action training, therefore in actual use can there are artificial limb action
The situation of grader recognition failures, i.e., be identified as other actions by the intention stroke defect of amputee.
Exemplary, amputee is before using myoelectric limb, it is necessary to first be instructed to artificial limb classification of motion device therein
Practice to adapt it to itself muscular features.The embodiment of the present invention is carried out by taking two-dimensional coordinate axis as an example to artificial limb classification of motion device
During training, four actions are trained, including：Hand opens, receipts and wrist abduction in hand closure, wrist.Completing what four were acted
After the training of preset times, the artificial limb classification of motion device of training completion is obtained, at this moment artificial limb classification of motion device can be used for identifying
The electromyography signal of user obtains corresponding result action, you can so that amputee uses, can be commented by the embodiment of the present invention
Estimate the control performance of the artificial limb classification of motion device of training completion.
When starting current test event, show starting point and test target, start simultaneously at timing.
Step 203, the current electromyography signal that subject produces for the test target of current test event is obtained.
Subject moves in order to which control action track reaches the test target from the starting point, it is necessary to produce multiple intentions
Make, so as to produce multiple electromyography signals, that is, need to correspond to multiple result actions, so as to need independent for each electromyography signal
It is identified, using the electromyography signal of the subject currently got as current electromyography signal.
Step 204, by the current electromyography signal input artificial limb classification of motion device, corresponding current results action is obtained.
Current electromyography signal is inputted into the artificial limb classification of motion device that training completes, by the identification of artificial limb classification of motion device,
Obtain corresponding current results action.
Step 205, according to current results action and default result action and the correspondence of track drafting is treated,
Determine corresponding currently to treat track drafting.
Exemplary, Fig. 3 is correspondence of the default result action with treating track drafting in the embodiment of the present invention
Exemplary plot, as shown in figure 3, when result action is including receipts in hand opening, hand closure, wrist or wrist abduction, default result action
Correspondence with treating track drafting can include：When result action opens for hand, it is to draw along y-axis upwards to treat track drafting
Track；When result action closes for hand, track drafting is treated to draw along the downward track of y-axis；When result action is wrist abduction, treat
Track drafting is track of the drafting along x-axis to the left；Result action is the time receiving in wrist, and it is to draw along x-axis to the right to treat track drafting
Track.Circle of different sizes in Fig. 3 represents the test target of different sizes of diverse location, i.e., in each test event,
The size and location of test target can occur at random according to default size and location.
Current results action and the result action in correspondence of the default result action with treating track drafting are carried out
Matching, during successful match, obtains that the result action is corresponding to treat track drafting, is currently treated as corresponding with current results action
Track drafting.
Step 206, the end for the history track drafting that control cursor is completed from the starting point or according to history electromyography signal
Point start it is mobile draw it is described currently treat track drafting, form current track drafting.
Wherein, history electromyography signal is the electromyography signal before current electromyography signal, history in current test event
Track drafting is to identify that the result action that history electromyography signal obtains draws the track to be formed according to artificial limb classification of motion device, due to
Each the corresponding track drafting of history electromyography signal is connected, so history track drafting includes all history electromyography signals pair
The track drafting answered.In first electromyography signal obtained during current electromyography signal is current test event, rail is currently drawn
Mark is exactly that complete current treats track drafting；First flesh obtained in current electromyography signal is not current test event
During electric signal, current track drafting is the current track for treating track drafting for including history track drafting and completing.
In first electromyography signal obtained during current electromyography signal is current test event, cursor is controlled from starting point
Start to draw it is described currently treat track drafting, form current track drafting, current timing time can also be recorded, i.e., from current
Test event starts to this to be drawn according to the first electromyography signal the time to form current track drafting, when which also referred to as reacts
Between；In first electromyography signal obtained during current electromyography signal is not current test event, control cursor is from according to history
The terminal for the history track drafting that electromyography signal is completed, which starts to draw, currently treats track drafting, forms current track drafting.
Reaction time refers not only to the reaction speed of subject, and contains after subject makes intention action and lead to myoelectric limb
The time that artificial limb classification of motion device identifies result action is spent, therefore this index can embody the identification of artificial limb classification of motion device
Speed.
Step 207, judge whether timing time reaches the first preset time or the terminal of the current track drafting and be
It is no to reach the test target and be remained above or equal to the second preset time, step 208 if it is performed, if otherwise
Perform step 203.
Wherein, the first preset time is the stipulated time of current test event, and the second preset time is current track drafting
Reach test target, and the time that need to retain in test target.
When timing time reaches the first preset time, terminate current test event；Or the end in current track drafting
When the time that point reaches test target and keeps is more than or equal to the second preset time, terminate current test event.Terminate to work as
Step 208 is performed after preceding test event, if above two condition is unsatisfactory for, returns and performs step 203, to continue to obtain
The electromyography signal of subject.
Optionally, when the current track drafting of current test event meets following at least one conditions, current test is judged
Project testing fails：
When timing time reaches the first preset time, the terminal of the current track drafting does not reach the test mesh
Mark；
The current track drafting, which is moved in the test target, not to stop the second preset time and removes the test again
Object definition overshoots number and is more than preset times once to overshoot；
During the test, the terminal of the current track drafting deviate test target distance be more than pre-determined distance or
Subject feedback's test crash.
During the test, the distance of the terminal deviation test target of current track drafting is more than pre-determined distance, can be true
It is scheduled in the first preset time, the corresponding track of result action that the electromyography signal produced by subject identifies no longer can
Get at and reach the test target, accordingly, it is determined that current test event test crash, such case are referred to as being uncontrolled
Bounce.During the test, can be actively if subject thinks that oneself successfully cannot control cursor to be moved to test target
Feedback test fails.
Step 208, it is the movement locus to determine current track drafting, and determines that current timing time is the test
Time.
Step 209, according to the movement locus of current test event and the testing time, determine that current test event is directed to
Test the test value of evaluation index.
Wherein, it is described test evaluation index it is optional include throughput, path effective percentage, test result, overshoot number and instead
At least one of between seasonable.The definition of each test evaluation index has been described above in the above-described embodiments, and which is not described herein again.
When determining current test event for the test value for testing evaluation index, some tests the test value of evaluation index
It can be determined in the test process of current test event, such as the reaction time.
Step 210, comprehensive the multiple test event obtains the artificial limb classification of motion for the test value of test evaluation index
Device is directed to the assessed value of total evaluation index.
The technical solution of the present embodiment, by carrying out timing when current test event starts, passes through the artificial limb classification of motion
Device identifies that current electromyography signal obtains corresponding current results action, and determines corresponding currently to treat track drafting, real-time display
The drawing process of current track drafting, the terminal that the first preset time or current track drafting are reached in timing time reach survey
Examination target is simultaneously remained above or during equal to the second preset time, determines that current track drafting is movement locus, current timing
Time is the testing time, determines that current test event is directed to the test value of evaluation index according to the movement locus and testing time,
And the test value of comprehensive multiple test events, the assessed value of corresponding evaluation index is obtained, realizes the reality to prosthesis control performance
When assess, and the assessment result quantified, objectively carries out artificial limb classification of motion device so as to safety and precise effective
Assessment.
Embodiment three
Fig. 4 is a kind of structural representation of the capability evaluating device for artificial limb classification of motion device that the embodiment of the present invention three provides
Figure, the present embodiment are applicable to be controlled the artificial limb classification of motion device in myoelectric limb the situation of Performance Evaluation, the device
It can be realized by software and/or hardware, can be generally integrated in the terminals such as computer.As shown in figure 4, described in the present embodiment
The capability evaluating device of artificial limb classification of motion device includes：Test event chooses module 310, movement locus drafting module 320, test
It is worth determining module 330 and assessed value determining module 340.
Wherein, test event chooses module 310, and a test event for determining in default multiple test events is
Current test event；
Movement locus drafting module 320, for showing starting point and survey in the current test event in reference axis
Target is tried, and continuously acquires the electromyography signal of subject, the electromyography signal is identified by artificial limb classification of motion device to be tied
Fruit acts, and the corresponding movement locus of the result action, and recording test time are drawn since the starting point；
Test value determining module 330, for the movement locus according to current test event and the testing time, determines to work as
Test value of the preceding test event for test evaluation index；
Assessed value determining module 340, for integrating test value of the multiple test event for test evaluation index, obtains
The assessed value of total evaluation index is directed to artificial limb classification of motion device.
Optionally, the movement locus drafting module includes：
Point target display unit is played, for showing starting point and test target in current test event in reference axis,
By cursor dwell in the starting point when starting to test, and start timing；
Electromyography signal acquiring unit, the current flesh produced for obtaining subject for the test target of current test event
Electric signal；
Result action determination unit, for the current electromyography signal to be inputted artificial limb classification of motion device, obtains corresponding
Current results act；
Currently treat track drafting determination unit, for according to the current results action and default result action with treating
The correspondence of track drafting, determines corresponding currently to treat track drafting；
Track drawing unit, for controlling cursor from the starting point or being painted according to the history that preceding history electromyography signal is completed
The terminal of track processed start it is mobile draw it is described currently treat track drafting, form current track drafting, and repeated trigger myoelectricity letter
Number acquiring unit, the terminal that the first preset time or the current track drafting are reached until timing time reach the test
Target is simultaneously remained above or equal to the second preset time；
Movement locus determination unit, for determining that current track drafting is the movement locus, and determines current timing
Time is the testing time.
Optionally, when the current track drafting of current test event meets following at least one conditions, current test is judged
Project testing fails：
When timing time reaches the first preset time, the terminal of the current track drafting does not reach the test mesh
Mark；
The current track drafting, which is moved in the test target, not to stop the second preset time and removes the test again
Object definition overshoots number and is more than preset times once to overshoot；
During the test, the terminal of the current track drafting deviate test target distance be more than pre-determined distance or
Subject feedback's test crash.
Optionally, the test evaluation index includes throughput, path effective percentage, test result, overshoot number and reaction
At least one of time.
Optionally, further include：
Test value display module, the test value for the current test event of real-time display for test evaluation index；
Assessed value display module, for obtain artificial limb classification of motion device be directed to total evaluation index assessed value when, show
Show the assessed value.
The capability evaluating device of above-mentioned artificial limb classification of motion device can perform the artificial limb that any embodiment of the present invention is provided and move
Make the performance estimating method of grader, possess the corresponding function module of execution method and beneficial effect.It is not detailed in the present embodiment
The ins and outs described to the greatest extent, reference can be made to the performance estimating method for the artificial limb classification of motion device that any embodiment of the present invention provides.
Example IV
Fig. 5 is a kind of structure diagram for terminal that the embodiment of the present invention four provides, as shown in figure 4, the terminal includes place
Manage device 410, memory 420, input unit 430 and output device 440；In terminal the quantity of processor 410 can be one or
It is multiple, in Fig. 4 by taking a processor 410 as an example；Processor 410, memory 420, input unit 430 and output dress in terminal
Putting 440 can be connected by bus or other modes, in Fig. 4 exemplified by being connected by bus.
Memory 420 is used as a kind of computer-readable recording medium, and journey is can perform available for storage software program, computer
Sequence and module, such as the corresponding programmed instruction/module of performance estimating method of the artificial limb classification of motion device in the embodiment of the present invention
(for example, the test event in the capability evaluating device of artificial limb classification of motion device chooses module 310, movement locus drafting module
320th, test value determining module 330 and assessed value determining module 340).Processor 410 is stored in memory 420 by operation
Software program, instruction and module, so as to perform various function application and the data processing of terminal, that is, realize above-mentioned vacation
Main drive makees the performance estimating method of grader.
Memory 420 can mainly include storing program area and storage data field, wherein, storing program area can store operation system
Application program needed for system, at least one function；Storage data field can be stored uses created data etc. according to terminal.This
Outside, memory 420 can include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 420 can be into one
Step includes that relative to the remotely located memory of processor 510, these remote memories network connection to terminal can be passed through.On
The example for stating network includes but not limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
Input unit 430 can be used for the numeral or character information for receiving input, and produce with the user setting of terminal with
And the key signals input that function control is related.Output device 440 may include the display devices such as display screen.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium for including computer executable instructions, and the computer can be held
Row instruction by computer processor when being performed for performing a kind of performance estimating method of artificial limb classification of motion device, this method bag
Include：
It is current test event to determine a test event in default multiple test events；
The starting point and test target in the current test event are shown in reference axis, and continuously acquires subject's
Electromyography signal, identifies that the electromyography signal to obtain result action, is painted since the starting point by artificial limb classification of motion device
Make the corresponding movement locus of the result action, and recording test time；
According to the movement locus of current test event and the testing time, determine that current test event is assessed for test
The test value of index；
Comprehensive the multiple test event obtains artificial limb classification of motion device for whole for the test value of test evaluation index
The assessed value of body evaluation index.
Certainly, a kind of storage medium for including computer executable instructions that the embodiment of the present invention is provided, its computer
The method operation that executable instruction is not limited to the described above, can also carry out the artificial limb action that any embodiment of the present invention is provided
Relevant operation in the performance estimating method of grader.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but the former is more in many cases
Good embodiment.Based on such understanding, what technical scheme substantially in other words contributed the prior art
Part can be embodied in the form of software product, which can be stored in computer-readable recording medium
In, floppy disk, read-only storage (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server, or network equipment etc.) performs the method described in each embodiment of the present invention.
It is worth noting that, in the embodiment of the capability evaluating device of above-mentioned artificial limb classification of motion device, included is each
Unit and module are simply divided according to function logic, but are not limited to above-mentioned division, as long as can realize corresponding
Function；In addition, the specific name of each functional unit is also only to facilitate mutually differentiation, is not intended to limit the invention
Protection domain.
Note that it above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
It can include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
- A kind of 1. performance estimating method of artificial limb classification of motion device, it is characterised in that the described method includes：It is current test event to determine a test event in default multiple test events；The starting point and test target in the current test event are shown in reference axis, and continuously acquires the myoelectricity of subject Signal, identifies that the electromyography signal to obtain result action, draws institute since the starting point by artificial limb classification of motion device State the corresponding movement locus of result action, and recording test time；According to the movement locus of current test event and the testing time, determine current test event for test evaluation index Test value；Comprehensive the multiple test event obtains artificial limb classification of motion device and is commented for overall for the test value of test evaluation index Estimate the assessed value of index.
- 2. according to the method described in claim 1, it is characterized in that, rising in the current test event is shown in reference axis Initial point and test target, and the electromyography signal of subject is continuously acquired, the electromyography signal is identified by artificial limb classification of motion device To obtain result action, the corresponding movement locus of the result action, and recording test time are drawn since the starting point, Including：S1, show in reference axis starting point and test target in current test event, starts that cursor dwell exists during test The starting point, and start timing；S2, obtain the current electromyography signal that subject produces for the test target of current test event；S3, by the current electromyography signal input artificial limb classification of motion device, obtain corresponding current results action；S4, according to current results action and default result action and treat the correspondence of track drafting, determines to correspond to Current treat track drafting；S5, control cursor are moved since the terminal of the starting point or the history track drafting completed according to preceding history electromyography signal It is dynamic draw it is described currently treats track drafting, current track drafting is formed, and repeat S2-S5, until timing time reaches the The terminal of the one preset time either current track drafting reaches the test target and is remained above or pre- equal to second If the time；S6, determine that current track drafting is the movement locus, and determines that current timing time is the testing time.
- 3. according to the method described in claim 2, it is characterized in that, the current track drafting of current test event meet it is following extremely During a kind of few condition, current test event test crash is judged：When timing time reaches the first preset time, the terminal of the current track drafting does not reach the test target；The current track drafting, which is moved in the test target, not to stop the second preset time and removes the test target again It is defined as once overshooting, and overshoots number and be more than preset times；During the test, the distance of the terminal deviation test target of the current track drafting is more than pre-determined distance or tested Person's feedback test fails.
- 4. according to the method described in claim 1, it is characterized in that, the test evaluation index is effective including throughput, path Rate, test result, overshoot at least one of number and reaction time.
- 5. according to the method described in claim 1, it is characterized in that, further include：Test value of the current test event of real-time display for test evaluation index；Obtain artificial limb classification of motion device be directed to total evaluation index assessed value when, show the assessed value.
- 6. a kind of capability evaluating device of artificial limb classification of motion device, it is characterised in that described device includes：Test event chooses module, for determining that a test event in default multiple test events is current test item Mesh；Movement locus drafting module, for showing starting point and test target in the current test event in reference axis, And the electromyography signal of subject is continuously acquired, the electromyography signal is identified to obtain result action by artificial limb classification of motion device, The corresponding movement locus of the result action, and recording test time are drawn since the starting point；Test value determining module, for the movement locus according to current test event and the testing time, determines current test Test value of the project for test evaluation index；Assessed value determining module, for integrating test value of the multiple test event for test evaluation index, obtains artificial limb Classification of motion device is directed to the assessed value of total evaluation index.
- 7. device according to claim 6, it is characterised in that the movement locus drafting module includes：Point target display unit is played, for showing starting point and test target in current test event in reference axis, is started By cursor dwell in the starting point during test, and start timing；Electromyography signal acquiring unit, the current myoelectricity letter produced for obtaining subject for the test target of current test event Number；Result action determination unit, for the current electromyography signal to be inputted artificial limb classification of motion device, obtains corresponding current Result action；Currently track drafting determination unit is treated, for being drawn according to current results action and default result action with waiting The correspondence of track, determines corresponding currently to treat track drafting；Track drawing unit, the history for controlling cursor from the starting point or being completed according to preceding history electromyography signal draw rail The terminal of mark start it is mobile draw it is described currently treat track drafting, form current track drafting, and repeated trigger electromyography signal obtains Unit is taken, the terminal that the first preset time or the current track drafting are reached until timing time reaches the test target And it is remained above or equal to the second preset time；Movement locus determination unit, for determining that current track drafting is the movement locus, and determines current timing time For the testing time.
- 8. device according to claim 6, it is characterised in that further include：Test value display module, the test value for the current test event of real-time display for test evaluation index；Assessed value display module, for obtain artificial limb classification of motion device be directed to total evaluation index assessed value when, show institute Commentary valuation.
- 9. a kind of terminal, it is characterised in that the terminal includes：One or more processors；Storage device, for storing one or more programs,When one or more of programs are performed by one or more of processors so that one or more of processors are real The now performance estimating method of the artificial limb classification of motion device as described in any in claim 1-5.
- 10. a kind of computer-readable storage medium, is stored thereon with computer program, it is characterised in that the program is executed by processor The performance estimating method of artificial limb classification of motion devices of the Shi Shixian as described in any in claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711336803.4A CN108008821B (en) | 2017-12-14 | 2017-12-14 | Performance evaluation method, device, terminal and storage medium of artificial limb action classifier |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711336803.4A CN108008821B (en) | 2017-12-14 | 2017-12-14 | Performance evaluation method, device, terminal and storage medium of artificial limb action classifier |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108008821A true CN108008821A (en) | 2018-05-08 |
| CN108008821B CN108008821B (en) | 2021-04-02 |
Family
ID=62058818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711336803.4A Active CN108008821B (en) | 2017-12-14 | 2017-12-14 | Performance evaluation method, device, terminal and storage medium of artificial limb action classifier |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108008821B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101987048A (en) * | 2009-08-03 | 2011-03-23 | 深圳先进技术研究院 | Artificial limb control method and system thereof |
| US20140371871A1 (en) * | 2013-06-12 | 2014-12-18 | Georg-August-Universitaet Goettingen Stiffung Oeffentlichen Rechts, Universitaetsmedizin | Control of limb device |
| CN106371590A (en) * | 2016-08-29 | 2017-02-01 | 华南理工大学 | High-performance motor imagery online brain-computer interface system based on OpenVIBE |
| CN106845419A (en) * | 2017-01-22 | 2017-06-13 | 深圳市唯特视科技有限公司 | A kind of method that Gait Recognition performance is assessed based on capturing movement framework |
-
2017
- 2017-12-14 CN CN201711336803.4A patent/CN108008821B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101987048A (en) * | 2009-08-03 | 2011-03-23 | 深圳先进技术研究院 | Artificial limb control method and system thereof |
| US20140371871A1 (en) * | 2013-06-12 | 2014-12-18 | Georg-August-Universitaet Goettingen Stiffung Oeffentlichen Rechts, Universitaetsmedizin | Control of limb device |
| CN106371590A (en) * | 2016-08-29 | 2017-02-01 | 华南理工大学 | High-performance motor imagery online brain-computer interface system based on OpenVIBE |
| CN106845419A (en) * | 2017-01-22 | 2017-06-13 | 深圳市唯特视科技有限公司 | A kind of method that Gait Recognition performance is assessed based on capturing movement framework |
Non-Patent Citations (2)
| Title |
|---|
| ORTIZ-CATALAN, MAX;HKANSSON, BO;BRNEMARK, RICKARD;: "Real-Time and Simultaneous Control of Artificial Limbs Based on Pattern Recognition Algorithms", 《IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING》 * |
| 田岚等: "基于微处理器的多功能肌电假肢控制系统", 《集成技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108008821B (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6952687B2 (en) | Cognitive state machine for prosthetic systems | |
| Bonaiuto et al. | Extending the mirror neuron system model, II: what did I just do? A new role for mirror neurons | |
| CN110710970B (en) | Method and device for recognizing limb actions, computer equipment and storage medium | |
| CN108289634B (en) | System and method for an operator to learn a brain-computer interface | |
| Mollazadeh et al. | Principal components of hand kinematics and neurophysiological signals in motor cortex during reach to grasp movements | |
| JP7070252B2 (en) | Performance measuring device, performance measuring method and performance measuring program | |
| AU2010286471A1 (en) | Characterizing a physical capability by motion analysis | |
| JP7070253B2 (en) | Performance measuring device, performance measuring method and performance measuring program | |
| US20210204853A1 (en) | Systems and Methods for Cognitive Diagnostics in Connection with Major Depressive Disorder and Response to Antidepressants | |
| KR20210076936A (en) | Cognitive platform for deriving effort metrics for optimizing cognitive therapy | |
| Soleymani et al. | Surgical skill evaluation from robot-assisted surgery recordings | |
| Amor et al. | Constrained particle filtering for movement identification in forearm prosthesis | |
| US7442212B2 (en) | Decoding algorithm for neuronal responses | |
| Pekedis et al. | Structural health monitoring for bolt loosening via a non-invasive vibro-haptics human–machine cooperative interface | |
| CA3157380A1 (en) | Systems and methods for cognitive diagnostics for neurological disorders: parkinson's disease and comorbid depression | |
| CN108008821A (en) | Performance estimating method, device, terminal and the storage medium of artificial limb classification of motion device | |
| US20230010664A1 (en) | Reinforcement Learning Based Adaptive State Observation for Brain-Machine Interface | |
| Wanglavan et al. | The development of attention detection model from child behavior for robot-assisted autism therapy | |
| Xue et al. | Using Probabilistic Movement Primitives in Analyzing Human Motion Differences Under Transcranial Current Stimulation | |
| Tichon | Evaluation of virtual reality training using affect | |
| Nisky et al. | Three alternatives to measure the human-likeness of a handshake model in a Turing-like test | |
| Liu et al. | Humans use similar posture sequences in a whole-body tracing task | |
| Trejos et al. | The application of force sensing to skills assessment in minimally invasive surgery | |
| Yang | Fatigue effect on task performance in haptic virtual environment for home-based rehabilitation | |
| Derry et al. | Extending myoelectric prosthesis control with shapable automation: a first assessment |
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 |