CN113509151A - Method and device for evaluating muscle tension level - Google Patents
Method and device for evaluating muscle tension level Download PDFInfo
- Publication number
- CN113509151A CN113509151A CN202111001080.9A CN202111001080A CN113509151A CN 113509151 A CN113509151 A CN 113509151A CN 202111001080 A CN202111001080 A CN 202111001080A CN 113509151 A CN113509151 A CN 113509151A
- Authority
- CN
- China
- Prior art keywords
- time domain
- grade
- inputting
- constructed
- 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.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
- A61B5/4519—Muscles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Rheumatology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a muscle tension grade assessment method and device, wherein the method comprises the following steps: acquiring a surface electromyographic signal acquired by wearable equipment at a wearing position; extracting the obtained surface electromyographic signals to obtain first time domain characteristics of the surface electromyographic signals; carrying out Fourier transform on the obtained surface electromyogram signal and extracting to obtain frequency domain characteristics; determining whether the wearer is in a fatigue state based on the first time-domain feature and the frequency-domain feature; if yes, executing: compensating the first time domain characteristic to obtain a second time domain characteristic; inputting the obtained second time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade; if not, executing: and inputting the obtained first time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade. The technical problem that the muscle tension cannot be measured by the current wearable equipment can be solved by the scheme.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a muscle tension grade evaluation method and device.
Background
At present, wearable equipment such as smart watch and bracelet can measure physical characteristics data such as the motion step number, rhythm of the heart, sleep index of wearing person to record health. The muscle tension is used for representing the tension degree of the static and relaxed muscle, and particularly has certain guiding significance on the rehabilitation of a patient, and the current wearable equipment does not have the function of measuring the muscle tension.
Therefore, there is a need for a method and apparatus for assessing muscle tone level to solve the above-mentioned problems.
Disclosure of Invention
In order to solve the technical problem that the conventional wearable device cannot measure muscle tension, the embodiment of the invention provides a muscle tension level evaluation method and device.
In a first aspect, an embodiment of the present invention provides a method for evaluating a muscle tone level, including:
acquiring a surface electromyographic signal acquired by wearable equipment at a wearing position;
extracting the obtained surface electromyographic signals to obtain first time domain characteristics of the surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
carrying out Fourier transform on the obtained surface electromyographic signals and extracting to obtain frequency domain characteristics of the surface electromyographic signals; wherein the frequency domain characteristics include an average frequency, a total power, an average power frequency, and a median frequency;
determining whether the wearer is in a state of fatigue based on the first time-domain feature and the frequency-domain feature;
if yes, executing: compensating the first time domain characteristic to obtain a second time domain characteristic; inputting the obtained second time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade;
if not, executing: and inputting the obtained first time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade.
In one possible design, the inputting the obtained first time domain features as input into a pre-constructed grade assessment model, and outputting the muscle tension grade includes:
inputting the obtained first time domain characteristics as input into a pre-constructed position identification model, and outputting position identification information of the wearing position;
according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information;
and inputting the obtained first time domain characteristics as input into the determined grade evaluation model, and outputting the muscle tension grade.
In one possible design, the wearable device has a plurality of electromyographic sensors;
the method for outputting the muscle tension grade by inputting the obtained first time domain characteristics into a pre-constructed grade evaluation model and taking the obtained first time domain characteristics as input comprises the following steps:
for each electromyographic sensor, performing: inputting the first time domain characteristics obtained by the electromyographic sensor into a pre-constructed position recognition model and outputting position identification information of the electromyographic sensor; according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information; inputting the first time domain characteristics obtained by the electromyographic sensor into the determined grade evaluation model, and outputting the muscle tension grade corresponding to the electromyographic sensor;
and determining the muscle tension grade with the largest output number as the output result of the muscle tension grade.
In one possible design, the location identification model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain a first time domain characteristic of each group of surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
and aiming at each preset position, taking the first time domain characteristic of the surface electromyographic signal corresponding to the preset position and the position identification information corresponding to the preset position as a sample set, and training a preset multilayer perceptron to obtain a position recognition model.
In one possible design, the rating model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain a first time domain characteristic of each group of surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
and aiming at each preset position, taking the first time domain characteristic and the muscle tension level of the surface electromyographic signal corresponding to the preset position as a sample set, and training a preset multilayer perceptron to obtain a level evaluation model corresponding to the preset position.
In one possible design, the determining whether the wearer is in fatigue based on the first time-domain feature and the frequency-domain feature includes:
inputting the first time domain characteristic and the frequency domain characteristic as input into a pre-constructed fatigue detection model, and outputting whether a wearer is in a fatigue state;
wherein the fatigue detection model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain the time domain characteristics of each group of surface electromyographic signals; wherein the time domain features include mean absolute value, waveform length, variance, root of mean square, Wilson amplitude, and adjusted mean;
performing Fourier transform on the time domain characteristics and extracting to obtain frequency domain characteristics; wherein the frequency domain characteristics include an average frequency, a total power, an average power frequency, and a median frequency;
and aiming at each preset position, taking the time domain characteristics and the frequency domain characteristics of the surface electromyographic signals corresponding to the preset position as an input sample set, taking the fatigue state as an output sample set, and training a preset multilayer perceptron to obtain a fatigue detection model corresponding to the preset position.
In one possible design, the wearable device has a plurality of electromyographic sensors;
the inputting the first time domain feature and the frequency domain feature as inputs to a pre-constructed fatigue detection model, and outputting whether a wearer is in a fatigue state, includes:
for each electromyographic sensor, performing: inputting the first time domain characteristics obtained by the electromyographic sensor into a pre-constructed position recognition model and outputting position identification information of the electromyographic sensor; according to the output position identification information, determining a pre-constructed fatigue detection model corresponding to the position identification information; inputting the first time domain characteristic and the frequency domain characteristic obtained by the electromyographic sensor into the determined fatigue detection model, and outputting a fatigue state corresponding to the electromyographic sensor;
and determining the fatigue state with the largest output number as the output result of the fatigue state.
In one possible design, the compensating the first time-domain characteristic to obtain a second time-domain characteristic includes:
acquiring time domain characteristics corresponding to a fatigue state and a non-fatigue state determined in a preset historical time period;
determining compensation coefficients respectively corresponding to an average absolute value and a root mean square included in the time domain characteristics based on the acquired time domain characteristics of the fatigue state and the non-fatigue state;
and compensating the mean absolute value and the square root included in the first time domain characteristic by using the determined compensation coefficients respectively corresponding to the mean absolute value and the square root to obtain a second time domain characteristic.
In a second aspect, an embodiment of the present invention further provides an apparatus for evaluating a muscle tension level, including:
the acquisition module is used for acquiring surface electromyographic signals acquired by the wearable device at a wearing position;
the extraction module is used for extracting the acquired surface electromyographic signals to obtain first time domain characteristics of the surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
the transformation module is used for carrying out Fourier transformation on the first time domain characteristic and extracting the first time domain characteristic to obtain a frequency domain characteristic; wherein the frequency domain characteristics include an average frequency, a total power, an average power frequency, and a median frequency;
a determination module for determining whether the wearer is in a state of fatigue based on the first time-domain feature and the frequency-domain feature;
an output module for performing, when the wearer is in a tired state: compensating the first time domain characteristic to obtain a second time domain characteristic; inputting the obtained second time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade; and performing, when the wearer is not in a tired state: and inputting the obtained first time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade.
In one possible design, the output module is configured to perform the following operations when performing the inputting of the obtained first time domain feature as an input into a pre-constructed grade assessment model and outputting the muscle tension grade:
inputting the obtained first time domain characteristics as input into a pre-constructed position identification model, and outputting position identification information of the wearing position;
according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information;
and inputting the obtained first time domain characteristics as input into the determined grade evaluation model, and outputting the muscle tension grade.
The embodiment of the invention provides a muscle tension grade evaluation method and device, wherein wearable equipment is used for obtaining a surface electromyographic signal of a wearer, extracting the obtained surface electromyographic signal to obtain a first time domain characteristic and a first frequency domain characteristic, determining whether the wearer is in a fatigue state or not based on the first time domain characteristic and the first frequency domain characteristic, and outputting a muscle tension grade according to a detection result of the fatigue state and the first time domain characteristic, so that the wearable equipment can measure the muscle tension of a human body.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of a method for assessing muscle tone according to an embodiment of the present invention;
fig. 2 is a hardware architecture diagram of an electronic device according to an embodiment of the present invention;
FIG. 3 is a block diagram of an apparatus for assessing muscle tone according to an embodiment of the present invention;
fig. 4 is a structural diagram of an eight-channel electromyography sensor according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a method for evaluating muscle tone level, the method including:
step 100: acquiring a surface electromyographic signal acquired by wearable equipment at a wearing position;
step 102: extracting the obtained surface electromyographic signals to obtain first time domain characteristics of the surface electromyographic signals; the first time domain characteristics comprise an average absolute value, a waveform length, a variance, a root of mean square, a Wilson amplitude and an adjustment average value;
step 104: carrying out Fourier transform and extraction on the obtained surface electromyographic signals to obtain frequency domain characteristics of the surface electromyographic signals; the frequency domain characteristics comprise average frequency, total power, average power frequency and median frequency;
step 106: determining whether the wearer is in a fatigue state based on the first time-domain feature and the frequency-domain feature;
step 108: if yes, executing: compensating the first time domain characteristic to obtain a second time domain characteristic; inputting the obtained second time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade; step 110: if not, executing: and inputting the obtained first time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade.
According to the embodiment of the invention, the wearable device is used for acquiring the surface electromyographic signal of the wearer, extracting the acquired surface electromyographic signal to obtain the first time domain characteristic, determining whether the wearer is in the fatigue state or not based on the first time domain characteristic and the frequency domain characteristic, and outputting the muscle tension grade according to the detection result of the fatigue state and the first time domain characteristic, so that the wearable device can measure the muscle tension of the human body.
The manner in which the various steps shown in fig. 1 are performed is described below.
For step 100, the wearing position may be, for example, the front part of the arm (i.e., the wrist) of the wearer, the wearable device may be, for example, a smart bracelet or a smart watch, and an electromyographic sensor is built in the wearable device to realize the acquisition of the surface electromyographic signal.
It is understood that the main body of the method may be a terminal device, such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, and the like.
For step 102, the average absolute value is determined by the following equation:
where Mav is the mean absolute value, N is the total number of sample points, xiThe characteristic value of the ith sampling point is obtained;
the waveform length is determined by the following equation:
wherein, WLkIs the length of the waveform, xiThe characteristic value of the ith sampling point is obtained;
the variance is determined by the following formula:
wherein, VARkIs the variance of the received signal and the received signal,
the square of the average characteristic value of all sampling points;
the root mean square is determined by the following formula:
wherein RMSkIs root of Square equal root;
the wilson amplitude is determined by the following equation:
wherein WAMP is Wilson amplitude, and th is a preset threshold;
the adjusted average is determined by the following formula:
wherein, MMAVlkTo adjust the average value.
The obtaining of the average frequency, the total power, the average power frequency and the median frequency for step 104 is well known to those skilled in the art and will not be described herein.
With respect to step 106, in some embodiments, step 106 includes:
inputting the first time domain characteristic and the frequency domain characteristic as input into a pre-constructed fatigue detection model, and outputting whether a wearer is in a fatigue state;
wherein the fatigue detection model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor (see fig. 4) arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain the time domain characteristics of each group of surface electromyographic signals; the time domain characteristics comprise an average absolute value, a waveform length, a variance, a root of mean square, a Wilson amplitude and an adjustment average value;
carrying out Fourier transform on the time domain characteristics and extracting to obtain frequency domain characteristics; the frequency domain characteristics comprise average frequency, total power, average power frequency and median frequency;
and aiming at each preset position, taking the time domain characteristics and the frequency domain characteristics of the surface electromyographic signals corresponding to the preset position as an input sample set, taking the fatigue state as an output sample set, and training a preset multilayer perceptron to obtain a fatigue detection model corresponding to the preset position.
In this embodiment, the fatigue detection model is trained, which is beneficial to outputting a more accurate detection result of fatigue detection.
Further, the wearable device has a plurality of myoelectric sensors;
inputting the first time domain characteristic and the frequency domain characteristic as input into a pre-constructed fatigue detection model, and outputting whether a wearer is in a fatigue state, wherein the method comprises the following steps:
for each electromyographic sensor, performing: inputting the first time domain characteristics obtained by the electromyographic sensor into a pre-constructed position recognition model and outputting position identification information of the electromyographic sensor; according to the output position identification information, determining a pre-constructed fatigue detection model corresponding to the position identification information; inputting the first time domain characteristic and the frequency domain characteristic obtained by the electromyographic sensor into the determined fatigue detection model, and outputting a fatigue state corresponding to the electromyographic sensor;
and determining the fatigue state with the largest output number as the output result of the fatigue state.
In this embodiment, by arranging a plurality of electromyographic sensors in the wearable device, the fatigue state corresponding to the corresponding position of each electromyographic sensor can be obtained, and the final fatigue state can be determined according to the number, so that the detection of the fatigue state is more accurate.
In some embodiments, the wearable device may have three myoelectric sensors, so that the wearable device is relatively high in cost and easy to install the three myoelectric sensors, for example, the wearable device is a smart watch, and the three myoelectric sensors are respectively arranged at two ends and in the middle of the inner side surface of the watch dial of the smart watch.
For step 108, the step 108 of "compensating the first time domain feature to obtain the second time domain feature" includes:
acquiring time domain characteristics corresponding to a fatigue state and a non-fatigue state determined in a preset historical time period;
determining compensation coefficients respectively corresponding to an average absolute value and a root mean square included in the time domain characteristics based on the acquired time domain characteristics of the fatigue state and the non-fatigue state;
and compensating the mean absolute value and the square root included in the first time domain characteristic by using the determined compensation coefficients respectively corresponding to the mean absolute value and the square root to obtain a second time domain characteristic.
In this embodiment, since the average absolute value of the fatigue state is reduced and the root-mean-square is increased relative to the average absolute value of the non-fatigue state, and the general grade evaluation model is trained based on the time-domain features in the non-fatigue state, if the time-domain features extracted in the fatigue state are used as the input of the grade evaluation model, the evaluation result is inaccurate, and therefore, the average absolute value and the root-mean-square included in the time-domain features need to be compensated. Specifically, the compensation coefficients are based on the average absolute value and the root-mean-square determined in the historical data.
In addition, for further limitation on "the obtained second time domain feature is used as an input and is input to the pre-constructed level assessment model to output the muscle tension level" in step 108, reference may be made to the following description of "the obtained first time domain feature is used as an input and is input to the pre-constructed level assessment model to output the muscle tension level", and only the first time domain feature and the second time domain feature need to be replaced at a time, which is not described herein again.
With respect to step 110, in some embodiments, the rating model is determined by:
muscle tone was classified into multiple grades according to the Ashworth scale; simulating the corresponding states of different muscle tension levels by using a hydraulic arm force device;
for each muscle tone level, performing: acquiring a surface electromyographic signal acquired by wearable equipment at a standard measurement position; extracting the obtained surface electromyographic signals to obtain first time domain characteristics of the surface electromyographic signals; the first time domain characteristics comprise an average absolute value, a waveform length, a variance, a root of mean square, a Wilson amplitude and an adjustment average value;
and training a preset multilayer perceptron by taking the muscle tension grade and the obtained first time domain characteristic as a sample set to obtain the grade evaluation model.
In this embodiment, the standard measurement position is the wearing position. The grade evaluation model is trained, so that the muscle tension grade corresponding to the moment is output according to the first time domain feature to be detected, and therefore evaluation of the wearable device on the muscle tension grade is completed.
It should be noted that, even though some wearable devices have the function of measuring muscle tension, since the muscle tension at different positions of the human body is different, when measuring the muscle tension, it is necessary to ensure that the wearing position of the wearable device is correct, otherwise, the obtained result of the muscle level is inaccurate. Therefore, if the wearing position is not the standard measurement position, it may result in inaccurate results of the obtained muscle level.
In some embodiments, to solve the technical problem, step 110 may include:
inputting the obtained first time domain characteristics as input into a pre-constructed position identification model, and outputting position identification information of the wearing position;
according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information;
and inputting the obtained first time domain characteristics as input into the determined grade evaluation model, and outputting the muscle tension grade.
In the embodiment, by setting the position identification model, if the wearable device has an error in the wearing position, the position identification information corresponding to the current wearing position can be obtained by using the position identification model trained in advance; the execution main body stores a plurality of grade evaluation models and the mapping relation between each wearing position and the grade evaluation model in advance, and the grade evaluation model corresponding to the current wearing position can be obtained through the obtained position identification information and the mapping relation, so that the accurate muscle tension grade is output.
It should be noted that the wearing position error in the embodiment of the present invention refers to an error of a rotational position of the wearable device in a circumferential direction of the arm, and not an axial error along the arm. Therefore, for example, eight positions may be provided in the circumferential direction of the front portion of the arm in advance, and the grade assessment model at each of the eight positions may be trained, where the training method is the same as the above training method, and will not be described herein again.
It will be further appreciated that the wearing position may not be directly opposite to one of the eight positions previously provided on the front of the arm, and therefore the measurement result may also be slightly inaccurate.
In some embodiments, to solve the technical problem, step 110 may include:
the wearable device is provided with a plurality of electromyographic sensors;
inputting the obtained first time domain characteristics as input into a pre-constructed grade evaluation model, and outputting a muscle tension grade, wherein the method comprises the following steps:
for each electromyographic sensor, performing: inputting the first time domain characteristics obtained by the electromyographic sensor into a pre-constructed position recognition model and outputting position identification information of the electromyographic sensor; according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information; inputting the first time domain characteristics obtained by the electromyographic sensor into the determined grade evaluation model, and outputting the muscle tension grade corresponding to the electromyographic sensor;
and determining the muscle tension grade with the largest output number as the output result of the muscle tension grade.
In the embodiment, a plurality of electromyographic sensors are arranged in the wearable device, so that the muscle tension level corresponding to the corresponding position of each electromyographic sensor can be obtained, and the final muscle tension level can be determined according to the number, so that the muscle tension level can be more accurately evaluated.
In some embodiments, the wearable device may have three myoelectric sensors, so that the wearable device is relatively high in cost and easy to install the three myoelectric sensors, for example, the wearable device is a smart watch, and the three myoelectric sensors are respectively arranged at two ends and in the middle of the inner side surface of the watch dial of the smart watch.
In some embodiments, the location identification model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor (see fig. 4) arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain a first time domain characteristic of each group of surface electromyographic signals; the first time domain characteristics comprise an average absolute value, a waveform length, a variance, a root of mean square, a Wilson amplitude and an adjustment average value;
and aiming at each preset position, taking the first time domain characteristic of the surface electromyographic signal corresponding to the preset position and the position identification information corresponding to the preset position as a sample set, and training a preset multilayer perceptron to obtain a position recognition model.
In this embodiment, by training the position recognition model, it is beneficial to output a more accurate muscle tension level evaluation result.
In some embodiments, the rating model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor (see fig. 4) arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain a first time domain characteristic of each group of surface electromyographic signals; the first time domain characteristics comprise an average absolute value, a waveform length, a variance, a root of mean square, a Wilson amplitude and an adjustment average value;
and aiming at each preset position, taking the first time domain characteristic and the muscle tension level of the surface electromyographic signal corresponding to the preset position as a sample set, and training a preset multilayer perceptron to obtain a level evaluation model corresponding to the preset position.
In this embodiment, by training the level evaluation model, it is beneficial to output a more accurate evaluation result of the muscle tension level.
It should be noted that the training method of the above-mentioned grade estimation model, which measures and trains data for one location, is different from the training method provided by this embodiment, which trains using data measured by a multi-channel electromyographic sensor.
As shown in fig. 2 and 3, the embodiment of the present invention provides a device for evaluating muscle tone level. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. From a hardware aspect, as shown in fig. 2, a hardware architecture diagram of an electronic device in which an apparatus for evaluating a muscle tension level according to an embodiment of the present invention is located is shown, in which besides the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 2, the electronic device in which the apparatus is located may also include other hardware, such as a forwarding chip responsible for processing a message. Taking a software implementation as an example, as shown in fig. 3, as a logical device, a CPU of the electronic device reads a corresponding computer program in the non-volatile memory into the memory for running.
As shown in fig. 3, the present embodiment provides an apparatus for evaluating muscle tone level, including:
the acquisition module 300 is configured to acquire a surface electromyographic signal acquired by the wearable device at a wearing position;
an extraction module 302, configured to extract an obtained surface electromyogram signal to obtain a first time domain feature of the surface electromyogram signal; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
a transform module 304, configured to perform fourier transform on the first time domain feature and extract the first time domain feature to obtain a frequency domain feature; the frequency domain characteristics comprise average frequency, total power, average power frequency and median frequency;
a determining module 306 for determining whether the wearer is in a fatigue state based on the first time-domain feature and the frequency-domain feature;
an output module 308 for performing, when the wearer is in a tired state: compensating the first time domain characteristic to obtain a second time domain characteristic; inputting the obtained second time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade; and performing, when the wearer is not in a tired state: and inputting the obtained first time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade.
In an embodiment of the present invention, the obtaining module 300 may be configured to perform step 100 in the above-described method embodiment, the extracting module 302 may be configured to perform step 102 in the above-described method embodiment, the transforming module 304 may be configured to perform step 104 in the above-described method embodiment, the determining module 306 may be configured to perform step 106 in the above-described method embodiment, and the outputting module 308 may be configured to perform step 108 and step 110 in the above-described method embodiment.
In an embodiment of the present invention, the output module 308 is configured to perform the following operations when performing the input of the obtained first time domain feature as an input to the pre-constructed level assessment model and outputting the muscle tension level:
inputting the obtained first time domain characteristics as input into a pre-constructed position identification model, and outputting position identification information of the wearing position;
according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information;
and inputting the obtained first time domain characteristics as input into the determined grade evaluation model, and outputting the muscle tension grade.
In one embodiment of the invention, the wearable device has a plurality of electromyographic sensors;
the output module 308 is configured to perform the following operations:
for each electromyographic sensor, performing: inputting the first time domain characteristics obtained by the electromyographic sensor into a pre-constructed position recognition model and outputting position identification information of the electromyographic sensor; according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information; inputting the first time domain characteristics obtained by the electromyographic sensor into the determined grade evaluation model, and outputting the muscle tension grade corresponding to the electromyographic sensor;
and determining the muscle tension grade with the largest output number as the output result of the muscle tension grade.
In one embodiment of the invention, the location identification model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain a first time domain characteristic of each group of surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
and aiming at each preset position, taking the first time domain characteristic of the surface electromyographic signal corresponding to the preset position and the position identification information corresponding to the preset position as a sample set, and training a preset multilayer perceptron to obtain a position recognition model.
In one embodiment of the present invention, the rating evaluation model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain a first time domain characteristic of each group of surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
and aiming at each preset position, taking the first time domain characteristic and the muscle tension level of the surface electromyographic signal corresponding to the preset position as a sample set, and training a preset multilayer perceptron to obtain a level evaluation model corresponding to the preset position.
In an embodiment of the present invention, the determining module 306 is configured to perform the following operations:
inputting the first time domain characteristic and the frequency domain characteristic as input into a pre-constructed fatigue detection model, and outputting whether a wearer is in a fatigue state;
wherein the fatigue detection model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain the time domain characteristics of each group of surface electromyographic signals; wherein the time domain features include mean absolute value, waveform length, variance, root of mean square, Wilson amplitude, and adjusted mean;
performing Fourier transform on the time domain characteristics and extracting to obtain frequency domain characteristics; wherein the frequency domain characteristics include an average frequency, a total power, an average power frequency, and a median frequency;
and aiming at each preset position, taking the time domain characteristics and the frequency domain characteristics of the surface electromyographic signals corresponding to the preset position as an input sample set, taking the fatigue state as an output sample set, and training a preset multilayer perceptron to obtain a fatigue detection model corresponding to the preset position.
In one embodiment of the invention, the wearable device has a plurality of electromyographic sensors;
the determining module 306 is configured to perform the following operations when the first time domain feature and the frequency domain feature are input into a pre-constructed fatigue detection model and whether the wearer is in a fatigue state is output:
for each electromyographic sensor, performing: inputting the first time domain characteristics obtained by the electromyographic sensor into a pre-constructed position recognition model and outputting position identification information of the electromyographic sensor; according to the output position identification information, determining a pre-constructed fatigue detection model corresponding to the position identification information; inputting the first time domain characteristic and the frequency domain characteristic obtained by the electromyographic sensor into the determined fatigue detection model, and outputting a fatigue state corresponding to the electromyographic sensor;
and determining the fatigue state with the largest output number as the output result of the fatigue state.
In an embodiment of the present invention, when performing the compensation on the first time domain characteristic to obtain the second time domain characteristic, the output module 308 is configured to perform the following operations:
acquiring time domain characteristics corresponding to a fatigue state and a non-fatigue state determined in a preset historical time period;
determining compensation coefficients respectively corresponding to an average absolute value and a root mean square included in the time domain characteristics based on the acquired time domain characteristics of the fatigue state and the non-fatigue state;
and compensating the mean absolute value and the square root included in the first time domain characteristic by using the determined compensation coefficients respectively corresponding to the mean absolute value and the square root to obtain a second time domain characteristic.
It is to be understood that the illustrated configuration of the embodiment of the present invention does not constitute a specific limitation of the apparatus for evaluating a muscle tension level. In other embodiments of the invention, a device for assessing muscle tone levels may include more or fewer components than shown, or some components may be combined, some components may be separated, or a different arrangement of components may be used. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
Because the content of information interaction, execution process, and the like among the modules in the device is based on the same concept as the method embodiment of the present invention, specific content can be referred to the description in the method embodiment of the present invention, and is not described herein again.
The embodiment of the present invention further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor executes the computer program to implement a muscle tension level assessment method in any embodiment of the present invention.
Embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the processor to perform a method for assessing a muscle tension level according to any one of the embodiments of the present invention.
Specifically, a system or an apparatus equipped with a storage medium on which software program codes that realize the functions of any of the above-described embodiments are stored may be provided, and a computer (or a CPU or MPU) of the system or the apparatus is caused to read out and execute the program codes stored in the storage medium.
In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.
Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.
Further, it should be clear that the functions of any one of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform a part or all of the actual operations based on instructions of the program code.
Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then causes a CPU or the like mounted on the expansion board or the expansion module to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the above-described embodiments.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an …" does not exclude the presence of other similar elements in a process, method, article, or apparatus that comprises the element.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
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 (10)
1. A method of assessing a muscle tone level, comprising:
acquiring a surface electromyographic signal acquired by wearable equipment at a wearing position;
extracting the obtained surface electromyographic signals to obtain first time domain characteristics of the surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
carrying out Fourier transform on the obtained surface electromyographic signals and extracting to obtain frequency domain characteristics of the surface electromyographic signals; wherein the frequency domain characteristics include an average frequency, a total power, an average power frequency, and a median frequency;
determining whether the wearer is in a state of fatigue based on the first time-domain feature and the frequency-domain feature;
if yes, executing: compensating the first time domain characteristic to obtain a second time domain characteristic; inputting the obtained second time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade;
if not, executing: and inputting the obtained first time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade.
2. The method of claim 1, wherein the inputting the obtained first time domain features as input into a pre-constructed grade assessment model to output muscle tension grade comprises:
inputting the obtained first time domain characteristics as input into a pre-constructed position identification model, and outputting position identification information of the wearing position;
according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information;
and inputting the obtained first time domain characteristics as input into the determined grade evaluation model, and outputting the muscle tension grade.
3. The method of claim 1, wherein the wearable device has a plurality of electromyographic sensors;
the method for outputting the muscle tension grade by inputting the obtained first time domain characteristics into a pre-constructed grade evaluation model and taking the obtained first time domain characteristics as input comprises the following steps:
for each electromyographic sensor, performing: inputting the first time domain characteristics obtained by the electromyographic sensor into a pre-constructed position recognition model and outputting position identification information of the electromyographic sensor; according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information; inputting the first time domain characteristics obtained by the electromyographic sensor into the determined grade evaluation model, and outputting the muscle tension grade corresponding to the electromyographic sensor;
and determining the muscle tension grade with the largest output number as the output result of the muscle tension grade.
4. A method according to claim 2 or 3, characterized in that the location identification model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain a first time domain characteristic of each group of surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
and aiming at each preset position, taking the first time domain characteristic of the surface electromyographic signal corresponding to the preset position and the position identification information corresponding to the preset position as a sample set, and training a preset multilayer perceptron to obtain a position recognition model.
5. A method according to claim 2 or 3, wherein the rating model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain a first time domain characteristic of each group of surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
and aiming at each preset position, taking the first time domain characteristic and the muscle tension level of the surface electromyographic signal corresponding to the preset position as a sample set, and training a preset multilayer perceptron to obtain a level evaluation model corresponding to the preset position.
6. The method of claim 2, wherein determining whether the wearer is in fatigue based on the first time-domain feature and the frequency-domain feature comprises:
inputting the first time domain characteristic and the frequency domain characteristic as input into a pre-constructed fatigue detection model, and outputting whether a wearer is in a fatigue state;
wherein the fatigue detection model is determined by:
acquiring a plurality of groups of surface electromyographic signals acquired by a plurality of positions preset in the arm of a wearer by a multi-channel electromyographic sensor arranged in a ring shape;
extracting multiple groups of acquired surface electromyographic signals to obtain the time domain characteristics of each group of surface electromyographic signals; wherein the time domain features include mean absolute value, waveform length, variance, root of mean square, Wilson amplitude, and adjusted mean;
performing Fourier transform on the time domain characteristics and extracting to obtain frequency domain characteristics; wherein the frequency domain characteristics include an average frequency, a total power, an average power frequency, and a median frequency;
and aiming at each preset position, taking the time domain characteristics and the frequency domain characteristics of the surface electromyographic signals corresponding to the preset position as an input sample set, taking the fatigue state as an output sample set, and training a preset multilayer perceptron to obtain a fatigue detection model corresponding to the preset position.
7. The method of claim 6, wherein the wearable device has a plurality of electromyographic sensors;
the inputting the first time domain feature and the frequency domain feature as inputs to a pre-constructed fatigue detection model, and outputting whether a wearer is in a fatigue state, includes:
for each electromyographic sensor, performing: inputting the first time domain characteristics obtained by the electromyographic sensor into a pre-constructed position recognition model and outputting position identification information of the electromyographic sensor; according to the output position identification information, determining a pre-constructed fatigue detection model corresponding to the position identification information; inputting the first time domain characteristic and the frequency domain characteristic obtained by the electromyographic sensor into the determined fatigue detection model, and outputting a fatigue state corresponding to the electromyographic sensor;
and determining the fatigue state with the largest output number as the output result of the fatigue state.
8. The method according to any of claims 1-7, wherein said compensating the first time domain feature to obtain a second time domain feature comprises:
acquiring time domain characteristics corresponding to a fatigue state and a non-fatigue state determined in a preset historical time period;
determining compensation coefficients respectively corresponding to an average absolute value and a root mean square included in the time domain characteristics based on the acquired time domain characteristics of the fatigue state and the non-fatigue state;
and compensating the mean absolute value and the square root included in the first time domain characteristic by using the determined compensation coefficients respectively corresponding to the mean absolute value and the square root to obtain a second time domain characteristic.
9. An apparatus for assessing muscle tone levels, comprising:
the acquisition module is used for acquiring surface electromyographic signals acquired by the wearable device at a wearing position;
the extraction module is used for extracting the acquired surface electromyographic signals to obtain first time domain characteristics of the surface electromyographic signals; wherein the first time domain features comprise an average absolute value, a waveform length, a variance, a root-mean-square, a Wilson amplitude, and an adjusted average;
the transformation module is used for carrying out Fourier transformation on the first time domain characteristic and extracting the first time domain characteristic to obtain a frequency domain characteristic; wherein the frequency domain characteristics include an average frequency, a total power, an average power frequency, and a median frequency;
a determination module for determining whether the wearer is in a state of fatigue based on the first time-domain feature and the frequency-domain feature;
an output module for performing, when the wearer is in a tired state: compensating the first time domain characteristic to obtain a second time domain characteristic; inputting the obtained second time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade; and performing, when the wearer is not in a tired state: and inputting the obtained first time domain characteristics as input into a pre-constructed grade evaluation model, and outputting the muscle tension grade.
10. The apparatus of claim 9, wherein the output module, when executing the inputting of the obtained first time domain feature as an input into a pre-constructed grade assessment model and outputting the muscle tension grade, is configured to:
inputting the obtained first time domain characteristics as input into a pre-constructed position identification model, and outputting position identification information of the wearing position;
according to the position identification information obtained through output, determining a pre-constructed grade evaluation model corresponding to the position identification information;
and inputting the obtained first time domain characteristics as input into the determined grade evaluation model, and outputting the muscle tension grade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111001080.9A CN113509151B (en) | 2021-08-30 | 2021-08-30 | Method and device for evaluating muscle tension level |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111001080.9A CN113509151B (en) | 2021-08-30 | 2021-08-30 | Method and device for evaluating muscle tension level |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113509151A true CN113509151A (en) | 2021-10-19 |
| CN113509151B CN113509151B (en) | 2022-03-25 |
Family
ID=78062969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111001080.9A Active CN113509151B (en) | 2021-08-30 | 2021-08-30 | Method and device for evaluating muscle tension level |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113509151B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115067949A (en) * | 2022-08-22 | 2022-09-20 | 深圳市鑫正宇科技有限公司 | Method and device for detecting muscle tension based on wearable equipment |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080058668A1 (en) * | 2006-08-21 | 2008-03-06 | Kaveh Seyed Momen | Method, system and apparatus for real-time classification of muscle signals from self-selected intentional movements |
| EP2632327A1 (en) * | 2010-10-29 | 2013-09-04 | Mika Herrala | A method and a device for measuring muscle signals |
| WO2013144866A1 (en) * | 2012-03-27 | 2013-10-03 | B10Nix S.R.L. | System for the acquisition and analysis of muscle activity and operation method thereof |
| US20140032462A1 (en) * | 2012-07-24 | 2014-01-30 | Rehabilitation Institute Of Chicago | Systems and methods for autoconfiguration of pattern-recognition controlled myoelectric prostheses |
| CN107518896A (en) * | 2017-07-12 | 2017-12-29 | 中国科学院计算技术研究所 | A kind of myoelectricity armlet wearing position Forecasting Methodology and system |
| WO2018029171A1 (en) * | 2016-08-08 | 2018-02-15 | Koninklijke Philips N.V. | System and method for assisting exercising of a subject |
| CN108523872A (en) * | 2017-03-06 | 2018-09-14 | 上海健康医学院 | A kind of physical therapy efficacy appraisal procedure and system |
| CN110870769A (en) * | 2018-09-03 | 2020-03-10 | 香港理工大学深圳研究院 | Method and equipment for detecting muscle fatigue grade |
| EP3636154A2 (en) * | 2018-10-12 | 2020-04-15 | DePuy Synthes Products, Inc. | Neuromuscular sensing device with multi-sensor array |
| WO2020193393A1 (en) * | 2019-03-27 | 2020-10-01 | Koninklijke Philips N.V. | Assessing muscle fatigue |
| CN112957056A (en) * | 2021-03-16 | 2021-06-15 | 苏州大学 | Method and system for extracting muscle fatigue grade features by utilizing cooperative network |
-
2021
- 2021-08-30 CN CN202111001080.9A patent/CN113509151B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080058668A1 (en) * | 2006-08-21 | 2008-03-06 | Kaveh Seyed Momen | Method, system and apparatus for real-time classification of muscle signals from self-selected intentional movements |
| EP2632327A1 (en) * | 2010-10-29 | 2013-09-04 | Mika Herrala | A method and a device for measuring muscle signals |
| WO2013144866A1 (en) * | 2012-03-27 | 2013-10-03 | B10Nix S.R.L. | System for the acquisition and analysis of muscle activity and operation method thereof |
| US20140032462A1 (en) * | 2012-07-24 | 2014-01-30 | Rehabilitation Institute Of Chicago | Systems and methods for autoconfiguration of pattern-recognition controlled myoelectric prostheses |
| WO2018029171A1 (en) * | 2016-08-08 | 2018-02-15 | Koninklijke Philips N.V. | System and method for assisting exercising of a subject |
| CN108523872A (en) * | 2017-03-06 | 2018-09-14 | 上海健康医学院 | A kind of physical therapy efficacy appraisal procedure and system |
| CN107518896A (en) * | 2017-07-12 | 2017-12-29 | 中国科学院计算技术研究所 | A kind of myoelectricity armlet wearing position Forecasting Methodology and system |
| CN110870769A (en) * | 2018-09-03 | 2020-03-10 | 香港理工大学深圳研究院 | Method and equipment for detecting muscle fatigue grade |
| EP3636154A2 (en) * | 2018-10-12 | 2020-04-15 | DePuy Synthes Products, Inc. | Neuromuscular sensing device with multi-sensor array |
| WO2020193393A1 (en) * | 2019-03-27 | 2020-10-01 | Koninklijke Philips N.V. | Assessing muscle fatigue |
| CN112957056A (en) * | 2021-03-16 | 2021-06-15 | 苏州大学 | Method and system for extracting muscle fatigue grade features by utilizing cooperative network |
Non-Patent Citations (3)
| Title |
|---|
| 李健等: "实验性咬合高点诱发头面部疼痛时的肌电分析研究", 《实用口腔医学杂志》 * |
| 贾淼等: "面向地铁低头族的颈部疲劳sEMG-JASA 评价模型", 《智能系统学报》 * |
| 赵龙飞等: "动力性运动诱发下肢肌肉酸痛过程中sEMG 信号的特征分析", 《体育科技》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115067949A (en) * | 2022-08-22 | 2022-09-20 | 深圳市鑫正宇科技有限公司 | Method and device for detecting muscle tension based on wearable equipment |
| CN115067949B (en) * | 2022-08-22 | 2022-11-18 | 深圳市鑫正宇科技有限公司 | Method and device for detecting muscle tension based on wearable equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113509151B (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109276255B (en) | Method and device for detecting tremor of limbs | |
| CN101815466B (en) | A non-invasive device NADI TARANGINI useful for quantitative detection of arterial NADI pulse waveform | |
| Phinyomark et al. | A feature extraction issue for myoelectric control based on wearable EMG sensors | |
| Luo et al. | Possibility of quantifying TCM finger-reading sensations: I. Bi-sensing pulse diagnosis instrument | |
| CN106419893A (en) | Sleep state detection method and device | |
| CN106859653A (en) | Dietary behavior detection means and dietary behavior detection method | |
| CN113288075B (en) | Floating, middle and deep pulse position identification method and system | |
| CN113509151B (en) | Method and device for evaluating muscle tension level | |
| Wang et al. | PulseDB: A large, cleaned dataset based on MIMIC-III and VitalDB for benchmarking cuff-less blood pressure estimation methods | |
| CN110659677A (en) | Human body falling detection method based on movable sensor combination equipment | |
| CN113693604B (en) | Method and device for evaluating muscle tension grade based on fatigue state of wearer | |
| CN114190897B (en) | Training method of sleep stage model, sleep stage method and device | |
| CN108091391A (en) | Illness appraisal procedure, terminal device and computer-readable medium | |
| CN113645901B (en) | Apparatus for assessing muscle fatigue and corresponding computer program product | |
| CN114340483B (en) | Blood pressure calibration selection method and modeling method thereof | |
| AU2021101097A4 (en) | A system and method for automatic playlist generation by analysing human emotions through physiological signals | |
| Xia et al. | Data-Fusion-Based Quality Enhancement for HR Measurements Collected by Wearable Sensors | |
| CN116636856A (en) | Electrocardiogram classification method, system, electronic equipment and storage medium | |
| CN116712099A (en) | Fetal heart state detection method based on multi-mode data, electronic equipment and storage medium | |
| JP7307507B2 (en) | Pathological condition analysis system, pathological condition analyzer, pathological condition analysis method, and pathological condition analysis program | |
| KR102617046B1 (en) | Sleep stage prediction method using deep learning model and analysis apparatus | |
| CN111723622B (en) | Heart beat classification method, heart beat classification device, wearable equipment and storage medium | |
| TWI765420B (en) | Assembly of heart failure prediction | |
| CN117423457B (en) | Remote health monitoring method and system thereof | |
| EP3863001B1 (en) | Information processing device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |