CN110850979B - Gesture recognition man-machine interaction method based on spaceflight medical supervision and medical insurance signal - Google Patents
Gesture recognition man-machine interaction method based on spaceflight medical supervision and medical insurance signal Download PDFInfo
- Publication number
- CN110850979B CN110850979B CN201911078657.9A CN201911078657A CN110850979B CN 110850979 B CN110850979 B CN 110850979B CN 201911078657 A CN201911078657 A CN 201911078657A CN 110850979 B CN110850979 B CN 110850979B
- Authority
- CN
- China
- Prior art keywords
- signals
- electromyographic
- forearm
- wave
- hand
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- General Business, Economics & Management (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention provides a novel gesture recognition man-machine interaction technology based on medical insurance signals of a spaceflight in a space environment, which is characterized in that the corresponding relationship between the surface electromyographic signals and the electrocardiosignals of corresponding areas is studied and utilized to distinguish through the acquisition, feature extraction and classification study of the surface electromyographic signals and the electrocardiosignals of spaceflight in the space environment, so that accurate control signals are obtained, further, an action executor is controlled to perform different actions, man-machine interaction is completed, and the utilization efficiency of a space assurance device is effectively improved. The technology has the characteristics of nature and high efficiency, and has exploratory significance for improving the operation efficiency of on-orbit personnel, considering medical insurance medical supervision application of the on-orbit personnel, and ensuring smooth completion of space experiment tasks.
Description
Technical Field
The invention relates to a novel gesture recognition man-machine interaction method based on medical insurance signals of a space doctor in a space environment, in particular to a gesture recognition method which is applied to a space station and a spacecraft and can be fused with a medical insurance system, and belongs to the field of man-machine interaction.
Background
In the future space laboratory and space station task stage of China, flight control and space experiment tasks of astronauts and space experiment personnel are more and more heavy, various physiological parameters of on-orbit personnel are monitored, physical health of the on-orbit personnel is guaranteed, man-machine interaction efficiency of the on-orbit personnel is improved, operation burden of the on-orbit personnel in task execution is reduced, and the method is one of important means for guaranteeing heavy space tasks. Moreover, the natural and efficient man-machine interaction means is also an important auxiliary technology for ground simulation training of astronauts and space laboratory staff.
In the development process of human civilization, gestures are an interaction means which very accords with the daily habits of human beings. Some additional information and emotion are conveyed through gestures during interpersonal language communication in daily life. In interpersonal communication where speech is not feasible, gestures can convey much information, whereas in some special populations, such as deaf-mutes, communication is almost entirely dependent on gestures. After the computer is invented, gestures cannot be used as an effective means of man-machine interaction for a long time because of the limitation of a computer software and hardware system, but with the development of the computer software and hardware level, the actions of the gestures in man-machine interaction are getting more and more attention of researchers. Therefore, the gesture recognition technology has natural and efficient natural advantages, can improve the man-machine interaction efficiency of on-orbit personnel, and is a development trend of space man-machine interaction technology.
At present, gesture recognition methods based on various sensing technologies are mainly divided into a gesture recognition method based on vision and a wearable gesture recognition method. The gesture interaction method based on vision has the defects of large operand, poor real-time performance and the like in addition to certain requirements on light and background. The wearable gesture recognition mainly comprises a data glove mode and an electromyographic signal mode. The glove type sensing device with certain thickness is required to be worn in the data glove mode, the electrode is only required to be placed on a specific part of the hand in the muscle electric signal mode, fine motion of the hand can be captured, fine control is achieved, and the hand type sensing device can be synchronously carried out with the physiological parameters of on-orbit detection personnel, so that the hand type sensing device is a man-machine interaction mode suitable for space task operation.
The invention provides a novel gesture recognition man-machine interaction technology based on medical insurance signals of a spaceflight in a space environment, which is characterized in that the corresponding relationship between the surface electromyographic signals and the electrocardiosignals of corresponding areas is studied and utilized to distinguish through the acquisition, feature extraction and classification study of the surface electromyographic signals and the electrocardiosignals of spaceflight in the space environment, so that accurate control signals are obtained, further, an action executor is controlled to perform different actions, man-machine interaction is completed, and the utilization efficiency of a space assurance device is effectively improved. The technology has the characteristics of nature and high efficiency, and has exploratory significance for improving the operation efficiency of on-orbit personnel, considering medical insurance medical supervision application of the on-orbit personnel, and ensuring smooth completion of space experiment tasks.
Disclosure of Invention
The invention aims to solve the technical problem of realizing complex and efficient man-machine interaction function in a space environment under the condition of reducing space load and wearing equipment of astronauts as much as possible. The invention discloses a novel man-machine interaction method facing aerospace activities. The method has the main innovation points that in the aerospace flight, the same sensor is used for completing medical supervision and medical insurance signal measurement and man-machine interaction signal acquisition, and simultaneously, the astronaut physiological parameter measurement and operation control tasks are completed.
The invention discloses a novel gesture recognition man-machine interaction method based on medical insurance signals of a spaceflight doctor in a space environment, which is realized by the following technical scheme:
step one:
and arranging the surface myoelectric electrode and the electrocardio electrode on the astronaut according to medical supervision and medical insurance requirements. The surface myoelectricity electrodes are 8 in total and are respectively arranged on the upper side, the lower side, the ulnar side and the radial side of the left and right forearms, so as to monitor hand myoelectricity signals. The electrocardio electrode is a 12-lead electrocardio electrode.
Step two:
and carrying out low-pass filtering on signals of the 8 surface myoelectric electrodes and the 12-lead electrocardio electrodes to filter high-frequency noise.
Step three:
and acquiring the filtered surface electromyographic signals and the electrocardiosignals according to medical supervision requirements, respectively obtaining amplitude, frequency characteristics and electrocardiosignal characteristics of muscle signals of the astronauts, and monitoring physiological parameters of the astronauts.
Step four:
the method comprises the steps of carrying out mathematical expression on amplitude signals of surface myoelectricity electrode signals, marking left-hand forearm myoelectricity amplitude signals as A (n), wherein A (1), A (2), A (3) and A (4) respectively represent myoelectricity amplitude signals of upper side, lower side, ulnar side and radial side of the left-hand forearm, marking right-hand forearm myoelectricity amplitude signals as B (n), and respectively representing myoelectricity amplitude signals of upper side, lower side, ulnar side and radial side of the left-hand forearm by B (1), B (2), B (3) and B (4).
The center frequency of the surface electromyographic electrode signal is expressed mathematically, the center frequency of the left hand forearm electromyographic signal is marked as C (n), wherein C (1), C (2), C (3), C (4) respectively represent the electromyographic signal center frequencies of the upper side, the lower side, the ulnar side and the radial side of the left hand forearm, the center frequency of the right hand forearm electromyographic signal is marked as D (n), and D (1), D (2), D (3) and D (4) respectively represent the electromyographic signal center frequencies of the upper side, the lower side, the ulnar side and the radial side of the left hand forearm.
The P, QRS, R, Q wave duration of the electrocardiograph is expressed mathematically, the P, QRS, R, Q wave duration is denoted as E (n), and the P, QRS, R, Q wave durations are denoted as E (1), E (2), E (3), E (4), respectively.
Step five:
the left hand fist, palm opening, palm depressing, forearm straightening, forearm bending actions are sequentially defined as m1, m2, m3, m4 and m5, and the right hand fist, palm opening, palm depressing, forearm straightening, forearm bending actions are sequentially defined as m6, m7, m8, m9 and m10.
Step six:
the convolution of the electromyographic signals and the electrocardiosignals during each action is calculated, and the physical and physiological significance of the convolution is that the electrocardiosignals are regarded as input signals, a muscle system is regarded as a transmission system, and the electromyographic signals are regarded as the results of electric signals generated by muscles during muscle movement and the electrocardiosignals transmitted in movement muscles.
The values of m1, m2, m3, m4, m5, m6, m7, m8, m9 and m10 are calculated according to the following formula:
mi=[A(n)/B(n)]*E(n)+[C(n)/D(n)]*E(n)
n=1、2、3、4、5,i=1、2、3…10
different actions of m1 and m2 … m10 can be distinguished according to different values of mi, and the different actions are defined as different operation commands, so that man-machine interaction is realized.
The corresponding relation between the mi value and the action can be obtained according to a statistical test and a clustering analysis, wherein the specific numerical range is related to individual difference, and the statistical test and the clustering analysis are conventional tests and analysis methods and are not repeated.
Step seven:
different operation meanings are defined for the different actions, so that the man-machine interaction function according to medical insurance signals is realized.
The beneficial effects are that:
1. according to the novel gesture recognition man-machine interaction technology of the medical insurance signal of the basic doctor in the space environment, through collection, feature extraction and classification research of the surface electromyographic signals and the electrocardiosignals of the astronauts in the space environment, action distinction is carried out by utilizing the corresponding relations between the surface electromyographic signals and the electrocardiosignals in different areas, the utilization rate of information in the medical insurance signal of the basic doctor is effectively improved, the action distinction function can be realized, and man-machine interaction is realized. The technology has the characteristics of nature and high efficiency, and has exploratory significance for improving the operation efficiency of on-orbit personnel and ensuring the smooth completion of space experiment tasks.
2. The novel gesture recognition man-machine interaction method based on the medical insurance signal of the spaceflight doctor in the space environment realizes action distinction and man-machine interaction without adding additional equipment, and has exploratory significance for reducing system load and completing complex on-orbit operation
Drawings
Without any means for
Detailed Description
The invention discloses a novel gesture recognition man-machine interaction method based on medical insurance signals of a spaceflight doctor in a space environment, which is realized by the following specific embodiments:
step one:
and arranging the surface myoelectric electrode and the electrocardio electrode on the astronaut according to medical supervision and medical insurance requirements. The surface myoelectricity electrodes are 8 in total and are respectively arranged on the upper side, the lower side, the ulnar side and the radial side of the left and right forearms, so as to monitor hand myoelectricity signals. The electrocardio electrode is a 12-lead electrocardio electrode.
Step two:
and carrying out low-pass filtering on the 8 surface myoelectric electrodes and the 12-lead electrocardio electrode signals, wherein the surface myoelectric electrode signals can be subjected to low-pass filtering with the cut-off frequency of 10kHz, and the electrocardio electrode signals can be subjected to low-pass filtering with the cut-off frequency of 60Hz, so that high-frequency noise is filtered.
Step three:
and acquiring the filtered surface electromyographic signals and electrocardio electrode signals according to medical supervision requirements, wherein the sampling frequency of the surface electromyographic signals is 50kHz, the sampling frequency of the electrocardio electrode signals is 600Hz, respectively obtaining the amplitude, the frequency characteristic and the electrocardio characteristic of the muscle electrical signals of the astronaut, and monitoring the physiological parameters of the astronaut.
Step four:
the method comprises the steps of carrying out mathematical expression on amplitude signals of surface myoelectricity electrode signals, marking left-hand forearm myoelectricity amplitude signals as A (n), wherein A (1), A (2), A (3) and A (4) respectively represent myoelectricity amplitude signals of upper side, lower side, ulnar side and radial side of the left-hand forearm, marking right-hand forearm myoelectricity amplitude signals as B (n), and respectively representing myoelectricity amplitude signals of upper side, lower side, ulnar side and radial side of the left-hand forearm by B (1), B (2), B (3) and B (4).
The center frequency of the surface electromyographic electrode signal is expressed mathematically, the center frequency of the left hand forearm electromyographic signal is marked as C (n), wherein C (1), C (2), C (3), C (4) respectively represent the electromyographic signal center frequencies of the upper side, the lower side, the ulnar side and the radial side of the left hand forearm, the center frequency of the right hand forearm electromyographic signal is marked as D (n), and D (1), D (2), D (3) and D (4) respectively represent the electromyographic signal center frequencies of the upper side, the lower side, the ulnar side and the radial side of the left hand forearm.
The P, QRS, R, Q wave duration of the electrocardiograph is expressed mathematically, the P, QRS, R, Q wave duration is denoted as E (n), and the P, QRS, R, Q wave durations are denoted as E (1), E (2), E (3), E (4), respectively.
Step five:
the left hand fist, palm opening, palm depressing, forearm straightening, forearm bending actions are sequentially defined as m1, m2, m3, m4 and m5, and the right hand fist, palm opening, palm depressing, forearm straightening, forearm bending actions are sequentially defined as m6, m7, m8, m9 and m10.
Step six:
the convolution of the electromyographic signals and the electrocardiosignals during each action is calculated, and the physical and physiological significance of the convolution is that the electrocardiosignals are regarded as input signals, a muscle system is regarded as a transmission system, and the electromyographic signals are regarded as the results of electric signals generated by muscles during muscle movement and the electrocardiosignals transmitted in movement muscles.
The values of m1, m2, m3, m4, m5, m6, m7, m8, m9 and m10 are calculated according to the following formula
mi=[A(n)/B(n)]*E(n)+[C(n)/D(n)]*E(n)
n=1、2、3、4、5,i=1、2、3…10
Different actions of m1 and m2 … m10 can be distinguished according to different values of mi, so that man-machine interaction is realized.
The corresponding relation between the mi value and the action can be obtained according to a statistical test and a clustering analysis, wherein the specific numerical range is related to individual difference, and the statistical test and the clustering analysis are conventional tests and analysis methods and are not repeated.
For example, m1=3.5, m2=7.5, m3=23.5, m4=15.5, m5=34.5, m6=0.93, m7=0.44, m8=0.083, m9=0.12 and m10=0.24, based on the average of 50 test data of two subjects
It is known that the above actions have a distinct distinction depending on the numerical values.
Step seven:
different operation meanings are defined for the different actions, so that the man-machine interaction function according to medical insurance signals is realized.
The scope of the present invention is not limited to the above embodiments, which are used for explaining the present invention, and all changes or modifications under the same principles and conceptual conditions as the present invention are within the scope of the present invention.
Claims (1)
1. The gesture recognition man-machine interaction method based on the aerospace doctor supervision medical insurance signal is characterized by comprising the following steps of:
step one:
arranging surface myoelectricity electrodes and electrocardio electrodes on a astronaut according to medical supervision requirements, wherein the total number of the surface myoelectricity electrodes is 8, and the surface myoelectricity electrodes are respectively arranged on the upper side, the lower side, the ulnar side and the radial side of the left and right forearms to monitor hand myoelectricity signals;
step two:
carrying out low-pass filtering on the 8 surface electromyographic signals and the 12-lead electrocardiosignals to filter high-frequency noise;
step three:
acquiring the filtered surface electromyographic signals and the electrocardiosignals according to medical supervision requirements, respectively obtaining amplitude, frequency characteristics and electrocardiosignal characteristics of the electromyographic signals of the astronauts, and monitoring physiological parameters of the astronauts;
step four:
the method comprises the steps of carrying out mathematical representation on amplitude signals of surface electromyographic signals, wherein the left-hand forearm electromyographic amplitude signals are marked as A (n), wherein A (1), A (2), A (3) and A (4) respectively represent electromyographic amplitude signals of the upper side, the lower side, the ulnar side and the radial side of the left-hand forearm, the right-hand forearm electromyographic amplitude signals are marked as B (n), and B (1), B (2), B (3) and B (4) respectively represent electromyographic amplitude signals of the upper side, the lower side, the ulnar side and the radial side of the right-hand forearm;
the center frequency of the surface electromyographic electrode signal is expressed mathematically, the center frequency of the left-hand forearm electromyographic signal is marked as C (n), wherein C (1), C (2), C (3) and C (4) respectively represent the center frequencies of electromyographic signals on the upper side, the lower side, the ulnar side and the radial side of the left-hand forearm, the center frequency of the right-hand forearm electromyographic signal is marked as D (n), and D (1), D (2), D (3) and D (4) respectively represent the center frequencies of electromyographic signals on the upper side, the lower side, the ulnar side and the radial side of the right-hand forearm;
the duration of P wave, QRS wave, R wave and Q wave of electrocardiosignal is expressed mathematically, the duration of P wave, QRS wave, R wave and Q wave is marked as E (n), and the duration of P wave, QRS wave, R wave and Q wave is marked as E (1), E (2), E (3) and E (4) respectively;
step five:
the left hand fist making, palm opening, palm pressing, forearm straightening and forearm bending actions are sequentially defined as m1, m2, m3, m4 and m5, and the right hand fist making, palm opening, palm pressing, forearm straightening and forearm bending actions are sequentially defined as m6, m7, m8, m9 and m10;
step six:
calculating convolution of the electromyographic signals and the electrocardiosignals during each action, wherein the electrocardiosignals are taken as input signals, a muscle system is taken as a transmission system, and the acquired electromyographic signals comprise the electric signals generated by muscles during the movement and the electrocardiosignals transmitted in the movement muscles;
the values of m1, m2, m3, m4, m5, m6, m7, m8, m9 and m10 are calculated according to the following formula:
mi=[A(n)/B(n)]*E(n)+[C(n)/D(n)]*E(n)
n=1、2、3、4,i=1、2、3...10
different actions of m1 and m 2..m10 are distinguished according to different values of mi, human-computer interaction is achieved, and the corresponding relation between the values of mi and the actions is obtained according to a statistical test and cluster analysis;
step seven:
different actions are defined as different operation meanings, so that a man-machine interaction function according to medical insurance signals is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911078657.9A CN110850979B (en) | 2019-11-07 | 2019-11-07 | Gesture recognition man-machine interaction method based on spaceflight medical supervision and medical insurance signal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911078657.9A CN110850979B (en) | 2019-11-07 | 2019-11-07 | Gesture recognition man-machine interaction method based on spaceflight medical supervision and medical insurance signal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110850979A CN110850979A (en) | 2020-02-28 |
CN110850979B true CN110850979B (en) | 2023-05-09 |
Family
ID=69598231
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911078657.9A Active CN110850979B (en) | 2019-11-07 | 2019-11-07 | Gesture recognition man-machine interaction method based on spaceflight medical supervision and medical insurance signal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110850979B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111671416B (en) * | 2020-05-29 | 2022-11-29 | 中国科学院深圳先进技术研究院 | Electrocardiosignal filtering method and device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0639754A (en) * | 1992-07-27 | 1994-02-15 | Nippon Telegr & Teleph Corp <Ntt> | Robot hand control device |
CN101598973A (en) * | 2009-06-26 | 2009-12-09 | 安徽大学 | Man-machine interactive system based on electro-ocular signal |
CN102426651A (en) * | 2011-08-25 | 2012-04-25 | 武汉理工大学 | Human body forearm surface electromyogram signal acquisition and pattern recognition system |
JP2014050590A (en) * | 2012-09-07 | 2014-03-20 | National Institute Of Advanced Industrial & Technology | Action recognition device for hand, artificial hand operation device, and composite sensor |
CN105824321A (en) * | 2016-04-29 | 2016-08-03 | 泰山医学院 | Four-axis aircraft control system and method based on surface electromyogram signals |
WO2017036147A1 (en) * | 2015-08-28 | 2017-03-09 | 华为技术有限公司 | Bioelectricity-based control method, device and controller |
CN108606882A (en) * | 2018-03-23 | 2018-10-02 | 合肥工业大学 | Intelligent wheelchair control system based on myoelectricity and acceleration self adaptive control |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8447704B2 (en) * | 2008-06-26 | 2013-05-21 | Microsoft Corporation | Recognizing gestures from forearm EMG signals |
-
2019
- 2019-11-07 CN CN201911078657.9A patent/CN110850979B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0639754A (en) * | 1992-07-27 | 1994-02-15 | Nippon Telegr & Teleph Corp <Ntt> | Robot hand control device |
CN101598973A (en) * | 2009-06-26 | 2009-12-09 | 安徽大学 | Man-machine interactive system based on electro-ocular signal |
CN102426651A (en) * | 2011-08-25 | 2012-04-25 | 武汉理工大学 | Human body forearm surface electromyogram signal acquisition and pattern recognition system |
JP2014050590A (en) * | 2012-09-07 | 2014-03-20 | National Institute Of Advanced Industrial & Technology | Action recognition device for hand, artificial hand operation device, and composite sensor |
WO2017036147A1 (en) * | 2015-08-28 | 2017-03-09 | 华为技术有限公司 | Bioelectricity-based control method, device and controller |
CN105824321A (en) * | 2016-04-29 | 2016-08-03 | 泰山医学院 | Four-axis aircraft control system and method based on surface electromyogram signals |
CN108606882A (en) * | 2018-03-23 | 2018-10-02 | 合肥工业大学 | Intelligent wheelchair control system based on myoelectricity and acceleration self adaptive control |
Non-Patent Citations (1)
Title |
---|
基于表面肌电控制的虚拟人机交互系统;杨宇;陈香;涂有强;张旭;杨基海;;系统仿真学报(03);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN110850979A (en) | 2020-02-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10959863B2 (en) | Multi-dimensional surface electromyogram signal prosthetic hand control method based on principal component analysis | |
CN109480838B (en) | Human body continuous complex movement intention prediction method based on surface electromyographic signals | |
CN107553499A (en) | Natural the gesture motion control system and method for a kind of Multi-shaft mechanical arm | |
He et al. | Spatial information enhances myoelectric control performance with only two channels | |
CN110826625A (en) | Finger gesture classification method based on surface electromyographic signals | |
Ye et al. | Optimal feature selection for EMG-based finger force estimation using LightGBM model | |
Tosin et al. | sEMG feature selection and classification using SVM-RFE | |
Kisa et al. | EMG based hand gesture classification using empirical mode decomposition time-series and deep learning | |
Li et al. | Wireless sEMG-based identification in a virtual reality environment | |
CN110850979B (en) | Gesture recognition man-machine interaction method based on spaceflight medical supervision and medical insurance signal | |
Park et al. | Korean finger number gesture recognition based on CNN using surface electromyography signals | |
Cheng et al. | Robotic arm control system based on brain-muscle mixed signals | |
CN110825232B (en) | Gesture recognition man-machine interaction device based on medical insurance monitoring signals of astronaut | |
Wang et al. | Brunnstrom stage automatic evaluation for stroke patients by using multi-channel sEMG | |
Powar et al. | Dynamic time warping for reducing the effect of force variation on myoelectric control of hand prostheses | |
Ge et al. | Gesture recognition and master–slave control of a manipulator based on sEMG and convolutional neural network–gated recurrent unit | |
Liu et al. | Hand gesture recognition based on deep neural network and sEMG signal | |
Tong et al. | sEMG based Gesture Recognition Method for Coal Mine Inspection Manipulator Using Multi-Stream CNN | |
Guo et al. | A novel fuzzy neural network-based rehabilitation stage classifying method for the upper limb rehabilitation robotic system | |
Vasiliev et al. | Robust neural network filtering in the tasks of building intelligent interfaces | |
Lukodono et al. | Arm Muscle Activation Performance Analysis Using Machine Learning Algorithm in the Assembly System | |
Roy et al. | Concurrent decoding of finger kinematic and kinetic variables based on motor unit discharges | |
Panchal et al. | Mapping Intrinsic and Extrinsic Muscle Myoelectric Activity During Natural Dynamic Movements Into Finger and Wrist Kinematics Using Deep Learning Prediction Models | |
Ge et al. | Gesture Recognition and Master-Slave Control of a Manipulator Based on sEMG and CNN-GRU | |
Yang et al. | Gesture Recognition Method Based on Computer Vision and Surface Electromyography: Implementing Intention Recognition of the Healthy Side in the Hand Assessment Process |
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 |