CN106527716A - Wearable equipment based on electromyographic signals and interactive method between wearable equipment and terminal - Google Patents
Wearable equipment based on electromyographic signals and interactive method between wearable equipment and terminal Download PDFInfo
- Publication number
- CN106527716A CN106527716A CN201610982437.9A CN201610982437A CN106527716A CN 106527716 A CN106527716 A CN 106527716A CN 201610982437 A CN201610982437 A CN 201610982437A CN 106527716 A CN106527716 A CN 106527716A
- Authority
- CN
- China
- Prior art keywords
- electromyographic signal
- gesture
- signal
- default
- eigenvalue
- 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
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Neurosurgery (AREA)
- General Health & Medical Sciences (AREA)
- Neurology (AREA)
- Health & Medical Sciences (AREA)
- Dermatology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- User Interface Of Digital Computer (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses wearable equipment based on electromyographic signals and an interactive method between the wearable equipment and a terminal. The method comprises the steps that operation electromyographic signal feature values are calculated according to the electromyographic signals of operation gestures, and the operation electromyographic signal feature values form an operation feature matrix; the operation feature matrix is compared with a preset feature matrix to acquire a terminal operation instruction corresponding to the operation feature matrix. The electromyographic signals of the operation gestures are calculated to obtain the operation electromyographic signal feature values, the operation feature matrix is formed and compared with the preset feature matrix, in this way, the terminal operation instruction corresponding to the operation feature matrix can be acquired, and the purpose of interaction with the terminal is achieved.
Description
Technical field
It is the present invention relates to the technical field of the wearable device based on electromyographic signal more particularly to a kind of based on electromyographic signal
Wearable device and its exchange method with terminal.
Background technology
Surface myoelectric (suRFace electromyography, sEMG) signal is that neuromuscular system is carrying out randomness
During the one-dimensional voltage obtained with biological Electrical change Jing surface electrodes guiding during non-random sexual activity, amplification, display and record
Between sequence signal, its amplitude is about 10-5000 μ V, and frequency 20-500Hz, signal aspect have stronger randomness and unstable
Property.Compared with traditional pin type electromyogram, the spatial resolution of sEMG is relatively low, but space exploration is larger, repeatability compared with
It is good, for Sports Scientific Research, rehabilitation medicine clinic and man-machine interaction etc. are with important learning value and application value
At present, what smart terminal product occurred is more and more, also so that people require more and more higher to intelligentized control method.With
This is simultaneously also with rapid changepl. never-ending changes and improvements for the research of electromyographic signal both at home and abroad, extracts more many from the initial a large amount of electrodes of needs
Eigenvalue is planted, simple wrist turnover is just recognized, to the hand that Various Complex nowadays can be recognized by small part electrode
Action.
The content of the invention
Present invention is primarily targeted at proposing a kind of wearable device based on electromyographic signal and its side of interaction with terminal
Method, it is intended to various gesture motions are recognized based on hand electromyographic signal, reaches the purpose of control terminal by different actions.
For achieving the above object, the side of interaction of a kind of wearable device based on electromyographic signal and terminal that the present invention is provided
Method, it is characterised in that including step:
Operation electromyographic signal eigenvalue is calculated according to the electromyographic signal of operating gesture, by the operation electromyographic signal eigenvalue
Composition performance characteristic matrix;
The performance characteristic matrix and default eigenmatrix are compared, is obtained corresponding with the performance characteristic matrix
Terminal operation instruction.
Alternatively, when operation electromyographic signal eigenvalue is calculated according to the electromyographic signal of operating gesture, including step:
The electromyographic signal of the operating gesture is filtered after noise reduction process;
Windowing process is carried out to the electromyographic signal for being filtered the operating gesture after noise reduction process by formula (1);
Wherein, Qn is the total energy value of the segment signal, and tn is the starting point of a certain time-ofday signals, and x represents the segment signal, represents
According to the signal segment length that the energy threshold of the electromyographic signal of the operating gesture is obtained;
Using sym8 small echos as basic function, the electromyographic signal of the operating gesture for being to length carries out wavelet packet point
Solution, and the statistical nature of every layer of wavelet coefficient is calculated respectively.
Alternatively, as basic function electromyographic signal of the length for the operating gesture of N is carried out using sym8 small echos
WAVELET PACKET DECOMPOSITION, and when calculating the statistical nature of every layer of wavelet coefficient respectively, including step:
The energy of every layer of wavelet coefficient is calculated by formula (2);
Wherein, j is port number and j=1:4;Total energy values of the Ej for wavelet coefficient, N is wavelet coefficient in the segment signal
Number, wavelet coefficients of the ri for corresponding point;
The gross energy of wavelet coefficient is calculated by formula (3);
E=E1+E2+E3+E4(3);
The energy percentage of every layer of wavelet coefficient is calculated by formula (4);
ρj=Ej/E (4);
The absolute average of wavelet coefficient is calculated by formula (5);
The variance of wavelet coefficient is calculated by formula (6);
Alternatively, before operation electromyographic signal eigenvalue is calculated according to the electromyographic signal of operating gesture, also including step:
Detect the intensity of the electromyographic signal of the operating gesture;If the intensity of the electromyographic signal of the operating gesture is higher than preset strength
Value, then into next step.
Alternatively, the default eigenmatrix is the default electromyographic signal calculated according to the electromyographic signal of default gesture
Eigenvalue cluster into;Also include the calibration steps to the default eigenmatrix:
The collection standard gesture consistent with the default gesture simultaneously calculates mark according to the electromyographic signal of the standard gesture
Quasi- electromyographic signal eigenvalue;The standard electromyographic signal eigenvalue is write into the described default spy corresponding with the default gesture
Levy in matrix.
Alternatively, also include the spread step to presetting eigenmatrix:
Self-defining first gesture is gathered, the first electromyographic signal feature is calculated according to the electromyographic signal of the first gesture
Value, and by the first electromyographic signal eigenvalue cluster into fisrt feature matrix;
The first gesture is gathered again, and the second myoelectricity is calculated according to the electromyographic signal of the first gesture for gathering again
Signal characteristic value, and the second electromyographic signal eigenvalue is write in the fisrt feature matrix;
When the times of collection of the first gesture is until after reach preset times, receive its corresponding terminal operation instruction,
And will be the fisrt feature matrix associated with the corresponding terminal operation instruction;
When the operating gesture is that the electromyographic signal eigenvalue in the first gesture, and the fisrt feature matrix does not reach
During to threshold value, by the first gesture corresponding operation electromyographic signal eigenvalue write fisrt feature matrix.
Additionally, for achieving the above object, the present invention also proposes a kind of wearable device based on electromyographic signal, including control system
System, it is characterised in that the control system includes:
Performance characteristic matrix calculation unit, for calculating operation electromyographic signal feature according to the electromyographic signal of operating gesture
Value, by the operation electromyographic signal eigenvalue cluster into performance characteristic matrix;
Terminal operation instructs acquiring unit, for the performance characteristic matrix and default eigenmatrix are compared, obtains
Take the terminal operation instruction corresponding with the performance characteristic matrix
Alternatively, the performance characteristic matrix calculation unit includes:
Filtering noise reduction process module, for being filtered noise reduction process to the electromyographic signal of the operating gesture;
Windowing processing module, for by formula (1) to being filtered the myoelectricity of the operating gesture after noise reduction process
Signal carries out windowing process;
Wherein, QnFor the total energy value of the segment signal, tnFor the starting point of a certain time-ofday signals, x represents the segment signal, and T is represented
According to the signal segment length that the energy threshold of the electromyographic signal of the operating gesture is obtained;
Statistical nature computing module, for using sym8 small echos as basic function, be the operating gesture of N to length
Electromyographic signal carries out WAVELET PACKET DECOMPOSITION, and calculates the statistical nature of every layer of wavelet coefficient respectively.
Alternatively, the control system also includes detecting signal unit, for detecting the electromyographic signal of the operating gesture
Intensity;If the intensity of the electromyographic signal of the operating gesture is higher than preset strength value, the control system is made in unlatching
State.
Alternatively, the default eigenmatrix is the default electromyographic signal calculated according to the electromyographic signal of default gesture
Eigenvalue cluster into;During the control system also includes default eigenmatrix alignment unit and default eigenmatrix expanding element
At least one;
The default eigenmatrix alignment unit is used to gather the standard gesture consistent with the default gesture basis
The electromyographic signal of the standard gesture calculates standard electromyographic signal eigenvalue;It is additionally operable to write the standard electromyographic signal eigenvalue
Enter in the described default eigenmatrix corresponding with the default gesture;
The default eigenmatrix expanding element includes:
Collection computing module, for gathering self-defining first gesture, calculates according to the electromyographic signal of the first gesture
First electromyographic signal eigenvalue, and by the first electromyographic signal eigenvalue cluster into fisrt feature matrix;
The collection computing module is additionally operable to gather the first gesture again, according to the first gesture for gathering again
Electromyographic signal calculate the second electromyographic signal eigenvalue, and will the second electromyographic signal eigenvalue write fisrt feature square
In battle array;
Relating module, for when the times of collection of the first gesture until after reach preset times, receiving which corresponding
Terminal operation is instructed, and will be the fisrt feature matrix associated with the corresponding terminal operation instruction;
Eigenvalue complementary module, in when the operating gesture for the first gesture, and the fisrt feature matrix
Electromyographic signal eigenvalue when being not up to threshold value, will be the first gesture corresponding operation electromyographic signal eigenvalue write first special
Levy matrix.
A kind of wearable device based on electromyographic signal proposed by the present invention and its exchange method with terminal, are believed based on myoelectricity
Number wearable device collect arm wrist human skin's electromyographic signal by using detecting electrode, by signal arrange put
Greatly, and the eigenvalue cluster of correlation is obtained into eigenmatrix, by comparing with default eigenmatrix, obtain and the operation is special
Levy the corresponding terminal operation instruction of matrix.
Description of the drawings
Structural representations of the Fig. 1 for the control system of the wearable device based on electromyographic signal of first embodiment of the invention;
Structural representations of the Fig. 2 for the performance characteristic matrix calculation unit of second embodiment of the invention;
Structural representations of the Fig. 3 for the control system of the wearable device based on electromyographic signal of fourth embodiment of the invention;
Structural representations of the Fig. 4 for the control system of the wearable device based on electromyographic signal of fifth embodiment of the invention;
Structural representations of the Fig. 5 for the control system of the wearable device based on electromyographic signal of sixth embodiment of the invention;
Fig. 6 is shown with the flow process of the exchange method of terminal for the wearable device based on electromyographic signal of seventh embodiment of the invention
It is intended to;
Fig. 7 is eighth embodiment of the invention when operation electromyographic signal eigenvalue is calculated according to the electromyographic signal of operating gesture
Schematic flow sheet;
Fig. 8 is shown with the flow process of the exchange method of terminal for the wearable device based on electromyographic signal of tenth embodiment of the invention
It is intended to;
Schematic flow sheets of the Fig. 9 for the calibration steps of the default eigenmatrix of eleventh embodiment of the invention;
Schematic flow sheets of the Figure 10 for the spread step of the default eigenmatrix of twelveth embodiment of the invention;
The realization of the object of the invention, functional characteristics and advantage will be described further in conjunction with the embodiments referring to the drawings.
Specific embodiment
It should be appreciated that specific embodiment described herein is not intended to limit the present invention only to explain the present invention.
In follow-up description, using the suffix for representing such as " module ", " part " or " unit " of element it is only
Be conducive to the explanation of the present invention, itself does not have specific meaning.Therefore, " module " mixedly can be made with " part "
With.
Terminal can be implemented in a variety of manners.For example, the present invention described in terminal can include such as mobile phone,
Smart phone, notebook computer, digit broadcasting receiver, PDA (personal digital assistant), PAD (panel computer), PMP are (portable
Multimedia player), the mobile terminal of guider etc. and such as numeral TV, desk computer, television set etc. consolidate
Determine terminal.
As shown in figure 1, first embodiment of the invention provides a kind of wearable device based on electromyographic signal, including control system
System, the control system include performance characteristic matrix calculation unit 10 and terminal operation instruction acquiring unit 20.
Performance characteristic matrix calculation unit 10 operates electromyographic signal feature for calculating according to the electromyographic signal of operating gesture
Value, and electromyographic signal eigenvalue cluster will be operated into performance characteristic matrix.Wherein, the electromyographic signal collection of operating gesture can be adopted
Differential electrode configuration mode (can certainly be gathered using other modes) of the prior art, sample rate is set to 2000Hz
(this sample rate can be arranged as the case may be).
Terminal operation instructs acquiring unit 20 for performance characteristic matrix is compared with default eigenmatrix, obtain with
The corresponding terminal operation instruction of performance characteristic matrix.More specifically, above-mentioned default eigenmatrix is to be pre-stored in data base for example
In grader " NET ", default eigenmatrix is special by presetting the calculated default electromyographic signal of the electromyographic signal of gesture
Value indicative composition, its computational methods is consistent with the method for performance characteristic matrix.Can also have in the data base and default spy
Levy the corresponding terminal operation instruction of matrix.
Second embodiment of the invention provides a kind of wearable device based on electromyographic signal, including control system, the control system
System includes performance characteristic matrix calculation unit 10 and terminal operation instruction acquiring unit 20.
Performance characteristic matrix calculation unit 10 operates electromyographic signal feature for calculating according to the electromyographic signal of operating gesture
Value, and electromyographic signal eigenvalue cluster will be operated into performance characteristic matrix;Wherein, the electromyographic signal collection of operating gesture can be adopted
Differential electrode configuration mode (can certainly be gathered using other modes) of the prior art, sample rate is set to 2000Hz
(this sample rate can be arranged as the case may be).
Terminal operation instructs acquiring unit 20 for performance characteristic matrix is compared with default eigenmatrix, obtain with
The corresponding terminal operation instruction of performance characteristic matrix.Above-mentioned default eigenmatrix is to be pre-stored in data base's such as grader
In " NET ", default eigenmatrix is the calculated default electromyographic signal eigenvalue cluster of electromyographic signal by presetting gesture
Into, its computational methods is consistent with the method for performance characteristic matrix.Can also have in the data base and default eigenmatrix
Corresponding terminal operation instruction.
As shown in Fig. 2 in the present embodiment, performance characteristic matrix calculation unit 10 includes filtering noise reduction process module 11, adds
Window processing module 12 and statistical nature computing module 13.
Wherein, filter noise reduction process module 11 for noise reduction process being filtered to the electromyographic signal of operating gesture;According to
The feature (20-500Hz) of electromyographic signal so as to by conventional band filter, filter less than 20Hz and more than 500Hz's
Noise, on here basis, then by noise reduction in the little wavestrip of prior art, makes the signal for collecting making an uproar between 20-500Hz
Sound has obtained a certain degree of suppression, more than process after signal when it is purer relative to primary signal is collected
Electromyographic signal.
Windowing processing module 12 is used for by formula (1) to being filtered the electromyographic signal of the operating gesture after noise reduction process
Carry out windowing process;
Wherein, QnFor the total energy value of the segment signal, tnFor the starting point of a certain time-ofday signals, x represents the segment signal, and T is represented
According to the signal segment length that the energy threshold of the electromyographic signal of operating gesture is obtained.
More specifically, in order to obtain the electromyographic signal signal characteristic parameter with regard to operating gesture, needing the noise reduction to obtaining
The electromyographic signal of operating gesture afterwards carries out active segment detection.For the electromyographic signal of some operating gesture, according to its energy
The change of value, carries out windowing process to which.
The principle of windowing process is estimated according to the signal energy value for collecting, according to formula (1) by whole
The calculating of signal energy, and the energy threshold A and B of the electromyographic signal according to the operating gesture, carry out active segment detection to which.Its
In, A, B are calculated obtained from meansigma methodss by the starting point to multiple actions and the continuous data of one section of terminating point.Specifically
, it will be assumed that elapsed from signal starting point backward, during movement, when occurring continuous 500, (this numerical value can be made by oneself
Justice) energy value of individual point is all higher than threshold value A, then it is assumed that it is exactly the starting point of action signal here, then proceedes to elapse backward, when goes out
When now the energy value of the individual point of continuous 500 (this numerical value can be with self-defined) is less than B, we are considered as action signal and tie herein
Beam.
The mobile windowing process of the electromyographic signal energy by this to operating gesture, and set with reference to suitable threshold parameter
Put, so that it may accurately detect the electromyographic signal of single operating gesture.Here the signal value for obtaining is seen in time domain, in threshold
Between value A and B, signal is normal value;And the signal outside A and B, entirely null value, now just it is believed that active segment
In signal after detection, the continuous part of independent non-zero is the electromyographic signal of our operating gesture.
Statistical nature computing module 13 is used for using sym8 small echos as basic function, to the operating gesture that length is N
Electromyographic signal carry out WAVELET PACKET DECOMPOSITION, and calculate the statistical nature of every layer of wavelet coefficient respectively;Those statistical natures can be made
To operate electromyographic signal eigenvalue.
Third embodiment of the invention provides a kind of wearable device based on electromyographic signal, including control system, the control system
System includes performance characteristic matrix calculation unit 10 and terminal operation instruction acquiring unit 20.
Performance characteristic matrix calculation unit 10 operates electromyographic signal feature for calculating according to the electromyographic signal of operating gesture
Value, and electromyographic signal eigenvalue cluster will be operated into performance characteristic matrix;Wherein, the electromyographic signal collection of operating gesture can be adopted
Differential electrode configuration mode (can certainly be gathered using other modes) of the prior art, sample rate is set to 2000Hz
(this sample rate can be arranged as the case may be).
Terminal operation instructs acquiring unit 20 for performance characteristic matrix is compared with default eigenmatrix, obtain with
The corresponding terminal operation instruction of performance characteristic matrix.Above-mentioned default eigenmatrix is to be pre-stored in data base's such as grader
In " NET ", default eigenmatrix is the calculated default electromyographic signal eigenvalue cluster of electromyographic signal by presetting gesture
Into, its computational methods is consistent with the method for performance characteristic matrix.Can also have in the data base and default eigenmatrix
Corresponding terminal operation instruction.
As shown in Fig. 2 the performance characteristic matrix calculation unit 10 includes filtering noise reduction process module 11, windowing processing module
12 and statistical nature computing module 13.
Wherein, filter noise reduction process module 11 for noise reduction process being filtered to the electromyographic signal of operating gesture;According to
The feature (20-500Hz) of electromyographic signal so as to by conventional band filter, filter less than 20Hz and more than 500Hz's
Noise, on here basis, then by noise reduction in the little wavestrip of prior art, makes the signal for collecting making an uproar between 20-500Hz
Sound has obtained a certain degree of suppression, more than process after signal when it is purer relative to primary signal is collected
Electromyographic signal.
Windowing processing module 12 is used for by formula (1) to being filtered the electromyographic signal of the operating gesture after noise reduction process
Carry out windowing process;
Wherein, QnFor the total energy value of the segment signal, tnFor the starting point of a certain time-ofday signals, x represents the segment signal, and T is represented
According to the signal segment length that the energy threshold of the electromyographic signal of operating gesture is obtained.
More specifically, in order to obtain the electromyographic signal signal characteristic parameter with regard to operating gesture, needing the noise reduction to obtaining
The electromyographic signal of operating gesture afterwards carries out active segment detection.For the electromyographic signal of some operating gesture, according to its energy
The change of value, carries out windowing process to which.
The principle of windowing process is estimated according to the signal energy value for collecting, according to formula (1) by whole
The calculating of signal energy, and the energy threshold A and B of the electromyographic signal according to the operating gesture, carry out active segment detection to which.Its
In, A, B are calculated obtained from meansigma methodss by the starting point to multiple actions and the continuous data of one section of terminating point.Specifically
, it will be assumed that elapsed from signal starting point backward, during movement, when occurring continuous 500, (this numerical value can be made by oneself
Justice) energy value of individual point is all higher than threshold value A, then it is assumed that it is exactly the starting point of action signal here, then proceedes to elapse backward, when goes out
When now the energy value of the individual point of continuous 500 (this numerical value can be with self-defined) is less than B, we are considered as action signal and tie herein
Beam.
The mobile windowing process of the electromyographic signal energy by this to operating gesture, and set with reference to suitable threshold parameter
Put, so that it may accurately detect the electromyographic signal of single operating gesture.Here the signal value for obtaining is seen in time domain, in threshold
Between value A and B, signal is normal value;And the signal outside A and B, entirely null value, now just it is believed that active segment
In signal after detection, the continuous part of independent non-zero is the electromyographic signal of our operating gesture.
Statistical nature computing module 13 is used for using sym8 small echos as basic function, to the operating gesture that length is N
Electromyographic signal carry out WAVELET PACKET DECOMPOSITION, and calculate the statistical nature of every layer of wavelet coefficient respectively;Those statistical natures can be made
To operate electromyographic signal eigenvalue.
In the present embodiment statistical nature computing module 13 specifically for:
The energy of every layer of wavelet coefficient is calculated by formula (2);
Wherein, j is port number and j=1:4;Total energy values of the Ej for wavelet coefficient, N is wavelet coefficient in the segment signal
Number, wavelet coefficients of the ri for corresponding point;
The gross energy of wavelet coefficient is calculated by formula (3);
E=E1+E2+E3+E4(3);
The energy percentage of every layer of wavelet coefficient is calculated by formula (4);
ρj=Ej/E (4);
The absolute average of wavelet coefficient is calculated by formula (5);
The variance of wavelet coefficient is calculated by formula (6);
As shown in figure 3, fourth embodiment of the invention provides a kind of wearable device based on electromyographic signal, including control system
System, the control system include performance characteristic matrix calculation unit 10, terminal operation instruction acquiring unit 20, detecting signal unit
30。
Performance characteristic matrix calculation unit 10 operates electromyographic signal feature for calculating according to the electromyographic signal of operating gesture
Value, and electromyographic signal eigenvalue cluster will be operated into performance characteristic matrix;Wherein, the electromyographic signal collection of operating gesture can be adopted
Differential electrode configuration mode (can certainly be gathered using other modes) of the prior art, sample rate is set to 2000Hz
(this sample rate can be arranged as the case may be).
Terminal operation instructs acquiring unit 20 for performance characteristic matrix is compared with default eigenmatrix, obtain with
The corresponding terminal operation instruction of performance characteristic matrix;Above-mentioned default eigenmatrix is to be pre-stored in data base's such as grader
In " NET ", default eigenmatrix is the calculated default electromyographic signal eigenvalue cluster of electromyographic signal by presetting gesture
Into, its computational methods is consistent with the method for performance characteristic matrix.Can also have in the data base and default eigenmatrix
Corresponding terminal operation instruction.As shown in Fig. 2 in the present embodiment, the performance characteristic matrix calculation unit 10 can equally be wrapped
Include filtering noise reduction process module 11, windowing processing module 12 and statistical nature computing module 13;Will not be described here.
Detecting signal unit 30 is used for the intensity of the electromyographic signal for detecting the operating gesture;If the flesh of the operating gesture
The intensity of the signal of telecommunication is, for example, 10 μ V higher than preset strength value, then make control system be in opening.In the present embodiment, work as letter
When the electromyographic signal intensity that number detector unit 30 is detected is higher than preset strength value, makes control system in open mode, work as letter
When the electromyographic signal intensity that number detector unit 30 is detected is less than preset strength value, control system is made in holding state, to reach
To the effect of the intelligent switch for making control system.
As shown in figure 4, fifth embodiment of the invention provides a kind of wearable device based on electromyographic signal, including control system
System, the control system include performance characteristic matrix calculation unit 10, terminal operation instruction acquiring unit 20, detecting signal unit
30th, preset eigenmatrix alignment unit 40.
Performance characteristic matrix calculation unit 10 operates electromyographic signal feature for calculating according to the electromyographic signal of operating gesture
Value, and electromyographic signal eigenvalue cluster will be operated into performance characteristic matrix;Wherein, the electromyographic signal collection of operating gesture can be adopted
Differential electrode configuration mode (can certainly be gathered using other modes) of the prior art, sample rate is set to 2000Hz
(this sample rate can be arranged as the case may be).
Terminal operation instructs acquiring unit 20 for performance characteristic matrix is compared with default eigenmatrix, obtain with
The corresponding terminal operation instruction of performance characteristic matrix;Above-mentioned default eigenmatrix is to be pre-stored in data base's such as grader
In " NET ", default eigenmatrix is the calculated default electromyographic signal eigenvalue cluster of electromyographic signal by presetting gesture
Into, its computational methods is consistent with the method for performance characteristic matrix.Can also have in the data base and default eigenmatrix
Corresponding terminal operation instruction.As shown in Fig. 2 in the present embodiment, the performance characteristic matrix calculation unit 10 can equally be wrapped
Include filtering noise reduction process module 11, windowing processing module 12 and statistical nature computing module 13;Will not be described here.
Detecting signal unit 30 is used for the intensity of the electromyographic signal for detecting the operating gesture;If the flesh of the operating gesture
The intensity of the signal of telecommunication is, for example, 10 μ V higher than preset strength value, then make control system be in opening.In the present embodiment, work as letter
When the electromyographic signal intensity that number detector unit 30 is detected is higher than preset strength value, makes control system in open mode, work as letter
When the electromyographic signal intensity that number detector unit 30 is detected is less than preset strength value, control system is made in holding state, to reach
To the effect of the intelligent switch for making control system.
Default eigenmatrix alignment unit 40 is used to gather the standard gesture consistent with default gesture and according to standard handss
The electromyographic signal of gesture calculates standard electromyographic signal eigenvalue;It is additionally operable to write and the default handss standard electromyographic signal eigenvalue
In the corresponding default eigenmatrix of gesture.
As user action custom is different, it is likely to imperfect or not accurate enough when standard operation is completed, such as
When user does the action of next, the angle that palm is lifted upwards is 45 degree or so, and we are in preset training of dispatching from the factory
Essentially 75 degree or so in data, such situation may result in the discrimination of the action than relatively low.
The standard operation that just can be done to user by presetting eigenmatrix alignment unit 40 is sampled, and will sampling
The eigenvalue for obtaining is write in same matrix with the preset eigenvalue that dispatches from the factory, and retrieves grader " NET ", thus, identification
Rate will be greatly improved.
Assume that preset features value is 3000 and is worth (A1-A3000) grader is trained as eigenvalue, most open in user
Beginning N (0<N<3000) in the middle of secondary beginning operating process, whenever an action is completed, system can point out user to select the dynamic of oneself
Whether it is correctly validated, if correct recognize, then by the signal of this group of data according to above-mentioned flow processing, and obtains corresponding
Eigenvalue in (B1-BN), to the accuracy for increasing identification.Here restriction to be made, the study of standard operation at most can only
It is fixed the data of action, it is assumed that for N number of, when the quantity of standard operation study is more than N, system can be automatically deleted
The data for learning earliest, to guarantee standard operation study less than N.
As shown in figure 5, sixth embodiment of the invention provides a kind of wearable device based on electromyographic signal, including control system
System, the control system include performance characteristic matrix calculation unit 10, terminal operation instruction acquiring unit 20, detecting signal unit
30th, preset eigenmatrix expanding element 50.
Performance characteristic matrix calculation unit 10 operates electromyographic signal feature for calculating according to the electromyographic signal of operating gesture
Value, and electromyographic signal eigenvalue cluster will be operated into performance characteristic matrix;Wherein, the electromyographic signal collection of operating gesture can be adopted
Differential electrode configuration mode (can certainly be gathered using other modes) of the prior art, sample rate is set to 2000Hz
(this sample rate can be arranged as the case may be).
Terminal operation instructs acquiring unit 20 for performance characteristic matrix is compared with default eigenmatrix, obtain with
The corresponding terminal operation instruction of performance characteristic matrix;Above-mentioned default eigenmatrix is to be pre-stored in data base's such as grader
In " NET ", default eigenmatrix is the calculated default electromyographic signal eigenvalue cluster of electromyographic signal by presetting gesture
Into, its computational methods is consistent with the method for performance characteristic matrix.Can also have in the data base and default eigenmatrix
Corresponding terminal operation instruction.As shown in Fig. 2 in the present embodiment, the performance characteristic matrix calculation unit 10 can equally be wrapped
Include filtering noise reduction process module 11, windowing processing module 12 and statistical nature computing module 13;Will not be described here.
Detecting signal unit 30 is used for the intensity of the electromyographic signal for detecting the operating gesture;If the flesh of the operating gesture
The intensity of the signal of telecommunication is, for example, 10 μ V higher than preset strength value, then make control system be in opening.In the present embodiment, work as letter
When the electromyographic signal intensity that number detector unit 30 is detected is higher than preset strength value, makes control system in open mode, work as letter
When the electromyographic signal intensity that number detector unit 30 is detected is less than preset strength value, control system is made in holding state, to reach
To the effect of the intelligent switch for making control system.
The standard operation defined when dispatching from the factory may not necessarily meet the demand of all users, so be accomplished by user by default spy
Matrix extension unit 50 oneself definition action is levied, to reach the purpose to free terminal control.Default eigenmatrix expanding element
50 include:
Collection computing module 51, for gathering self-defining first gesture, calculates the according to the electromyographic signal of first gesture
One electromyographic signal eigenvalue, and by the first electromyographic signal eigenvalue cluster into fisrt feature matrix;
Collection computing module 51 is additionally operable to gather first gesture again, according to the electromyographic signal of the first gesture for gathering again
The second electromyographic signal eigenvalue is calculated, and the second electromyographic signal eigenvalue is write in fisrt feature matrix;
Relating module 52, for when the times of collection of first gesture until after reaching preset times such as 10 times, receiving which
Corresponding terminal operation instruction, and will be fisrt feature matrix associated with the instruction of corresponding terminal operation;
Eigenvalue complementary module, is the electromyographic signal spy in first gesture, and fisrt feature matrix for working as operating gesture
When value indicative is not up to threshold value such as 3000, by first gesture corresponding operation electromyographic signal eigenvalue write fisrt feature matrix.
In another embodiment of the invention, default eigenmatrix alignment unit 40 can also be included simultaneously.
It should be noted that the default gesture in the present invention can be again by default electromyographic signal in default eigenmatrix
And the statistical characteristics of the corresponding electromyographic signal wavelet coefficient of default gesture, used as characteristic parameter, and combination supporting vector machine comes
Realize the classification to presetting gesture.Specifically:
|input paramete is mapped to high-dimensional feature space by the non-linear relation of its kernel function by support vector machine, and is constructed
Corresponding optimal separating hyper plane.To sample (xi, yi) for, the optimal classification discriminant function of support vector machine is represented by
Wherein, parameter alphaiWith b be need optimization calculate function coefficients, inner product k (x, xi) for its kernel function, m is sample number
And i=1,2 ... m.
Based on two class principles of classification, support vector machine are also extrapolated to multicategory classification problem, and which can pass through " a pair
One " and " one-to-many " two ways is realizing, " one-to-many " mode is used here.For K class classification problems, " one-to-many "
Mode constructs K binary classifier, i.e., by jth (j=1,2 ..., K) individual grader by the data of jth class and other class data
Make a distinction.For relative " one-to-one " mode, the classification speed of institute's employing mode is very fast
Before dispatching from the factory, it would be desirable to which pattern classifier is trained, for example:The sampled value of individual part is 3000
It is individual, and this 3000 values are input in SVM pattern classifiers, which is trained, classifier result " NET " is obtained.Afterwards,
We are written to " NET " in the middle of the chip of wearable device, enable to play a part of action recognition in follow-up use.
The wearable device based on electromyographic signal in the present invention can be by electrode deployment to bracelet, when the electrode on bracelet
During contact arm, electromyographic signal is detected;It is of course also possible to electrode is arranged on other objects facilitate will survey user its
The electromyographic signal at his position, is such as arranged on electrode on finger ring and detects electromyographic signal of finger etc..The present invention is not to wearing
The concrete form of equipment is limited.Additionally, same terminal can be equipped with multiple wearable devices e.g. controls bracelet, each is worn
The equipment of wearing has single data base to store the performance characteristic value of different user.
As shown in fig. 6, seventh embodiment of the invention provides interacting for a kind of wearable device based on electromyographic signal and terminal
Method, including step:
S1, according to the electromyographic signal of operating gesture calculate operation electromyographic signal eigenvalue, will operation electromyographic signal eigenvalue
Composition performance characteristic matrix;
Wherein, the electromyographic signal collection of operating gesture can be using differential electrode configuration mode of the prior art (certainly
Can also be gathered using other modes), sample rate is set to 2000Hz (this sample rate can be arranged as the case may be).
S2, performance characteristic matrix is compared with default eigenmatrix, obtain the end corresponding with performance characteristic matrix
End operational order.
More specifically, above-mentioned default eigenmatrix is pre-stored in data base's such as grader " NET ", feature square is preset
Battle array be by preset gesture the calculated default electromyographic signal eigenvalue cluster of electromyographic signal into, its computational methods with operation
The method of eigenmatrix is consistent.Can also there be the terminal operation instruction corresponding with default eigenmatrix in the data base.
Eighth embodiment of the invention provides the exchange method of a kind of wearable device based on electromyographic signal and terminal, including step
Suddenly:
S1, according to the electromyographic signal of operating gesture calculate operation electromyographic signal eigenvalue, will operation electromyographic signal eigenvalue
Composition performance characteristic matrix;
Wherein, the electromyographic signal collection of operating gesture can be using differential electrode configuration mode of the prior art (certainly
Can also be gathered using other modes), sample rate is set to 2000Hz (this sample rate can be arranged as the case may be).
As shown in fig. 7, in the present embodiment, calculating operation electromyographic signal eigenvalue according to the electromyographic signal of operating gesture
When, including step:
S11, the electromyographic signal to operating gesture are filtered noise reduction process;
According to the feature (20-500Hz) of electromyographic signal so as to by conventional band filter, filter less than 20Hz with
And more than the noise of 500Hz, on here basis, then by noise reduction in the little wavestrip of prior art, the signal for collecting is made in 20-
Noise between 500Hz has obtained a certain degree of suppression, more than process after signal when it is original relative to collecting
The purer electromyographic signal of signal;
S12, windowing process is carried out to the electromyographic signal for being filtered the operating gesture after noise reduction process by formula (1);
Wherein, QnFor the total energy value of the segment signal, tnFor the starting point of a certain time-ofday signals, x represents the segment signal, and T is represented
According to the signal segment length that the energy threshold of the electromyographic signal of operating gesture is obtained;
More specifically, in order to obtain the electromyographic signal signal characteristic parameter with regard to operating gesture, needing the noise reduction to obtaining
The electromyographic signal of operating gesture afterwards carries out active segment detection.For the electromyographic signal of some operating gesture, according to its energy
The change of value, carries out windowing process to which;
The principle of windowing process is estimated according to the signal energy value for collecting, according to formula (1) by whole
The calculating of signal energy, and the energy threshold A and B of the electromyographic signal according to the operating gesture, carry out active segment detection to which.Its
In, A, B are calculated obtained from meansigma methodss by the starting point to multiple actions and the continuous data of one section of terminating point.Specifically
, it will be assumed that elapsed from signal starting point backward, during movement, when occurring continuous 500, (this numerical value can be made by oneself
Justice) energy value of individual point is all higher than threshold value A, then it is assumed that it is exactly the starting point of action signal here, then proceedes to elapse backward, when goes out
When now the energy value of the individual point of continuous 500 (this numerical value can be with self-defined) is less than B, we are considered as action signal and tie herein
Beam;
The mobile windowing process of the electromyographic signal energy by this to operating gesture, and set with reference to suitable threshold parameter
Put, so that it may accurately detect the electromyographic signal of single operating gesture.Here the signal value for obtaining is seen in time domain, in threshold
Between value A and B, signal is normal value;And the signal outside A and B, entirely null value, now just it is believed that active segment
In signal after detection, the continuous part of independent non-zero is the electromyographic signal of our operating gesture;
S13, using sym8 small echos as basic function, small echo is carried out to electromyographic signal of the length for the operating gesture of N
Bag decomposes, and calculates the statistical nature of every layer of wavelet coefficient respectively;Those statistical natures can be used as operation electromyographic signal feature
Value;
S2, performance characteristic matrix is compared with default eigenmatrix, obtain the end corresponding with performance characteristic matrix
End operational order.
More specifically, above-mentioned default eigenmatrix is pre-stored in data base's such as grader " NET ", feature square is preset
Battle array be by preset gesture the calculated default electromyographic signal eigenvalue cluster of electromyographic signal into, its computational methods with operation
The method of eigenmatrix is consistent.Can also there be the terminal operation instruction corresponding with default eigenmatrix in the data base.
Ninth embodiment of the invention provides the exchange method of a kind of wearable device based on electromyographic signal and terminal, including step
Suddenly:
S1, according to the electromyographic signal of operating gesture calculate operation electromyographic signal eigenvalue, will operation electromyographic signal eigenvalue
Composition performance characteristic matrix;
Wherein, the electromyographic signal collection of operating gesture can be using differential electrode configuration mode of the prior art (certainly
Can also be gathered using other modes), sample rate is set to 2000Hz (this sample rate can be arranged as the case may be).
As shown in fig. 7, in the present embodiment, calculating operation electromyographic signal eigenvalue according to the electromyographic signal of operating gesture
When, including step:
S11, the electromyographic signal to operating gesture are filtered noise reduction process;
According to the feature (20-500Hz) of electromyographic signal so as to by conventional band filter, filter less than 20Hz with
And more than the noise of 500Hz, on here basis, then by noise reduction in the little wavestrip of prior art, the signal for collecting is made in 20-
Noise between 500Hz has obtained a certain degree of suppression, more than process after signal when it is original relative to collecting
The purer electromyographic signal of signal;
S12, windowing process is carried out to the electromyographic signal for being filtered the operating gesture after noise reduction process by formula (1);
Wherein, QnFor the total energy value of the segment signal, tnFor the starting point of a certain time-ofday signals, x represents the segment signal, and T is represented
According to the signal segment length that the energy threshold of the electromyographic signal of operating gesture is obtained;
More specifically, in order to obtain the electromyographic signal signal characteristic parameter with regard to operating gesture, needing the noise reduction to obtaining
The electromyographic signal of operating gesture afterwards carries out active segment detection.For the electromyographic signal of some operating gesture, according to its energy
The change of value, carries out windowing process to which;
The principle of windowing process is estimated according to the signal energy value for collecting, according to formula (1) by whole
The calculating of signal energy, and the energy threshold A and B of the electromyographic signal according to the operating gesture, carry out active segment detection to which.Its
In, A, B are calculated obtained from meansigma methodss by the starting point to multiple actions and the continuous data of one section of terminating point.Specifically
, it will be assumed that elapsed from signal starting point backward, during movement, when occurring continuous 500, (this numerical value can be made by oneself
Justice) energy value of individual point is all higher than threshold value A, then it is assumed that it is exactly the starting point of action signal here, then proceedes to elapse backward, when goes out
When now the energy value of the individual point of continuous 500 (this numerical value can be with self-defined) is less than B, we are considered as action signal and tie herein
Beam;
The mobile windowing process of the electromyographic signal energy by this to operating gesture, and set with reference to suitable threshold parameter
Put, so that it may accurately detect the electromyographic signal of single operating gesture.Here the signal value for obtaining is seen in time domain, in threshold
Between value A and B, signal is normal value;And the signal outside A and B, entirely null value, now just it is believed that active segment
In signal after detection, the continuous part of independent non-zero is the electromyographic signal of our operating gesture;
S13, using sym8 small echos as basic function, small echo is carried out to electromyographic signal of the length for the operating gesture of N
Bag decomposes, and calculates the statistical nature of every layer of wavelet coefficient respectively;Those statistical natures can be used as operation electromyographic signal feature
Value;
In the present embodiment, specifically, the energy of every layer of wavelet coefficient can be calculated by formula (2);
Wherein, j is port number and j=1:4;Total energy values of the Ej for wavelet coefficient, N is wavelet coefficient in the segment signal
Number, wavelet coefficients of the ri for corresponding point;
The gross energy of wavelet coefficient is calculated by formula (3);
E=E1+E2+E3+E4(3);
The energy percentage of every layer of wavelet coefficient is calculated by formula (4);
ρj=Ej/E (4);
The absolute average of wavelet coefficient is calculated by formula (5);
The variance of wavelet coefficient is calculated by formula (6);
S2, performance characteristic matrix is compared with default eigenmatrix, obtain the end corresponding with performance characteristic matrix
End operational order.
More specifically, above-mentioned default eigenmatrix is pre-stored in data base's such as grader " NET ", feature square is preset
Battle array be by preset gesture the calculated default electromyographic signal eigenvalue cluster of electromyographic signal into, its computational methods with operation
The method of eigenmatrix is consistent.Can also there be the terminal operation instruction corresponding with default eigenmatrix in the data base.
As shown in figure 8, tenth embodiment of the invention provides interacting for a kind of wearable device based on electromyographic signal and terminal
Method, including step:
The intensity of S10, the electromyographic signal of detection operating gesture;
Whether S20, the intensity of electromyographic signal for judging the operating gesture are, for example, 10 μ V higher than preset strength value, if so,
Step S1 is entered then;Otherwise, return to step S10;
S1, according to the electromyographic signal of operating gesture calculate operation electromyographic signal eigenvalue, will operation electromyographic signal eigenvalue
Composition performance characteristic matrix;
Wherein, the electromyographic signal collection of operating gesture can be using differential electrode configuration mode of the prior art (certainly
Can also be gathered using other modes), sample rate is set to 2000Hz (this sample rate can be arranged as the case may be).
As shown in fig. 7, when operation electromyographic signal eigenvalue is calculated according to the electromyographic signal of operating gesture, step can be included
Suddenly:
S11, the electromyographic signal to operating gesture are filtered noise reduction process;
According to the feature (20-500Hz) of electromyographic signal so as to by conventional band filter, filter less than 20Hz with
And more than the noise of 500Hz, on here basis, then by noise reduction in the little wavestrip of prior art, the signal for collecting is made in 20-
Noise between 500Hz has obtained a certain degree of suppression, more than process after signal when it is original relative to collecting
The purer electromyographic signal of signal;
S12, windowing process is carried out to the electromyographic signal for being filtered the operating gesture after noise reduction process by formula (1);
Wherein, QnFor the total energy value of the segment signal, tnFor the starting point of a certain time-ofday signals, x represents the segment signal, and T is represented
According to the signal segment length that the energy threshold of the electromyographic signal of operating gesture is obtained;
More specifically, in order to obtain the electromyographic signal signal characteristic parameter with regard to operating gesture, needing the noise reduction to obtaining
The electromyographic signal of operating gesture afterwards carries out active segment detection.For the electromyographic signal of some operating gesture, according to its energy
The change of value, carries out windowing process to which;
The principle of windowing process is estimated according to the signal energy value for collecting, according to formula (1) by whole
The calculating of signal energy, and the energy threshold A and B of the electromyographic signal according to the operating gesture, carry out active segment detection to which.Its
In, A, B are calculated obtained from meansigma methodss by the starting point to multiple actions and the continuous data of one section of terminating point.Specifically
, it will be assumed that elapsed from signal starting point backward, during movement, when occurring continuous 500, (this numerical value can be made by oneself
Justice) energy value of individual point is all higher than threshold value A, then it is assumed that it is exactly the starting point of action signal here, then proceedes to elapse backward, when goes out
When now the energy value of the individual point of continuous 500 (this numerical value can be with self-defined) is less than B, we are considered as action signal and tie herein
Beam;
The mobile windowing process of the electromyographic signal energy by this to operating gesture, and set with reference to suitable threshold parameter
Put, so that it may accurately detect the electromyographic signal of single operating gesture.Here the signal value for obtaining is seen in time domain, in threshold
Between value A and B, signal is normal value;And the signal outside A and B, entirely null value, now just it is believed that active segment
In signal after detection, the continuous part of independent non-zero is the electromyographic signal of our operating gesture;
S13, using sym8 small echos as basic function, small echo is carried out to electromyographic signal of the length for the operating gesture of N
Bag decomposes, and calculates the statistical nature of every layer of wavelet coefficient respectively;Those statistical natures can be used as operation electromyographic signal feature
Value;
Specifically, the energy of every layer of wavelet coefficient can be calculated by formula (2);
Wherein, j is port number and j=1:4;Total energy values of the Ej for wavelet coefficient, N is wavelet coefficient in the segment signal
Number, wavelet coefficients of the ri for corresponding point;
The gross energy of wavelet coefficient is calculated by formula (3);
E=E1+E2+E3+E4(3);
The energy percentage of every layer of wavelet coefficient is calculated by formula (4);
ρj=Ej/E (4);
The absolute average of wavelet coefficient is calculated by formula (5);
The variance of wavelet coefficient is calculated by formula (6);
S2, performance characteristic matrix is compared with default eigenmatrix, obtain the end corresponding with performance characteristic matrix
End operational order.
More specifically, above-mentioned default eigenmatrix is pre-stored in data base's such as grader " NET ", feature square is preset
Battle array be by preset gesture the calculated default electromyographic signal eigenvalue cluster of electromyographic signal into, its computational methods with operation
The method of eigenmatrix is consistent.Can also there be the terminal operation instruction corresponding with default eigenmatrix in the data base.
As user action custom is different, it is likely to imperfect or not accurate enough when standard operation is completed, such as
When user does the action of next, the angle that palm is lifted upwards is 45 degree or so, and we are in preset training of dispatching from the factory
Essentially 75 degree or so in data, such situation may result in the discrimination of the action than relatively low.Therefore, as shown in figure 9, originally
Invent the 11st embodiment and a kind of calibration steps of default eigenmatrix is provided, adopted by the standard operation done to user
Sample, and the sampling eigenvalue for obtaining and the preset eigenvalue that dispatches from the factory are write in same matrix, retrieve grader " NET "
So as to improve discrimination.
Above-mentioned default eigenmatrix is the default electromyographic signal eigenvalue calculated according to the electromyographic signal of default gesture
Composition;The calibration steps of the default eigenmatrix is specifically included:
S51, the collection standard gesture consistent with default gesture simultaneously calculates mark according to the electromyographic signal of the standard gesture
Quasi- electromyographic signal eigenvalue;
S52, standard electromyographic signal eigenvalue is write in the default eigenmatrix corresponding with default gesture.
More specifically, it is assumed that preset features value is 3000 values (A1-A3000) to train grader as eigenvalue,
Most start N (0 in user<N<3000), in the middle of secondary beginning operating process, whenever an action is completed, system can point out user to select
Select whether the action of oneself is correctly validated, if correct recognize, then by the signal of this group of data according to above-mentioned flow processing,
And (B1-BN) in corresponding eigenvalue is obtained, to the accuracy for increasing identification.Here restriction, of standard operation will be made
Practise, at most can only obtain the data of fixed action, it is assumed that for N number of, when the quantity of standard operation study is more than N, be
System can be automatically deleted the data for learning earliest, to guarantee standard operation study less than N.
The standard operation defined during due to dispatching from the factory may not necessarily meet the demand of all users, so be accomplished by user oneself fixed
Adopted action, to reach the purpose to free terminal control.Therefore, as shown in Figure 10, the 12nd embodiment of the present invention is also proposed
A kind of spread step to presetting eigenmatrix, specifically includes:
S61, the self-defining first gesture of collection, calculate the first electromyographic signal feature according to the electromyographic signal of first gesture
Value, and by the first electromyographic signal eigenvalue cluster into fisrt feature matrix;
S62, first gesture is gathered again, the second electromyographic signal is calculated according to the electromyographic signal of the first gesture for gathering again
Eigenvalue, and the second electromyographic signal eigenvalue is write in fisrt feature matrix;
S63, judge whether the times of collection of first gesture reaches preset times such as 10 times, if it is not, then return to step
S62;If so, then enter step S64;
S64, its corresponding terminal operation instruction is received, and fisrt feature matrix is related to the instruction of corresponding terminal operation
Connection;
S65, judge when operating gesture whether be first gesture, if it is not, then terminating process as shown at step s 68;If so, then
Into step S66;
When whether S66, the electromyographic signal eigenvalue judged in fisrt feature matrix reach threshold value such as 3000, if it is not, then
Into step S67;If it is not, then terminating process as shown at step s 68;
S67, by first gesture corresponding operation electromyographic signal eigenvalue write fisrt feature matrix.
The present invention provides a kind of wearable device based on electromyographic signal and its exchange method with terminal, by by manipulator
The electromyographic signal of gesture is calculated operation electromyographic signal eigenvalue and constitutes performance characteristic matrix, and which is entered with default eigenmatrix
Row is compared, and can just be obtained the terminal operation instruction corresponding with performance characteristic matrix, be reached the purpose with terminal interaction.In operation
In the calculating process of electromyographic signal eigenvalue, by filtering noise reduction process, windowing process and being used as base letter using sym8 small echos
The WAVELET PACKET DECOMPOSITION that number is carried out processes the accuracy for all improving gesture identification.The calibration and expansion of default eigenmatrix are provided more
Exhibition, to solve user personality difference, enriches operating gesture;Lift Consumer's Experience.
It should be noted that herein, term " including ", "comprising" or its any other variant are intended to non-row
His property is included, so that a series of process, method, article or device including key elements not only include those key elements, and
And also include other key elements being not expressly set out, or also include for this process, method, article or device institute inherently
Key element.In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
Also there is other identical element in the process of key element, method, article or device.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
The part for going out contribution can be embodied in the form of software product, and the computer software product is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), use so that a station terminal equipment including some instructions (can be mobile phone, computer, clothes
Business device, air-conditioner, or network equipment etc.) perform method described in each embodiment of the invention.
The preferred embodiments of the present invention are these are only, the scope of the claims of the present invention is not thereby limited, it is every using this
Equivalent structure or equivalent flow conversion that bright description and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. the exchange method of a kind of wearable device based on electromyographic signal and terminal, it is characterised in that including step:
According to the electromyographic signal of operating gesture calculate operation electromyographic signal eigenvalue, by it is described operation electromyographic signal eigenvalue cluster into
Performance characteristic matrix;
The performance characteristic matrix and default eigenmatrix are compared, the end corresponding with the performance characteristic matrix is obtained
End operational order.
2. the exchange method of the wearable device based on electromyographic signal according to claim 1 and terminal, it is characterised in that
When calculating operation electromyographic signal eigenvalue according to the electromyographic signal of operating gesture, including step:
The electromyographic signal of the operating gesture is filtered after noise reduction process;
Windowing process is carried out to the electromyographic signal for being filtered the operating gesture after noise reduction process by formula (1);
Wherein, QnFor the total energy value of the segment signal, tnFor the starting point of a certain time-ofday signals, x represents the segment signal, and T represents basis
The signal segment length that the energy threshold of the electromyographic signal of the operating gesture is obtained;
Using sym8 small echos as basic function, WAVELET PACKET DECOMPOSITION is carried out to electromyographic signal of the length for the operating gesture of N, and
The statistical nature of every layer of wavelet coefficient is calculated respectively.
3. the exchange method of the wearable device based on electromyographic signal according to claim 2 and terminal, it is characterised in that
Using sym8 small echos as basic function, WAVELET PACKET DECOMPOSITION, and difference are carried out to electromyographic signal of the length for the operating gesture of N
When calculating the statistical nature of every layer of wavelet coefficient, including step:
The energy of every layer of wavelet coefficient is calculated by formula (2);
Wherein, j is port number and j=1:4;Total energy values of the Ej for wavelet coefficient, N are the individual of wavelet coefficient in the segment signal
Number, wavelet coefficients of the ri for corresponding point;
The gross energy of wavelet coefficient is calculated by formula (3);
E=E1+E2+E3+E4(3);
The energy percentage of every layer of wavelet coefficient is calculated by formula (4);
ρj=Ej/E (4);
The absolute average of wavelet coefficient is calculated by formula (5);
The variance of wavelet coefficient is calculated by formula (6);
4. the exchange method of the wearable device based on electromyographic signal according to claim 1 and terminal, it is characterised in that
Before operation electromyographic signal eigenvalue is calculated according to the electromyographic signal of operating gesture, also including step:Detect the operating gesture
Electromyographic signal intensity;If the intensity of the electromyographic signal of the operating gesture is higher than preset strength value, into next step.
5. the exchange method of the wearable device based on electromyographic signal according to claim 1 and terminal, it is characterised in that institute
State default eigenmatrix be the default electromyographic signal eigenvalue cluster that calculated according to the electromyographic signal of default gesture into;Also wrap
Include the calibration steps to the default eigenmatrix:
The collection standard gesture consistent with the default gesture simultaneously calculates standard flesh according to the electromyographic signal of the standard gesture
Signal characteristics value;The standard electromyographic signal eigenvalue is write into the described default feature square corresponding with the default gesture
In battle array.
6. the exchange method of the wearable device based on electromyographic signal according to claim 1 and terminal, it is characterised in that also
Including the spread step to presetting eigenmatrix:
Self-defining first gesture is gathered, the first electromyographic signal eigenvalue is calculated according to the electromyographic signal of the first gesture, and
By the first electromyographic signal eigenvalue cluster into fisrt feature matrix;
The first gesture is gathered again, and the second electromyographic signal is calculated according to the electromyographic signal of the first gesture for gathering again
Eigenvalue, and the second electromyographic signal eigenvalue is write in the fisrt feature matrix;
When the times of collection of the first gesture is until after reaching preset times, receiving its corresponding terminal operation instruction, and inciting somebody to action
The fisrt feature matrix is associated with the corresponding terminal operation instruction;
When the operating gesture is that the electromyographic signal eigenvalue in the first gesture, and the fisrt feature matrix is not up to threshold
During value, by the first gesture corresponding operation electromyographic signal eigenvalue write fisrt feature matrix.
7. a kind of wearable device based on electromyographic signal, including control system, it is characterised in that the control system includes:
Performance characteristic matrix calculation unit, for calculating operation electromyographic signal eigenvalue according to the electromyographic signal of operating gesture, will
The operation electromyographic signal eigenvalue cluster is into performance characteristic matrix;
Terminal operation instruct acquiring unit, for the performance characteristic matrix and default eigenmatrix are compared, obtain with
The corresponding terminal operation instruction of the performance characteristic matrix.
8. the wearable device based on electromyographic signal according to claim 7, it is characterised in that the performance characteristic matrix meter
Calculating unit includes:
Filtering noise reduction process module, for being filtered noise reduction process to the electromyographic signal of the operating gesture;
Windowing processing module, for by formula (1) to being filtered the electromyographic signal of the operating gesture after noise reduction process
Carry out windowing process;
Wherein, QnFor the total energy value of the segment signal, tnFor the starting point of a certain time-ofday signals, x represents the segment signal, and T represents basis
The signal segment length that the energy threshold of the electromyographic signal of the operating gesture is obtained;
Statistical nature computing module, for using sym8 small echos as basic function, to length for the operating gesture of N myoelectricity
Signal carries out WAVELET PACKET DECOMPOSITION, and calculates the statistical nature of every layer of wavelet coefficient respectively.
9. the wearable device based on electromyographic signal according to claim 7, it is characterised in that the control system also includes
Detecting signal unit, for detecting the intensity of the electromyographic signal of the operating gesture;If the electromyographic signal of the operating gesture
Intensity is higher than preset strength value, then make the control system be in opening.
10. the wearable device based on electromyographic signal according to claim 7, it is characterised in that the default eigenmatrix
The default electromyographic signal eigenvalue cluster that calculated according to the electromyographic signal of default gesture into;The control system also includes
At least one of default eigenmatrix alignment unit and default eigenmatrix expanding element;
The default eigenmatrix alignment unit is used to gather the standard gesture consistent with the default gesture and according to described
The electromyographic signal of standard gesture calculates standard electromyographic signal eigenvalue;Be additionally operable to by the standard electromyographic signal eigenvalue write with
In the corresponding described default eigenmatrix of the default gesture;
The default eigenmatrix expanding element includes:
Collection computing module, for gathering self-defining first gesture, calculates first according to the electromyographic signal of the first gesture
Electromyographic signal eigenvalue, and by the first electromyographic signal eigenvalue cluster into fisrt feature matrix;
The collection computing module is additionally operable to gather the first gesture again, according to the flesh of the first gesture for gathering again
The signal of telecommunication calculates the second electromyographic signal eigenvalue, and the second electromyographic signal eigenvalue is write the fisrt feature matrix
It is interior;
Relating module, for when the times of collection of the first gesture until after reach preset times, receiving its corresponding terminal
Operational order, and will be the fisrt feature matrix associated with the corresponding terminal operation instruction;
Eigenvalue complementary module, is the flesh in the first gesture, and the fisrt feature matrix for working as the operating gesture
When signal characteristics value is not up to threshold value, by the first gesture corresponding operation electromyographic signal eigenvalue write fisrt feature square
Battle array.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610982437.9A CN106527716B (en) | 2016-11-09 | 2016-11-09 | Wearable device based on electromyographic signals and interaction method of wearable device and terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610982437.9A CN106527716B (en) | 2016-11-09 | 2016-11-09 | Wearable device based on electromyographic signals and interaction method of wearable device and terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106527716A true CN106527716A (en) | 2017-03-22 |
CN106527716B CN106527716B (en) | 2020-12-29 |
Family
ID=58351356
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610982437.9A Active CN106527716B (en) | 2016-11-09 | 2016-11-09 | Wearable device based on electromyographic signals and interaction method of wearable device and terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106527716B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106959756A (en) * | 2017-03-28 | 2017-07-18 | 努比亚技术有限公司 | The sky mouse recognition methods acted based on electromyographic signal monitoring and device |
CN107479704A (en) * | 2017-08-08 | 2017-12-15 | 广东小天才科技有限公司 | A kind of control method of wearable device, device, equipment and storage medium |
CN107861628A (en) * | 2017-12-19 | 2018-03-30 | 许昌学院 | A kind of hand gestures identifying system based on human body surface myoelectric signal |
CN108227930A (en) * | 2018-01-18 | 2018-06-29 | 四川斐讯信息技术有限公司 | The gestural control method and wearable device of a kind of wearable device |
CN108211309A (en) * | 2017-05-25 | 2018-06-29 | 深圳市未来健身衣科技有限公司 | The guidance method and device of body building |
CN108415560A (en) * | 2018-02-11 | 2018-08-17 | 广东欧珀移动通信有限公司 | Electronic device, method of controlling operation thereof and Related product |
CN108890621A (en) * | 2018-07-10 | 2018-11-27 | 安春亭 | A kind of wearable smart machine control method that auxiliary is carried |
CN108958472A (en) * | 2018-05-17 | 2018-12-07 | 北京邮电大学 | A kind of method and device of gesture control suitcase |
CN111052049A (en) * | 2017-10-09 | 2020-04-21 | 华为技术有限公司 | Action identification method and device and terminal |
WO2021042971A1 (en) * | 2019-09-03 | 2021-03-11 | 北京海益同展信息科技有限公司 | Surface electromyogram signal processing method and apparatus, and wearable device |
CN112773380A (en) * | 2019-11-07 | 2021-05-11 | 深圳市理邦精密仪器股份有限公司 | Electromyographic signal processing method, processing device and storage medium |
CN113625882A (en) * | 2021-10-12 | 2021-11-09 | 四川大学 | Myoelectric gesture recognition method based on sparse multichannel correlation characteristics |
CN114442798A (en) * | 2020-11-06 | 2022-05-06 | 复旦大学附属妇产科医院 | Portable control system and control method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345641A (en) * | 2013-07-16 | 2013-10-09 | 杭州电子科技大学 | Hand electromyographic signal motion recognition method based on wavelet entropy and support vector machine |
CN103777752A (en) * | 2013-11-02 | 2014-05-07 | 上海威璞电子科技有限公司 | Gesture recognition device based on arm muscle current detection and motion sensor |
US20150109202A1 (en) * | 2013-10-22 | 2015-04-23 | Thalmic Labs Inc. | Systems, articles, and methods for gesture identification in wearable electromyography devices |
US20150169074A1 (en) * | 2013-12-12 | 2015-06-18 | Thalmic Labs Inc. | Systems, articles, and methods for gesture identification in wearable electromyography devices |
CN105373214A (en) * | 2014-08-25 | 2016-03-02 | 深圳Tcl新技术有限公司 | Terminal control method and system |
CN105807640A (en) * | 2014-12-30 | 2016-07-27 | 深圳Tcl新技术有限公司 | Terminal control method and terminal control system |
-
2016
- 2016-11-09 CN CN201610982437.9A patent/CN106527716B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345641A (en) * | 2013-07-16 | 2013-10-09 | 杭州电子科技大学 | Hand electromyographic signal motion recognition method based on wavelet entropy and support vector machine |
US20150109202A1 (en) * | 2013-10-22 | 2015-04-23 | Thalmic Labs Inc. | Systems, articles, and methods for gesture identification in wearable electromyography devices |
CN103777752A (en) * | 2013-11-02 | 2014-05-07 | 上海威璞电子科技有限公司 | Gesture recognition device based on arm muscle current detection and motion sensor |
US20150169074A1 (en) * | 2013-12-12 | 2015-06-18 | Thalmic Labs Inc. | Systems, articles, and methods for gesture identification in wearable electromyography devices |
CN105373214A (en) * | 2014-08-25 | 2016-03-02 | 深圳Tcl新技术有限公司 | Terminal control method and system |
CN105807640A (en) * | 2014-12-30 | 2016-07-27 | 深圳Tcl新技术有限公司 | Terminal control method and terminal control system |
Non-Patent Citations (1)
Title |
---|
李博,李强: "基于小波特征分析的手指动作识别研究", 《现代生物医学进展》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106959756A (en) * | 2017-03-28 | 2017-07-18 | 努比亚技术有限公司 | The sky mouse recognition methods acted based on electromyographic signal monitoring and device |
CN108211309A (en) * | 2017-05-25 | 2018-06-29 | 深圳市未来健身衣科技有限公司 | The guidance method and device of body building |
CN107479704A (en) * | 2017-08-08 | 2017-12-15 | 广东小天才科技有限公司 | A kind of control method of wearable device, device, equipment and storage medium |
CN111052049A (en) * | 2017-10-09 | 2020-04-21 | 华为技术有限公司 | Action identification method and device and terminal |
CN107861628A (en) * | 2017-12-19 | 2018-03-30 | 许昌学院 | A kind of hand gestures identifying system based on human body surface myoelectric signal |
CN108227930A (en) * | 2018-01-18 | 2018-06-29 | 四川斐讯信息技术有限公司 | The gestural control method and wearable device of a kind of wearable device |
CN108415560A (en) * | 2018-02-11 | 2018-08-17 | 广东欧珀移动通信有限公司 | Electronic device, method of controlling operation thereof and Related product |
CN108415560B (en) * | 2018-02-11 | 2020-12-04 | Oppo广东移动通信有限公司 | Electronic device, operation control method and related product |
CN108958472A (en) * | 2018-05-17 | 2018-12-07 | 北京邮电大学 | A kind of method and device of gesture control suitcase |
CN108958472B (en) * | 2018-05-17 | 2020-09-04 | 北京邮电大学 | Method and device for controlling travel suitcase through gestures |
CN108890621A (en) * | 2018-07-10 | 2018-11-27 | 安春亭 | A kind of wearable smart machine control method that auxiliary is carried |
WO2021042971A1 (en) * | 2019-09-03 | 2021-03-11 | 北京海益同展信息科技有限公司 | Surface electromyogram signal processing method and apparatus, and wearable device |
CN112773380A (en) * | 2019-11-07 | 2021-05-11 | 深圳市理邦精密仪器股份有限公司 | Electromyographic signal processing method, processing device and storage medium |
CN112773380B (en) * | 2019-11-07 | 2023-09-22 | 深圳市理邦精密仪器股份有限公司 | Myoelectric signal processing method, processing equipment and storage medium |
CN114442798A (en) * | 2020-11-06 | 2022-05-06 | 复旦大学附属妇产科医院 | Portable control system and control method |
CN114442798B (en) * | 2020-11-06 | 2024-05-07 | 复旦大学附属妇产科医院 | Portable control system and control method |
CN113625882A (en) * | 2021-10-12 | 2021-11-09 | 四川大学 | Myoelectric gesture recognition method based on sparse multichannel correlation characteristics |
CN113625882B (en) * | 2021-10-12 | 2022-06-14 | 四川大学 | Myoelectric gesture recognition method based on sparse multichannel correlation characteristics |
Also Published As
Publication number | Publication date |
---|---|
CN106527716B (en) | 2020-12-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106527716A (en) | Wearable equipment based on electromyographic signals and interactive method between wearable equipment and terminal | |
CN101976115B (en) | Motor imagery and P300 electroencephalographic potential-based functional key selection method | |
US9720515B2 (en) | Method and apparatus for a gesture controlled interface for wearable devices | |
US9612661B2 (en) | Closed loop feedback interface for wearable devices | |
CN103793058B (en) | A kind of active brain-computer interactive system Mental imagery classification of task method and device | |
US20190082996A1 (en) | Detecting and Using Body Tissue Electrical Signals | |
CN106383579A (en) | EMG and FSR-based refined gesture recognition system and method | |
Zhang et al. | Recognizing hand gestures with pressure-sensor-based motion sensing | |
CN107037889B (en) | Natural writing character input method and system based on visual brain-computer interface | |
CN105117003A (en) | Intelligent wearing equipment and working method thereof | |
CN107300971A (en) | The intelligent input method and system propagated based on osteoacusis vibration signal | |
CN103699217A (en) | Two-dimensional cursor motion control system and method based on motor imagery and steady-state visual evoked potential | |
CN101776981A (en) | Method for controlling mouse by jointing brain electricity and myoelectricity | |
Li et al. | Hand gesture recognition and real-time game control based on a wearable band with 6-axis sensors | |
Rosenberg | Computing without mice and keyboards: text and graphic input devices for mobile computing | |
CN106991409A (en) | A kind of Mental imagery EEG feature extraction and categorizing system and method | |
Fan et al. | What is that in your hand? recognizing grasped objects via forearm electromyography sensing | |
Veer | Experimental study and characterization of SEMG signals for upper limbs | |
CN204765638U (en) | Surface electromyography signal data acquisition system | |
CN104090653A (en) | Detecting method for multi-modal brain switch based on SSVEP and P300 | |
CN210697629U (en) | Signal acquisition device, mobile terminal and signal analysis system | |
Jia | Neural network in the application of EEG signal classification method | |
CN108681412B (en) | Emotion recognition device and method based on array type touch sensor | |
CN105867618A (en) | Terminal and holding strength detecting method thereof | |
Dinulescu et al. | A smart bracelet supporting tactile communication and interaction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20211026 Address after: 518000 1601, building 2, Chongwen Park, Nanshan Zhiyuan, No. 3370 Liuxian Avenue, Fuguang community, Taoyuan Street, Nanshan District, Shenzhen, Guangdong Patentee after: Shenzhen ZTE Mobile Software Co.,Ltd. Address before: 518000 6-8 / F, 10-11 / F, 6 / F, 6-10 / F, C zone, Han's innovation building, No. 9018, Beihuan Avenue, high tech Zone, Nanshan District, Shenzhen City, Guangdong Province Patentee before: NUBIA TECHNOLOGY Co.,Ltd. |