CN114707562B - Electromyographic signal sampling frequency control method and device and storage medium - Google Patents
Electromyographic signal sampling frequency control method and device and storage medium Download PDFInfo
- Publication number
- CN114707562B CN114707562B CN202210612029.XA CN202210612029A CN114707562B CN 114707562 B CN114707562 B CN 114707562B CN 202210612029 A CN202210612029 A CN 202210612029A CN 114707562 B CN114707562 B CN 114707562B
- Authority
- CN
- China
- Prior art keywords
- electromyographic
- gesture
- action
- time
- sampling frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005070 sampling Methods 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000009471 action Effects 0.000 claims abstract description 195
- 238000012216 screening Methods 0.000 claims abstract description 18
- 230000036982 action potential Effects 0.000 claims description 72
- 230000033001 locomotion Effects 0.000 claims description 37
- 238000012549 training Methods 0.000 claims description 30
- 230000009467 reduction Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims 2
- 230000003183 myoelectrical effect Effects 0.000 abstract description 12
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 210000003811 finger Anatomy 0.000 description 27
- 238000010079 rubber tapping Methods 0.000 description 9
- 239000011664 nicotinic acid Substances 0.000 description 8
- 238000005265 energy consumption Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000003414 extremity Anatomy 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000003796 beauty Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002567 electromyography Methods 0.000 description 1
- 210000005224 forefinger Anatomy 0.000 description 1
- 210000004247 hand Anatomy 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000002232 neuromuscular Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a myoelectric signal sampling frequency control method, a myoelectric signal sampling frequency control device and a storage medium, wherein the method comprises the following steps: acquiring a plurality of electromyographic signals, and determining a gesture action corresponding to each electromyographic signal based on the plurality of electromyographic signals; acquiring time information corresponding to each gesture action, and screening out the same gesture actions; and determining the duration of the same gesture action based on the same gesture action and the time information corresponding to each gesture action, and controlling the sampling frequency of the electromyographic signals based on the duration. The invention can realize the control of the electromyographic signal sampling frequency and is beneficial to reducing the power consumption of the electromyographic equipment.
Description
Technical Field
The invention relates to the technical field of electromyographic signal acquisition, in particular to an electromyographic signal sampling frequency control method, an electromyographic signal sampling frequency control device and a storage medium.
Background
With the development of artificial intelligence technology and bioelectricity collection technology, people increasingly strongly demand intelligent auxiliary equipment. In the life of disabled people, the requirement of the artificial limb is not only limited to beauty and some simple aids, but also the desire of intelligent artificial limb, so that the appearance of intelligent bionic hands is promoted. The intelligent bionic hand is an intelligent product with high integration of a brain-computer interface technology and an artificial intelligence algorithm. The bionic hand can identify the movement intention of the wearer by extracting the arm neuromuscular signals of the wearer and convert the movement schematic diagram into the actions of the bionic hand, so that the dexterity and intelligence are achieved, and the hand moves with the heart.
At present, the bionic hand basically collects the myoelectric signals uninterruptedly, so that the timeliness and the accuracy of the myoelectric signal collection can be ensured. However, because of the continuous collection of the electromyographic signals, the energy consumption of the bionic hand is high, the use of the user is influenced,
thus, there is a need for improvements and enhancements in the art.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method, an apparatus and a storage medium for controlling the sampling frequency of an electromyographic signal, aiming at solving the problems that the energy consumption of a bionic hand is high and the use of a user is affected due to the continuous acquisition of the electromyographic signal in the prior art.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
in a first aspect, the present invention provides a method for controlling sampling frequency of an electromyographic signal, wherein the method comprises:
acquiring a plurality of electromyographic signals, and determining a gesture action corresponding to each electromyographic signal based on the plurality of electromyographic signals;
acquiring time information corresponding to each gesture action, and screening out the same gesture actions;
and determining the duration of the same gesture action based on the same gesture action and the time information corresponding to each gesture action, and controlling the sampling frequency of the electromyographic signals based on the duration.
In one implementation, the determining, based on a plurality of the electromyographic signals, a gesture corresponding to each of the electromyographic signals includes:
inputting a plurality of electromyographic signals into a pre-trained gesture recognition model for recognizing gesture actions;
and processing the electromyographic signals through the gesture recognition model, and outputting corresponding gesture actions.
In one implementation, the training process of the gesture recognition model includes:
collecting a plurality of electromyographic sample signals, determining sample gesture actions corresponding to each electromyographic sample signal, and forming a training data set, wherein the training data set has a mapping relation between the electromyographic sample signals and the sample gesture actions;
and inputting the training data set into a preset neural network model for training to obtain the gesture recognition model.
In one implementation, the obtaining time information corresponding to each gesture motion and screening out the same gesture motion includes:
recording time information corresponding to each gesture action, and binding the gesture actions with the time information;
acquiring action potential information corresponding to each gesture action;
taking one piece of action potential information as a matching item, and sequentially comparing the matching item with the rest action potential information;
and repeatedly executing the steps of taking one piece of action potential information as a matching item and sequentially comparing the matching item with the rest of action potential information until all pieces of action potential information are taken as matching items so as to screen out the same gesture action.
In one implementation, the determining the duration of the same gesture motion based on the same gesture motion and the time information corresponding to each gesture motion includes:
determining the initial time and the end time of each same gesture action from the time information of each same gesture action;
determining a duration of the same gesture action based on the initial time and the end time.
In one implementation, the controlling of the sampling frequency of the electromyographic signal based on the duration includes:
comparing the duration with a preset first time threshold and a preset second time threshold in sequence, wherein the first time threshold is smaller than the second time threshold;
if the duration is greater than the first time threshold, reducing the sampling frequency of the electromyographic signals;
and if the duration is greater than the second time threshold, continuing to reduce the sampling frequency of the electromyographic signal.
In one implementation, the controlling of the sampling frequency of the electromyographic signal based on the duration includes:
acquiring the sampling frequency of the reduced electromyographic signal, and comparing the sampling frequency of the reduced electromyographic signal with a frequency threshold;
and if the sampling frequency of the electromyographic signals after being reduced is smaller than the frequency threshold, stopping reducing the sampling frequency of the electromyographic signals, and sampling the electromyographic signals by using the frequency threshold.
In a second aspect, an embodiment of the present invention further provides an electromyographic signal sampling frequency control apparatus, where the apparatus includes:
the action determining module is used for acquiring a plurality of electromyographic signals and determining a gesture action corresponding to each electromyographic signal based on the plurality of electromyographic signals;
the action screening module is used for acquiring the time information corresponding to each gesture action and screening out the same gesture action;
and the frequency control module is used for determining the duration time of the same gesture action based on the same gesture action and the time information corresponding to each gesture action, and controlling the sampling frequency of the electromyographic signal based on the duration time.
In one implementation, the action determination module includes:
the model input unit is used for inputting a plurality of electromyographic signals into a pre-trained gesture recognition model for recognizing gesture actions;
and the model output unit is used for processing the electromyographic signals through the gesture recognition model and outputting corresponding gesture actions.
In one implementation, the apparatus further comprises:
the system comprises a sample acquisition module, a data processing module and a data processing module, wherein the sample acquisition module is used for acquiring a plurality of electromyographic sample signals and determining sample gesture actions corresponding to each electromyographic sample signal to form a training data set, and the training data set is provided with a mapping relation between the electromyographic sample signals and the sample gesture actions;
and the model training module is used for inputting the training data set into a preset neural network model for training to obtain the gesture recognition model.
In one implementation, the action filtering module includes:
the time recording unit is used for recording time information corresponding to each gesture action and binding the gesture action with the time information;
the potential acquisition unit is used for acquiring action potential information corresponding to each gesture action;
the potential comparison unit is used for taking one piece of action potential information as a matching item and sequentially comparing the matching item with the rest action potential information;
and the action screening unit is used for repeatedly executing the steps of taking one piece of action potential information as a matching item and sequentially comparing the matching item with the rest action potential information until all pieces of action potential information are taken as matching items so as to screen out the same gesture action.
In one implementation, the frequency control module includes:
a time information analysis unit for determining an initial time and an end time of the same gesture motion from time information of each of the same gesture motions;
and the duration determining unit is used for determining the duration of the same gesture action based on the initial time and the end time.
In one implementation, the frequency control module includes:
the time comparison unit is used for sequentially comparing the duration with a preset first time threshold and a preset second time threshold, wherein the first time threshold is smaller than the second time threshold;
the first frequency reduction unit is used for reducing the sampling frequency of the electromyographic signal if the duration is greater than the first time threshold;
and the second frequency reducing unit is used for continuously reducing the sampling frequency of the electromyographic signals if the duration is greater than the second time threshold.
In one implementation, the frequency control module includes:
the frequency reduction control unit is used for acquiring the sampling frequency of the reduced electromyographic signal and comparing the sampling frequency of the reduced electromyographic signal with a frequency threshold;
and the frequency reduction stopping unit is used for stopping reducing the sampling frequency of the electromyographic signal and sampling the electromyographic signal by the frequency threshold if the sampling frequency of the reduced electromyographic signal is less than the frequency threshold.
In a third aspect, an embodiment of the present invention further provides an electromyographic device, where the electromyographic device includes a memory, a processor, and an electromyographic signal sampling frequency control program stored in the memory and executable on the processor, and when the processor executes the electromyographic signal sampling frequency control program, the step of implementing the electromyographic signal sampling frequency control method according to any one of the above schemes is implemented.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where an electromyographic signal sampling frequency control program is stored on the computer-readable storage medium, and when the electromyographic signal sampling frequency control program is executed by a processor, the steps of the electromyographic signal sampling frequency control method according to any one of the above schemes are implemented.
Has the advantages that: compared with the prior art, the invention provides an electromyographic signal sampling frequency control method. And then, acquiring time information corresponding to each gesture action, and screening out the same gesture action. And finally, determining the duration of the same gesture action based on the same gesture action and the time information corresponding to each gesture action, and controlling the sampling frequency of the electromyographic signals based on the duration. The myoelectric device comprises a myoelectric device, a touch screen and a touch screen, wherein the touch screen is used for displaying a gesture action, and the gesture action is displayed on the touch screen.
Drawings
Fig. 1 is a flowchart of a detailed implementation of a method for controlling a sampling frequency of an electromyographic signal according to an embodiment of the present invention.
Fig. 2 is a schematic block diagram of an electromyographic signal sampling frequency control apparatus according to an embodiment of the present invention.
Fig. 3 is a schematic block diagram of an electromyographic apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment provides an electromyographic signal sampling frequency control method, and the method based on the embodiment can control the sampling frequency of the electromyographic signal, so that the control of the energy consumption of the electromyographic equipment is realized. In specific implementation, a plurality of electromyographic signals are collected first, and a gesture corresponding to each electromyographic signal is determined based on the plurality of electromyographic signals. Then, the embodiment acquires time information corresponding to each gesture action, and screens out the same gesture action. Finally, in this embodiment, based on the same gesture motion and the time information corresponding to each gesture motion, the duration of the same gesture motion is determined, and based on the duration, the sampling frequency of the electromyographic signal is controlled. The electromyographic signals are analyzed to determine the duration time of one gesture, and the duration time of one gesture can reflect the action which the user wants to perform for a long time, so that the electromyographic signals collected within the period of time are the same and have no great difference, and the sampling frequency of the electromyographic devices can be controlled to control the energy consumption of the electromyographic devices.
For example, the muscle point device first collects a plurality of electromyographic signals, and then analyzes the electromyographic signals one by one to obtain corresponding gesture actions. For example, the gesture motion obtained by the analysis is: index finger tap 1, index finger tap 2, index finger tap 3, index finger tap 4, finger open 5. And recording the time information of each gesture, wherein the time information of the first finger tapping 1 is 9:01:25, the time information of the first finger tapping 2 is 9:01:26, the time information of the first finger tapping 3 is 9:01:27, the time information of the first finger tapping 4 is 9:01:28, and the time information of the finger opening 5 is 9:01: 29. And the myoelectric device screens out the gesture actions which belong to the same, namely the finger knocking 1, the index finger knocking 2, the index finger knocking 3 and the index finger knocking 4 belong to the same gesture actions which are the index finger knocking actions. Then, the electromyographic device can determine that the duration of the tapping action of the index finger is 4 seconds, if the electromyographic signals collected by the electromyographic device within the 4 seconds are the same, the action which the user wants to continuously execute at the moment is the tapping action of the index finger, therefore, the electromyographic signals continuously collected by the electromyographic device are basically the same, the electromyographic device can reduce the sampling frequency of the electromyographic signals at the moment, the recognition effect of the gesture action cannot be influenced, and the energy consumption of the electromyographic device can also be reduced.
Exemplary method
The electromyographic signal sampling frequency control method in this embodiment is applied to an electromyographic device, which may be a terminal such as an intelligent bionic hand, and specifically, as shown in fig. 1, the electromyographic signal sampling frequency control method includes the following steps:
s100, collecting a plurality of electromyographic signals, and determining a gesture corresponding to each electromyographic signal based on the plurality of electromyographic signals.
The electromyographic device in this embodiment collects a plurality of electromyographic signals, analyzes the electromyographic signals, and determines a gesture corresponding to each electromyographic signal, where the purpose of determining the gesture is to determine an action and an action intention that a user wants to perform at that time.
In one implementation manner, in the embodiment, when the gesture motion is determined, the following steps are included:
s101, inputting a plurality of electromyographic signals into a pre-trained gesture recognition model for recognizing gesture actions;
and S102, processing the electromyographic signals through the neural network model, and outputting corresponding gesture actions.
Specifically, in this embodiment, a gesture recognition model may be trained in advance, where the gesture recognition model is used to recognize gesture actions, and after a plurality of electromyographic signals are collected in this embodiment, the electromyographic signals are input into the trained gesture recognition model, and then corresponding gesture actions may be output, so as to improve the gesture recognition efficiency. When the gesture recognition model is trained, a large number of electromyographic sample signals are collected, and then the sample gesture actions corresponding to each electromyographic sample signal are determined based on the priori knowledge and the stored gesture template. In the embodiment, the gesture template is preset with a corresponding relationship between the electromyographic signals and the action potential information, and different action potential information represents different gesture actions, so that the action potential information corresponding to each electromyographic sample signal can be determined based on the gesture template, and further the corresponding sample gesture action is determined. After the sample gesture actions are determined, the electromyography sample signals and the sample gesture actions are bound to form a training data set. In the embodiment, the myoelectric sample signal is labeled with the signal characteristics corresponding to the action potential information of the sample gesture action, so that the myoelectric sample signal can be associated with the sample gesture action, and the training data set has the mapping relation between the myoelectric sample signal and the sample gesture action. After the training data set is input into a preset neural network model for training, the neural network model can automatically learn the association between the myoelectric sample signals and the sample gesture actions, and after repeated training, the neural network model can automatically learn the recognition of the gesture actions, so that a gesture recognition model is obtained, and the gesture recognition model can automatically recognize the gesture actions corresponding to each myoelectric signal.
And S200, acquiring time information corresponding to each gesture action, and screening out the same gesture actions.
When a plurality of electromyographic signals are collected, the present embodiment may collect the electromyographic signals within a preset time period, for example, collect the electromyographic signals for half a minute. Each electromyographic signal is acquired in real time, so each electromyographic signal corresponds to respective time information. In this embodiment, after the gesture corresponding to each electromyographic signal is recognized, time information corresponding to each gesture is obtained. And the embodiment also screens out the same gesture motion from all recognized gesture motions.
In one implementation, the step S200 includes the following steps:
step S201, recording time information corresponding to each gesture action, and binding the gesture action with the time information;
step S202, acquiring action potential information corresponding to each gesture action;
step S203, taking one of the action potential information as a matching item, and comparing the matching item with the rest action potential information in sequence;
and S204, repeatedly executing the step of taking one piece of action potential information as a matching item and sequentially comparing the matching item with the rest pieces of action potential information until all pieces of action potential information are taken as matching items so as to screen out the same gesture action.
Specifically, in the embodiment, first, time information corresponding to each gesture action is recorded, and the gesture action is bound with the time information, where the purpose of the binding is to carry the corresponding time information when the gesture action is called in a subsequent process, so that the processing is facilitated. Then, the embodiment acquires the action potential information corresponding to each gesture action, and since the action potential information corresponding to different gesture actions is different, the embodiment can screen out the same gesture action according to the similarity of the action potential information. Specifically, in this embodiment, one of the pieces of action potential information is first used as a matching item, the matching item is sequentially compared with the remaining pieces of action potential information, and then the step of sequentially comparing one of the pieces of action potential information as a matching item with the remaining pieces of action potential information is repeatedly performed until all pieces of action potential information are used as matching items, so that all pieces of action potential information can be ensured to be compared with each other, and the same gesture action can be screened out more accurately. For example, the action potential information for which all gesture actions are recognized includes action potential information a, action potential information B, action potential information C, and action potential information D. Firstly, comparing action potential information A serving as a matching item with action potential information B, action potential information C and action potential information D in sequence; after the comparison is finished, the action potential information B is taken as a matching item and is sequentially compared with the action potential information C and the action potential information D; after the comparison, the action potential information C is used as a matching item to be compared with the action potential information D, so that all the action potential information can be ensured to be compared once. In the comparison process, when the similarity between the two pieces of action potential information is greater than the preset threshold (e.g., 95%), it can be determined that the gesture actions corresponding to the two pieces of action potential information are the same gesture actions, and based on this, all the same gesture actions can be screened out in the embodiment.
Step S300, determining the duration of the same gesture action based on the same gesture action and the time information corresponding to each gesture action, and controlling the sampling frequency of the electromyographic signal based on the duration.
After the same gesture actions are screened out, the duration time of the same gesture actions can be determined based on the same gesture actions and the time information corresponding to each gesture action, and the duration time can reflect the action intention of the user and the tendency of the user to execute a certain gesture action for a long time, so that the sampling frequency of the electromyographic signals is controlled according to the duration time.
In one implementation manner, in the present embodiment, when controlling the sampling frequency, the method includes the following steps:
step S301, determining the initial time and the end time of the same gesture action from the time information of each gesture action in the same gesture actions;
step S302, determining the duration of the same gesture action based on the initial time and the end time;
step S303, comparing the duration time with a preset first time threshold and a preset second time threshold in sequence, wherein the first time threshold is smaller than the second time threshold;
step S304, if the duration time is greater than the first time threshold, reducing the sampling frequency of the electromyographic signal;
and S305, if the duration is greater than the second time threshold, continuing to reduce the sampling frequency of the electromyographic signals.
Specifically, all gesture actions correspond to time information, so that after the same gesture actions are screened out in this embodiment, the embodiment can acquire the time information corresponding to the same gesture actions, then determine the initial time and the end time of the same gesture actions based on the sequence of the time information, and determine the duration of the same gesture actions based on the initial time and the end time. For example, the duration of the gesture motion of the index finger tap 1 is determined to be 4 seconds because the time information of the index finger tap 1 is 9:01:25, the time information of the index finger tap 2 is 9:01:26, the time information of the index finger tap 3 is 9:01:27, and the time information of the index finger tap 4 is 9:01:28, the same gesture motion is used as the index finger tap, and the initial time of the index finger tap is 9:01:25 and the end time of the index finger tap is 9:01: 28.
Further, after the duration is determined, the duration is compared with a preset first time threshold and a preset second time threshold, respectively, and the first time threshold is smaller than the second time threshold. Since the duration in this embodiment can reflect the action intention and the tendency of the user to continue, comparing the duration with the first time threshold and the second time threshold can determine whether the user continues a certain gesture for a long time. Specifically, if the duration is longer than the first time threshold (e.g., 2 seconds), it indicates that the user has continuously performed the same gesture motion (e.g., the index finger tapping motion in the above example) for a period of time, and it may be determined that the user may continue to perform the index finger tapping motion, so that the sampling frequency of the electromyographic device on the electromyographic signal may be reduced, and since the sampling frequency is reduced, the acquisition amount of the electromyographic signal is reduced, and therefore triggering of a control command caused by the electromyographic signal is reduced, so that unintentional fluctuation of the control command is avoided, and energy consumption of the electromyographic device is also reduced. And at this time, the duration of the same gesture motion can be continuously monitored, if the duration is prolonged and is greater than a second time threshold (for example, 4 seconds), it indicates that the user has performed the same gesture motion (for example, the forefinger tapping motion in the above example) for a long time, and this embodiment can further reduce the sampling frequency of the electromyographic signals by the electromyographic device.
Further, the present embodiment also obtains the sampling frequency of the reduced electromyographic signal, and compares the sampling frequency of the reduced electromyographic signal with a frequency threshold. If the sampling frequency of the electromyographic signal after being reduced is smaller than the frequency threshold, the reduction of the sampling frequency of the electromyographic signal is stopped, at this time, the sampling frequency is lower than a limit value (frequency threshold), and at this time, the sampling frequency cannot be reduced any more.
In another implementation manner, the present embodiment may also control the timing of the electromyographic device stopping the frequency reduction based on the frequency reduction number of the electromyographic device, for example, the present embodiment may set a number threshold (e.g., twice), and if the frequency of the electromyographic device reducing the electromyographic signal sampling frequency has reached the number threshold (i.e., twice), at this time, the electromyographic device may be controlled to sample the electromyographic signal by using the frequency threshold. In addition, when the electromyographic device in this embodiment cannot continue to reduce the sampling frequency, the user may be reminded based on a reminding manner such as voice, light, vibration, and the like, so that the user can use the electromyographic device better.
In summary, in this embodiment, a plurality of electromyographic signals are collected first, and a gesture corresponding to each of the electromyographic signals is determined based on the plurality of electromyographic signals. Then, the embodiment acquires time information corresponding to each gesture action, and screens out the same gesture action. Finally, the embodiment determines the duration of the same gesture motion based on the same gesture motion and the time information corresponding to each gesture motion, and controls the sampling frequency of the electromyographic signals based on the duration. The electromyographic signals are analyzed to determine the duration time of one gesture, and the duration time of one gesture can reflect the action which the user wants to perform for a long time, so that the electromyographic signals collected within the period of time are the same and have no great difference, and the sampling frequency of the electromyographic devices can be controlled to control the energy consumption of the electromyographic devices.
Exemplary devices
Based on the above embodiment, the present invention also provides an electromyographic signal sampling frequency control apparatus, as shown in fig. 2, the apparatus including: an action determination module 10, an action filtering module 20 and a frequency control module 30. Specifically, the action determining module 10 is configured to acquire a plurality of electromyographic signals, and determine, based on the plurality of electromyographic signals, a gesture action corresponding to each of the electromyographic signals. The motion screening module 20 is configured to obtain time information corresponding to each gesture motion, and screen out the same gesture motion. The frequency control module 30 is configured to determine duration of the same gesture motion based on the same gesture motion and time information corresponding to each gesture motion, and control a sampling frequency of the electromyographic signal based on the duration.
In one implementation, the action determining module 10 includes:
the model input unit is used for inputting a plurality of electromyographic signals into a pre-trained gesture recognition model for recognizing gesture actions;
and the model output unit is used for processing the electromyographic signals through the neural network model and outputting corresponding gesture actions.
In one implementation, the apparatus further comprises:
the system comprises a sample acquisition module, a data processing module and a data processing module, wherein the sample acquisition module is used for acquiring a plurality of electromyographic sample signals and determining sample gesture actions corresponding to each electromyographic sample signal to form a training data set, and the training data set is provided with a mapping relation between the electromyographic sample signals and the sample gesture actions;
and the model training module is used for inputting the training data set into a preset neural network model for training to obtain the gesture recognition model.
In one implementation, the action filtering module 20 includes:
the time recording unit is used for recording time information corresponding to each gesture action and binding the gesture action with the time information;
the potential acquisition unit is used for acquiring action potential information corresponding to each gesture action;
the potential comparison unit is used for taking one piece of action potential information as a matching item and sequentially comparing the matching item with the rest action potential information;
and the action screening unit is used for repeatedly executing the steps of taking one piece of action potential information as a matching item and sequentially comparing the matching item with the rest of action potential information until all pieces of action potential information are taken as matching items so as to screen out the same gesture action.
In one implementation, the frequency control module 30 includes:
a time information analysis unit for determining an initial time and an end time of the same gesture motion from time information of each of the same gesture motions;
and the duration determining unit is used for determining the duration of the same gesture action based on the initial time and the end time.
In one implementation, the frequency control module 30 includes:
the time comparison unit is used for sequentially comparing the duration with a preset first time threshold and a preset second time threshold, wherein the first time threshold is smaller than the second time threshold;
the first frequency reduction unit is used for reducing the sampling frequency of the electromyographic signal if the duration is greater than the first time threshold;
and the second frequency reduction unit is used for continuously reducing the sampling frequency of the electromyographic signal if the duration is greater than the second time threshold.
In one implementation, the frequency control module 30 includes:
the frequency reduction control unit is used for acquiring the sampling frequency of the reduced electromyographic signals and comparing the sampling frequency of the reduced electromyographic signals with a frequency threshold;
and the frequency reduction stopping unit is used for stopping reducing the sampling frequency of the electromyographic signals and sampling the electromyographic signals by the frequency threshold if the sampling frequency of the reduced electromyographic signals is less than the frequency threshold.
The working principle of each module in the electromyographic signal sampling frequency control device of this embodiment is the same as the principle of each step in the above method embodiments, and details are not repeated here.
Based on the above embodiments, the invention also provides an electromyographic device, and a functional block diagram of the electromyographic device may be as shown in fig. 3. The electromyographic device comprises a processor and a memory which are connected through a system bus, wherein the processor and the memory are arranged in a host. Wherein, the processor of the electromyographic device is used for providing calculation and control capability. The memory of the electromyographic device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The network interface of the electromyographic equipment is used for being connected and communicated with an external terminal through network communication. The computer program is executed by a processor to implement a method of electromyogram signal sampling frequency control.
It will be understood by those skilled in the art that the schematic block diagram shown in fig. 3 is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the electromyographic device to which the scheme of the present invention is applied, and a specific electromyographic device may include more or less components than those shown in the figure, or may combine some components, or have a different arrangement of components.
In one embodiment, an electromyographic device is provided, where the electromyographic device includes a memory, a processor, and an electromyographic signal sampling frequency control method program stored in the memory and executable on the processor, and when the processor executes the electromyographic signal sampling frequency control method program, the following operation instructions are implemented:
acquiring a plurality of electromyographic signals, and determining a gesture action corresponding to each electromyographic signal based on the plurality of electromyographic signals;
acquiring time information corresponding to each gesture action, and screening out the same gesture actions;
and determining the duration of the same gesture action based on the same gesture action and the time information corresponding to each gesture action, and controlling the sampling frequency of the electromyographic signals based on the duration.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a non-volatile computer-readable storage medium, and the computer program may include the processes of the embodiments of the methods described above when executed. Any reference to memory, storage, operational databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
In summary, the invention discloses a method, a device and a storage medium for controlling the sampling frequency of an electromyographic signal, wherein the method comprises the following steps: acquiring a plurality of electromyographic signals, and determining a gesture action corresponding to each electromyographic signal based on the plurality of electromyographic signals; acquiring time information corresponding to each gesture action, and screening out the same gesture actions; and determining the duration of the same gesture action based on the same gesture action and the time information corresponding to each gesture action, and controlling the sampling frequency of the electromyographic signals based on the duration. The invention can realize the control of the electromyographic signal sampling frequency and is beneficial to reducing the power consumption of the electromyographic equipment.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. An electromyographic signal sampling frequency control method, the method comprising:
acquiring a plurality of electromyographic signals, and determining a gesture action corresponding to each electromyographic signal based on the plurality of electromyographic signals;
acquiring time information corresponding to each gesture action, and screening out the same gesture actions;
determining the duration time of the same gesture actions based on the same gesture actions and the time information corresponding to each gesture action, and controlling the sampling frequency of the electromyographic signals based on the duration time;
the determining the gesture action corresponding to each electromyographic signal based on the plurality of electromyographic signals comprises:
inputting a plurality of electromyographic signals into a pre-trained gesture recognition model for recognizing gesture actions;
processing the electromyographic signals through the gesture recognition model, and outputting corresponding gesture actions;
the training process of the gesture recognition model comprises the following steps:
acquiring a plurality of electromyographic sample signals, determining sample gesture actions corresponding to each electromyographic sample signal based on prior knowledge and a stored gesture template to form a training data set, wherein the gesture template is preset with corresponding relations between the electromyographic signals and action potential information, and different action potential information represents different gesture actions;
labeling signal characteristics in the electromyographic sample signals, wherein the signal characteristics correspond to action potential information of sample gesture actions, so that the electromyographic sample signals are linked with the sample gesture actions, and the training data set has a mapping relation between the electromyographic sample signals and the sample gesture actions;
inputting the training data set into a preset neural network model for training to obtain the gesture recognition model;
the acquiring of the time information corresponding to each gesture action and the screening of the same gesture action include:
recording time information corresponding to each gesture action, and binding the gesture action with the time information;
acquiring action potential information corresponding to each gesture action;
taking one piece of action potential information as a matching item, and sequentially comparing the matching item with the rest action potential information;
repeatedly executing the step of taking one piece of action potential information as a matching item and sequentially comparing the matching item with the rest of action potential information until all pieces of action potential information are taken as matching items so as to screen out the same gesture action;
the control of the sampling frequency of the electromyographic signals based on the duration comprises:
comparing the duration with a preset first time threshold and a preset second time threshold in sequence, wherein the first time threshold is smaller than the second time threshold;
if the duration is greater than the first time threshold, reducing the sampling frequency of the electromyographic signals;
if the duration is longer than the second time threshold, continuing to reduce the sampling frequency of the electromyographic signals;
the control of the sampling frequency of the electromyographic signals based on the duration comprises:
acquiring the sampling frequency of the reduced electromyographic signal, and comparing the sampling frequency of the reduced electromyographic signal with a frequency threshold;
if the sampling frequency of the electromyographic signals after being reduced is smaller than the frequency threshold, stopping reducing the sampling frequency of the electromyographic signals, and sampling the electromyographic signals by the frequency threshold;
or,
and setting a frequency threshold, and controlling the electromyographic equipment to sample the electromyographic signal by the frequency threshold if the frequency of the electromyographic equipment for carrying out frequency reduction on the electromyographic signal sampling reaches the frequency threshold.
2. The electromyographic signal sampling frequency control method of claim 1, wherein determining the duration of the same gesture action based on the same gesture action and the time information corresponding to each gesture action comprises:
determining the initial time and the end time of each same gesture action from the time information of each same gesture action;
determining a duration of the same gesture action based on the initial time and the end time.
3. An electromyographic signal sampling frequency control apparatus, the apparatus comprising:
the action determining module is used for acquiring a plurality of electromyographic signals and determining a gesture action corresponding to each electromyographic signal based on the plurality of electromyographic signals;
the action screening module is used for acquiring the moment information corresponding to each gesture action and screening out the same gesture action;
the frequency control module is used for determining the duration time of the same gesture action based on the same gesture action and the time information corresponding to each gesture action, and controlling the sampling frequency of the electromyographic signal based on the duration time;
the action determination module includes:
the model input unit is used for inputting a plurality of electromyographic signals into a pre-trained gesture recognition model for recognizing gesture actions;
the model output unit is used for processing the electromyographic signals through the gesture recognition model and outputting corresponding gesture actions;
the device further comprises:
the system comprises a sample acquisition module, a gesture recognition module and a gesture recognition module, wherein the sample acquisition module is used for acquiring a plurality of electromyographic sample signals, determining sample gesture actions corresponding to each electromyographic sample signal based on priori knowledge and a stored gesture template to form a training data set, the gesture template is preset with the corresponding relation between the electromyographic signals and action potential information, and different action potential information represents different gesture actions;
labeling signal characteristics in the electromyographic sample signals, wherein the signal characteristics correspond to action potential information of sample gesture actions, so that the electromyographic sample signals are linked with the sample gesture actions, and the training data set has a mapping relation between the electromyographic sample signals and the sample gesture actions;
the model training module is used for inputting the training data set into a preset neural network model for training to obtain the gesture recognition model;
the action screening module comprises:
the time recording unit is used for recording time information corresponding to each gesture action and binding the gesture action with the time information;
the potential acquisition unit is used for acquiring action potential information corresponding to each gesture action;
the potential comparison unit is used for taking one piece of action potential information as a matching item and sequentially comparing the matching item with the rest action potential information;
the action screening unit is used for repeatedly executing the steps of taking one piece of action potential information as a matching item and sequentially comparing the matching item with the rest pieces of action potential information until all pieces of action potential information are taken as matching items so as to screen out the same gesture action;
the frequency control module includes:
the time comparison unit is used for sequentially comparing the duration with a preset first time threshold and a preset second time threshold, wherein the first time threshold is smaller than the second time threshold;
the first frequency reduction unit is used for reducing the sampling frequency of the electromyographic signal if the duration is greater than the first time threshold;
the second frequency reduction unit is used for continuously reducing the sampling frequency of the electromyographic signal if the duration time is greater than the second time threshold;
the frequency control module includes:
the frequency reduction control unit is used for acquiring the sampling frequency of the reduced electromyographic signal and comparing the sampling frequency of the reduced electromyographic signal with a frequency threshold;
the frequency reduction stopping unit is used for stopping reducing the sampling frequency of the electromyographic signals and sampling the electromyographic signals by the frequency threshold if the sampling frequency of the reduced electromyographic signals is smaller than the frequency threshold;
or,
and setting a frequency threshold, and controlling the electromyographic equipment to sample the electromyographic signal by the frequency threshold if the frequency of the electromyographic equipment for carrying out frequency reduction on the electromyographic signal sampling reaches the frequency threshold.
4. The electromyographic signal sampling frequency control apparatus of claim 3, wherein the frequency control module comprises:
a time information analysis unit for determining an initial time and an end time of the same gesture motion from time information of each of the same gesture motions;
and the duration determining unit is used for determining the duration of the same gesture action based on the initial time and the end time.
5. An electromyographic device comprising a memory, a processor, and an electromyographic signal sampling frequency control program stored in the memory and executable on the processor, the steps of implementing the electromyographic signal sampling frequency control method of any one of claims 1-2 when the processor executes the electromyographic signal sampling frequency control program.
6. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon an electromyogram signal sampling frequency control program, which when executed by a processor, implements the steps of the electromyogram signal sampling frequency control method of any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210612029.XA CN114707562B (en) | 2022-06-01 | 2022-06-01 | Electromyographic signal sampling frequency control method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210612029.XA CN114707562B (en) | 2022-06-01 | 2022-06-01 | Electromyographic signal sampling frequency control method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114707562A CN114707562A (en) | 2022-07-05 |
| CN114707562B true CN114707562B (en) | 2022-09-02 |
Family
ID=82176121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210612029.XA Active CN114707562B (en) | 2022-06-01 | 2022-06-01 | Electromyographic signal sampling frequency control method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114707562B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115153985B (en) * | 2022-09-08 | 2022-12-09 | 深圳市心流科技有限公司 | Control method, device and terminal of intelligent artificial limb and computer readable storage medium |
| CN115204242B (en) * | 2022-09-09 | 2022-12-09 | 深圳市心流科技有限公司 | Method and device for adjusting action template comparison threshold and storage medium |
| CN115251957A (en) * | 2022-09-26 | 2022-11-01 | 深圳市心流科技有限公司 | Method, device and storage medium for adjusting sampling frequency step by step |
| CN116449967A (en) * | 2023-06-20 | 2023-07-18 | 浙江强脑科技有限公司 | Bionic hand teaching aid, control method thereof and main control equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111870242A (en) * | 2020-08-03 | 2020-11-03 | 南京邮电大学 | Intelligent gesture action generation method based on electromyographic signals |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114452054A (en) * | 2022-02-23 | 2022-05-10 | 深圳市心流科技有限公司 | Control method and device of intelligent artificial limb, intelligent artificial limb and storage medium |
-
2022
- 2022-06-01 CN CN202210612029.XA patent/CN114707562B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111870242A (en) * | 2020-08-03 | 2020-11-03 | 南京邮电大学 | Intelligent gesture action generation method based on electromyographic signals |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114707562A (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114707562B (en) | Electromyographic signal sampling frequency control method and device and storage medium | |
| CN108182937B (en) | Keyword recognition method, device, equipment and storage medium | |
| CN110555468A (en) | Electroencephalogram signal identification method and system combining recursion graph and CNN | |
| CN103294199B (en) | A kind of unvoiced information identifying system based on face's muscle signals | |
| Carfi et al. | Online human gesture recognition using recurrent neural networks and wearable sensors | |
| CN109800720A (en) | Emotion identification model training method, Emotion identification method, apparatus, equipment and storage medium | |
| CN114625257B (en) | Action recognition method and device based on electromyographic signals | |
| Shin et al. | Korean sign language recognition using EMG and IMU sensors based on group-dependent NN models | |
| CN103412640A (en) | Device and method for character or command input controlled by teeth | |
| CN111870242A (en) | Intelligent gesture action generation method based on electromyographic signals | |
| CN112016367A (en) | Emotion recognition system and method and electronic equipment | |
| CN114652493B (en) | Electromyographic signal control method and device, electromyographic equipment and storage medium | |
| CN110443113A (en) | A kind of virtual reality Writing method, system and storage medium | |
| CN112001305B (en) | Feature optimization SSVEP asynchronous recognition method based on gradient lifting decision tree | |
| CN113208593A (en) | Multi-modal physiological signal emotion classification method based on correlation dynamic fusion | |
| Malešević et al. | Decoding of individual finger movements from surface EMG signals using vector autoregressive hierarchical hidden Markov models (VARHHMM) | |
| CN106484082B (en) | Control method and device based on bioelectricity and controller | |
| Koch et al. | Regression of hand movements from sEMG data with recurrent neural networks | |
| Kumar et al. | A deep spatio-temporal model for EEG-based imagined speech recognition | |
| Ibrahimy et al. | Design and performance analysis of artificial neural network for hand motion detection from EMG signals | |
| Jaramillo-Yanez et al. | Short-term hand gesture recognition using electromyography in the transient state, support vector machines, and discrete wavelet transform | |
| CN108491792B (en) | Office scene human-computer interaction behavior recognition method based on electro-oculogram signals | |
| Jo et al. | Real-time hand gesture classification using crnn with scale average wavelet transform | |
| CN114668563A (en) | Multi-level regulation method for sampling frequency of electromyographic signals | |
| Singh et al. | A reliable and efficient machine learning pipeline for american sign language gesture recognition using EMG sensors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Han Bicheng Inventor before: Han Bicheng |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |