CN112690808B - Human muscle fatigue identification method and system based on surface electromyographic signals and phase space reconstruction method - Google Patents
Human muscle fatigue identification method and system based on surface electromyographic signals and phase space reconstruction method Download PDFInfo
- Publication number
- CN112690808B CN112690808B CN202011526899.2A CN202011526899A CN112690808B CN 112690808 B CN112690808 B CN 112690808B CN 202011526899 A CN202011526899 A CN 202011526899A CN 112690808 B CN112690808 B CN 112690808B
- Authority
- CN
- China
- Prior art keywords
- muscle
- electromyographic
- fatigue
- signals
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a human muscle fatigue identification method and system based on a surface electromyogram signal and a phase space reconstruction method. The method comprises the steps of collecting surface electromyographic signals generated by human muscles during movement by using an electromyographic sensor, processing the signals by combining a phase space reconstruction method and a frequency domain analysis method, and identifying whether the muscles are in a fatigue state. The method can automatically intercept useful components from the electromyographic signals generated by the muscles in the motion state and screen out useless pure noise components; the method introduces an initialization mechanism, each user performs initialization operation at the beginning of use, and initializes each parameter involved in the method; the method judges fatigue by using the frequency spectrum information entropy of the electromyographic signal frequency spectrum distribution concentration degree, and combines multiple recent judgments by using the queue, thereby effectively reducing the judgment errors caused by accidental factors, and having higher accuracy compared with the identification method simply depending on a frequency domain analysis method.
Description
Technical Field
The invention relates to the field of pattern recognition and wearable equipment, in particular to a human muscle fatigue recognition method and system based on a surface electromyogram signal and a phase space reconstruction method.
Background
With the miniaturization and wearability of sensors, more and more physiological sensors are used in wearable devices, which are infused with huge vitality, and it is expected that a human physiological state (including fatigue, hunger, injury, etc.) recognition system based on the wearable physiological sensors will be widely applied in the current and near future, including but not limited to exercise training, soldier physical monitoring, elderly activity assistance, infant monitoring, and the like.
The human body surface electromyographic signals are weak voltages generated on the surface of human body muscles during contraction, and can reflect the movement information of the muscles. The electromyographic sensor is close to an oscilloscope in function, acquires voltage difference by using an electrode, amplifies a weak signal by using an analog operational amplifier and generates output. Although the human body surface electromyogram signal can reflect the state of the muscle to a great extent, the muscle only generates the surface electromyogram signal in the contraction state, but does not generate the surface electromyogram signal in the relaxation state, and the signal acquired by the sensor in the muscle relaxation state is an invalid signal only containing an interference signal. The muscle in the motion state is in a state of continuous alternation of diastole and contraction, the signals collected by the electromyographic sensor are directly taken for processing, the result can be greatly interfered by invalid signals collected in the muscle diastole state, and the result is not representative, which is just the main reason that many other methods for identifying muscle fatigue by using the electromyographic signals can only be used when a testee actively exerts force in the rest state but cannot be used in the motion state, the problem is solved, and the application scene of the muscle fatigue identification method can be expanded to the motion scene, so that the application range of the method is greatly improved, and the application prospect is expanded.
According to the method, a phase space reconstruction theory is utilized, useful signals collected in a muscle contraction state are screened out from a series of electromyographic signal time sequences collected in a motion state and used for judging fatigue, and invalid signals collected in a muscle relaxation state are discarded.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a human muscle fatigue identification method and a human muscle fatigue identification system based on a surface electromyogram signal and a phase space reconstruction method. Experiments show that when muscles enter a fatigue state, the frequency spectrum of the corresponding muscle electromyographic signal sequence is distributed more intensively, and the corresponding information entropy is reduced, so that the frequency spectrum can be used as a basis for fatigue judgment. The method utilizes a phase space reconstruction method to screen out useful signals collected in a muscle contraction state from a series of electromyographic signal time sequences collected in a motion state for judging fatigue, and discards invalid signals collected in a muscle relaxation state.
In order to achieve the above purpose, the technical implementation scheme of the invention is as follows:
the invention firstly discloses a human muscle fatigue identification method based on a surface electromyogram signal and a phase space reconstruction method, which comprises the following steps:
1) the myoelectric sensors measure and acquire muscle surface myoelectric signals corresponding to the myoelectric sensors respectively, the myoelectric signals are amplified and then output analog signals, and the analog signals are converted into digital sequences by the multi-channel data acquisition board;
2) the muscle fatigue degree is identified through the received electromyographic signal sequence, and the method comprises the following steps:
2.1) solving the maximum embedding dimension of the electromyographic signal sequence by using a phase space reconstruction method, judging whether the sequence is acquired under muscle contraction according to the maximum embedding dimension, if not, discarding, and if so, transmitting and carrying out the step 2.2);
2.2) obtaining a fast Fourier transform frequency spectrum of the electromyographic signal sequence, obtaining the information entropy of the whole frequency spectrum, comparing the information entropy with a preset information entropy reference value in a normal state to obtain a difference, and comparing the difference with a preset threshold value to determine whether the muscle is tired or not;
2.3) enqueuing the fatigue recognition result of each sequence and dequeuing the old recognition result, and summing all elements in the queue once every updating of the queue as the final recognition result of whether the muscle is fatigue.
Preferably, the initial value preset in step 2.2) is obtained by:
when a user is not tired, the electromyographic sensors are arranged on corresponding muscles, then force is exerted, a plurality of groups of electromyographic sequences available for electromyography are collected during the force exerting, frequency domain maximum amplitude frequency points and spectrum information entropies of the electromyographic sequences are respectively calculated, and average values are calculated and recorded to serve as preset initial values.
The invention also discloses a human muscle fatigue recognition system based on the surface electromyogram signal and the phase space reconstruction method, which comprises the following steps:
the myoelectric sensor is used for measuring and acquiring corresponding myoelectric signals on the surface of muscle, and outputting analog signals after amplification;
the multi-channel data acquisition board converts the analog signal of the electromyographic sensor into a digital sequence;
the muscle fatigue degree identification module is used for solving the maximum embedding dimension of the electromyographic signal sequence by utilizing a phase space reconstruction method, judging whether the sequence is acquired under muscle contraction according to the maximum embedding dimension, discarding the sequence if the sequence is not acquired under muscle contraction, solving the fast Fourier transform spectrum of the electromyographic signal sequence if the sequence is acquired under muscle contraction, solving the information entropy of the whole spectrum, comparing the information entropy with the preset information entropy reference value under a normal state to solve a difference, and determining whether the muscle is fatigue or not according to the comparison of the difference and a preset threshold value;
the queue maintenance module enqueues the fatigue identification result of each sequence processed by the muscle fatigue degree identification module, dequeues the old identification result, and calculates the sum of all elements in the queue once every time the queue is updated, so as to be used as the final identification result of whether the muscle is fatigued;
according to an embodiment of the present invention, the human muscle fatigue identification system further comprises: and the display module is used for displaying the final identification result of the queue maintaining module.
According to an embodiment of the present invention, the human muscle fatigue identification system further comprises: and the user initialization module is used for collecting a plurality of groups of electromyographic sequences which are applied by the user in a non-fatigue state, respectively solving the frequency domain maximum amplitude frequency point and the frequency spectrum information entropy of the electromyographic sequences, and solving and recording the average value as an initial value preset by the muscle fatigue degree identification module.
Compared with the prior art, the invention has the beneficial effects that: the system has good expansibility, if the observed muscles need to be increased, the aim can be achieved only by adding corresponding myoelectric sensors and carrying out corresponding initialization, and in addition, after the fatigue degrees of some local muscles are obtained, the overall motion fatigue condition of the human can be further judged on the basis of the fatigue degrees; the method solves the requirement that the prior similar physiological state identification technology needs to lead the human body to be in a resting state, automatically screens available electromyographic signal sequences through phase space reconstruction, enables a physiological state identification system to be applied to users in a motion state, greatly improves the practicability of the fatigue identification system, and can be used for the aspects of athlete training assistance, combat soldier constitution monitoring, old people and infant monitoring and the like; the method judges fatigue by using the information entropy reflecting the concentration degree of the frequency spectrum distribution of the electromyographic signals, and integrates multiple recognition results by combining a sliding queue, thereby reducing the error probability and improving the recognition accuracy.
Drawings
FIG. 1 is a block diagram showing a hardware configuration of a muscle fatigue recognition system according to an embodiment;
fig. 2 is a flowchart of a muscle fatigue identification method.
Detailed Description
The present invention will be further described below with reference to specific embodiments and accompanying drawings, so that the technical means, effects, and the like of the present invention can be more clearly understood.
As shown in fig. 1, the human muscle fatigue recognition system based on the surface electromyogram signal and the phase space reconstruction method of the invention comprises an electromyogram sensor, a multi-channel data acquisition board, a muscle fatigue degree recognition module, a queue maintenance module, an LCD display module and a user initialization module;
the user initialization module, the muscle fatigue degree identification module and the queue maintenance module are all located in the raspberry group 4 development board, the raspberry group 4 development board controls the multichannel data acquisition board to acquire an electromyographic signal sequence of each muscle with the length of 200, whether the corresponding muscle enters a fatigue state or not is judged according to the sequence, then the fatigue state is displayed on the LCD display module, and the fatigue state is sent to the monitoring center server side through a network. The raspberry pi 4 development board reads the key information through the I/O port and responds to the key input, so as to realize the starting, restarting, exiting and system initialization operation of the program.
The function of each component module in the embodiment is as follows:
the myoelectric sensor is used for measuring and acquiring corresponding myoelectric signals on the surface of muscle, and outputting analog signals after amplification;
the multi-channel data acquisition board converts the analog signal of the electromyographic sensor into a digital sequence;
the muscle fatigue degree identification module is used for solving the maximum embedding dimension of the electromyographic signal sequence by utilizing a phase space reconstruction method, judging whether the sequence is acquired under muscle contraction according to the maximum embedding dimension, discarding the sequence if the sequence is not acquired under muscle contraction, solving the fast Fourier transform spectrum of the electromyographic signal sequence if the sequence is acquired under muscle contraction, solving the information entropy of the whole spectrum, comparing the information entropy with the preset information entropy reference value under a normal state to solve a difference, and determining whether the muscle is fatigue or not according to the comparison of the difference and a preset threshold value;
the queue maintenance module enqueues the fatigue identification result of each sequence processed by the muscle fatigue degree identification module, dequeues the old identification result, and calculates the sum of all elements in the queue once every time the queue is updated, so as to be used as the final identification result of whether the muscle is fatigued;
and the display module is used for displaying the final identification result of the queue maintaining module.
And the user initialization module is used for collecting a plurality of groups of electromyographic sequences which are applied by the user in a non-fatigue state, respectively solving the frequency domain maximum amplitude frequency point and the frequency spectrum information entropy of the electromyographic sequences, and solving and recording the average value as an initial value preset by the muscle fatigue degree identification module.
The invention can be further provided with a control center server or performs data interaction with an external control center server to realize big data management and processing. The server side of the control center monitors information of the raspberry pi 4 development board, the two modules are communicated through the 4G module, the raspberry pi 4 development board sends a judgment result to the server port in a text information mode after obtaining the judgment result, and the server port analyzes the text information into data after monitoring the information.
The raspberry pi 4 development board controls a display screen through an HDMI display interface, and the display screen is a raspberry pi 3.5 inch touch screen MP 13508.
As shown in fig. 2, the human muscle fatigue identification method based on the surface electromyogram signal and the phase space reconstruction method includes the following steps:
1) the myoelectric sensors measure and acquire muscle surface myoelectric signals corresponding to the myoelectric sensors respectively, the myoelectric signals are amplified and then output analog signals, and the analog signals are converted into digital sequences by the multi-channel data acquisition board;
2) the muscle fatigue degree is identified through the received electromyographic signal sequence, and the method comprises the following steps:
2.1) solving the maximum embedding dimension of the electromyographic signal sequence by using a phase space reconstruction method, judging whether the sequence is acquired under muscle contraction according to the maximum embedding dimension, if not, discarding, and if so, transmitting and carrying out the step 2.2);
2.2) obtaining a fast Fourier transform frequency spectrum of the electromyographic signal sequence, obtaining the information entropy of the whole frequency spectrum, comparing the information entropy with a preset information entropy reference value in a normal state to obtain a difference, and comparing the difference with a preset threshold value to determine whether the muscle is tired or not;
2.3) enqueuing the fatigue recognition result of each sequence and dequeuing the old recognition result, and summing all elements in the queue once every updating of the queue as the final recognition result of whether the muscle is fatigue.
Wherein, the preset initial value in the step 2.2) is obtained by the following method: before each person uses the method, a sensor is arranged on corresponding muscle when fatigue does not exist, then force is applied, 20 groups of electromyographic available electromyographic sequences are collected during the force application, the frequency domain maximum amplitude frequency point and the frequency spectrum information entropy of the 20 groups of electromyographic sequences are respectively calculated and averaged to be recorded, the 20 groups of electromyographic sequences are used as reference points for monitoring in the subsequent use process, the specific values of the parameters are different among different individuals and muscles at different parts of the same individual, so the initialization operation is necessary, and the method after the initialization operation has higher identification accuracy and wider application range.
In one embodiment, raspberry pi 4 reads the key signal through the I/O port, receives the start, restart, and exit program commands and the initialize system command, and responds accordingly. When initialization operation is carried out, a user actively contracts muscles to exert force, the system collects 20 groups of available myoelectric signal sequences for each muscle, finds out a maximum amplitude frequency point and a spectrum information entropy after solving a frequency spectrum, and the average value of 20 groups of results is stored as an identification reference in subsequent use.
In a specific embodiment of the present invention, the step 2.1) is specifically:
the method comprises the steps of utilizing an autocorrelation coefficient method to obtain the optimal reconstruction delay time of an electromyographic signal time sequence (the sampling frequency is 1kHz, the length is 200 data points), utilizing a false neighbor method to obtain the maximum reconstruction embedding dimension of the electromyographic signal time sequence based on the obtained optimal delay time, wherein the muscle does not generate surface electromyography in a relaxation state, so that data collected by a sensor is interference signals, the maximum reconstruction embedding dimension value is very small, a large number of experiments show that the maximum reconstruction embedding dimension of the electromyographic signal time sequence does not exceed 5, the muscle can generate extremely complex surface electromyography in a contraction force state, the data collected by the sensor is the electromyographic signals containing interference, the maximum reconstruction embedding dimension value is very large, and a large number of experiments show that the maximum embedding dimension of the surface electromyographic signal time sequence can reach more than 20, according to the method, signals with the maximum embedding dimension of phase space reconstruction not more than 10 are considered as invalid signals collected in a muscle relaxation state and discarded, signals higher than 10 are considered as valid signals collected in a muscle contraction state, and the signals are sent to a subsequent fatigue identification algorithm for further judgment.
In a specific embodiment of the present invention, the step 2.2) is specifically: the time sequence of the electromyographic signals which are determined to be useful by screening is subjected to Fourier transform firstly, the frequency spectrum of the sequence is calculated, experiments show that the frequency spectrum distribution of the same muscle in a fatigue state is far more concentrated than the distribution of the same muscle in an un-fatigue state, the corresponding information entropy is larger, the difference between the frequency spectrum distribution and the information entropy reference value in a normal state which is set during initialization is calculated, the absolute value of the difference is compared with a preset threshold value, and if the absolute value is larger than the threshold value, the electromyographic signal sequence is judged to be acquired under muscle fatigue.
In a specific embodiment of the present invention, step 2.3) is specifically:
maintaining a queue of length 20, enqueuing the result and dequeuing the oldest decision each time a decision is made, wherein if a certain electromyographic signal sequence is acquired under muscle fatigue, enqueuing 1, otherwise enqueuing-1. Summing all elements in the queue to obtain a final result; if the sum is more than 0, the final result is fatigue, otherwise, the final result is fatigue-free. The queue has the function similar to a sliding window, and the results of multiple judgments are integrated, so that the identification accuracy can be further improved due to the existence of the queue.
The Takens theorem indicates that through observation of a single variable of a nonlinear system, a reconstruction space mapping which has a finite dimension and is homomorphic with the original system can be reconstructed, and the reconstruction system can equivalently reflect all motion information of the original system. The phase space reconstruction process in the method comprises two steps, wherein in the first step, an autocorrelation function of a surface electromyogram signal sequence is solved, and a time point with the minimum value of the autocorrelation function is found and used as the optimal delay time; and the second step of solving the maximum embedding dimension by using a false nearest neighbor method according to the optimal delay time solved in the first step. The maximum embedding dimension effectively reflects the complexity of the motion track of the original system, and the higher the maximum embedding dimension is, the more complex the motion of the original system is.
Human muscle can be regarded as a chaotic system, surface electromyographic signals generated when the muscle contracts are very complex, and noise interference in space is relatively simple and monotonous. The method comprises the steps of carrying out phase space reconstruction on a surface electromyogram signal acquired by a sensor, if the maximum embedding dimension of an obtained reconstruction system is very high, indicating that the section of the signal is the surface electromyogram signal which is generated by muscle contraction and has partial noise interference, and if the maximum embedding dimension is too low, indicating that the section of the signal is not the signal generated by the muscle but is only pure noise interference, wherein the signal does not reflect the state of the muscle, and therefore, the signal is an invalid signal and can be directly discarded.
A large number of experiments show that the maximum embedding dimension of the electromyographic signal phase space reconstruction acquired by the sensor in the muscle relaxation state is lower than 5, the maximum embedding dimension of the electromyographic signal phase space reconstruction acquired in the contraction state is higher than 20, and the difference between the maximum embedding dimension and the embedding dimension is very different, so that the maximum embedding dimension is used for screening useful signals, the accuracy is very good, and the method has the greatest advantage.
Experiments show that when muscles enter a fatigue state, the frequency spectrums corresponding to the muscle electromyographic signal sequences are distributed more intensively, and the corresponding information entropy is reduced, so that the frequency spectrum information entropy of the muscle electromyographic signal sequences in the fatigue state is obviously lower than that in a normal state of the muscles. In the method initialization process, the acquired spectrum information entropy under the normal state is used as a reference value in advance, the difference between the reference value and the spectrum information entropy of the sequence to be detected is taken as an absolute value, and the absolute value can be used as a basis for fatigue judgment according to the magnitude of the absolute value.
Muscle fatigue is a long-term, very slowly changing state, so it is feasible and beneficial to fuse the results of multiple determinations into consideration: the judgment results of multiple times are fused by utilizing a first-in first-out queue, and accidental wrong judgment is covered by the fused results, so that the fatigue identification accuracy is improved.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (7)
1. A human muscle fatigue identification method based on a surface electromyogram signal and a phase space reconstruction method is characterized by comprising the following steps:
1) the myoelectric sensors measure and acquire muscle surface myoelectric signals corresponding to the myoelectric sensors respectively, the myoelectric signals are amplified and then output analog signals, and the analog signals are converted into digital sequences by the multi-channel data acquisition board;
2) the muscle fatigue degree is identified through the received electromyographic signal sequence, and the method comprises the following steps:
2.1) solving the maximum embedding dimension of the electromyographic signal sequence by using a phase space reconstruction method, judging whether the sequence is acquired under muscle contraction according to the maximum embedding dimension, if not, discarding, and if so, transmitting and carrying out the step 2.2);
the step 2.1) is specifically as follows: calculating the reconstruction optimal delay time of the electromyographic signal time sequence by using an autocorrelation coefficient method, and calculating the reconstruction maximum embedding dimension of the electromyographic signal time sequence by using a false neighbor method based on the calculated optimal delay time;
setting a threshold value, wherein signals with the maximum embedding dimension of the phase space reconstruction not exceeding the set threshold value are all considered as invalid signals collected in a muscle relaxation state and are discarded, and signals higher than the threshold value are all considered as valid signals collected in a muscle contraction state;
2.2) obtaining a fast Fourier transform frequency spectrum of the electromyographic signal sequence, obtaining the information entropy of the whole frequency spectrum, comparing the information entropy with a preset information entropy reference value in a normal state to obtain a difference, and comparing the difference with a preset threshold value to determine whether the muscle is tired or not;
2.3) enqueuing the fatigue recognition result of each sequence and dequeuing the old recognition result, and summing all elements in the queue once every updating of the queue as the final recognition result of whether the muscle is fatigue.
2. The human muscle fatigue recognition method based on the surface electromyogram signal and the phase space reconstruction method according to claim 1, wherein the initial value preset in step 2.2) is obtained by:
when a user is not tired, the electromyographic sensors are arranged on corresponding muscles, then force is exerted, a plurality of groups of electromyographic sequences available for electromyography are collected during the force exerting, frequency domain maximum amplitude frequency points and spectrum information entropies of the electromyographic sequences are respectively calculated, and average values are calculated and recorded to serve as preset initial values.
3. The human muscle fatigue identification method based on the surface electromyogram signal and the phase space reconstruction method according to claim 1, wherein the step 2.2) is specifically as follows:
firstly, Fourier transform is carried out on the time series of the electromyographic signals which are screened and confirmed to be useful, and the frequency spectrum of the time series and the information entropy corresponding to the frequency spectrum are obtained; calculating a difference value between the information entropy and a set information entropy reference value in a normal state, taking an absolute value of the difference value and comparing the absolute value with a preset threshold value, and judging that the electromyographic signal sequence is acquired under muscle fatigue if the absolute value is greater than the threshold value; otherwise, the muscle is considered not to be fatigued.
4. The human muscle fatigue identification method based on the surface electromyogram signal and the phase space reconstruction method according to claim 1, wherein the step 2.3) is specifically as follows:
maintaining a queue with a set length, enqueuing the result and dequeuing the oldest judgment result every time a judgment is obtained, and summing all elements in the queue to obtain a final result.
5. A human muscle fatigue recognition system based on a surface electromyogram signal and a phase space reconstruction method is characterized by comprising the following steps:
the myoelectric sensor is used for measuring and acquiring corresponding myoelectric signals on the surface of muscle, and outputting analog signals after amplification;
the multi-channel data acquisition board converts the analog signal of the electromyographic sensor into a digital sequence;
the muscle fatigue degree identification module is used for solving the reconstruction optimal delay time of the electromyographic signal time sequence by utilizing an autocorrelation coefficient method and then solving the reconstruction maximum embedding dimension of the electromyographic signal time sequence by utilizing a false neighbor method based on the solved optimal delay time; setting a threshold, considering signals of which the maximum embedding dimension of phase space reconstruction does not exceed the set threshold as invalid signals collected in a muscle relaxation state, discarding the invalid signals, if so, obtaining a fast Fourier transform frequency spectrum of an electromyographic signal sequence, obtaining the information entropy of the whole frequency spectrum, comparing the information entropy with a preset information entropy reference value in a normal state, obtaining a difference, and comparing the difference with the preset threshold to determine whether the muscle is tired;
and the queue maintaining module enqueues the fatigue identification result of each sequence processed by the muscle fatigue degree identification module, dequeues the old identification result, and calculates the sum of all elements in the queue once every time the queue is updated, so as to be used as the final identification result of whether the muscle is fatigued or not.
6. The system for recognizing human muscle fatigue based on surface electromyography and phase-space reconstruction method according to claim 5, further comprising:
and the display module is used for displaying the final identification result of the queue maintaining module.
7. The system for recognizing human muscle fatigue based on surface electromyography and phase-space reconstruction method according to claim 5, further comprising:
and the user initialization module is used for collecting a plurality of groups of electromyographic sequences which are applied by the user in a non-fatigue state, respectively solving the frequency domain maximum amplitude frequency point and the frequency spectrum information entropy of the electromyographic sequences, and solving and recording the average value as an initial value preset by the muscle fatigue degree identification module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011526899.2A CN112690808B (en) | 2020-12-22 | 2020-12-22 | Human muscle fatigue identification method and system based on surface electromyographic signals and phase space reconstruction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011526899.2A CN112690808B (en) | 2020-12-22 | 2020-12-22 | Human muscle fatigue identification method and system based on surface electromyographic signals and phase space reconstruction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112690808A CN112690808A (en) | 2021-04-23 |
| CN112690808B true CN112690808B (en) | 2022-03-15 |
Family
ID=75510227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011526899.2A Active CN112690808B (en) | 2020-12-22 | 2020-12-22 | Human muscle fatigue identification method and system based on surface electromyographic signals and phase space reconstruction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112690808B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107198509A (en) * | 2016-08-26 | 2017-09-26 | 常州市钱璟康复股份有限公司 | Feature extracting method and system based on surface myoelectric |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930284B (en) * | 2012-09-13 | 2015-06-17 | 杭州电子科技大学 | Surface electromyogram signal pattern recognition method based on empirical mode decomposition and fractal |
| US10854104B2 (en) * | 2015-08-28 | 2020-12-01 | Icuemotion Llc | System for movement skill analysis and skill augmentation and cueing |
| CN110870769B (en) * | 2018-09-03 | 2022-08-09 | 香港理工大学深圳研究院 | Method and equipment for detecting muscle fatigue grade |
-
2020
- 2020-12-22 CN CN202011526899.2A patent/CN112690808B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107198509A (en) * | 2016-08-26 | 2017-09-26 | 常州市钱璟康复股份有限公司 | Feature extracting method and system based on surface myoelectric |
Non-Patent Citations (3)
| Title |
|---|
| Analysis of Biceps Brachii sEMG signal using Multiscale Fuzzy Approximate Entropy;Navaneethakrishna M等;《2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)》;20151105;第7881-7884页 * |
| Muscle fatigue and contraction intensity modulates the complexity of surface electromyography;Joshua G.A. Cashaback等;《Journal of Electromyography and Kinesiology》;20130228;第23卷(第1期);第78-83页 * |
| 表面肌电信号特征与人体运动机能状态的映射机制研究;胡晋嘉;《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》;20200615(第06期);第9-62页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112690808A (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Phinyomark et al. | Feature extraction of the first difference of EMG time series for EMG pattern recognition | |
| McFarland et al. | Sensorimotor rhythm-based brain–computer interface (BCI): model order selection for autoregressive spectral analysis | |
| CN105796096B (en) | A kind of heart rate variance analyzing method, system and terminal | |
| EP3096686B1 (en) | Heart monitoring device | |
| JP5860894B2 (en) | EEG signal analysis to detect hypoglycemia | |
| WO2007030868A1 (en) | Method and system for detecting and classifying facial muscle movements | |
| CN108852349B (en) | Motion decoding method using cortical electroencephalogram signal | |
| Makaram et al. | Analysis of dynamics of EMG signal variations in fatiguing contractions of muscles using transition network approach | |
| KR20130092849A (en) | Method and apparatus for eliminating motion artifact of biosignal using personalized biosignal pattern | |
| Dan et al. | An identification system based on portable EEG acquisition equipment | |
| Ijaz et al. | Anomaly detection of electromyographic signals | |
| Tan et al. | ECG biometric identification using wavelet analysis coupled with probabilistic random forest | |
| CN106901732B (en) | Measuring method and measuring device for muscle strength and muscle tension in mutation state | |
| CN112690808B (en) | Human muscle fatigue identification method and system based on surface electromyographic signals and phase space reconstruction method | |
| US11076793B2 (en) | Respiration estimation method and apparatus | |
| KR100967994B1 (en) | Method for a Real Time Compressing Transmission and Storage of Periodic Bio-signal Data, and Cardiovascular System therefor | |
| Grönlund et al. | On-line signal quality estimation of multichannel surface electromyograms | |
| Sathawane et al. | Prediction and analysis of ECG signal behaviour using soft computing | |
| Freitas et al. | A real-time embedded system design for ERD/ERS measurement on EEG-based brain-computer interfaces | |
| Bedeeuzzaman et al. | Dispersion measures and entropy for seizure detection | |
| KR102630840B1 (en) | EMG signal-based recognition information extraction system and EMG signal-based recognition information extraction method using the same | |
| CN112634871B (en) | Lie detection method and system based on voice and radar dual sensors | |
| Lobacheva et al. | Automated real-time classification of functional states based on physiological parameters | |
| KR101627581B1 (en) | Method and apparatus for respiration rate detection using adaptive double threshold | |
| Rihana et al. | Efficient eye blink detection system using RBF classifier |
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 |