CN111481197B - A living-machine multimode information acquisition fuses device for man-machine natural interaction - Google Patents
A living-machine multimode information acquisition fuses device for man-machine natural interaction Download PDFInfo
- Publication number
- CN111481197B CN111481197B CN202010322650.3A CN202010322650A CN111481197B CN 111481197 B CN111481197 B CN 111481197B CN 202010322650 A CN202010322650 A CN 202010322650A CN 111481197 B CN111481197 B CN 111481197B
- Authority
- CN
- China
- Prior art keywords
- main control
- module
- control module
- power supply
- interface
- 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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/1036—Measuring load distribution, e.g. podologic studies
- A61B5/1038—Measuring plantar pressure during gait
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6828—Leg
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
Abstract
The invention provides a living-machine multi-mode information acquisition and fusion device for man-machine natural interaction. The device carries out signal conditioning modes of primary signal amplification, high-pass filtering, low-pass filtering, secondary signal amplification, power frequency interference removal and the like of a pre-amplification circuit on the collected electromyographic signals, and when the plantar pressure signals are collected, the detection circuit adopts double parallel switches to detect the contact state of the sole and the ground, signal data comprises nine data of three-axis acceleration, three-axis angular velocity and three-axis Euler angle, serial buses are adopted to realize the cascade mounting of a plurality of limb acceleration sensor modules, the device integrates data of three different types of sensors, the accuracy rate of lower limb behavior recognition reaches more than 98 percent through feature extraction and analysis, and the high-speed data transmission protocol is adopted to shorten the information interaction time, the time of a single data acquisition and data fusion process is less than 100ms, the single decoding time of the overall signal characteristics is less than 300ms, and the real-time requirement is met.
Description
Technical Field
The invention relates to the crossing field of biomedical engineering and mechanical electronic engineering, in particular to a living-machine multi-mode information acquisition and fusion device for man-machine natural interaction.
Background
The human and the machine keep good coordinated linkage, which is one of the key technical problems of man-machine fusion. Good cooperation between human and machine requires that the controlled robot not only make a quick and accurate response to the control instruction, but also sense the behavior intention of the controller in real time. The latter implementation requires a sensor to collect human body action data, and the human body action data is rapidly processed and analyzed and transmitted to the robot, so that the robot can acquire human behavior intention information in real time, thereby improving human-computer cooperation degree and avoiding many accidents caused by uncoordinated human-computer actions.
Most of the existing man-machine cooperation systems adopt single-type sensor data, complementary relations among multi-mode data cannot be effectively utilized based on a single-mode data analysis and processing conventional method, and in the process of identifying the body behaviors, a model trained by the single-mode data is poor in identification effect and low in robustness, so that the accuracy and the real-time performance of lower limb behavior identification cannot meet application requirements.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a living-machine multi-modal information acquisition and fusion device for man-machine natural interaction, which mainly comprises a light, real-time and efficient lower limb behavior mode multi-modal data acquisition, fusion and analysis processing system, wherein the multi-modal information data specifically comprises: myoelectric signal data, limb acceleration signal data and plantar pressure signal data, the total weight of the device is less than 200g, and the device is light and portable.
In order to realize the technical effects, the invention provides a living organism multi-mode information acquisition and fusion device for man-machine natural interaction, which is a laminated structure comprising an upper layer of design board and a lower layer of design board, wherein the upper layer of design board and the lower layer of design board are supported by four copper studs arranged at four corners, the upper layer of design board is provided with an embedded main control module, a 5V power supply interface, a limb acceleration sensor interface and an upper layer data transmission interface, an external limb acceleration sensor arranged on the limb of a patient is connected into the limb acceleration sensor interface through a USB-to-RS-485 debugging line, the limb acceleration sensor interface is connected with the embedded main control module through a USB communication protocol, limb acceleration signal data acquired by the external limb acceleration sensor is transmitted to the embedded main control module through the limb acceleration sensor interface, one end of the 5V power supply interface is connected with, the other end of the 5V power interface is connected with external 5V power supply equipment;
the lower layer design board comprises a lower layer data transmission interface, an AUX port, a sole contact state detection circuit, a signal interface, a myoelectric acquisition and conversion circuit and a power supply conversion circuit, wherein an myoelectric signal acquisition device arranged on the skin of a patient is connected into the AUX port through a differential electrode wire, the other end of the AUX port is connected with an amplification module AD8220 in the myoelectric acquisition and conversion circuit, myoelectric signal data acquired by the myoelectric signal acquisition device is processed by the myoelectric acquisition and conversion circuit and then transmitted to the lower layer data transmission interface through an SPI high-speed serial bus, a sole pressure detection device arranged on the sole of the patient is connected into the sole contact state detection circuit and the signal interface in a wired mode, the sole contact state detection circuit and the signal interface are connected with the lower layer data transmission interface through flying wires, and the lower layer data transmission interface is connected with the upper layer data transmission interface through a data, the data transmission of an upper layer and a lower layer is realized, the external 12V power supply equipment is connected to the power supply conversion circuit through a 12V power supply interface in the power supply conversion circuit, the conversion of a 12V direct-current power supply and a +/-5V bipolar power supply is realized through a positive and negative voltage linear voltage stabilizer module in the power supply conversion circuit, and a +/-5V power supply voltage is provided for the myoelectricity acquisition and conversion circuit;
the limb acceleration sensor interface is used for receiving limb acceleration signal data acquired by the external limb acceleration sensor;
the AUX port is used for receiving electromyographic signal data acquired by the electromyographic signal acquisition device;
the sole contact state detection circuit and the signal interface are used for receiving and processing sole pressure signal data acquired by the sole pressure detection device;
the electromyographic signal acquisition and conversion circuit is used for carrying out signal processing on electromyographic signal data and converting the electromyographic signal data after the signal processing into a digital quantity signal, and the signal processing comprises primary signal amplification, high-pass filtering, low-pass filtering, secondary signal amplification and power frequency interference removal;
the power supply conversion circuit is used for converting an external 12V direct-current power supply into +/-5V voltage;
the 5V power supply interface is used for externally connecting 5V power supply equipment to meet the 5V power supply requirement of the embedded main control module;
the embedded main control module is used for receiving and fusing multi-mode information data, and the multi-mode information data comprises limb acceleration signal data, myoelectric signal data and plantar pressure signal data.
Further, the detection circuit in the sole contact state detection circuit and the signal interface detects the contact state of the sole and the ground by adopting a double parallel switch, the contact state comprises a suspension state and a contact state, the suspension state is that the foot leaves the ground and is in the suspension state, the contact state is that the foot contacts the ground, the high level mark is defined as the suspension state and is represented by a numeral 1, the low level mark is defined as the contact state and is represented by a numeral 0, the embedded main control module continuously reads the GPIO port state, when the low level is 0, the foot contacts the ground, and when the high level is 1, the foot leaves the ground and is in the suspension state.
The external limb acceleration transducerThe sensors are respectively arranged at the center of the body of a patient, the middle parts of thighs, the middle parts of crus and ankle joints of the patient, the directions of three-dimensional space coordinate systems of all external limb acceleration sensors arranged on the same patient need to be kept consistent, the rotating directions all follow the right-hand rule, and the limb acceleration signal data acquired by the external limb acceleration sensors comprise three-axis acceleration (acceleration: (the third axis)a x，a y，a z) Three-axis angular velocity: (θ x，θ y，θ z) Three axes euler angle (gamma)x，γy，γz）。
One end of the limb acceleration sensor interface is connected with the embedded main control module through a USB communication protocol, the other end of the limb acceleration sensor interface is used for realizing cascade mounting of the accessed external limb acceleration sensor through an RS-485 serial bus, the external limb acceleration sensors which are cascaded on the serial bus adopt the same communication speed, communication addresses of different sensors are set through upper computer software, and the embedded main control module accesses each accessed external limb acceleration sensor in a polling register address mode through the limb acceleration sensor interface to realize the acquisition work of limb acceleration signal data.
Furthermore, the myoelectricity collecting and converting circuit is designed as follows: electromyographic signal data input through an AUX port is subjected to preposed primary amplification through an instrument amplification module AD8220, the electromyographic signal data are amplified to a sampling range of an AD conversion module, then high-frequency noise and power frequency interference are removed through a high-pass filter, a Butterworth low-pass filter circuit and a band-stop filter in sequence, finally the electromyographic signal data are input to the AD conversion module after secondary amplification, and the electromyographic signal data output by the AD conversion module are input to an embedded main control module;
the AD conversion module adopts an AD7606 multi-channel synchronous digital-to-analog conversion module supporting bipolar input to realize hardware synchronization of multi-channel surface electromyogram signals, and two AD7606 channels are carried in parallel in the AD conversion module to realize parallel synchronous sampling of 16 channels;
the butterworth low pass filter circuit is designed with an AD8642 amplifier.
The power conversion circuit is designed as follows: the 12V direct current power supply input by the 12V power supply equipment is connected with an input pin of the positive voltage output linear voltage stabilizer module, an output pin of the positive voltage output linear voltage stabilizer module is connected with a grounding pin of the negative voltage output linear voltage stabilizer module, the input pin of the negative voltage output linear voltage stabilizer module is connected with a power ground, a positive and negative bipolar power supply is generated by utilizing the voltage relativity, and output pins of the negative voltage output linear voltage stabilizer module respectively supply power for an instrument amplification module AD8220 and an instrument amplification module AD8642 in the myoelectricity acquisition and conversion circuit;
the positive voltage output linear voltage regulator module adopts LM7810 CT;
the negative voltage output linear voltage regulator module adopts LM7905 CT.
The embedded main control module is used for receiving and fusing multi-mode information data, and is specifically expressed as follows:
s1: the embedded main control module collects electromyographic signal data at a sampling frequency of 1000Hz, collects plantar pressure signal data at a sampling frequency of 1000Hz, collects limb acceleration signal data at a sampling frequency of 100Hz, and stores the multi-modal information data collected in parallel into a first-level cache region of the embedded main control module;
s2: under one working mode, a timer in the embedded main control module is used for timing, a clock signal in the embedded main control module is triggered once every 1ms, and after the embedded main control module captures the clock signal of 1ms, one frame of electromyographic signal data and one frame of plantar pressure signal data are read from a first-level cache region and stored in a second-level cache region for caching;
under one working mode, a timer in the embedded main control module is used for timing, a clock signal in the embedded main control module is triggered every 10ms, and after the embedded main control module captures the clock signal of 10ms, a frame of limb acceleration signal data is read from a first-level cache region and stored in a second-level cache region for caching;
s3: and the embedded main control module marks a time tag on the multi-mode information data cached in the secondary cache region to form a data packet, so that the multi-mode fusion work of the multi-mode information data is completed.
The embedded main control module is integrated with a TCP/IP network communication module, can be connected with a PC (personal computer) through a TCP/IP network communication protocol, and the upper layer board can be externally connected with an HDMI display screen through an HDMI line.
The embedded main control module adopts a four-core processor BCM2837 with a core of Cortex A-53;
the external limb acceleration sensor adopts a WT901C485 nine-axis sensor module;
the 5V power interface type is a micro USB type.
The invention has the beneficial effects that:
the invention provides an animator multi-mode information acquisition and fusion device for man-machine natural interaction, which is used for acquiring myoelectric signals for controlling the lower limb behaviors of a human body, acceleration signals for describing the lower limb behaviors and plantar pressure signals, and designing a multi-mode data acquisition and analysis processing hardware circuit system for fusing an animator sensor aiming at the problems that most of the existing man-machine cooperation systems adopt single type sensor data, so that the accuracy and the real-time performance of lower limb behavior identification cannot meet application requirements and the like. The system integrates data of three different types of sensors, the accuracy rate of lower limb behavior identification reaches more than 98% through feature extraction and analysis, and a high-speed data transmission protocol is adopted, so that the information interaction time of the whole man-machine cooperation system is shortened, the time of a single data acquisition and data integration process is less than 100ms, the time of single decoding of the overall signal features is less than 300ms, and the real-time requirement is met.
Drawings
FIG. 1 is a system block diagram of a living-machine multi-modal information acquisition and fusion device for man-machine natural interaction in the present invention;
FIG. 2 is a hardware structure diagram of the living organism multi-modal information collection and fusion device for man-machine natural interaction in the present invention;
FIG. 3 is a schematic diagram of an experimental system of the living-machine multi-modal information acquisition and fusion device for man-machine natural interaction in the present invention;
FIG. 4 is a schematic diagram of a myoelectric acquisition and conversion circuit of the bio-mechanical multi-modal information acquisition and fusion device for man-machine natural interaction in the present invention;
FIG. 5 is a schematic position diagram of a plantar pressure detection device of the bio-mechanical multi-modal information collection and fusion device for man-machine natural interaction in the present invention;
FIG. 6 is a schematic design diagram of plantar pressure detection of the living-machine multi-modal information acquisition and fusion device for man-machine natural interaction in the present invention;
FIG. 7 is a schematic diagram of a power conversion circuit of the living organism multi-modal information collection and fusion device for man-machine natural interaction in the present invention;
FIG. 8 is a schematic diagram of a multi-modal data fusion processing mechanism of the bio-mechanical multi-modal information collection and fusion device for natural human-computer interaction in the present invention;
FIG. 9 is a data fusion programming flow chart of the living organism multi-modal information collection and fusion device for man-machine natural interaction in the present invention;
FIG. 10 is a schematic circuit diagram of an AD conversion module of the living organism multi-modal information collection and fusion device for man-machine natural interaction in the present invention;
in the figure, the power interface 1 and 12V, the power interface 2, the copper stud 3, the myoelectric signal expansion interface 4, the plantar contact state detection circuit and signal interface 5, the AD conversion module 6, the limb acceleration sensor interface 7-1, the upper data transmission interface 7-2, the lower data transmission interface 8, the embedded main control module, the power interface 9 and 5V, the AUX port 10, the AUX port 11, the power conversion chip 12, the plantar pressure detection device detection position point 13, the external limb acceleration sensor detection position point 14, the backpack 15 and the myoelectric signal acquisition device detection position point.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
As shown in fig. 1-2, a living organism multi-mode information acquisition and fusion device for man-machine natural interaction comprises a laminated structure of an upper layer design board and a lower layer design board, wherein the upper layer design board and the lower layer design board are supported by four copper studs arranged at four corners, the upper layer design board is provided with an embedded main control module 8, a 5V power supply interface 9, a limb acceleration sensor interface 6 and an upper layer data transmission interface 7-1, an external limb acceleration sensor arranged on a limb of a patient is connected into the limb acceleration sensor interface 6 through a USB-to-RS-485 debugging line, the limb acceleration sensor interface 6 is connected with the embedded main control module 8 through a USB communication protocol, limb acceleration signal data acquired by the external limb acceleration sensor is transmitted to the embedded main control module 8 through the limb acceleration sensor interface 6, one end of the 5V power supply interface 9 is connected with the embedded main, the other end of the 5V power interface 9 is connected with an external 5V power supply device, and 2.5A power supply equipment supplies power to the upper-layer design board;
the lower layer design board comprises a lower layer data transmission interface 7-2, an AUX port 10, a sole contact state detection circuit, a signal interface 4, an electromyographic acquisition and conversion circuit and a power supply conversion circuit, wherein an electromyographic signal acquisition device installed on the skin of a patient is connected to the AUX port 10 through a differential electrode wire, the other end of the AUX port 10 is connected with an amplification module AD8220 in the electromyographic acquisition and conversion circuit, and electromyographic signal data acquired by the electromyographic signal acquisition device is processed by the electromyographic acquisition and conversion circuit and then transmitted to the lower layer data transmission interface 7-2 through an SPI high-speed serial bus;
the plantar pressure detection device installed on the plantar of a patient is connected into a plantar contact state detection circuit and a signal interface 4 in a wired mode, the plantar contact state detection circuit and the signal interface 4 are connected with a lower-layer data transmission interface 7-2 through flying wires, the lower-layer data transmission interface 7-2 is connected with an upper-layer data transmission interface 7-1 through a data transmission line to achieve data transmission of an upper layer and a lower layer, external 12V power supply equipment is connected into a power conversion circuit through a 12V power interface 1 in the power conversion circuit, conversion between a 12V direct-current power supply and a +/-5V bipolar power supply is achieved through a positive and negative voltage linear voltage stabilizer module in the power conversion circuit, and +/-5V power supply voltage is provided for a myoelectricity acquisition and conversion circuit;
the limb acceleration sensor interface 6 is used for receiving limb acceleration signal data acquired by an external limb acceleration sensor;
one end of the limb acceleration sensor interface 6 is connected with the embedded main control module 8 through a USB communication protocol, one end of the limb acceleration sensor interface realizes cascade mounting of the accessed external limb acceleration sensor through an RS-485 serial bus, the external limb acceleration sensors which are cascaded on the serial bus adopt the same communication speed, communication addresses of different sensors are set through host computer software, and the embedded main control module 8 accesses each accessed external limb acceleration sensor in a polling register address mode through the limb acceleration sensor interface 6 to realize the acquisition work of limb acceleration signal data.
The external limb acceleration sensors are respectively arranged at the center of the body of a patient, the middle parts of thighs, the middle parts of crus and ankle joints of the patient, the directions of three-dimensional space coordinate systems of all the external limb acceleration sensors arranged on the same patient need to be kept consistent, the rotating directions all follow the right-hand rule, and the limb acceleration signal data acquired by the external limb acceleration sensors comprise three-axis acceleration (acceleration)a x，a y，a z) Three-axis angular velocity: (θ x，θ y，θ z) Three axes euler angle (gamma)x，γy，γz）。
The AUX port 10 is used for receiving electromyographic signal data acquired by the electromyographic signal acquisition device;
the myoelectricity acquisition and conversion circuit is designed as follows: myoelectric signal data input through an AUX port 10 is subjected to prepositive primary amplification through an instrument amplification module AD8220, the myoelectric signal data are amplified to a sampling range of an AD conversion module, then high-pass filtering, a Butterworth low-pass filter circuit and a band-stop filter are sequentially carried out to remove high-frequency noise and power frequency interference, finally the myoelectric signal data are subjected to secondary amplification and then input to an AD conversion module 5, conversion between analog quantity and digital quantity is realized through the AD conversion module 5, and the myoelectric signal data output through the AD conversion module 5 are input to an embedded main control module 8;
the AD conversion module 5 adopts an AD7606 multi-channel synchronous digital-to-analog conversion module supporting bipolar input to realize hardware synchronization of multi-channel surface electromyogram signals, and two AD7606 channels are carried in parallel in the AD conversion module 5 to realize parallel synchronous sampling of 16 channels;
the butterworth low pass filter circuit is designed with an AD8642 amplifier.
The sole contact state detection circuit and the signal interface 4 are used for receiving and processing sole pressure signal data acquired by the sole pressure detection device;
the detection circuit in sole contact state detection circuitry and signal interface 4 adopts the contact state of two parallel switches detection sole and ground, contact state includes suspension state and contact state, suspension state means that the foot leaves the ground and is in suspension state, the contact state means that the foot touches ground, it marks as suspension state to define the high level, and show with figure 1, it marks as contact state to define the low level, and show with figure 0, embedded host system continuously reads GPIO port state, when being low level 0, it touches ground to show the foot, when being high level 1, it is in suspension state to show the foot leaves ground.
The electromyographic signal acquisition and conversion circuit is used for carrying out signal processing on electromyographic signal data and converting the electromyographic signal data after the signal processing into a digital quantity signal, and the signal processing comprises primary signal amplification, high-pass filtering, low-pass filtering, secondary signal amplification and power frequency interference removal;
the power supply conversion circuit is used for converting an external 12V direct-current power supply into +/-5V voltage;
the power conversion circuit is designed as follows: the 12V direct current power supply input by the 12V power supply equipment is connected with an input pin of the positive voltage output linear voltage stabilizer module, an output pin of the positive voltage output linear voltage stabilizer module is connected with a grounding pin of the negative voltage output linear voltage stabilizer module, the input pin of the negative voltage output linear voltage stabilizer module is connected with a power ground, a positive and negative bipolar power supply is generated by utilizing the voltage relativity, and output pins of the negative voltage output linear voltage stabilizer module respectively supply power for an instrument amplification module AD8220 and an instrument amplification module AD8642 in the myoelectricity acquisition and conversion circuit;
the positive voltage output linear voltage regulator module adopts LM7810 CT;
the negative voltage output linear voltage regulator module adopts LM7905 CT.
The 5V power interface 9 is used for externally connecting 5V power supply equipment to meet the 5V power supply requirement of the embedded main control module 8;
the embedded main control module 8 is used for receiving and fusing multi-mode information data, wherein the multi-mode information data comprises limb acceleration signal data, myoelectric signal data and plantar pressure signal data.
The embedded main control module 8 is integrated with a TCP/IP network communication module, can be connected with a PC (personal computer) through a TCP/IP network communication protocol, and can be externally connected with an HDMI display screen through an HDMI line to display a data processing result.
The embedded main control module 8 adopts a four-core processor BCM2837 with a core of Cortex A-53;
the external limb acceleration sensor adopts a WT901C485 nine-axis sensor module;
the 5V power interface 9 is of a micro USB type.
As shown in fig. 2, in the data collecting part of the limb acceleration signal in this embodiment, the limb acceleration sensor interface 6 is designed on the upper design board, the limb acceleration sensor interface 6 is connected to the USB-to-RS-485 debugging line and connected to the external limb acceleration sensor, the external limb acceleration sensor is a WT901C485 nine-axis sensor module, the 5V power interface 9 is of a micro USB type, the 5V and 2.5A power supplies power to the upper design board, the embedded main control module 8 is a core-Cortex a-53 four-core processor BCM2837, and uses a serial bus to realize the cascade operation of a plurality of external limb acceleration sensors, the plurality of external limb sensors cascaded on the serial bus use the same communication rate, and different device addresses can be set through upper computer software MiniIMU, the embedded main control module 8 accesses the connected limb acceleration sensors in a polling register address manner, meanwhile, the upper layer design board can be connected with a PC (personal computer) through a TCP/IP (transmission control protocol/Internet protocol) network communication protocol and can be externally connected with an HDMI (high-definition multimedia interface) display screen to display a data processing result.
In the embodiment, the electromyographic signal data acquisition part acquires electromyographic signals through a wet electrode sheet directly attached to the skin of a human body, and sequentially performs signal conditioning modes such as primary signal amplification, high-pass filtering, low-pass filtering, secondary signal amplification, power frequency interference removal and the like on the human body electromyographic signals according to the characteristics of weak and easy interference of the human body electromyographic signals, wherein 6 AUX ports 10 and 6 electromyographic signal expansion interfaces 3 are designed in the device, a differential electrode input mode is adopted in an experiment to pick up weak electromyographic signal data, the weak electromyographic signal data are input from the AUX ports 10, the primary amplification is realized through an instrument amplification module AD8220, the electromyographic signals are amplified to the sampling range of an AD conversion module 5, meanwhile, the amplification module AD8200 has higher common mode rejection ratio, the common mode interference can be effectively inhibited when the electromyographic signals generated by the human body are differential, and the low-frequency, after the first-stage amplification, the direct current component in the electromyographic signal is also amplified, so that the direct current signal and part of high-frequency noise are filtered by the filter circuit before the second-stage amplification, in this embodiment, the AD8642 amplifier is adopted to design a butterworth low-pass filter circuit and a band-elimination filter to remove the influence of the high-frequency noise and power frequency interference, then the processed electromyographic signal is input to the AD conversion module 5 through the second-stage amplification, and the AD conversion module 5 adopts an AD7606 multi-channel synchronous digital-to-analog conversion module supporting bipolar input, so that the hardware synchronization of the multi-channel surface electromyographic signal is realized. A single AD7606 module can synchronously sample and convert data of up to 8 channels with 16-bit conversion precision, the synchronous sampling rate can reach 200kHz, and the data are parallelly output to the embedded main control module 8 through the SPI high-speed serial transmission interface.
In the sole pressure signal data acquisition part in the embodiment, a double parallel switch is used for detecting the contact state of a sole and the ground, a high level mark suspension state and a low level mark contact state are designed and respectively represented by numbers 1 and 0, a sole pressure detection device is connected to a GPIO port on an embedded main control module 8 through a lead and is connected with the GPIO port, the embedded main control module continuously reads the state of the GPIO port, and when the low level is 0, the foot is shown to be in contact with the ground; when the signal level is high level 1, it indicates that the foot is in a suspended state away from the ground, a schematic position diagram of the sole pressure detection device is shown in fig. 5, and a schematic design diagram of the sole pressure detection principle is shown in fig. 6, where the resistors R1, R2, and R3 need to satisfy R1= R2> > R3.
In the embodiment, the myoelectric signal finally changes in a range of +/-5V, and accordingly, the AD7606 module must be set in a working mode of +/-5V range through a hardware port, and therefore, a 12V power input by the 12V power interface 1 needs to be converted to a voltage of +/-5V for supplying power, the power supply in the device is designed to use a linear voltage regulator module LM7810CT outputting a positive voltage and a linear voltage regulator module LM7905CT outputting a negative voltage, a schematic diagram of the power supply conversion circuit is shown in fig. 7, the 12V power serves as an input voltage of LM7810CT, the LM7810CT outputs a stable 10V voltage and inputs the voltage to the ground of the LM7905CT, the power ground of the device is connected to the input end of the LM7905CT, so as to realize the input of-10V to the LM7905CT, at this time, the LM79 7905CT outputs a voltage of-5V, and the output end of the LM7810CT outputs a voltage value higher than the output end of the LM7905CT, that is 5V, that is the voltage value, when the myoelectricity acquisition and conversion circuit is designed, the ground end of the acquisition circuit is connected with the output end of the LM7905CT, so that +/-5V voltage relative to signal ground is generated, a 12V direct-current power supply is converted into a +/-5V bipolar power supply by the power supply conversion circuit, the requirement of a chip power supply is met, the myoelectricity acquisition and conversion circuit is directly powered, and the hardware corresponding to the power supply conversion circuit is a power supply conversion chip 11 in the figure 2;
the embedded main control module 8 is configured to receive and fuse multimodal information data, and the programming language adopted is C/C + +, and a programming flow chart of the embedded main control module is shown in fig. 9 and specifically expressed as:
s1: the embedded main control module 8 collects electromyographic signal data at a sampling frequency of 1000Hz, collects plantar pressure signal data at a sampling frequency of 1000Hz, collects limb acceleration signal data at a sampling frequency of 100Hz, and stores the multi-modal information data collected in parallel into a first-level cache region of the embedded main control module 8;
s2: under one working mode, a timer in the embedded main control module 8 is used for timing, a clock signal in the embedded main control module 8 is triggered once every 1ms, and after the embedded main control module captures the clock signal of 1ms, a frame of electromyographic signal data and a frame of plantar pressure signal data are read from a first-level cache region and stored in a second-level cache region for caching;
in one working mode, a timer in the embedded main control module 8 is used for timing, a clock signal in the embedded main control module 8 is triggered every 10ms, and after the embedded main control module 8 captures the clock signal of 10ms, a frame of limb acceleration signal data is read from a first-level cache region and stored in a second-level cache region for caching;
s3: the embedded main control module 8 marks the multi-mode information data cached in the secondary cache region with a time tag to form a data packet, and thus, multi-mode fusion work of the multi-mode information data is completed.
The acquisition system of the invention acquires three signal data, each signal acquisition has corresponding circuit hardware design, correspondingly, the sampling frequency, sampling speed and data format of various acquired signals are different, and in order to realize synchronous fusion of the three signal data and optimize characteristic sample data, the invention adopts a data fusion mechanism of parallel acquisition and synchronous cache.
The acquisition device initially realizes the respective sampling of three signals in a data acquisition part, the electromyographic signals realize the 1000Hz synchronous sampling of multi-channel electromyographic signals through an AD7606 module, the limb acceleration signals realize the synchronization under the sampling frequency of 100Hz, the plantar pressure signals realize the synchronization through a GPIO port of an embedded main control module 8, and further the synchronous fusion of the three signals is considered.
In the actual experiment process, considering the delay effect caused by a plurality of factors of program operation, the system collects electromyographic signal data at the frequency slightly higher than 1000Hz, collects plantar pressure signal data at the same frequency, collects limb acceleration signal data at the frequency slightly higher than 100Hz, the parallelly collected signal data is firstly stored in a first-level cache, a timer is used for timing, a clock signal is triggered every 1ms, the system immediately captures the clock signal, a counting variable is increased, the system reads a frame of electromyographic signal data and plantar pressure signal data from the first-level cache and stores the data in a second-level cache, the limb acceleration signal data is read from the first-level cache every 10ms and stores the data in a second-level cache, and at the moment, a time label is marked on the second-level cache data to form a data packet, so that the multi-mode fusion of the three data is completed.
During the experiment, the system is placed in a backpack 14 carried by an experimental patient, and the gait recognition experiment of the lower limb behavior is used for recognizing the gait state of a single leg. Taking the right leg as an example, a wet electrode is attached to two gastrocnemius muscles of lower limb rectus femoris, vastus medialis, vastus lateralis and crus, and is taken as a mounting position point 15 of an electromyographic signal acquisition device, and is directly connected to the acquisition device by a differential electrode wire, and in view of that the position change of the lower limbs of a human body can be regarded as the space link motion among the trunk, the thighs and the crus of the human body approximately, the behavior motion mode identification of the lower limbs is realized by analyzing the mutual motion relation among the three, therefore, the experiment selects the center of the trunk of the human body, the side surfaces of the thighs, the side surfaces of the crus and the ankle joints as external limb acceleration sensor detection position points 13, each limb acceleration sensor is connected to the acquisition device through RS-485 buses in series, the sole pressure detection devices are arranged at the soles, the system of the invention takes less than 100ms from data acquisition to multi-mode data fusion, the whole process takes less than 100ms, the device of the invention is communicated with a computer through a TCP/IP protocol, the characteristic extraction, the characteristic analysis, the model training and the mode identification are further completed, the single decoding time of the whole signal characteristic is less than 300ms, the real-time requirement is met, the schematic diagram of the experimental system is shown in figure 3, the electromyographic signal acquisition device adopts a wet electrode sheet which can be directly attached to a human body to acquire electromyographic signal data, the model of the limb acceleration sensor is WT901C485 nine-axis sensor module, the limb acceleration sensors are mainly distributed in the center of the body, the middle of the thigh, the middle of the calf and the ankle joint of the human body, the coordinate systems of all the limb acceleration sensors keep consistent, the rotating directions all follow the right hand rule, the acquired limb, The three-axis angular velocity and the three-axis Euler angles are nine data, the plantar pressure detection device is made of TPU materials through 3D printing and forming, the plantar pressure detection device is attached to a sole in a wearing mode, and the specific structure is disclosed in the invention patent of wearable plantar-ground contact force measurement device and method for accurately identifying gait (application number is 201910326488. X). Note that in order to ensure the graphical effect, the limb acceleration module is placed at the left leg position for display, and should be placed at the corresponding position of the right leg during the experiment.
Claims (9)
1. An in-person multi-mode information acquisition and fusion device for man-machine natural interaction is characterized in that the device is of a laminated structure comprising an upper layer of design board and a lower layer of design board, the upper layer of design board and the lower layer of design board are supported by four copper studs arranged at four corners, the upper layer of design board is provided with an embedded main control module, a 5V power supply interface, a limb acceleration sensor interface and an upper layer data transmission interface, an external limb acceleration sensor arranged on a limb of a patient is connected into the limb acceleration sensor interface through a USB-RS-485 serial bus, the limb acceleration sensor interface is connected with the embedded main control module through a USB communication protocol, limb acceleration signal data acquired by the external limb acceleration sensor is transmitted to the embedded main control module through the limb acceleration sensor interface, one end of the 5V power supply interface is connected with the, the other end of the 5V power interface is connected with external 5V power supply equipment;
the lower layer design board comprises a lower layer data transmission interface, an AUX port, a sole contact state detection circuit, a signal interface, a myoelectric acquisition and conversion circuit and a power supply conversion circuit, wherein an myoelectric signal acquisition device arranged on the skin of a patient is connected into the AUX port through a differential electrode wire, the other end of the AUX port is connected with an amplification module AD8220 in the myoelectric acquisition and conversion circuit, myoelectric signal data acquired by the myoelectric signal acquisition device is processed by the myoelectric acquisition and conversion circuit and then transmitted to the lower layer data transmission interface through an SPI high-speed serial bus, a sole pressure detection device arranged on the sole of the patient is connected into the sole contact state detection circuit and the signal interface in a wired mode, the sole contact state detection circuit and the signal interface are connected with the lower layer data transmission interface through flying wires, and the lower layer data transmission interface is connected with the upper layer data transmission interface through a data, the data transmission of an upper layer and a lower layer is realized, the external 12V power supply equipment is connected to the power supply conversion circuit through a 12V power supply interface in the power supply conversion circuit, the conversion of a 12V direct-current power supply and a +/-5V bipolar power supply is realized through a positive and negative voltage linear voltage stabilizer module in the power supply conversion circuit, and a +/-5V power supply voltage is provided for the myoelectricity acquisition and conversion circuit;
the limb acceleration sensor interface is used for receiving limb acceleration signal data acquired by the external limb acceleration sensor;
the AUX port is used for receiving electromyographic signal data acquired by the electromyographic signal acquisition device;
the sole contact state detection circuit and the signal interface are used for receiving and processing sole pressure signal data acquired by the sole pressure detection device;
the electromyographic signal acquisition and conversion circuit is used for carrying out signal processing on electromyographic signal data and converting the electromyographic signal data after the signal processing into a digital quantity signal, and the signal processing comprises primary signal amplification, high-pass filtering, low-pass filtering, secondary signal amplification and power frequency interference removal;
the power supply conversion circuit is used for converting an external 12V direct-current power supply into +/-5V voltage;
the 5V power supply interface is used for externally connecting 5V power supply equipment to meet the 5V power supply requirement of the embedded main control module;
the embedded main control module is used for receiving and fusing multi-mode information data, and the multi-mode information data comprises limb acceleration signal data, myoelectric signal data and plantar pressure signal data.
2. The bio-mechanical multi-modal information acquisition and fusion device for man-machine natural interaction according to claim 1, wherein the detection circuit in the sole contact state detection circuit and the signal interface detects the contact state of the sole and the ground by using a double parallel switch, the contact state comprises a suspension state and a contact state, the suspension state refers to the state that the foot leaves the ground and is suspended, the contact state refers to the state that the foot contacts the ground, a high level mark is defined as the suspension state and is represented by a number 1, a low level mark is defined as the contact state and is represented by a number 0, the embedded main control module continuously reads the state of the GPIO port, when the low level is 0, the foot contacts the ground, and when the high level is 1, the foot leaves the ground and is suspended.
3. The living organism multi-mode information acquisition and fusion device for man-machine natural interaction as claimed in claim 1, wherein the external limb acceleration sensors are respectively installed at the center of the body of the patient, the middle of the thigh, the middle of the calf and the ankle joint of the patient, the directions of the three-dimensional space coordinate systems of all the external limb acceleration sensors installed on the same patient need to be kept consistent, the rotation directions all follow the right-hand rule, and the limb acceleration signal data acquired by the external limb acceleration sensors include three-axis acceleration (acceleration of three axes: (a)a x，a y，a z) Three-axis angular velocity: (θ x，θ y，θ z) Three axes euler angle (gamma)x，γy，γz）。
4. The living machine multi-mode information acquisition and fusion device for man-machine natural interaction as claimed in claim 1, wherein one end of the limb acceleration sensor interface is connected with the embedded main control module through a USB communication protocol, the other end of the limb acceleration sensor interface realizes cascade mounting of the accessed external limb acceleration sensor through an RS-485 serial bus, the external limb acceleration sensors which are cascaded on the serial bus adopt the same communication speed, communication addresses of different sensors are set through upper computer software, and the embedded main control module accesses each accessed external limb acceleration sensor in a polling register address mode through the limb acceleration sensor interface to realize acquisition work of limb acceleration signal data.
5. The living organism multi-modal information collection and fusion device for man-machine natural interaction of claim 1, wherein the myoelectric collection and conversion circuit is designed as follows: electromyographic signal data input through an AUX port is subjected to preposed primary amplification through an instrument amplification module AD8220, the electromyographic signal data are amplified to a sampling range of an AD conversion module, then high-frequency noise and power frequency interference are removed through a high-pass filter, a Butterworth low-pass filter circuit and a band-stop filter in sequence, finally the electromyographic signal data are input to the AD conversion module after secondary amplification, and the electromyographic signal data output by the AD conversion module are input to an embedded main control module;
the AD conversion module adopts an AD7606 multi-channel synchronous digital-to-analog conversion module supporting bipolar input to realize hardware synchronization of multi-channel surface electromyogram signals, and two AD7606 channels are carried in parallel in the AD conversion module to realize parallel synchronous sampling of 16 channels;
the butterworth low pass filter circuit is designed with an AD8642 amplifier.
6. The living organism multi-modal information collection and fusion device for man-machine natural interaction of claim 1, wherein the power conversion circuit is designed as follows: the 12V direct current power supply input by the 12V power supply equipment is connected with an input pin of the positive voltage output linear voltage stabilizer module, an output pin of the positive voltage output linear voltage stabilizer module is connected with a grounding pin of the negative voltage output linear voltage stabilizer module, the input pin of the negative voltage output linear voltage stabilizer module is connected with a power ground, a positive and negative bipolar power supply is generated by utilizing the voltage relativity, and output pins of the negative voltage output linear voltage stabilizer module respectively supply power for an instrument amplification module AD8220 and an instrument amplification module AD8642 in the myoelectricity acquisition and conversion circuit;
the positive voltage output linear voltage regulator module adopts LM7810 CT;
the negative voltage output linear voltage regulator module adopts LM7905 CT.
7. The living organism multi-modal information collection and fusion device for man-machine natural interaction according to claim 1, wherein the embedded main control module is used for receiving and fusing multi-modal information data, and is specifically expressed as:
s1: the embedded main control module collects electromyographic signal data at a sampling frequency of 1000Hz, collects plantar pressure signal data at a sampling frequency of 1000Hz, collects limb acceleration signal data at a sampling frequency of 100Hz, and stores the multi-modal information data collected in parallel into a first-level cache region of the embedded main control module;
s2: under one working mode, a timer in the embedded main control module is used for timing, a clock signal in the embedded main control module is triggered once every 1ms, and after the embedded main control module captures the clock signal of 1ms, one frame of electromyographic signal data and one frame of plantar pressure signal data are read from a first-level cache region and stored in a second-level cache region for caching;
under one working mode, a timer in the embedded main control module is used for timing, a clock signal in the embedded main control module is triggered every 10ms, and after the embedded main control module captures the clock signal of 10ms, a frame of limb acceleration signal data is read from a first-level cache region and stored in a second-level cache region for caching;
s3: and the embedded main control module marks a time tag on the multi-mode information data cached in the secondary cache region to form a data packet, so that the multi-mode fusion work of the multi-mode information data is completed.
8. The living machine multi-mode information acquisition and fusion device for man-machine natural interaction as claimed in claim 1, wherein the embedded main control module is integrated with a TCP/IP network communication module, and can be connected with a PC machine through a TCP/IP network communication protocol, and the upper layer board can be externally connected with an HDMI display screen through an HDMI cable.
9. The living-machine multi-modal information collection and fusion device for man-machine natural interaction of claim 1, wherein the embedded master control module employs a four-core processor BCM2837 with a core of Cortex a-53;
the external limb acceleration sensor adopts a WT901C485 nine-axis sensor module;
the 5V power interface type is a micro USB type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010322650.3A CN111481197B (en) | 2020-04-22 | 2020-04-22 | A living-machine multimode information acquisition fuses device for man-machine natural interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010322650.3A CN111481197B (en) | 2020-04-22 | 2020-04-22 | A living-machine multimode information acquisition fuses device for man-machine natural interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111481197A CN111481197A (en) | 2020-08-04 |
| CN111481197B true CN111481197B (en) | 2021-01-26 |
Family
ID=71789700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010322650.3A Active CN111481197B (en) | 2020-04-22 | 2020-04-22 | A living-machine multimode information acquisition fuses device for man-machine natural interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111481197B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112704491B (en) * | 2020-12-28 | 2022-01-28 | 华南理工大学 | Lower limb gait prediction method based on attitude sensor and dynamic capture template data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103876756A (en) * | 2014-04-18 | 2014-06-25 | 南京工程学院 | Lower limb power-assisted exoskeleton robot gait pattern identification method and system |
| CN107454742A (en) * | 2016-04-01 | 2017-12-08 | 三星电子株式会社 | Printed circuit board (PCB) and the electronic installation including the printed circuit board (PCB) |
| WO2018198571A1 (en) * | 2017-04-28 | 2018-11-01 | 日東電工株式会社 | Laminate for biosensor and method for producing laminate for biosensor |
| US10588004B2 (en) * | 2006-05-16 | 2020-03-10 | RedSky Technologies, Inc. | Method and system for locating a network device in an emergency situation |
| CN111035362A (en) * | 2018-10-12 | 2020-04-21 | 德普伊新特斯产品公司 | Wireless neuromuscular sensing device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103584857B (en) * | 2013-12-02 | 2016-06-15 | 上海海事大学 | From the portable motor electrical signal collection device of storage |
| US10022614B1 (en) * | 2016-05-02 | 2018-07-17 | Bao Tran | Smart device |
| US10378975B1 (en) * | 2018-01-27 | 2019-08-13 | Nextiles Inc. | Systems, methods, and devices for static and dynamic body measurements |
| CN209347928U (en) * | 2018-11-11 | 2019-09-06 | 上海诺昊医疗科技有限公司 | Gait correcting instrument |
| CN109876428A (en) * | 2019-03-22 | 2019-06-14 | 五邑大学 | A kind of body-sensing device, game machine and limb action signal processing method |
-
2020
- 2020-04-22 CN CN202010322650.3A patent/CN111481197B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10588004B2 (en) * | 2006-05-16 | 2020-03-10 | RedSky Technologies, Inc. | Method and system for locating a network device in an emergency situation |
| CN103876756A (en) * | 2014-04-18 | 2014-06-25 | 南京工程学院 | Lower limb power-assisted exoskeleton robot gait pattern identification method and system |
| CN107454742A (en) * | 2016-04-01 | 2017-12-08 | 三星电子株式会社 | Printed circuit board (PCB) and the electronic installation including the printed circuit board (PCB) |
| WO2018198571A1 (en) * | 2017-04-28 | 2018-11-01 | 日東電工株式会社 | Laminate for biosensor and method for producing laminate for biosensor |
| CN111035362A (en) * | 2018-10-12 | 2020-04-21 | 德普伊新特斯产品公司 | Wireless neuromuscular sensing device |
Non-Patent Citations (4)
| Title |
|---|
| A soft robotic hand: design, analysis, sEMG control, and experiment;Naishi Feng等;《The International Journal of Advanced Manufacturing Technology》;20181231;第97卷;第319-333页 * |
| Improved prosthetic hand control with concurrent use of myoelectric and inertial measurements;Agamemnon Krasoulis等;《Journal of NeuroEngineering and Rehabilitation》;20171231;第1-14页 * |
| 基于虚拟仪器技术的肌肉电信号测量***;赵长宽 等;《仪器仪表学报》;20060630;第27卷(第6期);第435-437页 * |
| 基于虚拟仪器的多通道MEMS 加速度计自动化测试***;明安杰 等;《红外与激光工程》;20140630;第43卷(第6期);第1955-1959页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111481197A (en) | 2020-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107553499A (en) | Natural the gesture motion control system and method for a kind of Multi-shaft mechanical arm | |
| CN107397649B (en) | Upper limb exoskeleton movement intention identification method based on radial basis function neural network | |
| Bright et al. | EEG-based brain controlled prosthetic arm | |
| WO2017092225A1 (en) | Emg-based wearable text input system and method | |
| CN105415374B (en) | Robotic transfer unit online system failure diagnosis based on cooperative | |
| CN103777752A (en) | Gesture recognition device based on arm muscle current detection and motion sensor | |
| CN107856014B (en) | Mechanical arm pose control method based on gesture recognition | |
| CN109215774B (en) | Real-time remote pulse-taking system and working method thereof | |
| CN107616898B (en) | Upper limb wearable rehabilitation robot based on daily actions and rehabilitation evaluation method | |
| CN105232052A (en) | Device for recognizing human lower limbs movement posture by virtue of combined sensor | |
| CN110058691A (en) | Based on Embedded wearable wireless dry electrode brain wave acquisition processing system and method | |
| CN205318387U (en) | Multinode parkinson disease symptom ration evaluation device | |
| CN110537921A (en) | Portable gait multi-sensing data acquisition system | |
| CN111481197B (en) | A living-machine multimode information acquisition fuses device for man-machine natural interaction | |
| JP2022544793A (en) | Methods and systems for analyzing biomechanical activity and exposure to biomechanical risk factors for a subject in the context of physical activity | |
| CN105411594A (en) | Novel sensor used for collecting human motion signals | |
| CN205508194U (en) | Intelligence gloves | |
| Tam et al. | A wearable wireless armband sensor for high-density surface electromyography recording | |
| CN203829261U (en) | Data collecting and processing system for upper limb rehabilitation robots | |
| CN104227733A (en) | Human-body-induced mechanical arm | |
| CN113627500A (en) | Gait information acquisition system based on multi-sensor fusion and recognition algorithm | |
| CN108784694A (en) | A kind of signal acquisition circuit, signal acquisition method and wearable device | |
| CN110103226B (en) | Auxiliary robot control method and system | |
| CN111714129A (en) | Human gait information acquisition system | |
| CN110624217A (en) | Rehabilitation glove based on multi-sensor fusion and implementation method thereof |
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 |