CN111904416A - Muscle fatigue detection method, computer device, and storage medium - Google Patents

Muscle fatigue detection method, computer device, and storage medium Download PDF

Info

Publication number
CN111904416A
CN111904416A CN202010734489.0A CN202010734489A CN111904416A CN 111904416 A CN111904416 A CN 111904416A CN 202010734489 A CN202010734489 A CN 202010734489A CN 111904416 A CN111904416 A CN 111904416A
Authority
CN
China
Prior art keywords
muscle
wavelet packet
fatigue
packet energy
detection method
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.)
Pending
Application number
CN202010734489.0A
Other languages
Chinese (zh)
Inventor
王灿
段声才
吴新宇
李梦瑶
何柏霖
郭子铭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Advanced Technology of CAS
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Priority to CN202010734489.0A priority Critical patent/CN111904416A/en
Publication of CN111904416A publication Critical patent/CN111904416A/en
Pending legal-status Critical Current

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
    • A61B5/22—Ergometry; Measuring muscular strength or the force of a muscular blow
    • A61B5/224—Measuring muscular strength
    • A61B5/225—Measuring muscular strength of the fingers, e.g. by monitoring hand-grip force
    • 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
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • 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
    • 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
    • A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters

Abstract

The application relates to the technical field of human motion function detection, and discloses a muscle fatigue detection method, computer equipment and a computer-readable storage medium. The muscle fatigue detection method comprises the following steps: acquiring surface electromyogram data of target muscles; dividing the surface electromyogram data into a plurality of data segments according to time sequence; calculating the wavelet packet energy entropy of each data segment; and generating a muscle fatigue index of the target muscle based on the wavelet packet energy entropy. Through the mode, the muscle fatigue detection method and the muscle fatigue detection device can be used for quantifying the fatigue degree of the muscle and improving the muscle fatigue detection accuracy.

Description

Muscle fatigue detection method, computer device, and storage medium
Technical Field
The present application relates to the field of human motion function detection technology, and in particular, to a muscle fatigue detection method, a computer device, and a computer-readable storage medium.
Background
Muscle fatigue is manifested as a decrease in muscle output, which results in a decrease in work efficiency, and excessive muscle fatigue causes irreversible damage to the muscle. Human muscle contraction is mainly divided into static contraction and dynamic contraction.
Static contraction, also commonly referred to as isometric contraction, refers to the tension of muscles, which generally occurs when the body is in a fixed posture. Correspondingly, dynamic contraction refers to the change of muscle length when the muscle is in tension, which generally occurs in the situation of repetitive labor of human body. The research related to muscle fatigue has wide application prospect in the fields of human-computer interfaces, human ergonomics, sports health care, medical rehabilitation and the like.
At present, muscle fatigue detection technology and quantification method are still the hot spots and difficulties of research.
Disclosure of Invention
The technical problem mainly solved by the application is to provide a muscle fatigue detection method, a computer device and a computer readable storage medium, which can be used for quantifying the fatigue degree of muscles and improving the muscle fatigue detection accuracy.
In order to solve the technical problem, the application adopts a technical scheme that: provided is a muscle fatigue detection method including: acquiring surface electromyogram data of target muscles; dividing the surface electromyogram data into a plurality of data segments according to time sequence; calculating the wavelet packet energy entropy of each data segment; and generating a muscle fatigue index of the target muscle based on the wavelet packet energy entropy.
In order to solve the above technical problem, another technical solution adopted by the present application is: providing a computer device comprising a processor and a memory coupled to the processor; wherein the memory is adapted to store program data and the processor is adapted to execute the program data to implement the muscle fatigue detection method as described above.
In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided a computer readable storage medium having stored program data for implementing the muscle fatigue detection method as described above, when the program data is executed by a processor.
The beneficial effect of this application is: different from the prior art, the muscle fatigue detection method is based on the principle that low-frequency components in a power spectrum of a surface electromyogram signal are increased, high-frequency components are reduced and the frequency spectrum is shifted left when muscles are fatigued, the surface electromyogram data of target muscles are obtained, the surface electromyogram data are divided into a plurality of data sections according to time sequence, wavelet packet energy and information entropy are jointly used for calculating the wavelet packet energy entropy of each data section, and the muscle fatigue state can be expressed due to the numerical value of the wavelet packet energy entropy, so that the method is suitable for fatigue state evaluation of static and dynamic muscle contraction, muscle fatigue indexes of the target muscles can be generated based on the wavelet packet energy entropy, and the muscle fatigue indexes are used for representing the fatigue state of a user.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram of an embodiment of a muscle fatigue detection method of the present application;
fig. 2 is a detailed flowchart of S160 in the muscle fatigue detection method shown in fig. 1;
FIG. 3 is a schematic diagram of a three-layer wavelet packet decomposition binary tree according to an embodiment of the muscle fatigue detection method of the present application;
FIG. 4 is a schematic representation of the positions of the major muscles of the upper limbs of a human body;
FIG. 5 is a schematic view of a detailed flow chart of S180 in the muscle fatigue detection method shown in FIG. 1;
FIG. 6 is another detailed flowchart of S180 of the muscle fatigue detection method shown in FIG. 1;
FIG. 7 is a schematic block diagram of an embodiment of a computer apparatus of the present application;
FIG. 8 is a schematic diagram of an embodiment of a computer-readable storage medium of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," and the like in this application are used for distinguishing between different objects and not for describing a particular order or structure. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Currently, the detection technology of muscle fatigue mainly includes surface electromyography (sEMG), myotone signal (MMG), ultrasound image (ultrasound), near-infrared spectroscopy (NIRS), inertial sensing unit (IMU), and the like.
In the related technology, the fatigue detection technology based on the B-mode ultrasonic image and the near infrared spectrum technology has the defects of immature commercialization of signal acquisition equipment, complex use and operation and the like, and is difficult to be successfully applied to muscle fatigue detection in a large scale.
At present, the technology generally applied to muscle fatigue detection is surface electromyographic signals, but most of muscle fatigue detection algorithms based on the surface electromyographic signals are simpler, and the muscle fatigue information cannot be well expressed.
The muscle fatigue judging method based on the root mean square of the surface electromyographic signals is mainly based on the principle that more muscle fiber movement units are gathered for maintaining the contractility during muscle fatigue so as to enhance the surface electromyographic signals; a muscle fatigue judging method based on the median frequency and the average power frequency of a surface electromyogram signal is mainly based on the principle that low-frequency components in a power spectrum of the surface electromyogram signal are increased, high-frequency components in the power spectrum of the surface electromyogram signal are reduced, and the frequency spectrum is shifted left during muscle fatigue. It is understood that "low frequency" and "high frequency" are relative concepts, and are used to illustrate the change of the power spectrum of the surface electromyogram signal, such as the left shift of the frequency spectrum when the muscle is fatigued.
The muscle fatigue detection method based on the surface electromyogram signal is generally applied to the evaluation of static muscle contraction fatigue rather than more general dynamic muscle contraction fatigue, whether a muscle fatigue phenomenon exists is estimated by observing the change of a fatigue parameter, the numerical value of the fatigue parameter cannot express fatigue information, and further quantification of fatigue conditions and judgment of fatigue trends are difficult.
Therefore, the application provides a muscle fatigue detection method to solve the problems that the muscle fatigue detection method cannot quantify fatigue conditions and is low in accuracy.
Referring to fig. 1-4, fig. 1 is a schematic flow chart of an embodiment of a muscle fatigue detection method according to the present application. Fig. 2 is a schematic specific flowchart of S160 in the muscle fatigue detection method shown in fig. 1. Fig. 3 is a schematic diagram of a three-layer wavelet packet decomposition binary tree according to an embodiment of the muscle fatigue detection method of the present application. Figure 4 is a schematic representation of the positions of the major muscles of the upper limbs of a human body.
In this embodiment, the muscle fatigue detection method includes:
s120: and acquiring surface electromyographic data of the target muscle.
During actual detection, the muscle to be detected, that is, the target muscle used when the target mechanism performs a specific motion for the detected object, can be determined according to the actual motion type.
In an application scenario, a myoelectric signal of a surface of a target muscle during human body movement can be collected by a myoelectric collecting device, and a surface myoelectric sensor is attached to the target muscle.
Alternatively, the target muscle may be single or plural. Wherein each target muscle corresponds to one myoelectric channel.
When the target muscle is plural, step S120 may include:
and superposing the surface electromyographic data of a plurality of target muscles and averaging. It is understood that the average value is the acquired surface electromyogram data.
The muscle fatigue quantification of a plurality of target muscles can be realized by superposing and averaging the surface electromyographic data of the plurality of target muscles.
Optionally, filtering processing can be performed on the surface electromyographic signals of all the acquired target muscles respectively, wherein the filtering processing comprises band-pass filtering and power frequency notch filtering, and the purpose is to remove clutter such as power frequency interference.
S140: the surface electromyogram data is divided into a plurality of data segments in time series.
In one embodiment, the surface electromyography signals may be subjected to sliding window processing (which may also be referred to as sliding window thinning), aiming at dividing the dense surface electromyography signals by a certain time period, so as to divide the surface electromyography data into a plurality of data segments in time sequence to prepare for further processing.
S160: and calculating the wavelet packet energy entropy of each data segment.
Referring to fig. 2, step S160 may include:
s161: and carrying out wavelet packet decomposition on the data segment to obtain a plurality of decomposition nodes.
S162: and calculating the normalized wavelet packet energy of each decomposition node.
S163: and calculating the wavelet packet energy entropy of the data segment based on the normalized wavelet packet energy of the decomposition nodes.
In step S163, specifically, the wavelet packet energy entropy may be calculated based on the following formula:
Figure BDA0002604361350000051
wherein WPEE is wavelet packet energy entropy, Pi jThe normalized wavelet packet energy of the jth decomposition node of the ith layer after wavelet decomposition is ln, which is a natural logarithm.
According to the wavelet packet theory, a signal can be decomposed into nodes of any binary tree.
This will be described in detail with reference to fig. 3. In fig. 3, a three-level wavelet packet decomposition tree is taken as an example, where (0, 0) represents an original signal, and (i, j) represents a wavelet packet decomposition node, i represents a level of wavelet packet decomposition, j represents a frequency segment corresponding to the level, and the larger j is, the higher the corresponding frequency is.
The vector corresponding to each node is recorded as
Figure BDA0002604361350000052
The orthogonal basis of the two wavelet packets at a node is denoted as:
Figure BDA0002604361350000053
Figure BDA0002604361350000054
wherein g (n) ═ 1nh (1-n), i.e., g (n) and h (n), are a pair of orthogonal bases. Thus, each node in the binary wavelet packet tree may be recursively divided into two orthogonal subspaces.
Because the Daubechies wavelet basis function (db1) has good compactnessAnd (3) sex, smoothness and approximate symmetry, and the function can be selected for decomposition and synthesis of the wavelet packet in the embodiment. Reconstructing the energy of the signal i level j data segment after wavelet packet decomposition
Figure BDA0002604361350000064
The calculation is as follows:
Figure BDA0002604361350000061
wherein the content of the first and second substances,
Figure BDA0002604361350000065
the coefficient of the k-th discrete point of the decomposition node (i, j) is, and M is the number of discrete points of the decomposed signal data segment.
Then, normalizing the energy characteristics to obtain a relative value of the energy of a single frequency band, and reflecting the energy distribution P of the signal in each frequency band in the total frequency rangei j：
Figure BDA0002604361350000062
Probability Pi jAlso known as relative wavelet packet energy. Combining the energy distribution of the wavelet packet decomposition coefficient with the information entropy, and calculating the energy entropy of the ith-level wavelet packet as follows:
Figure BDA0002604361350000063
according to the calculation process, the wavelet packet energy entropy can quantitatively measure the disorder degree of the frequency distribution of the surface myoelectric signals.
S180: and generating a muscle fatigue index of the target muscle based on the wavelet packet energy entropy.
According to the definition of the wavelet packet energy entropy, if the wavelet packet energy is concentrated in one sub-band, the WPEE is 0, namely the surface electromyographic signals are ordered; on the contrary, if the wavelet packet energy is randomly distributed in each sub-band, the surface electromyographic signals are disordered.
According to the principle that low-frequency components in a power spectrum of a surface electromyogram signal are increased, high-frequency components are reduced and the frequency spectrum is shifted left when muscles are fatigued, it is known that when the muscles are in a fatigue state, the frequency of the electromyogram is compressed to low frequency, so that the WPEE value is reduced, namely the WPEE value can indicate the fatigue degree, and the smaller the value is, the fatigued muscles are indicated.
Therefore, the wavelet packet energy entropy obtained by the method of the embodiment can quantitatively express the muscle fatigue condition, and is suitable for fatigue state evaluation of static and dynamic muscle contraction.
In one embodiment, generating the muscle fatigue indicator for the target muscle based on the wavelet packet energy entropy may be:
and determining the muscle fatigue degree of the target muscle according to the comparison result of the wavelet packet energy entropy and the fatigue threshold.
Alternatively, the fatigue threshold may be one or more.
When the fatigue threshold is one, if the wavelet packet energy entropy is smaller than the fatigue threshold, the fatigue is judged to possibly generate adverse effects on the human body; if the wavelet packet energy entropy is larger than the fatigue threshold, the non-fatigue state is judged, and the damage to the human body can be ignored.
When the fatigue threshold is multiple, a fatigue comparison table can be formed by the multiple fatigue thresholds, and multiple numerical intervals are formed, wherein the numerical interval in which the wavelet packet energy entropy falls in smaller numerical values represents the more serious fatigue degree.
It is understood that the magnitude of the fatigue threshold may be adjusted according to the age, physical ability, etc. of the user to be tested.
The muscle fatigue detection method of the embodiment can be applied to detecting the muscle fatigue condition of the human body during daily activities.
The muscle fatigue detection method of the embodiment can also be applied to detecting the muscle fatigue condition when the human body performs the human-computer cooperative exercise. With the development of the robot technology, the use and popularization of the robot greatly promote the development of the economic society, and the man-machine cooperation becomes essential content in production and life. The efficiency of completing corresponding tasks is improved by the user under the cooperation of the machine, but the user can also cause muscle fatigue due to frequent operation of the machine, and the muscle fatigue condition is fed back to the user, so that the extreme muscle fatigue can be avoided, the muscle damage is reduced, and the better man-machine cooperation effect is achieved.
In order to verify the effectiveness and accuracy of the muscle fatigue detection method of the present embodiment, the applicant also performed the following fatigue test and set a control test group.
Referring to fig. 4, in an application scenario, in the muscle fatigue detection method of this embodiment, for quantification of fatigue of upper limb muscles in a human-computer cooperation process, a myoelectric acquisition device is used to acquire a surface myoelectric signal of a target muscle of a human body in the human-computer cooperation process, a sampling frequency is set to 512Hz, and surface myoelectric sensors are respectively attached to biceps brachii, brachioradialis and flexor carpi radialis of two arms.
(1) In the fatigue test, the person to be tested sits and stands on a seat at an appropriate height position, and the weight block on one side of the portal frame is stretched by using both hands. The fatigue test is carried out for 5 groups totally, the weight of five groups of weights is 1, 3, 5, 7, 8 weight blocks in sequence, the weight of each weight block is 5 pounds, each group stretches continuously for one minute, each group of tested personnel can rest for 1-3 minutes, and the fatigue test gradually causes the hand muscle of the tested personnel to enter into the fatigue state. And only synchronously acquiring the surface electromyogram signals of the selected muscle channels in the stretching process, and suspending the acquisition of the surface electromyogram signals at the rest time. After each group of fatigue tests are finished, the experimental organization personnel provide a single-hand electronic grip dynamometer for the tested personnel, so that the tested personnel can tightly grip the grip dynamometer by force, the grip strength of the left hand and the grip strength of the right hand are respectively measured and recorded; the tested person can also select Borg subjective fatigue quantization table scores according to the fatigue state of the tested person, and the scores are recorded by an experimental organizer. The grip of one hand is gradually reduced, the scores of the Borg scale are sequentially increased, and the qualitative representation shows that the fatigue degree of the arm muscles of the tested person is gradually increased.
(2) Preprocessing the collected surface electromyographic signals, wherein the preprocessing comprises the following steps: firstly carrying out 50Hz notch treatment and then carrying out 10-500Hz band-pass filtering; in order to sparsify the dense surface electromyogram data, the filtered data is subjected to sliding window processing, and the surface electromyogram signal is divided according to the length of a 1s window. In the step (1), each muscle channel has data of 5 minutes in total, and the sliding window processing divides the muscle channels into 300 surface electromyographic signal data segments in total.
(3) Calculating the average power frequency f of the surface electromyographic signals in each data segment of each muscle channel in the step (2)meanThe calculation method is as follows:
Figure BDA0002604361350000081
300 average power frequencies f will be obtained per muscle channelmeanFor f in each muscle channelmeanPerforming a least squares fit, f for three muscle channels per armmeanAnd performing least square fitting after the superposition average is obtained.
According to the theory of frequency spectrum shift to the left in muscle fatigue process, fmeanA negative rate of change indicates that there is fatigue in the muscle, otherwise the muscle has not reached a state of fatigue.
It is understood that the grip dynamometer readings and Borg fatigue quantification table data in (1) are subjective perceptions of muscle fatigue, belonging to the control group; (3) the average power frequency and the rate of change thereof in (1) were also used as a control group.
(4) With the muscle fatigue detection method of the present embodiment described above, the fatigue status of a single muscle and a plurality of muscles is quantitatively evaluated.
The muscle fatigue of the multi-muscle channel is quantified, and the whole fatigue state of the upper limbs of the human body can be represented. Specifically, the fatigue quantitative evaluation of the 3 muscle channels corresponding to the arm is as follows: correspondingly superposing the surface electromyographic signals of 3 muscle channels corresponding to each arm in the step 2), and then calculating an average value. An average of 300 data segments will be obtained, representing the surface electromyography of the entire arm. Then, the operation in step 4) is carried out on the data, so that the muscle fatigue state and the muscle fatigue dynamic trend of the whole arm (corresponding to 3 muscle channels) are obtained, and the muscle fatigue of the arm in a future period of time is predicted.
By applying the muscle fatigue detection method in the embodiment to the practical portal frame stretching movement and lower limb exoskeleton robot system of the fitness equipment and comparing the results with the results obtained by the traditional muscle fatigue detection method, the test results show that the muscle fatigue detection method in the embodiment has higher real-time performance and accuracy.
Based on this, in the technical application stage, the following human-computer cooperation tasks are also set in the application:
the first human-computer cooperation task of quantifying the muscle fatigue of the upper limb is as follows: under the condition that the exoskeleton control system does not have human fatigue feedback, the tested person normally walks by using the lower limb exoskeleton robot with the crutch. Meanwhile, according to the collected surface electromyographic data of the arm surface electromyographic signals collected in the step (1), muscle fatigue quantification is carried out according to the step (4).
Quantifying human-computer cooperation task II for upper limb muscle fatigue: under the condition that the exoskeleton control system has human fatigue feedback, a tested person normally walks by using the lower limb exoskeleton robot with the crutch, the fatigue threshold value is determined to be 0.8 according to a fatigue test, and when the WPEE value of one hand is lower than the threshold value, the walking speed of the exoskeleton is reduced, more fatigue recovery time is given to upper limbs, and muscle fatigue is relieved. Meanwhile, according to the collected surface electromyographic data of the arm surface electromyographic signals collected in the step (1), muscle fatigue quantification is carried out according to the step (4).
Quantifying human-computer cooperation task three of upper limb muscle fatigue: the exoskeleton control system has no human fatigue feedback, and a tested person uses the lower limb exoskeleton robot with the crutch to cross an obstacle. Meanwhile, according to the collected surface electromyographic data of the arm surface electromyographic signals collected in the step (1), muscle fatigue quantification is carried out according to the step (4).
The purpose of the human-computer cooperation task is to verify that muscle fatigue can generate difference in the two situations of 'no human fatigue feedback' and 'human fatigue feedback'. Experiments prove that the muscle fatigue feedback can avoid extreme muscle fatigue and reduce muscle damage, thereby achieving better human-computer cooperation effect. The application value of fatigue detection is reflected, and not only can the fatigue state be detected and quantified, but also the fatigue state can be improved by feeding back the fatigue state.
According to the muscle fatigue detection method, based on the principle that low-frequency components in a power spectrum of a surface electromyogram signal are increased, high-frequency components are reduced and the frequency spectrum is shifted left when muscles are fatigued, by obtaining surface electromyogram data of target muscles, dividing the surface electromyogram data into a plurality of data segments according to time sequence, and jointly using wavelet packet energy and information entropy to calculate wavelet packet energy entropy of each data segment.
Referring to fig. 5, fig. 5 is a schematic flowchart illustrating a specific process of S180 in an embodiment of the muscle fatigue detection method of the present application.
Optionally, step S180 generates a muscle fatigue index of the target muscle based on the wavelet packet energy entropy, including:
s181: and normalizing the wavelet packet energy entropies of the data segments.
It can be understood that the normalized value of wavelet packet energy entropy is between 0 and 1.
S182: dividing a plurality of value ranges from 0 to 1, and counting the number of the normalized wavelet packet energy entropy falling into each value range.
Alternatively, a plurality of numerical ranges may be evenly divided between 0 and 1.
S183: determining the fatigue degree of the target muscle based on the statistical result.
Since the smaller the value of the wavelet packet energy entropy is, the more serious the fatigue degree of the human body is, and different numerical ranges can represent different fatigue levels, the fatigue degree of the target muscle can be determined based on the statistical result.
Still taking the above application scenario as an example, the surface electromyogram signal is segmented according to the length of 1s window, and the total data of each muscle channel in step (1) is 5 minutes, and the sliding window process will segment the surface electromyogram signal into 300 segments, that is, 300 corresponding WPEE values that can be calculated by each muscle channel.
In order to further visually express muscle fatigue conditions, the WPEE values of all muscle channels are respectively subjected to normalization processing, the normalized WPEE values are subjected to uniform layered statistics, and are sequentially divided into WPEE e [0,0.25 ], [0.25,0.5 ], [0.5,0.75 ], and [0.75,1), and the proportion of the normalized wavelet packet energy entropy in all the value ranges is represented by percentage or decimal number, namely layered statistics is carried out. Based on statistical results, the larger the proportion of the WPEE value at a low level (i.e., the smaller the numerical range), the deeper the degree of fatigue. For example, [0,0.25) indicates that the muscle has been in an extremely fatigued state, and long-term exposure to this state will cause damage to the muscle; [0.75,1) indicates that the muscle is in an acceptable state of fatigue and that there is generally no damage to the muscle.
In one embodiment, step S183 may include:
and determining the fatigue degree of the target muscle according to the numerical range with the maximum number of the normalized wavelet packet energy entropies.
That is, if the normalized wavelet packet energy entropy falls within the numerical range of the largest number of values of [0,0.25 ], it is determined directly from this result that the muscle is already in an extremely fatigued state. If the normalized wavelet packet energy entropy falls into the numerical range with the largest quantity [0.75,1 ], determining that the muscle is in an acceptable fatigue state directly according to the result.
Referring to fig. 6, fig. 6 is another specific flowchart of S180 in an embodiment of the muscle fatigue detection method of the present application.
Optionally, step S180 generates a muscle fatigue index of the target muscle based on the wavelet packet energy entropy, including:
s184: and calculating the change rate of the wavelet packet energy entropy along with the time according to the wavelet packet energy entropy of the plurality of data segments.
Alternatively, step S184 may include:
normalizing the wavelet packet energy entropies of the data segments;
and carrying out curve fitting on the normalized wavelet packet energy entropy to obtain a fatigue curve, and obtaining the slope of the fatigue curve.
The curve fitting may adopt a least square method.
S185: a fatigue trend of the target muscle is determined based on the rate of change.
Since the smaller the value of the wavelet packet energy entropy is, the more serious the fatigue of the human body is, the negative change rate of the wavelet packet energy entropy indicates that the muscle fatigue is progressing, and the regular change rate indicates that the muscle is recovering from the fatigue state.
In addition, since muscle fatigue is a gradual process, the change rate of the energy entropy of the wavelet packet can also indicate the fatigue trend of the muscle in a future period of time to a certain extent. For example, if the muscle is in an extremely tired state at present, it is predicted that the muscle will be in a tired state in a future period of time because the fatigue recovery takes time.
It will be appreciated that in this embodiment, the methods shown in fig. 5 and 6 may be combined to determine both the degree of fatigue of the target muscle and the tendency of fatigue of the target muscle. In one embodiment, after normalization processing is performed on wavelet packet energy entropies of a plurality of data segments, the normalized WPEE values can be subjected to hierarchical statistics respectively by using the steps S182 and S183, so as to determine the fatigue degree of the target muscle; and determines a fatigue tendency of the target muscle using steps S184 and S185.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an embodiment of a computer apparatus according to the present application.
In this embodiment, the computer device 100 includes a processor 110 and a memory 120 connected to the processor 110. The memory 120 is used for storing program data and the processor 110 is used for executing the program data to implement the muscle fatigue detection method in the above-described embodiment.
The processor 110 may also be referred to as a Central Processing Unit (CPU). The processor 110 may be an integrated circuit chip having signal processing capabilities. The processor 110 may also be a general purpose processor 110, a digital signal processor 110(DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The general purpose processor 110 may be a microprocessor 110 or the processor 110 may be any conventional processor 110 or the like.
Referring to fig. 8, fig. 8 is a schematic diagram of an embodiment of a computer-readable storage medium according to the present application.
The computer-readable storage medium 200 is used for storing program data 210, which program data 210, when being executed by a processor, is capable of implementing the muscle fatigue detection method in the above-described embodiments.
It is understood that the computer-readable storage medium 200 in this embodiment may be applied to a server, and specific implementation thereof may refer to the foregoing embodiment, which is not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules or units is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated units in the other embodiments described above may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solution of the present application may be substantially or partially implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the S of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
According to the muscle fatigue detection method, according to the principles of low-frequency component increase, high-frequency component reduction and frequency spectrum left shift in a power frequency spectrum of a surface electromyogram signal during muscle fatigue, through acquiring the surface electromyogram data of target muscles, dividing the surface electromyogram data into a plurality of data segments according to time sequence, and jointly using wavelet packet energy and information entropy to calculate the wavelet packet energy entropy of each data segment, because the numerical value of the wavelet packet energy entropy can express the muscle fatigue state and is suitable for fatigue state evaluation of static and dynamic muscle contraction, the muscle fatigue index of the target muscles can be generated based on the wavelet packet energy entropy and is used for representing the fatigue state of a user, namely the muscle fatigue degree can be quantized by the method, and the muscle fatigue detection accuracy is improved.
The above embodiments are merely examples and are not intended to limit the scope of the present disclosure, and all modifications, equivalents, and flow charts using the contents of the specification and drawings of the present disclosure or those directly or indirectly applied to other related technical fields are intended to be included in the scope of the present disclosure.

Claims (11)

1. A muscle fatigue detection method, comprising:
acquiring surface electromyogram data of target muscles;
dividing the surface electromyogram data into a plurality of data segments according to time sequence;
calculating the wavelet packet energy entropy of each data segment;
and generating a muscle fatigue index of the target muscle based on the wavelet packet energy entropy.
2. The muscle fatigue detection method according to claim 1, wherein the step of calculating the wavelet packet energy entropy of each of the data segments comprises:
performing wavelet packet decomposition on the data segment to obtain a plurality of decomposition nodes;
calculating the normalized wavelet packet energy of each decomposition node;
and calculating the wavelet packet energy entropy of the data segment based on the normalized wavelet packet energies of the plurality of decomposition nodes.
3. The muscle fatigue detection method of claim 2, wherein the step of calculating wavelet packet energy entropy of the data segment based on the wavelet packet energies of the plurality of decomposition nodes comprises:
calculating the wavelet packet energy entropy based on the following formula:
Figure FDA0002604361340000011
wherein WPEE is the wavelet packet energy entropy, Pi jAnd the normalized wavelet packet energy of the j decomposition node of the i layer after wavelet decomposition is ln, which is a natural logarithm.
4. The muscle fatigue detection method according to claim 1, wherein the step of generating the muscle fatigue index of the target muscle based on the wavelet packet energy entropy:
and determining the fatigue degree of the target muscle according to the comparison result of the wavelet packet energy entropy and a fatigue threshold.
5. The muscle fatigue detection method according to claim 1, wherein the step of generating the muscle fatigue index of the target muscle based on the wavelet packet energy entropy:
normalizing the wavelet packet energy entropies of the plurality of data segments;
dividing a plurality of numerical ranges between 0 and 1, and counting the number of the normalized wavelet packet energy entropy falling into each numerical range;
determining a degree of fatigue of the target muscle based on the statistical result.
6. The muscle fatigue detection method according to claim 5, wherein the step of determining the degree of fatigue of the target muscle based on the statistical result comprises:
and determining the fatigue degree of the target muscle according to the numerical range with the maximum number of the normalized wavelet packet energy entropies.
7. The muscle fatigue detection method according to claim 1, wherein the step of generating the muscle fatigue index of the target muscle based on the wavelet packet energy entropy:
calculating the change rate of the wavelet packet energy entropy along with time according to the wavelet packet energy entropy of the plurality of data segments;
determining a fatigue trend of the target muscle based on the rate of change.
8. The muscle fatigue detection method according to claim 7, wherein the step of calculating the rate of change of the wavelet packet energy entropy with time from the wavelet packet energy entropies of the plurality of data segments:
normalizing the wavelet packet energy entropies of the plurality of data segments;
and carrying out curve fitting on the normalized wavelet packet energy entropy to obtain a fatigue curve, and acquiring the slope of the fatigue curve.
9. The muscle fatigue detection method according to claim 1, wherein the step of acquiring surface electromyography data of the target muscle comprises:
and superposing the surface electromyographic data of the target muscles and averaging.
10. A computer device, comprising a processor and a memory coupled to the processor;
wherein the memory is adapted to store program data and the processor is adapted to execute the program data to implement the muscle fatigue detection method according to any of claims 1-9.
11. A computer-readable storage medium, characterized in that the computer-readable storage medium is used for storing program data, which when executed by a processor is used for implementing the muscle fatigue detection method according to any one of claims 1-9.
CN202010734489.0A 2020-07-27 2020-07-27 Muscle fatigue detection method, computer device, and storage medium Pending CN111904416A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010734489.0A CN111904416A (en) 2020-07-27 2020-07-27 Muscle fatigue detection method, computer device, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010734489.0A CN111904416A (en) 2020-07-27 2020-07-27 Muscle fatigue detection method, computer device, and storage medium

Publications (1)

Publication Number Publication Date
CN111904416A true CN111904416A (en) 2020-11-10

Family

ID=73280927

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010734489.0A Pending CN111904416A (en) 2020-07-27 2020-07-27 Muscle fatigue detection method, computer device, and storage medium

Country Status (1)

Country Link
CN (1) CN111904416A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN113288182A (en) * 2021-07-09 2021-08-24 深圳京柏医疗科技股份有限公司 Pelvic floor muscle fatigue judgment method and pelvic floor muscle rehabilitation training method and device
CN114366589A (en) * 2022-01-21 2022-04-19 珠海格力电器股份有限公司 Control method and control device for massage equipment, storage medium and electronic device
CN114504334A (en) * 2022-02-07 2022-05-17 苏州微创畅行机器人有限公司 State prediction method, state prediction device, computer equipment and storage medium
CN115985463A (en) * 2023-03-17 2023-04-18 山东大学齐鲁医院 Wearable device-based method and system for predicting muscle fatigue degree in real time
CN114504334B (en) * 2022-02-07 2024-04-26 苏州微创畅行机器人有限公司 State prediction method, state prediction device, computer equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040019290A1 (en) * 2002-07-24 2004-01-29 Tanita Corporation Muscle fatigue measuring equipment
CN103345641A (en) * 2013-07-16 2013-10-09 杭州电子科技大学 Hand electromyographic signal motion recognition method based on wavelet entropy and support vector machine
CN104382595A (en) * 2014-10-27 2015-03-04 燕山大学 Upper limb rehabilitation system and method based on myoelectric signal and virtual reality interaction technology
CN107137080A (en) * 2017-05-25 2017-09-08 中国科学院深圳先进技术研究院 Chronic back pain patient muscle's active state determination methods and system
US20170354377A1 (en) * 2016-06-10 2017-12-14 Panasonic Intellectual Property Management Co., Ltd. Muscle fatigue output device, muscle fatigue output method, and recording medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040019290A1 (en) * 2002-07-24 2004-01-29 Tanita Corporation Muscle fatigue measuring equipment
CN103345641A (en) * 2013-07-16 2013-10-09 杭州电子科技大学 Hand electromyographic signal motion recognition method based on wavelet entropy and support vector machine
CN104382595A (en) * 2014-10-27 2015-03-04 燕山大学 Upper limb rehabilitation system and method based on myoelectric signal and virtual reality interaction technology
US20170354377A1 (en) * 2016-06-10 2017-12-14 Panasonic Intellectual Property Management Co., Ltd. Muscle fatigue output device, muscle fatigue output method, and recording medium
CN107137080A (en) * 2017-05-25 2017-09-08 中国科学院深圳先进技术研究院 Chronic back pain patient muscle's active state determination methods and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张博文: ""基于SEMG的肌肉疲劳度评估及其在上肢康复产品设计中的应用研究"", 《中国优秀博硕士学位论文全文数据库（硕士）工程科技Ⅱ辑》 *
陈伟婷等: "基于熵的动态收缩sEMG信号疲劳特征分析", 《中国医学物理学杂志》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN112957056B (en) * 2021-03-16 2022-12-30 苏州大学 Method and system for extracting muscle fatigue grade features by utilizing cooperative network
CN113288182A (en) * 2021-07-09 2021-08-24 深圳京柏医疗科技股份有限公司 Pelvic floor muscle fatigue judgment method and pelvic floor muscle rehabilitation training method and device
CN114366589A (en) * 2022-01-21 2022-04-19 珠海格力电器股份有限公司 Control method and control device for massage equipment, storage medium and electronic device
CN114504334A (en) * 2022-02-07 2022-05-17 苏州微创畅行机器人有限公司 State prediction method, state prediction device, computer equipment and storage medium
CN114504334B (en) * 2022-02-07 2024-04-26 苏州微创畅行机器人有限公司 State prediction method, state prediction device, computer equipment and storage medium
CN115985463A (en) * 2023-03-17 2023-04-18 山东大学齐鲁医院 Wearable device-based method and system for predicting muscle fatigue degree in real time

Similar Documents

Publication Publication Date Title
CN111904416A (en) Muscle fatigue detection method, computer device, and storage medium
Cifrek et al. Surface EMG based muscle fatigue evaluation in biomechanics
Talib et al. A review on crosstalk in myographic signals
Xie et al. Classification of the mechanomyogram signal using a wavelet packet transform and singular value decomposition for multifunction prosthesis control
CN102622605B (en) Surface electromyogram signal feature extraction and action pattern recognition method
Mokaya et al. Burnout: A wearable system for unobtrusive skeletal muscle fatigue estimation
Dua et al. Novel classification of coronary artery disease using heart rate variability analysis
Meng et al. Evaluation of decomposition parameters for high-density surface electromyogram using fast independent component analysis algorithm
CN113261981A (en) Quantitative assessment method and system for upper limb spasm based on surface myoelectric signal
CN113274033A (en) Movement function monitoring and management method based on cross frequency coupling of brain and muscle electricity
CN114052744A (en) Electrocardiosignal classification method based on pulse neural network
Aguilar et al. EEG signals processing based on fractal dimension features and classified by neural network and support vector machine in motor imagery for a BCI
Tu et al. Lower limb motion recognition based on surface electromyography
CN106901732A (en) The measuring method and measurement apparatus of muscular strength and Muscle tensility under mutation status
Wu et al. Classification and simulation of process of linear change for grip force at different grip speeds by using supervised learning based on sEMG
CN107320097A (en) The method and apparatus that muscular fatigue feature is extracted using electromyographic signal marginal spectrum entropy
Marri et al. Analysis of biceps brachii muscles in dynamic contraction using sEMG signals and Multifractal DMA algorithm
Wahyunggoro et al. DWT analysis of sEMG for muscle fatigue assessment of dynamic motion flexion-extension of elbow joint
CN106983511B (en) Method and device for identifying muscle strength and muscle tension state mutation points
Jegan et al. Real-time ECG peak detection for heart rate measurement using wavelet packet transform
Mobarak et al. Hand movement classification using transient state analysis of surface multichannel EMG signal
Suganthi et al. Evaluation of muscle fatigue based on SEMG using deep learning techniques
Hu et al. Evaluation of emg feature extraction for classification of exercises in preventing falls in the elderly
Chen et al. Evaluation of muscle fatigue based on CRP and RQA for upper limb exoskeleton
Kholdorov et al. Analysis of methods and algorithms for feature extraction of biosignals of muscle activity

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