WO2018214522A1 - Procédé et appareil d'acquisition de signal électromyographique - Google Patents

Procédé et appareil d'acquisition de signal électromyographique Download PDF

Info

Publication number
WO2018214522A1
WO2018214522A1 PCT/CN2018/072323 CN2018072323W WO2018214522A1 WO 2018214522 A1 WO2018214522 A1 WO 2018214522A1 CN 2018072323 W CN2018072323 W CN 2018072323W WO 2018214522 A1 WO2018214522 A1 WO 2018214522A1
Authority
WO
WIPO (PCT)
Prior art keywords
action type
user
frequency
acquisition
action
Prior art date
Application number
PCT/CN2018/072323
Other languages
English (en)
Chinese (zh)
Inventor
包磊
Original Assignee
深圳市前海未来无限投资管理有限公司
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 深圳市前海未来无限投资管理有限公司 filed Critical 深圳市前海未来无限投资管理有限公司
Publication of WO2018214522A1 publication Critical patent/WO2018214522A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction

Definitions

  • the invention belongs to the technical field of wearable electronic devices, and in particular relates to a method and device for collecting myoelectric signals.
  • Electromyographic signal is a comprehensive effect of superficial muscle EMG and nerve trunk electrical activity on the surface of the skin. It can reflect neuromuscular activity to a certain extent. It is an important biological information carrier for evaluating the motor function of the neuromuscular system. It has been widely used in medical research, clinical diagnosis and rehabilitation. In recent years, myoelectric signals have begun to be applied in the field of sports biomechanics. Specifically, in the process of performing exercise training by the user, the myoelectric signals of specific parts of the human body can be collected, and based on the analysis results of the myoelectric signals, the user is Analysis and guidance of exercise effects.
  • the motion monitoring device When the motion monitoring device is applied in the field of fitness sports, it is usually based on the effect that a preset fitness action should achieve, thereby determining the user based on the myoelectric signal collected by the user during the fitness process. Whether the actual fitness effect has reached the preset fitness effect. In the process of collecting myoelectric signals, if the proportion of ineffective myoelectric signals is large, the fitness effects of the motion monitoring equipment based on these electromyographic signals will be significantly different from the preset fitness effects.
  • the acquired EMG signal is actually generated by the user performing a dumbbell press exercise, and the preset fitness effect is set according to the fitness action of the parallel bar arm flexion and extension, the fitness effect achieved by the two actually If there is no comparability, then the EMG signal collected in this case is actually an invalid EMG signal, but the motion monitoring equipment will still output guidance such as the position error or the strength error, which makes the user mistakenly think that it is their own.
  • the buckling arm flexion and extension movement is not standard. Therefore, this situation will provide users with fitness guidance suggestions with lower reference value, making it difficult for users to perform fitness exercises scientifically and effectively.
  • the embodiments of the present invention provide a method and device for collecting myoelectric signals, so as to solve the problem that the user does not scientifically and effectively guide the user to perform fitness exercise when the proportion of the invalid myoelectric signals is large in the prior art. .
  • a first aspect of the embodiments of the present invention provides a method for collecting an electromyogram signal, including:
  • the acquisition frequency of the acquisition module is adjusted to a second frequency, and the second frequency is smaller than the first frequency.
  • a second aspect of the embodiments of the present invention provides an EMG signal acquisition apparatus, including:
  • control unit configured to control an acquisition module in the wearable device to collect a myoelectric signal of a preset human body position
  • An analysis unit configured to parse the collected myoelectric signal, and acquire an action type of the action performed by the user
  • a first acquiring unit configured to acquire a preset reference action type
  • a first adjusting unit configured to adjust an acquisition frequency of the collection module to a first frequency if an action type of the action performed by the user is the same as the reference action type
  • a second adjusting unit configured to: if an action type of the action performed by the user is different from the reference action type, adjust an acquisition frequency of the collection module to a second frequency, where the second frequency is smaller than the first frequency.
  • the action type of the action performed by the user is recognized in real time, and the action type is compared with the reference action type as the motion effect judgment reference, and the acquisition module is reduced on the electromyogram if the two do not match.
  • the frequency of the signal acquisition makes the proportion of the collected data of the invalid myoelectric signal can be appropriately reduced.
  • the fitness guide with higher reference value can be output. It is also suggested that the user can also regulate his or her fitness exercises according to more accurate fitness guidance suggestions, and improve the scientific and effective performance of the user's exercise.
  • FIG. 1 is a flowchart showing an implementation of a method for collecting an electromyogram signal according to Embodiment 1 of the present invention
  • FIG. 2 is a flowchart of a specific implementation of an electromyography signal collection method S102 according to Embodiment 1 of the present invention
  • FIG. 3 is a flowchart showing an implementation of a method for collecting an electromyogram signal according to Embodiment 3 of the present invention
  • FIG. 4 is a flowchart showing an implementation of a method for collecting an electromyogram signal according to Embodiment 4 of the present invention
  • FIG. 5 is a flowchart showing an implementation of a method for collecting an electromyogram signal according to Embodiment 5 of the present invention.
  • FIG. 6 is a structural block diagram of an electromyogram signal collecting apparatus according to Embodiment 6 of the present invention.
  • the wearable device may be a wearable smart fitness garment, or may be a collection of one or more collection modules that are wearable and attachable.
  • the wearable device when the wearable device is a wearable smart fitness garment, it may be a garment or pants made of a flexible fabric, and a plurality of collection modules are embedded on the side of the flexible fabric close to the human skin. Each collection module is fixed at different points of the smart fitness garment so that after the user wears the smart fitness garment, each collection module can be attached to each muscle of the user's body.
  • at least one control module is also embedded, and each of the acquisition modules is separately connected to the control module.
  • a wire and a circuit board may be disposed in the wearable device, wherein the circuit board is used to fix various communication buses and the acquisition module.
  • the circuit board and its various solder joints are wrapped with a waterproof glue.
  • the wearable device can be washed by fixing a waterproof trace on the laundry.
  • each acquisition module may include only an acquisition electrode having a somatosensory sensor function, or an integrated circuit having an acquisition function.
  • the above collection electrodes include, but are not limited to, fabric electrodes, rubber electrodes, gel electrodes, and the like.
  • each acquisition module is an integrated circuit having an acquisition function and a wireless transmission function, and the integrated circuit includes the above-mentioned acquisition electrode having a somatosensory sensor function.
  • the EMG signal collected by the acquisition module is transmitted to the remote control module through the wireless network, and the control module is located in the remote terminal device or the remote control box used in conjunction with the acquisition module.
  • FIG. 1 is a flowchart showing an implementation process of an electromyogram signal collection method according to an embodiment of the present invention. As shown in FIG. 1 , the method includes steps S101 to S105, which are described in detail as follows:
  • S101 Control an acquisition module in the wearable device to collect a myoelectric signal of a human body position preset by a user.
  • a plurality of sets of data related to the fitness exercise program are stored inside the application client matched with the wearable device. These data are displayed in the display interface of the application client in the name of their corresponding fitness exercise program.
  • the application client issues an EMG signal acquisition command to the control module.
  • the control module controls each acquisition module to collect the EMG signal from the preset body position.
  • the control module when the acquisition module is communicatively connected with the control module on the wearable device and the acquisition module only includes the collection electrode, the control module outputs a high level signal to turn on the connection between each collection module and the control module, thereby implementing Acquisition control of myoelectric signals.
  • the control module wirelessly connects to the control module, the control module sends a control data packet to the acquisition module, so that the acquisition module connected to the control data packet can perform the collection of the myoelectric signal according to the control parameter in the control data packet.
  • the preset human body position refers to the position of the human body that the acquisition module contacts, and the collection module is disposed on the wearable device, and the different human body positions contacted by the different acquisition modules are different, that is, the corresponding muscle parts are different, and therefore, the control module can be collected by the acquisition module.
  • the EMG signals from different muscle parts are transmitted, and the collected EMG signals are transmitted to the terminal device for subsequent analysis processing.
  • S102 Parse the collected myoelectric signal, and acquire an action type of the action performed by the user.
  • the control module performs recognition processing on these myoelectric signals to determine the type of fitness action performed by the user at the last moment.
  • each moment is a preset minimum time unit. Since the user performs the exercise exercise, the same exercise action often needs to be repeated multiple times. Therefore, by determining the type of exercise performed by the user at the last moment, the fitness action type is within the error tolerance. Also determine the type of fitness action that the user is about to perform at the current time.
  • the foregoing S102 specifically includes:
  • S201 intercepting an active segment of the myoelectric signal in the myoelectric signal by using a preset algorithm.
  • the signal segments corresponding to the execution of the motion are extracted, and the extracted signal segments are the active segments of the EMG signal.
  • the start and stop collection time corresponding to each active segment of the myoelectric signal it is determined that the user is performing a fitness exercise, that is, each active segment of the myoelectric signal is determined to be an effective muscle corresponding to the fitness action. electric signal.
  • the algorithm for detecting the active segment of the myoelectric signal includes, but is not limited to, a short-time Fourier algorithm, a self-organizing artificial neural network algorithm, and a moving average algorithm.
  • the starting point and the ending point of the fitness action are determined, and the active segment of the myoelectric signal is intercepted from all the collected myoelectric signals. If the EMG signal that has been acquired before any acquisition time has more than one active segment of the EMG signal detected, only one active segment of the EMG signal closest to the current time is intercepted.
  • S202 Extract an absolute value mean ratio characteristic of the active segment of the myoelectric signal.
  • the control module Since the EMG signals collected by the control module are respectively derived from different acquisition modules in the wearable device, the control module divides the acquired EMG signals into N-channel sub-signals according to the acquisition module source identifier carried by the EMG signal. , N is the number of acquisition modules. For the active segment of the myoelectric signal taken from the myoelectric signal, it also contains the N-channel sub-signal.
  • the feature information in the active segment of the myoelectric signal is acquired by using the time domain method.
  • the feature information is selected as an absolute value mean ratio (MAVR) feature.
  • MAVR absolute value mean ratio
  • the extraction process for the absolute value ratio ratio features mainly includes:
  • s i (t) represents the magnitude of the myoelectric amplitude corresponding to the i-th channel sub-signal in the active segment of the myoelectric signal at time t
  • N is the length of the active segment of the myoelectric signal
  • the active segment of the myoelectric signal contains a multi-channel sub-signal
  • the active segment of the myoelectric signal contains multiple MAV features, each of which corresponds to a sub-signal of one channel.
  • the MAVR feature of each channel sub-signal in the active segment of the myoelectric signal is calculated by a preset calculation formula, and the calculation formula includes:
  • C is the total number of sub-signal channels included in the active segment of the myoelectric signal.
  • S203 Input the absolute value mean ratio feature into a preset action classifier, and output an action type of the action performed by the user.
  • the action classifier includes, but is not limited to, a common classifier such as a linear judgment classifier, a multi-layer perceptron neural network, and a support vector machine.
  • the motion classifier when the motion classifier is a Markov distance classifier based on the minimum risk Bayesian criterion, after the MAVR feature corresponding to each channel sub-signal is input into the classifier, the classifier converts each MAVR feature.
  • the i-dimensional feature vector is used, and the feature vector is identified and processed by using a pre-trained classification model to output an action type corresponding to the active segment of the myoelectric signal.
  • the action type of the active segment of the myoelectric signal is output as the action type of the action performed by the user.
  • the application client corresponds to the name of the fitness exercise program.
  • the plurality of consecutive fitness action types are transmitted to the control module, so that the control module can determine one of the plurality of fitness action types received by the control module at any one time as the reference action type corresponding to the user at the current time.
  • the foregoing S101 specifically includes S301
  • the foregoing S103 specifically includes S303. Details are as follows:
  • S301 When the collection event is triggered, start counting, and control the collection module in the wearable device to collect the myoelectric signal of the human body position preset by the user.
  • the collection event is triggered when the terminal device receives the fitness exercise plan selection instruction issued by the user.
  • the application client issues an EMG signal acquisition command to the control module.
  • the control module controls each of the acquisition modules on the wearable fitness garment to collect the EMG signal from the preset human body position. And, from this point on, the counter inside the control module starts to operate, and is used for cumulative calculation of the number of pulses. The greater the number of accumulated pulses corresponding to a certain time, the larger the count value corresponding to that time.
  • S303 Acquire an action type corresponding to the count value in a preset action type storage list according to a count value corresponding to the collection time of the myoelectric signal, and determine the action type as the reference action type. .
  • Each fitness action type carries a corresponding count value tag when receiving a plurality of consecutive fitness action types corresponding to the fitness exercise program name.
  • the control module stores each fitness action type carrying the corresponding count value tag to the action type storage list, and stores the historical data in the action type in the action type until receiving a plurality of consecutive fitness action types corresponding to the other fitness exercise program name. Clear. And based on the accumulated count value in each time counter, the control module determines, from the plurality of fitness action types of the action type storage list, a count value flag corresponding to the cumulative count value, thereby marking the fitness value type corresponding to the count value The output is the reference action type of the user at the current time.
  • the control module determines, from the action type storage list, the fitness action type whose count value is marked as “5” as the reference action type of the current time.
  • the control module compares the action type of the action performed by the user in S102 with the reference action type read in S103, and determines whether the two are the same. In the case of the same two, it means that the fitness action to be performed by the user at the current time matches the fitness action that should be performed, and in the process of the fitness action to be performed by the user, the generated electromyogram signal is an effective myoelectric signal.
  • the terminal device analyzes based on the effective myoelectric signal to obtain exercise effect data, the exercise effect data also has a high fitness guiding significance. Therefore, the acquisition frequency of the acquisition module is adjusted, and the acquisition frequency is changed to a preset first frequency. The first frequency is greater than or equal to the normal acquisition frequency of the acquisition module.
  • the process returns to S101, so that the acquisition module collects the myoelectric signal of the human body position preset by the user at the first frequency, and sequentially performs subsequent steps.
  • the acquisition frequency of the acquisition module is lowered, and the acquisition frequency is adjusted to a preset second frequency.
  • the first frequency is lower than the normal acquisition frequency of the acquisition module.
  • the process returns to S101, so that the acquisition module collects the myoelectric signal of the human body position preset by the user at the second frequency, and sequentially performs subsequent steps.
  • the type of the fitness action that is actually to be performed is predicted, and the collection can be controlled if the type of the fitness action predicted and the type of the reference action are the same or different.
  • the module adjusts the acquisition frequency, so that the acquisition module in the wearable device no longer relies on a single acquisition frequency to acquire the myoelectric signal, but specifically uses different acquisition frequencies in real time according to the actual fitness action matching effect of the user. Improve the collection effectiveness and accuracy of EMG signals.
  • the action type of the action performed by the user is recognized in real time, and the action type is compared with the reference action type as the motion effect judgment reference, and the acquisition module is reduced on the electromyogram if the two do not match.
  • the frequency of the signal acquisition makes the proportion of the collected data of the invalid myoelectric signal can be appropriately reduced.
  • the fitness guide with higher reference value can be output. It is also suggested that the user can also regulate his or her fitness exercises according to more accurate fitness guidance suggestions, and improve the scientific and effective performance of the user's exercise.
  • the foregoing S105 specifically includes:
  • S501 If the action type of the action performed by the user is different from the reference action type, adjust an acquisition frequency of the collection module to a second frequency, and control the wearable device or connect with the wearable device.
  • the peripheral device issues a voice alert, the second frequency being less than the first frequency.
  • the language alarm prompt information may be sent by any module on the wearable device, or may be sent by an application client used in conjunction with the wearable device.
  • an audio prompt message is also generated, so that the user can perceive what he has done at the current moment.
  • the fitness action is different from the reference fitness action, and the posture can be corrected in time to complete the exercise according to the fitness action that should be performed at various moments according to the fitness exercise program, thereby improving the exercise effectiveness of the user.
  • the EMG signal acquisition method provided by the embodiment of the present invention further includes S106.
  • the present invention is implemented.
  • the electromyographic signal acquisition method provided by the example further includes S107, and S104 specifically includes S401.
  • the implementation principles of each step are as follows:
  • S106 Parsing the active segment of the myoelectric signal to determine the focused muscle group of the user.
  • the control module Since the EMG signals collected by the control module are respectively derived from different acquisition modules on the wearable device, the control module divides the acquired EMG signals into N-channel sub-signals according to the acquisition module source identifier carried by the EMG signal. , N is the number of acquisition modules. For the active segment of the myoelectric signal taken from the myoelectric signal, it also contains the N-channel sub-signal. Since the human muscle group attached to each collection module is preset in the control module, the control module divides the N-channel sub-signal corresponding to the active segment of the myoelectric signal according to the correspondence relationship between the source identifier of the acquisition module and the human muscle group. M groups.
  • M is the total number of muscle groups of the human muscle group attached to the acquisition module in the wearable device, and M is less than or equal to N.
  • the control module identifies the acquisition module source as the K channel sub-signals of the K acquisition modules as one group.
  • M, N, and K are both positive integers.
  • the control module performs comprehensive analysis and processing on the M sub-signal groups corresponding to the active segment of the myoelectric signal, and calculates the ratio of the average myoelectric amplitude corresponding to the maximum value of the preset myoelectric amplitude respectively. And outputting the ratio as the percentage of the myoelectric amplitude of the human muscle group corresponding to the sub-signal group.
  • the preset maximum value of the myoelectric amplitude corresponds to the human muscle group, that is, when acquiring the preset maximum value of the myoelectric amplitude corresponding to each sub-signal group, it is necessary to obtain corresponding to each sub-signal group.
  • the muscles of the human body are determined. If the myoelectric data of the myoelectric amplitude percentage is greater than the preset threshold is a certain group of the M groups, then one of the human muscle groups corresponding to each of the certain groups will be Determine the focus of the muscles for the user's focus.
  • the reference motion muscle group corresponding to each reference action type is preset in the control module. Therefore, after determining a reference action type of the current time from S103, each reference exercise muscle group corresponding to the reference action type can be read.
  • the reference exercise muscle group matches the key force muscle group, that is, comparing each of the user's key force muscle groups with each reference exercise muscle group, thereby determining whether each key force muscle group is For reference to the motor muscle group, and whether the total number of focused muscle groups is the same as the total number of reference motor muscle groups. That is, it is judged whether the reference exercise muscle group and the key force muscle group are completely identical.
  • each of the focused muscle groups is a reference motor muscle group, and the total number of reference motor muscle groups is the same as the total number of the focus force muscle groups, it is determined that the focused force muscle group matches the reference exercise muscle group.
  • the control module adjusts the acquisition frequency of the acquisition module to change it to the first frequency greater than or equal to the normal acquisition frequency.
  • the acquisition frequency of the acquisition module is adjusted to the first frequency, and the module can be collected at the previous time.
  • the acquisition frequency is the second frequency, the acquisition frequency is reset with the user's actual fitness action matching effect, real-time adjustment of the acquisition frequency is realized, and the acquisition accuracy of the EMG signal is improved.
  • FIG. 6 is a structural block diagram of an electromyogram signal collection device according to an embodiment of the present invention. For convenience of description, only the embodiment of the present invention is shown. part.
  • the EMG signal acquisition device includes:
  • the control unit 61 is configured to control the acquisition module in the wearable device to collect the myoelectric signal of the human body position preset by the user.
  • the parsing unit 62 is configured to parse the collected myoelectric signal and acquire the action type of the action performed by the user.
  • the first obtaining unit 63 is configured to acquire a preset reference action type.
  • the first adjusting unit 64 is configured to adjust the acquisition frequency of the collection module to the first frequency if the action type of the action performed by the user is the same as the reference action type.
  • the second adjusting unit 65 is configured to: when the action type of the action performed by the user is different from the reference action type, adjust an acquisition frequency of the collection module to a second frequency, where the second frequency is smaller than the first a frequency.
  • the parsing unit 62 includes:
  • the intercepting subunit is configured to intercept an active segment of the myoelectric signal in the myoelectric signal by a preset algorithm.
  • An extraction subunit is configured to extract an absolute value mean ratio characteristic of the active segment of the myoelectric signal.
  • an output subunit configured to input the absolute value mean ratio feature into a preset action classifier, and output an action type of the action performed by the user.
  • the EMG signal acquisition device further includes:
  • a determining unit for parsing the active segment of the myoelectric signal to determine the focused muscle group of the user.
  • a second acquiring unit configured to acquire a reference moving muscle group of the reference action type.
  • the first adjusting unit 64 includes:
  • the acquisition frequency of the acquisition module is Adjusted to the first frequency.
  • control unit 61 includes:
  • a counting subunit configured to start counting when the collecting event is triggered, and control the collecting module in the wearable device to collect the myoelectric signal of the human body position preset by the user.
  • the parsing unit 62 includes:
  • Determining a subunit configured to acquire an action type corresponding to the count value in a preset action type storage list according to a count value corresponding to the collection time of the myoelectric signal, and determine the action type as Refer to the type of action.
  • the second adjusting unit 65 includes:
  • a prompting subunit configured to control the wearable device or a peripheral device connected to the wearable device to issue a voice alarm prompt.
  • each functional unit and module described above is exemplified. In practical applications, the above functions may be assigned to different functional units as needed.
  • the module is completed by dividing the internal structure of the device into different functional units or modules to perform all or part of the functions described above.
  • Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit, and the integrated unit may be implemented by hardware.
  • Formal implementation can also be implemented in the form of software functional units.
  • the specific names of the respective functional units and modules are only for the purpose of facilitating mutual differentiation, and are not intended to limit the scope of protection of the present application.
  • For the specific working process of the unit and the module in the foregoing system reference may be made to the corresponding process in the foregoing method embodiment, and details are not described herein again.
  • the disclosed apparatus and method may be implemented in other manners.
  • the system embodiment described above is merely illustrative.
  • the division of the module or unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be used. Combinations can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the medium includes a plurality of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the methods described in various embodiments of the embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Signal Processing (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

L'invention concerne un procédé et un appareil d'acquisition de signal électromyographique, applicables au domaine technique des dispositifs électroniques vestimentaires. Le procédé consiste : à commander un module d'acquisition dans un appareil vestimentaire pour acquérir des signaux électromyographiques à des positions corporelles prédéfinies par un utilisateur (S101) ; à analyser les signaux électromyographiques acquis pour obtenir un type de mouvement des mouvements effectués par l'utilisateur (S102) ; à obtenir un type de mouvement de référence prédéfini (S103) ; si le type de mouvement des mouvements effectués par l'utilisateur est le même que le type de mouvement de référence, à régler la fréquence d'acquisition du module d'acquisition sur une première fréquence (S104) ; et si le type de mouvement des mouvements effectués par l'utilisateur est différent du type de mouvement de référence, à régler la fréquence d'acquisition du module d'acquisition sur une seconde fréquence, la seconde fréquence étant inférieure à la première fréquence (S105). La présente invention réduit le volume d'acquisition de signaux électromyographiques invalides, et permet de délivrer des orientations de condition physique et des suggestions avec des valeurs de référence supérieures lors de la génération de données d'effet de condition physique selon des signaux électromyographiques valides en proportion plus élevée, de telle sorte que l'utilisateur peut réguler ses propres mouvements de condition physique en fonction des orientations et des suggestions de condition physique plus précises.
PCT/CN2018/072323 2017-05-25 2018-01-12 Procédé et appareil d'acquisition de signal électromyographique WO2018214522A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710378814.2A CN108229283B (zh) 2017-05-25 2017-05-25 肌电信号采集方法及装置
CN201710378814.2 2017-05-25

Publications (1)

Publication Number Publication Date
WO2018214522A1 true WO2018214522A1 (fr) 2018-11-29

Family

ID=62656592

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/072323 WO2018214522A1 (fr) 2017-05-25 2018-01-12 Procédé et appareil d'acquisition de signal électromyographique

Country Status (2)

Country Link
CN (1) CN108229283B (fr)
WO (1) WO2018214522A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112773380A (zh) * 2019-11-07 2021-05-11 深圳市理邦精密仪器股份有限公司 一种肌电信号的处理方法、处理设备以及存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111475206B (zh) * 2019-01-04 2023-04-11 优奈柯恩(北京)科技有限公司 用于唤醒可穿戴设备的方法及装置
CN112773381B (zh) * 2019-11-07 2023-09-22 深圳市理邦精密仪器股份有限公司 一种肌电信号的处理方法、处理设备以及存储介质
CN114676737B (zh) * 2022-05-26 2022-09-27 深圳市心流科技有限公司 一种肌电信号的采样频率的动态调节方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004073386A (ja) * 2002-08-13 2004-03-11 Japan Science & Technology Corp インピーダンス測定装置及び運動学習支援装置
CN104706359A (zh) * 2015-04-01 2015-06-17 深圳柔微传感科技有限公司 一种实现运动实时监测的方法和智能服装
CN106650243A (zh) * 2016-12-06 2017-05-10 北京体育大学 一种防止运动员肌肉损伤的放松活动系统
CN106667441A (zh) * 2016-12-30 2017-05-17 包磊 生理监测结果的反馈方法及装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9314190B1 (en) * 2006-05-11 2016-04-19 Great Lakes Neurotechnologies Inc. Movement disorder recovery system and method
US8108039B2 (en) * 2007-07-13 2012-01-31 Neuro Wave Systems Inc. Method and system for acquiring biosignals in the presence of HF interference
CN102622605B (zh) * 2012-02-17 2015-06-03 国电科学技术研究院 一种表面肌电信号的特征提取及动作模式识别方法
CN102940933A (zh) * 2012-11-26 2013-02-27 南京伟思医疗科技有限责任公司 一种智能电刺激电路装置
CN103519820A (zh) * 2013-09-29 2014-01-22 上海致趣网络科技有限公司 穿戴式设备运动检测方法
CN105181998B (zh) * 2015-08-03 2018-10-26 简极科技有限公司 一种检测投篮时手臂的semg与动作轨迹的方法
CN105561567B (zh) * 2015-12-29 2018-11-13 中国科学技术大学 一种计步及运动状态评估装置
CN106691447B (zh) * 2017-02-23 2023-09-12 北京纳通科技集团有限公司 肌肉训练辅助装置、肌肉训练评估装置及方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004073386A (ja) * 2002-08-13 2004-03-11 Japan Science & Technology Corp インピーダンス測定装置及び運動学習支援装置
CN104706359A (zh) * 2015-04-01 2015-06-17 深圳柔微传感科技有限公司 一种实现运动实时监测的方法和智能服装
CN106650243A (zh) * 2016-12-06 2017-05-10 北京体育大学 一种防止运动员肌肉损伤的放松活动系统
CN106667441A (zh) * 2016-12-30 2017-05-17 包磊 生理监测结果的反馈方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112773380A (zh) * 2019-11-07 2021-05-11 深圳市理邦精密仪器股份有限公司 一种肌电信号的处理方法、处理设备以及存储介质
CN112773380B (zh) * 2019-11-07 2023-09-22 深圳市理邦精密仪器股份有限公司 一种肌电信号的处理方法、处理设备以及存储介质

Also Published As

Publication number Publication date
CN108229283B (zh) 2020-09-22
CN108229283A (zh) 2018-06-29

Similar Documents

Publication Publication Date Title
WO2018214522A1 (fr) Procédé et appareil d'acquisition de signal électromyographique
Fajardo et al. EMG hand gesture classification using handcrafted and deep features
WO2018214526A1 (fr) Procédé et appareil de guidage d'exercice physique
Moniri et al. Real-time forecasting of sEMG features for trunk muscle fatigue using machine learning
CN104107134B (zh) 基于肌电反馈的上肢训练方法及系统
WO2018214529A1 (fr) Procédé et appareil d'acquisition de signal électromyographique
WO2018214532A1 (fr) Procédé et appareil de rétroaction de données d'exercice physique
CN112788993A (zh) 使用脑机接口(bci)的中风康复方法和系统
CN105595995B (zh) 生理数据检测系统、检测装置、终端设备、数据分析方法
CN106726030A (zh) 基于临床脑电信号控制机械手运动的脑机接口系统及其应用
WO2018214523A1 (fr) Procédé et appareil d'acquisition de signaux électromyographiques
Misgeld et al. Body-sensor-network-based spasticity detection
EP2976991B1 (fr) Dispositif pour l'évaluation, la prévention et le traitement de la douleur lombaire, basé sur la rééducation posturale
Gorur et al. Glossokinetic potential based tongue–machine interface for 1-D extraction
JP2011076177A (ja) 歯の接触によって誘発された脳波を利用した機器制御方法及び機器制御装置
CN114298089A (zh) 一种多模态力量训练辅助方法和系统
Tryon et al. Classification of task weight during dynamic motion using EEG–EMG fusion
Gorur et al. Glossokinetic potential based tongue–machine interface for 1-D extraction using neural networks
Chandrasekhar et al. Design of a real time portable low-cost multi-channel surface electromyography system to aid neuromuscular disorder and post stroke rehabilitation patients
Ai et al. Advanced rehabilitative technology: neural interfaces and devices
JP6344254B2 (ja) 眠気検知装置
CN116312951B (zh) 一种基于多模态耦合分析的运动功能评估方法及其系统
Zhang et al. Activity recognition of the torso based on surface electromyography for exoskeleton control
Wang et al. DeepLap: A deep learning based non-specific low back pain symptomatic muscles recognition system
CN115624338A (zh) 一种上肢刺激反馈康复装置及其控制方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18806194

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18806194

Country of ref document: EP

Kind code of ref document: A1