CN105561567A - Step counting and motion state evaluation device - Google Patents

Step counting and motion state evaluation device Download PDF

Info

Publication number
CN105561567A
CN105561567A CN201511017130.7A CN201511017130A CN105561567A CN 105561567 A CN105561567 A CN 105561567A CN 201511017130 A CN201511017130 A CN 201511017130A CN 105561567 A CN105561567 A CN 105561567A
Authority
CN
China
Prior art keywords
information
feature
motion
feature extraction
carried out
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.)
Granted
Application number
CN201511017130.7A
Other languages
Chinese (zh)
Other versions
CN105561567B (en
Inventor
陈思同
陈香
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Science and Technology of China USTC
Original Assignee
University of Science and Technology of China USTC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by University of Science and Technology of China USTC filed Critical University of Science and Technology of China USTC
Priority to CN201511017130.7A priority Critical patent/CN105561567B/en
Publication of CN105561567A publication Critical patent/CN105561567A/en
Application granted granted Critical
Publication of CN105561567B publication Critical patent/CN105561567B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
    • A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
    • A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
    • A63B71/0669—Score-keepers or score display devices
    • 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
    • A61B5/1123—Discriminating type of movement, e.g. walking or running
    • 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
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B2220/00—Measuring of physical parameters relating to sporting activity
    • A63B2220/80—Special sensors, transducers or devices therefor
    • A63B2220/803—Motion sensors
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B2220/00—Measuring of physical parameters relating to sporting activity
    • A63B2220/80—Special sensors, transducers or devices therefor
    • A63B2220/83—Special sensors, transducers or devices therefor characterised by the position of the sensor
    • A63B2220/836—Sensors arranged on the body of the user
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B2230/00—Measuring physiological parameters of the user
    • A63B2230/60—Measuring physiological parameters of the user muscle strain, i.e. measured on the user

Abstract

The invention discloses a step counting and motion state evaluation device. According to the step counting and motion state evaluation device, motion posture characteristics are acquired by using a motion sensor, muscle activity levels are acquired by using a multi-channel surface myoelectricity sensor, and with the combination of the motion posture and the muscle activity degree, the steps in different motion modes can be counted, and the calorie consumption can be calculated. With the combination of a surface myoelectricity pedometer and an analysis device, the step counting and motion state evaluation device is relatively professional when being compared with a conventional pedometer, relatively rich muscle physiological information can be provided, and the step counting and motion state evaluation device is particularly applicable to motion and rehabilitation evaluation.

Description

A kind of meter step and motion state apparatus for evaluating
Technical field
The present invention relates to motion and rehabilitation field, particularly relate to a kind of meter step and motion state apparatus for evaluating.
Background technology
Along with the development of embedded chip technology, the fields such as Wearable is widely used in athletic rehabilitation, health detection.The modal product of motion analysis is the meter step bracelet of Worn type pedometer and similar functions.Conventional meter step and analytical equipment are primarily of sensor, calculating section and display section composition.The signal that sensor produces in motion process for detecting user; Calculating section calculates step number according to signal and body moves status information; Display section is for showing step number and other bodies move feature, and some basic parameters such as time.At rehabilitation field, due to the impact of the diseases such as lower limb hemiplegia and astogeny, a lot of people loses normal ability to act, make one and can gather lower limb dynamic data and the portable wearable device realizing specific function assessment, the aid of exercise both can be provided to normal person, also can for and motor dysfunction of lower limb sufferer a kind of rehabilitation training evaluation measures is provided.
In existing meter step and analytical equipment, existing multiple take accelerometer as the pedometer of sensor, and such pedometer is recommended to be worn to waist, realizes step function.
In existing pedometer, existing multiple take mercoid switch as the pedometer of sensor, and such pedometer distinguishes motion state and rest state by the numerical value change of mercoid switch in motion.
In existing gait analysis device, there is a kind of portable gait information collecting device, be provided with electromyographic signal collection module, gyro module, plantar pressure sensor module, laser range finder, microprocessor, SD card module, display panel module.
In above-mentioned existing meter step and gait analysis device, pedometer and similar meter step bracelet only can realize the simple motion analysis such as meter step, calorie consumption; Gait analysis device is mainly used in auxiliary walk lower limb sufferer and the elderly laboriously and completes rehabilitation training, for colony less.Therefore, need a kind of complete function, while having motion state evaluation function, the Wearable physiology of basic rehabilitation assessment and body can be provided to move signal processing and analysis device for the sufferer of lower limb obstacle.
Summary of the invention
The object of this invention is to provide a kind of meter step and motion state apparatus for evaluating, more muscle physiological information can be provided, be particularly useful for motion and rehabilitation assessment.
The object of the invention is to be achieved through the following technical solutions:
A kind of meter step and motion state apparatus for evaluating, comprising: multi-channel surface myoelectric sensor, motion sensor and main control unit; Wherein:
Described multi-channel surface myoelectric sensor, for gathering the myoelectric information on muscle group surface;
Described motion sensor, for motion track information;
Described main control unit, for the pattern set according to user, and in conjunction with the information that multi-channel surface myoelectric sensor and motion sensor collect, user movement situation is analyzed: if the pattern set is as counting step mode, then feature extraction is carried out to the information collected, then judge current action by feature identification and counting statistics and calorie calculating are carried out to motion; If the pattern of setting is exercise mode, then feature extraction is carried out to the information collected, and according to the feature extracted, motion state is assessed; If the pattern of setting is rehabilitation modality, then feature extraction being carried out to the information collected, and the feature extracted and the canonical reference masterplate preset are compared, when reaching the certain movement time or the many stack features that extract are abnormal, sending alarm.
Further, described main control unit, for the pattern set according to user, and the information collected in conjunction with multi-channel surface myoelectric sensor and motion sensor is analyzed user movement situation and is specifically comprised:
If the pattern set is as counting step mode, then feature extraction is carried out to the information collected, reference template under the age of the feature extracted and setting, body weight and height is carried out pattern-recognition, thus judge current action walking, run, ride, jump or go upstairs, and counting statistics is carried out to different motion and calorie calculates;
If the pattern of setting is exercise mode, then carry out feature extraction according to the information of S group action before starting under exercise mode, and generating reference feature, in subsequent action process, feature extraction is carried out to the information collected, and the feature extracted and described fixed reference feature are compared, the difficulty action accomplishment of subsequent action is assessed;
If the pattern of setting is rehabilitation modality, then feature extraction is carried out to the information collected, the feature extracted and the canonical reference masterplate preset are compared, when the many stack features extracted are abnormal, send alarm.
Further, described main control unit processes the information collected, and treatment step comprises:
After collecting fresh information, carry out active segment segmentation and feature extraction successively; Specific as follows:
Active segment is split: main control unit initializes all kinds of index variables, and wherein Active represents current and collects fresh information whether in active segment, and Last represents that the last time processes the sampling time at information place, and Cur represents the sampling time at current process information place;
If Cur-Last>W represents that the fresh information collected more than W sampling time not yet processes, then start to judge fresh information whether in active segment; If Active is that the information of single treatment before 1 expression is in active segment, as long as the Sample Entropy meeting current information is greater than the threshold value of regulation, then judge that current information is similarly in active segment, and according to the mode of sub-frame processing with 64 for step-length, 128 operations performing feature extraction for window is long; If current information Sample Entropy is less than defined threshold when Active is 1, then inactive segment counter adds 1; If inactive segment counter superposes continuously reach P herein, judge that now active segment exits completely;
Feature extraction:
For myoelectric information, extract temporal signatures absolute value average MAV, extract frequency domain character autoregression AR model coefficient;
The absolute value average MAV computing formula of electromyographic signal is:
MAV c = 1 N f Σ i = 1 N f | SEMG c ( i ) |
In formula, MAV refers to absolute value average, and c represents the surface myoelectric sensor passage corresponding to electromyographic signal, N ffor frame length, SEMG ci () represents the numerical value of c passage electromyographic signal i-th point collected;
The AR model coefficient of electromyographic signal adopts Burg algorithm to calculate;
Point frame technique is adopted to extract the feature of myoelectric information: the myoelectric information in an active segment is divided into multiple fragment, and each snippet extraction goes out a stack features, and use length is N f, step-length is S frolling average window mobile from the starting point of active segment, each mobile time window in the information that comprises all as all data in present frame, until terminate during data deficiencies below, abandon not enough part;
After framing, every frame data of every passage myoelectric information comprise 5 characteristic values: 1 MAV and 4 AR coefficient, and use length for N fhamming window filtering is carried out to every frame data, Hamming window computing formula is:
w i n ( n ) = 0.54 - 0.46 c o s c o s ( 2 π n N f - 1 ) ;
In formula, n=[0, N f-1];
For motion track information, sampling is computation of mean values and standard deviation also; Described motion sensor is integrated with 3 axis accelerometers, 3 axis angular rate meters and 3 axle magnetometers, and the feature of motion track information is every passage 64 sample points, totally 9 passages; Then i-th of 9 passages sample point is placed on the i-th row, forms the eigenmatrix that 64 row 9 arrange, wherein, i=[1,64].
Further, describedly carry out feature extraction according to the information of S group action before starting under exercise mode, and generating reference feature, in subsequent action process, feature extraction is carried out to the information collected, and the feature extracted and described fixed reference feature are compared, assessment is carried out to the difficulty action accomplishment of subsequent action and comprises:
Feature extraction is carried out to the information of S group action before starting under exercise mode, and calculates the barycenter of characteristic set, using barycenter as with reference to feature;
Feature extraction is carried out to the information after S group, and calculates the Euclidean distance of feature and the described fixed reference feature extracted, by this Euclidean distance index in the grade form preset, thus obtain corresponding scoring.
Further, feature extraction is carried out to the information collected, the feature extracted and the canonical reference masterplate preset is compared, when the many stack features extracted are abnormal, send alarm and comprise:
Described default canonical reference masterplate is set by the sex according to user, age, height and body weight;
After completing feature extraction, the feature extracted and the canonical reference masterplate preset are compared, judge that whether effectively and add up effective action this action; If when the many stack features extracted continuously are all greater than threshold value with the difference of the canonical reference masterplate preset, automatic alarm prompting user has a rest, and records the duration of this rehabilitation training.
Further, the information that multi-channel surface myoelectric sensor and motion sensor collect is read in the timing of described main control unit; Wherein:
The information that multi-channel surface myoelectric sensor collects carries out analog-to-digital conversion by analog-digital converter ADC, when upgrading ADC sampling flag bit with 1kHz in timer interrupt program, main control unit reads the information after one group of ADC conversion by communication interface, ADC sampling mark is removed after the information of all passages after to be converted all reads, and by information stored in data buffer storage;
When upgrading motion sensor sampling flag bit with 100Hz in timer interrupt program, main control unit reads by communication interface the information that one group of motion sensor collects, and continues and takes rear removing motion sensor sampling mark, and by information stored in data buffer storage.
Further, this device also comprises:
Communication module, transmits for the data realizing main control unit and external equipment;
When main control unit is in the information that reading multi-channel surface myoelectric sensor and motion sensor collect, if the real-time display collection signal that user is configured with, then main control unit is by communication module, and real time data is sent to external equipment.
Further, this device also comprises: program storage unit (PSU) and data storage card;
Described program storage unit (PSU), for supplying access data in system start-up and operation process;
Described data storage card, the reference template for storing feature identification, when comparing and canonical reference masterplate, and the information that collects of multi-channel surface myoelectric sensor and motion sensor and analysis result.
Further, this device also comprises:
Display floater, described display floater comprises: regulate button and display screen;
Described adjustment button is for setting present mode as meter step mode, exercise mode or rehabilitation modality; Described display screen is for showing the movable information under each pattern.
As seen from the above technical solution provided by the invention, athletic posture feature is gathered by motion sensor, muscle activity level is gathered by multi-channel surface myoelectric sensor, in conjunction with athletic posture and muscle activity degree, gait under different motion pattern is counted and calculates caloric consumption.The relatively existing pedometer of the pedometer of mating surface myoelectricity and analytical equipment is more professional, can provide more muscle physiological information, is particularly useful for motion and rehabilitation assessment.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
A kind of schematic diagram counting step and motion state apparatus for evaluating that Fig. 1 provides for the embodiment of the present invention;
The electrode topologies figure that Fig. 2 provides for the embodiment of the present invention;
The specific works flow process figure of the main control module that Fig. 3 provides for the embodiment of the present invention;
The flow chart of the information that multi-channel surface myoelectric sensor and motion sensor collect is read in the main control unit timing that Fig. 4 provides for the embodiment of the present invention;
The process chart of the meter step mode that Fig. 5 provides for the embodiment of the present invention;
What Fig. 6 provided for the embodiment of the present invention carries out to the information collected the flow chart that Classification and Identification is carried out in feature extraction again;
Point frame technique schematic diagram that Fig. 7 provides for the embodiment of the present invention;
Process chart under the exercise mode that Fig. 8 provides for the embodiment of the present invention;
Process chart under the rehabilitation modality that Fig. 9 provides for the embodiment of the present invention;
The meter step mode situation schematic diagram that Figure 10 provides for the embodiment of the present invention;
The exercise mode situation schematic diagram that Figure 11 provides for the embodiment of the present invention;
The rehabilitation modality situation schematic diagram that Figure 12 provides for the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on embodiments of the invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to protection scope of the present invention.
The embodiment of the present invention provides a kind of meter step and motion state apparatus for evaluating (calling this device in the following text), it gathers athletic posture feature by motion sensor, muscle activity level is gathered by myoelectric sensor, in conjunction with athletic posture and muscle activity degree, gait under different motion pattern is counted and calculates caloric consumption.The relatively existing pedometer of the pedometer of mating surface myoelectricity and analytical equipment is more professional, can provide more muscle physiological information, is particularly useful for motion and rehabilitation assessment.
As shown in Figure 1, this device mainly comprises: multi-channel surface myoelectric sensor 110, motion sensor 120, main control unit 130, analog-digital converter (ADC chip 140), communication module 150, display floater 160, program storage unit (PSU) 170, data storage card 180; Main control unit 130 is communicated with miscellaneous part by bus.
Be described in detail for each parts below:
1, multi-channel surface myoelectric sensor.
In the embodiment of the present invention, described multi-channel surface myoelectric sensor, it comprises multiple electrode channel that can gather the myoelectric information on muscle group surface, and port number K can select according to actual conditions, such as, selectable channel number K=6.In the embodiment of the present invention, described multi-channel surface myoelectric sensor can be arranged in elastic bands according to certain intervals, can be tied on shank or arm and use.
Electrode is dry type list differential electrode, electrode topologies as shown in Figure 2, two the grey round dots in left side represent silver differential electrode, and surface electromyogram signal is through electrode to instrument amplifier, and instrument amplifier reduces various extraneous common-mode noise to greatest extent while amplifying faint electromyographic signal.
The apparatus design that the embodiment of the present invention provides uses the high-pass filter of cut-off frequency 20Hz to wear because of the signal tail that dislocation of electrode brings in process with filtering at instrument amplifier end, and multiplication factor and cut-off frequency arrange as follows, and the real part of G is multiplication factor.
G = 1 + 49.4 K R 1 + 1 j w · C 5 , Re a l ( G ) = 1 + 49.4 K 150 ≈ 330 ;
f G = 1 2 π · 150 · 47 u F ≈ 22 H z ;
In formula, R1 and C5 is Fig. 2 China National Instruments Import & Export Corporation amplifier element, R1 and C5 connects the elementary multiplication factor of adjustable myoelectric sensor, can play the effect of high-pass filtering simultaneously.49.4K is the intrinsic parameter of the instrumentation amplifier selected in the present embodiment; In the present embodiment, R1 gets 150 Ω, and C5 gets 47uF.
In addition, effective frequency range of surface electromyogram signal is 20Hz ~ 500Hz, and the high-frequency signal therefore adopting the filtering of Butterworth bandpass filter unnecessary in the rear end of instrument amplifier is in case stop signal aliasing.As the amplifier circuit on the right side of Fig. 2, the cut-off frequency of low pass and high pass is as follows, and the overall multiplication factor of circuit is R3/R2=1.47.
f L = 1 2 π · R 2 · C 6 = 1 2 π · 680 k · 22 n ≈ 10 H z
f H = 1 2 π · R 3 · C 7 = 1 2 π · 1 M · 330 p ≈ 480 H z
Secondary amplification is a bandpass filter, and R3 gets 1M Ω, and R2 gets 680K Ω, determines the multiplication factor of secondary amplification circuit; C6 gets 22nF, and R2, C6 determine this bandpass filter lower limiting frequency, and C7 gets 330pF, and R3, C7 determine this bandpass filter upper cut off frequency.
It should be noted that, the concrete numerical value of each components and parts involved in above-mentioned formula is only citing and is not construed as limiting.In real work, user can set according to the concrete numerical value of actual conditions to each components and parts.
2, ADC chip.
ADC chip, for converting the electromyographic signal of simulation to data signal.
3, motion sensor.
In the embodiment of the present invention, motion sensor is the motion sensor that can detect 3-axis acceleration signal, three axis angular rate signals and three axle magnetometer signals, as the sensor of acceleration and angular velocity detecting, general acceleration and angular-rate sensor can be adopted.
Preferably, nine axle sensors being integrated with accelerometer, gyroscope and electronic compass can also be adopted.Three axles of three axles of acceleration, three axles of angular speed and magnetometer are the intrinsic direction of this device, change along with the change of the attitude (direction, inclination, rotation) of device.
4, main control unit.
This main control unit has the interfaces such as SPI, I2C, the information that the information collected by data-interface reading multi-channel surface myoelectric sensor and motion sensor collect, and judge whether the experimenter carrying this device exists body kinematics with this, and effects on surface electromyographic signal and motor message carry out pattern-recognition and classification, finally realize statistics to dissimilar step number under meter step mode, and the assessment of moving in exercise mode and rehabilitation modality.
5, program storage unit (PSU)
Described program storage unit (PSU), for supplying access data in system start-up and operation process;
Specifically: program storage unit (PSU) can store and perform in this device programmed algorithm and program process from the template that exterior storage is loaded into, because pattern-recognition computing relates to a large amount of matrix multiple computing, in sheet, flash and RAM may not be enough to storage program and a large amount of characteristic; The embodiment of the present invention, is preferably Norflash.
6, data storage card
Described data storage card, the reference template for storing feature identification, when comparing and canonical reference masterplate, and the information that collects of multi-channel surface myoelectric sensor and motion sensor and analysis result.
In the embodiment of the present invention, exterior storage can select TF card, during system electrification, feature templates (reference template and canonical reference masterplate) is read in fortune from TF card and deposits, and uses as coupling during Classification and Identification; The motion conditions of specific time period can be parsed into form according to user's request and be stored in TF card by this device.
7, display floater,
Described display floater comprises: regulate button and display screen;
Described adjustment button is for setting present mode as meter step mode, exercise mode or rehabilitation modality; Described display screen is for showing the movable information under each pattern.
8, communication module
In the present embodiment, communication module can be serial ports type bluetooth module, transmits for the data realizing main control unit and external equipment; When main control unit is in the information that reading multi-channel surface myoelectric sensor and motion sensor collect, if user configures display Real-time Collection signal, then main control unit is by communication module, and real time data is sent to external equipment.
Being more than the composition structure of this device, for the ease of understanding, elaborating for its course of work below.
In the embodiment of the present invention, described main control unit, for the pattern set according to user, and in conjunction with the information that multi-channel surface myoelectric sensor and motion sensor collect, user movement situation is analyzed: if the pattern set is as counting step mode, then feature extraction is carried out to the information collected, then judge current action by feature identification and counting statistics and calorie calculating are carried out to motion; If the pattern of setting is exercise mode, then feature extraction is carried out to the information collected, and according to the feature extracted, displacement state is assessed; If the pattern of setting is rehabilitation modality, then feature extraction being carried out to the information collected, and the feature extracted and the canonical reference masterplate preset are compared, when reaching the certain movement time or the many stack features that extract are abnormal, sending alarm.
The specific works flow process of main control module can be as shown in Figure 3.Operational module is selected by the adjustment button on display floater (interactive interface), user selects corresponding functional mode to be divided into as required: meter step mode, for completing conventional function of passometer, the amount of movement of being good for away, running, riding, skipping rope or going upstairs can be measured and calculate calorie consumption; Exercise mode, for completing the analysis and evaluation of selected motion, the one of selected training of being good for away, running, riding, skipping rope and going upstairs or self-defining action, analyze the difficulty action accomplishment of the type action in continuous exercise routine and the degree of fatigue of related muscles; Rehabilitation modality, the daily reconditioning of patient for auxiliary motor dysfunction of lower limb, when the difference of the template characteristic of the feature obviously detected in rehabilitation user training process and current selection exceedes threshold value, alarm also records the information such as this rehabilitation training duration.
As shown in Figure 3, under three functional modes, all relate to the step of information gathering, in the embodiment of the present invention, the information collected by main control unit timing reading multi-channel surface myoelectric sensor and motion sensor; As shown in Figure 4, first, timer is configured for generation of counting interrupt.
When upgrading ADC sampling flag bit with the frequency of 1kHz in timer interrupt program, main control unit reads the information after one group of ADC conversion by communication interface, ADC sampling mark is removed after the information of all passages after to be converted all reads, and by information stored in data buffer storage;
When upgrading motion sensor sampling flag bit with the frequency of 100Hz in timer interrupt program, main control unit reads by communication interface the information that one group of motion sensor collects, continue and take rear removing motion sensor sampling mark, and by information stored in data buffer storage.
While collection, if user has configured show collection signal in real time, main control unit has enabled communication module, and real time data is sent to upper computer end.
1) at meter step mode, also comprise: feature extraction is carried out to the information collected, reference template under the age of the feature extracted and setting, body weight and height is carried out pattern-recognition, thus judge current action walking, run, ride, jump or go upstairs, and counting statistics is carried out to different motion and calorie calculates.
The information collected is processed and mainly comprises: after collecting fresh information, carry out active segment segmentation and feature extraction successively, then carry out Classification and Identification, and judge that whether action is effective and add up effective action quantity; As shown in Figure 5.(active segment segmentation, feature extraction, Classification and Identification are sane levels, are all the flow processs successively of algorithm process)
As shown in Figure 6, active segment is split: main control unit initializes all kinds of index variables, wherein Active represents current and collects fresh information whether in active segment, Last represents that the last time processes the sampling time (i.e. sampling point position) at information place, and Cur represents the sampling time at current process information place;
If Cur-Last>W represents that the fresh information collected more than W sampling time not yet processes, then start to judge fresh information whether in active segment; If Active is that the information of single treatment before 1 expression is in active segment, as long as the Sample Entropy meeting current information is greater than the threshold value of regulation, then judge that current information is similarly in active segment, and according to the mode of sub-frame processing with 64 for step-length, 128 operations performing feature extraction for window is long; If current information Sample Entropy is less than defined threshold when Active is 1, then inactive segment counter adds 1; If inactive segment counter superposes continuously reach P herein (such as, 15) then judge that now active segment exits completely (in the process that counter adds up, be greater than the phenomenon of ThreD if there is En, then counter resets be 0 and upper once time again add up).Active segment detect step-length be 8, therefore Last can add up 8 when having calculated Sample Entropy at every turn, so next time can from Last position again calculating.
Feature extraction:
For myoelectric information, extract temporal signatures absolute value average MAV, extract frequency domain character autoregression AR model coefficient;
The absolute value average MAV computing formula of electromyographic signal is:
MAV c = 1 N f Σ i = 1 N f | SEMG c ( i ) |
In formula, MAV refers to absolute value average, and c represents the surface myoelectric sensor passage corresponding to electromyographic signal, N ffor frame length, SEMG ci () represents the numerical value of c passage electromyographic signal i-th point collected;
The AR model coefficient of electromyographic signal adopts Burg algorithm to calculate;
As shown in Figure 7, point frame technique is adopted to extract the feature of myoelectric information: the myoelectric information in an active segment is divided into multiple fragment, and each snippet extraction goes out a stack features, and use length is N f, step-length is S frolling average window mobile from the starting point of active segment, each mobile time window in the information that comprises all as all data in present frame, until terminate during data deficiencies below, abandon not enough part;
After framing, every frame data of every passage myoelectric information comprise 5 characteristic values: 1 MAV and 4 AR coefficient, and the Hamming window using length to be Nf carries out filtering to every frame data, and Hamming window computing formula is:
w i n ( n ) = 0.54 - 0.46 c o s c o s ( 2 π n N f - 1 ) ;
In formula, n=[0, N f-1];
For motion track information, sampling is computation of mean values and standard deviation also; Described motion sensor is integrated with three axis accelerometer, three axis angular rate meters and three axle magnetometers, and the feature of motion track information is every passage 64 sample points, totally 9 passages; Then i-th of 9 passages sample point is placed on the i-th row, forms the eigenmatrix that 64 row 9 arrange, wherein, i=[1,64].
Classification and Identification:
Need Classification and Identification walking, run, ride, jump or go upstairs, consider that action kind is fewer, therefore in the present embodiment, directly select linear classifier to distinguish.
2) exercise mode.
Fig. 8 is the flow chart under exercise mode.
Exercise mode is intended to according to user's own characteristic, analyzes difficulty action accomplishment and the muscular fatigue characteristic situation of change in time of specific training (as being good for away, jog, skip rope, ride, stair climbing etc.) action within the duration.
In fact, because exercise mode does not relate to the Classification and Identification of different action, only as the similarity-rough set of same type action in continuous time, motor pattern is selected to be not limited to stair climbing, to jog, rope skipping etc.Such as, when user carries out arm strength training, this meter can also to be walked and motion state apparatus for evaluating bandage be placed on arm correct position, function is set as exercise mode and carry out lifting the dumbbell, the action such as chin-up.
Under exercise mode, feature extraction is carried out to the information of S group action before beginning, and generating reference feature, in subsequent action process, feature extraction is carried out to the information collected, and the feature extracted and described fixed reference feature are compared, the difficulty action accomplishment of subsequent action is assessed.
In the embodiment of the present invention, due to the slightly difference of wearing position, and difference wears the difference of moment electromyographic signal activity level, under exercise mode, think that front S action difficulty action accomplishment is the highest, and be regarded as this standard operation of taking exercise, and generate accordingly with reference to vectorial Vo and grade form T1.In subsequent motion, characteristic vector Vi and the Euclidean distance d with reference to vectorial Vo are calculated to action, and index grade form T1 provides the scoring of action completeness.
As shown in Figure 8, under exercise mode, first make Mode=TRAIN, now fixed reference feature Vo not yet generates; Carry out signals collecting successively afterwards, active segment splits and extract feature Vi (information gathering process is introduced in detail above, similar also with under meter step mode of simultaneously feature extraction, be all first carry out active segment segmentation, then carry out feature extraction, repeat no more herein); After extracting characteristic vector Vi, judge to be whether now the TRAIN process of station work pattern, if, then training vector is temporarily stored in buffer memory, training vector quantity to be counted reaches S (such as, can S=10 be established), the barycenter Vo of calculation training vector set, this barycenter is namely as this fixed reference feature.Meanwhile, Mode set is become CAL, turn signal gatherer process, perform follow-up evaluation stage.
When MODE is the CAL stage, calculate the Euclidean distance d of new feature vector Vi and template vector Vo, and by Euclidean distance d index in the grade form preset, thus obtain corresponding scoring, and score value is stored in data storage card.
In said process, TRAIN and CAL is all flag bit, is used for distinguishing a front S standard operation and follow-up action to be assessed.
3) rehabilitation modality
Rehabilitation modality is intended to for the patient of motor dysfunction of lower limb provides simple and effective lower limb rehabilitation aid, specific implementation is, by Real-time Collection electromyographic signal and accelerometer, gyroscope, magnetometer motor message, be partitioned into active segment and extract validity feature, statistics effective exercise number; Contrast the walking feature of normal population of the corresponding sex of this rehabilitation user, age, height, body weight, when a certain characteristic item difference is obviously greater than threshold value, device alarm user has a rest, and this rehabilitation training terminates and records the training time simultaneously.
The normal population feature templates of corresponding sex, age, height, body weight needs statistics gatherer in advance, contrast the image data evaluation appropriate threshold of this age bracket lower limb obstacle crowd afterwards, final feature templates and threshold value are all stored in data storage card as a part for system file.
Information gathering process is introduced in detail above, algorithm process also first carries out active segment segmentation simultaneously, carry out feature extraction again, the feature Vn extracted is: the absolute value average MAV of electromyographic signal, AR coefficient, the average of trajectory signal and standard deviation, extracting mode is consistent with counting in step mode above; The Sample Entropy reflection electromyographic signal energy response of another extraction electromyographic signal, mode of asking for is for adding up each channel signal as a signal and calculating Sample Entropy.
As shown in Figure 9, under rehabilitation modality, first input rehabilitation user physiologic information, comprise sex, age, height, body weight etc., system is selected to be loaded into suitable normal population canonical reference masterplate accordingly; In rehabilitation exercise process, system carries out signals collecting, active segment segmentation and feature extraction successively; After extraction obtains feature Vn, on the one hand carry out Classification and Identification, whether acts of determination is effectively and add up effective action number; On the other hand, the canonical reference masterplate of the normal population that contrast is loaded into, if when the many stack features extracted continuously are all greater than threshold value with the difference of the canonical reference masterplate preset, automatic alarm prompting user has a rest, and records the duration of this rehabilitation training.
In the embodiment of the present invention, the application situation of meter step mode, motor pattern, rehabilitation modality as shown in figs. 10-12.
Figure 10 is the meter step situation schematic diagram representing meter step and motion state apparatus for evaluating.This device is tied to shank by user, and identifiable design statistics are good for away, run, ride, skip rope, are gone upstairs and step number, and to get it right the calorie consumption that should move according to the sex preset, age, height and batheroom scale.
Figure 11 is the exercise mode situation schematic diagram representing meter step and motion state apparatus for evaluating.User carries out single type action exercise, device can be tied to leg or arm, and as the action that lifts the dumbbell in figure, device is not limited to be tied to shank.After entering exercise mode, S group training action before device identification also calculates this reference feature vector of taking exercise.In follow-up exercise routine, to action extract feature and and reference feature compare, result is stored simultaneously.After user terminates this exercise, this appreciation information of taking exercise can be transferred from memory cell.
Figure 12 is the rehabilitation modality situation schematic diagram representing meter step and motion state apparatus for evaluating.Rehabilitation user formulates rehabilitation training plans according to the suggestion of doctor, and arranges meter step and motion state apparatus for evaluating relevant parameter according to plan.When performing rehabilitation training, device detects rehabilitation user movement physiologic information, and when rehabilitation exercise is enough, alarm user has a rest in time and records this rehabilitation training information.Rehabilitation can regularly go to hospital to check and revise rehabilitation programme.
The above; be only the present invention's preferably detailed description of the invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claims.

Claims (9)

1. meter step and a motion state apparatus for evaluating, is characterized in that, comprising: multi-channel surface myoelectric sensor, motion sensor and main control unit; Wherein:
Described multi-channel surface myoelectric sensor, for gathering the myoelectric information on muscle group surface;
Described motion sensor, for motion track information;
Described main control unit, for the pattern set according to user, and in conjunction with the information that multi-channel surface myoelectric sensor and motion sensor collect, user movement situation is analyzed: if the pattern set is as counting step mode, then feature extraction is carried out to the information collected, then judge current action by feature identification and counting statistics and calorie calculating are carried out to motion; If the pattern of setting is exercise mode, then feature extraction is carried out to the information collected, and according to the feature extracted, motion state is assessed; If the pattern of setting is rehabilitation modality, then feature extraction being carried out to the information collected, and the feature extracted and the canonical reference masterplate preset are compared, when reaching the certain movement time or the many stack features that extract are abnormal, sending alarm.
2. one meter step according to claim 1 and motion state apparatus for evaluating, it is characterized in that, described main control unit, for the pattern set according to user, and the information collected in conjunction with multi-channel surface myoelectric sensor and motion sensor is analyzed user movement situation and is specifically comprised:
If the pattern set is as counting step mode, then feature extraction is carried out to the information collected, reference template under the age of the feature extracted and setting, body weight and height is carried out pattern-recognition, thus judge current action walking, run, ride, jump or go upstairs, and counting statistics is carried out to different motion and calorie calculates;
If the pattern of setting is exercise mode, then carry out feature extraction according to the information of S group action before starting under exercise mode, and generating reference feature, in subsequent action process, feature extraction is carried out to the information collected, and the feature extracted and described fixed reference feature are compared, the difficulty action accomplishment of subsequent action is assessed;
If the pattern of setting is rehabilitation modality, then feature extraction is carried out to the information collected, the feature extracted and the canonical reference masterplate preset are compared, when the many stack features extracted are abnormal, send alarm.
3. one meter step according to claim 1 and 2 and motion state apparatus for evaluating, it is characterized in that, described main control unit processes the information collected, and treatment step comprises:
After collecting fresh information, carry out active segment segmentation and feature extraction successively; Specific as follows:
Active segment is split: main control unit initializes all kinds of index variables, and wherein Active represents current and collects fresh information whether in active segment, and Last represents that the last time processes the sampling time at information place, and Cur represents the sampling time at current process information place;
If Cur-Last>W represents that the fresh information collected more than W sampling time not yet processes, then start to judge fresh information whether in active segment; If Active is that the information of single treatment before 1 expression is in active segment, as long as the Sample Entropy meeting current information is greater than the threshold value of regulation, then judge that current information is similarly in active segment, and according to the mode of sub-frame processing with 64 for step-length, 128 operations performing feature extraction for window is long; If current information Sample Entropy is less than defined threshold when Active is 1, then inactive segment counter adds 1; If inactive segment counter superposes continuously reach P herein, judge that now active segment exits completely;
Feature extraction:
For myoelectric information, extract temporal signatures absolute value average MAV, extract frequency domain character autoregression AR model coefficient;
The absolute value average MAV computing formula of electromyographic signal is:
MAV c = 1 N f Σ i = 1 N f | SEMG c ( i ) |
In formula, MAV refers to absolute value average, and c represents the surface myoelectric sensor passage corresponding to electromyographic signal, N ffor frame length, SEMG ci () represents the numerical value of c passage electromyographic signal i-th point collected;
The AR model coefficient of electromyographic signal adopts Burg algorithm to calculate;
Point frame technique is adopted to extract the feature of myoelectric information: the myoelectric information in an active segment is divided into multiple fragment, and each snippet extraction goes out a stack features, and use length is N f, step-length is S frolling average window mobile from the starting point of active segment, each mobile time window in the information that comprises all as all data in present frame, until terminate during data deficiencies below, abandon not enough part;
After framing, every frame data of every passage myoelectric information comprise 5 characteristic values: 1 MAV and 4 AR coefficient, and use length for N fhamming window filtering is carried out to every frame data, Hamming window computing formula is:
w i n ( n ) = 0.54 - 0.46 c o s c o s ( 2 π n N f - 1 ) ;
In formula, n=[0, N f-1];
For motion track information, sampling is computation of mean values and standard deviation also; Described motion sensor is integrated with 3 axis accelerometers, 3 axis angular rate meters and 3 axle magnetometers, and the feature of motion track information is every passage 64 sample points, totally 9 passages; Then i-th of 9 passages sample point is placed on the i-th row, forms the eigenmatrix that 64 row 9 arrange, wherein, i=[1,64].
4. the one meter step according to claim 1 or 2 or 3 and motion state apparatus for evaluating, it is characterized in that, describedly carry out feature extraction according to the information of S group action before starting under exercise mode, and generating reference feature, in subsequent action process, feature extraction is carried out to the information collected, and the feature extracted and described fixed reference feature is compared, assessment is carried out to the difficulty action accomplishment of subsequent action and comprises:
Feature extraction is carried out to the information of S group action before starting under exercise mode, and calculates the barycenter of characteristic set, using barycenter as with reference to feature;
Feature extraction is carried out to the information after S group, and calculates the Euclidean distance of feature and the described fixed reference feature extracted, by this Euclidean distance index in the grade form preset, thus obtain corresponding scoring.
5. the one meter step according to claim 1 or 2 or 3 and motion state apparatus for evaluating, it is characterized in that, feature extraction is carried out to the information collected, the feature extracted and the canonical reference masterplate preset are compared, when the many stack features extracted are abnormal, send alarm and comprise:
Described default canonical reference masterplate is set by the sex according to user, age, height and body weight;
After completing feature extraction, the feature extracted and the canonical reference masterplate preset are compared, judge that whether effectively and add up effective action this action; If when the many stack features extracted continuously are all greater than threshold value with the difference of the canonical reference masterplate preset, automatic alarm prompting user has a rest, and records the duration of this rehabilitation training.
6. one meter step according to claim 1 and 2 and motion state apparatus for evaluating, is characterized in that, the information that described main control unit timing reading multi-channel surface myoelectric sensor and motion sensor collect; Wherein:
The information that multi-channel surface myoelectric sensor collects carries out analog-to-digital conversion by analog-digital converter ADC, when upgrading ADC sampling flag bit with 1kHz in timer interrupt program, main control unit reads the information after one group of ADC conversion by communication interface, ADC sampling mark is removed after the information of all passages after to be converted all reads, and by information stored in data buffer storage;
When upgrading motion sensor sampling flag bit with 100Hz in timer interrupt program, main control unit reads by communication interface the information that one group of motion sensor collects, and continues and takes rear removing motion sensor sampling mark, and by information stored in data buffer storage.
7. one meter step according to claim 1 and 2 and motion state apparatus for evaluating, it is characterized in that, this device also comprises:
Communication module, transmits for the data realizing main control unit and external equipment;
When main control unit is in the information that reading multi-channel surface myoelectric sensor and motion sensor collect, if the real-time display collection signal that user is configured with, then main control unit is by communication module, and real time data is sent to external equipment.
8. one meter step according to claim 2 and motion state apparatus for evaluating, it is characterized in that, this device also comprises: program storage unit (PSU) and data storage card;
Described program storage unit (PSU), for supplying access data in system start-up and operation process;
Described data storage card, the reference template for storing feature identification, when comparing and canonical reference masterplate, and the information that collects of multi-channel surface myoelectric sensor and motion sensor and analysis result.
9. one meter step according to claim 1 and 2 and motion state apparatus for evaluating, it is characterized in that, this device also comprises:
Display floater, described display floater comprises: regulate button and display screen;
Described adjustment button is for setting present mode as meter step mode, exercise mode or rehabilitation modality; Described display screen is for showing the movable information under each pattern.
CN201511017130.7A 2015-12-29 2015-12-29 A kind of meter step and motion state apparatus for evaluating Active CN105561567B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201511017130.7A CN105561567B (en) 2015-12-29 2015-12-29 A kind of meter step and motion state apparatus for evaluating

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201511017130.7A CN105561567B (en) 2015-12-29 2015-12-29 A kind of meter step and motion state apparatus for evaluating

Publications (2)

Publication Number Publication Date
CN105561567A true CN105561567A (en) 2016-05-11
CN105561567B CN105561567B (en) 2018-11-13

Family

ID=55872540

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201511017130.7A Active CN105561567B (en) 2015-12-29 2015-12-29 A kind of meter step and motion state apparatus for evaluating

Country Status (1)

Country Link
CN (1) CN105561567B (en)

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106691447A (en) * 2017-02-23 2017-05-24 北京纳通科技集团有限公司 Muscle training auxiliary device and muscle training evaluation device and method
CN106730627A (en) * 2016-12-01 2017-05-31 上海长海医院 Foot recovers moving electron pin ring
CN107185214A (en) * 2017-06-22 2017-09-22 厦门钢宇工业有限公司 A kind of body building method raced based on muscle group and system
CN107808694A (en) * 2016-09-08 2018-03-16 深圳先进技术研究院 The system and method for CP children locomotor activity is judged based on GMFCS
CN107966161A (en) * 2017-11-09 2018-04-27 内蒙古大学 Walking detection method based on FFT
CN108229283A (en) * 2017-05-25 2018-06-29 深圳市前海未来无限投资管理有限公司 Electromyographic signal collection method and device
CN108211311A (en) * 2017-05-25 2018-06-29 深圳市前海未来无限投资管理有限公司 The movement effects display methods and device of body-building action
CN108309308A (en) * 2018-02-06 2018-07-24 吉林大学 A kind of apparatus and system for teaching angiocardiopathy athletic rehabilitation
CN108514159A (en) * 2017-02-27 2018-09-11 南京网河智能科技有限公司 A kind of supplemental training clothes and its working method
CN108804455A (en) * 2017-04-28 2018-11-13 中移（杭州）信息技术有限公司 A kind of data reordering method and device
CN108832953A (en) * 2018-07-13 2018-11-16 国家康复辅具研究中心 A kind of wisdom bracelet monitoring limb activity information
CN108921907A (en) * 2018-07-26 2018-11-30 上海慧子视听科技有限公司 A kind of method, apparatus, equipment and the storage medium of exercise test scoring
CN109394230A (en) * 2018-12-07 2019-03-01 北京大学深圳研究生院 A kind of gait analysis system based on surface electromyogram signal
CN109846487A (en) * 2019-02-26 2019-06-07 浙江理工大学 Thigh measuring method for athletic posture and device based on MIMU/sEMG fusion
CN110102039A (en) * 2019-04-26 2019-08-09 太平洋未来科技（深圳）有限公司 A kind of sensor device of measurable human arm muscular movement intensity
CN110141239A (en) * 2019-05-30 2019-08-20 东北大学 A kind of motion intention identification and installation method for lower limb exoskeleton
CN110163489A (en) * 2019-04-28 2019-08-23 湖南师范大学 A kind of drug rehabilitation motion exercise effect assessment method
CN110464349A (en) * 2019-08-30 2019-11-19 南京邮电大学 A kind of upper extremity exercise function score method based on hidden Semi-Markov Process
CN110573075A (en) * 2017-03-03 2019-12-13 创新民族株式会社 Walking teaching system and walking teaching method
CN110638457A (en) * 2019-08-26 2020-01-03 广东省人民医院(广东省医学科学院) Method and equipment for monitoring frozen gait of Parkinson disease patient
CN111714129A (en) * 2020-05-07 2020-09-29 广西科技大学 Human gait information acquisition system
CN112315459A (en) * 2020-11-26 2021-02-05 中国科学技术大学 Multifunctional digital assessment intelligent seat
CN113160931A (en) * 2021-04-12 2021-07-23 深圳英鸿骏智能科技有限公司 Fitness action energy consumption evaluation method, device, equipment and storage medium
TWI816909B (en) * 2018-10-12 2023-10-01 日商住友製藥股份有限公司 A method for evaluating the correlation between the degree of health in the health care field and each preventive intervention action, a device for evaluating the correlation between the degree of health in the health care field and each preventive intervention action, and an evaluation of the degree of health and prevention in the health care field. Computer programs related to various sexual intervention behaviors

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060004298A1 (en) * 2004-06-30 2006-01-05 Kennedy Philip R Software controlled electromyogram control systerm
CN1968293A (en) * 2005-11-15 2007-05-23 黄煜树 Mobile phone apparatus capable of measuring motion state and supporting motion training
CN102641196A (en) * 2011-12-30 2012-08-22 中国科学院深圳先进技术研究院 Rehealthy training robot control system and control method thereof
CN203224907U (en) * 2013-04-26 2013-10-02 赵平 Rehabilitation exercise guiding system
CN103646366A (en) * 2013-11-15 2014-03-19 北京耀华康业科技发展有限公司 Interactive type autonomous heath management system and method
KR101448106B1 (en) * 2011-02-17 2014-10-08 주식회사 라이프사이언스테크놀로지 Analisys Method of Rehabilitation status using Electromyogram
CN104536558A (en) * 2014-10-29 2015-04-22 三星电子（中国）研发中心 Intelligent ring and method for controlling intelligent equipment
CN104571837A (en) * 2013-10-12 2015-04-29 深圳先进技术研究院 Method and system for realizing human-computer interaction
CN104939815A (en) * 2015-07-15 2015-09-30 张鸣生 Comprehensive feedback type pulmonary rehabilitation assessment treatment instrument

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060004298A1 (en) * 2004-06-30 2006-01-05 Kennedy Philip R Software controlled electromyogram control systerm
CN1968293A (en) * 2005-11-15 2007-05-23 黄煜树 Mobile phone apparatus capable of measuring motion state and supporting motion training
KR101448106B1 (en) * 2011-02-17 2014-10-08 주식회사 라이프사이언스테크놀로지 Analisys Method of Rehabilitation status using Electromyogram
CN102641196A (en) * 2011-12-30 2012-08-22 中国科学院深圳先进技术研究院 Rehealthy training robot control system and control method thereof
CN203224907U (en) * 2013-04-26 2013-10-02 赵平 Rehabilitation exercise guiding system
CN104571837A (en) * 2013-10-12 2015-04-29 深圳先进技术研究院 Method and system for realizing human-computer interaction
CN103646366A (en) * 2013-11-15 2014-03-19 北京耀华康业科技发展有限公司 Interactive type autonomous heath management system and method
CN104536558A (en) * 2014-10-29 2015-04-22 三星电子（中国）研发中心 Intelligent ring and method for controlling intelligent equipment
CN104939815A (en) * 2015-07-15 2015-09-30 张鸣生 Comprehensive feedback type pulmonary rehabilitation assessment treatment instrument

Cited By (34)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107808694A (en) * 2016-09-08 2018-03-16 深圳先进技术研究院 The system and method for CP children locomotor activity is judged based on GMFCS
CN107808694B (en) * 2016-09-08 2023-04-14 深圳先进技术研究院 System and method for judging walking ability of cerebral palsy child patient based on GMFCS
CN106730627A (en) * 2016-12-01 2017-05-31 上海长海医院 Foot recovers moving electron pin ring
CN106691447B (en) * 2017-02-23 2023-09-12 北京纳通科技集团有限公司 Muscle training aid device, muscle training evaluation device and method
CN106691447A (en) * 2017-02-23 2017-05-24 北京纳通科技集团有限公司 Muscle training auxiliary device and muscle training evaluation device and method
CN108514159A (en) * 2017-02-27 2018-09-11 南京网河智能科技有限公司 A kind of supplemental training clothes and its working method
CN110573075A (en) * 2017-03-03 2019-12-13 创新民族株式会社 Walking teaching system and walking teaching method
CN110573075B (en) * 2017-03-03 2022-06-03 创新民族株式会社 Walking teaching system and walking teaching method
CN108804455A (en) * 2017-04-28 2018-11-13 中移（杭州）信息技术有限公司 A kind of data reordering method and device
CN108211311A (en) * 2017-05-25 2018-06-29 深圳市前海未来无限投资管理有限公司 The movement effects display methods and device of body-building action
CN108229283A (en) * 2017-05-25 2018-06-29 深圳市前海未来无限投资管理有限公司 Electromyographic signal collection method and device
CN107185214A (en) * 2017-06-22 2017-09-22 厦门钢宇工业有限公司 A kind of body building method raced based on muscle group and system
CN107966161A (en) * 2017-11-09 2018-04-27 内蒙古大学 Walking detection method based on FFT
CN108309308A (en) * 2018-02-06 2018-07-24 吉林大学 A kind of apparatus and system for teaching angiocardiopathy athletic rehabilitation
CN108832953A (en) * 2018-07-13 2018-11-16 国家康复辅具研究中心 A kind of wisdom bracelet monitoring limb activity information
CN108921907A (en) * 2018-07-26 2018-11-30 上海慧子视听科技有限公司 A kind of method, apparatus, equipment and the storage medium of exercise test scoring
CN108921907B (en) * 2018-07-26 2022-03-08 上海慧子视听科技有限公司 Exercise test scoring method, device, equipment and storage medium
TWI816909B (en) * 2018-10-12 2023-10-01 日商住友製藥股份有限公司 A method for evaluating the correlation between the degree of health in the health care field and each preventive intervention action, a device for evaluating the correlation between the degree of health in the health care field and each preventive intervention action, and an evaluation of the degree of health and prevention in the health care field. Computer programs related to various sexual intervention behaviors
CN109394230A (en) * 2018-12-07 2019-03-01 北京大学深圳研究生院 A kind of gait analysis system based on surface electromyogram signal
CN109846487A (en) * 2019-02-26 2019-06-07 浙江理工大学 Thigh measuring method for athletic posture and device based on MIMU/sEMG fusion
CN109846487B (en) * 2019-02-26 2021-12-31 浙江理工大学 Thigh movement posture measuring method and device based on MIMU/sEMG fusion
CN110102039A (en) * 2019-04-26 2019-08-09 太平洋未来科技（深圳）有限公司 A kind of sensor device of measurable human arm muscular movement intensity
CN110102039B (en) * 2019-04-26 2020-11-06 太平洋未来科技（深圳）有限公司 Sensor device capable of measuring muscle movement intensity of human arm
CN110163489A (en) * 2019-04-28 2019-08-23 湖南师范大学 A kind of drug rehabilitation motion exercise effect assessment method
CN110163489B (en) * 2019-04-28 2023-07-14 湖南师范大学 Method for evaluating rehabilitation exercise effect
CN110141239B (en) * 2019-05-30 2020-08-04 东北大学 Movement intention recognition and device method for lower limb exoskeleton
CN110141239A (en) * 2019-05-30 2019-08-20 东北大学 A kind of motion intention identification and installation method for lower limb exoskeleton
CN110638457B (en) * 2019-08-26 2023-02-21 广东省人民医院(广东省医学科学院) Method and equipment for monitoring frozen gait of Parkinson disease patient
CN110638457A (en) * 2019-08-26 2020-01-03 广东省人民医院(广东省医学科学院) Method and equipment for monitoring frozen gait of Parkinson disease patient
CN110464349A (en) * 2019-08-30 2019-11-19 南京邮电大学 A kind of upper extremity exercise function score method based on hidden Semi-Markov Process
CN111714129A (en) * 2020-05-07 2020-09-29 广西科技大学 Human gait information acquisition system
CN112315459A (en) * 2020-11-26 2021-02-05 中国科学技术大学 Multifunctional digital assessment intelligent seat
CN113160931A (en) * 2021-04-12 2021-07-23 深圳英鸿骏智能科技有限公司 Fitness action energy consumption evaluation method, device, equipment and storage medium
CN113160931B (en) * 2021-04-12 2024-04-09 深圳英鸿骏智能科技有限公司 Exercise energy consumption evaluation method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN105561567B (en) 2018-11-13

Similar Documents

Publication Publication Date Title
CN105561567A (en) Step counting and motion state evaluation device
CN106971059B (en) Wearable equipment based on neural network self-adaptation health monitoring
CN109480858B (en) Wearable intelligent system and method for quantitatively detecting motor retardation symptoms of Parkinson patients
CN104398263B (en) A kind of disturbances in patients with Parkinson disease based on approximate entropy and mutual approximate entropy tremble symptom quantify evaluating method
CN102138789B (en) Dynamic electrocardiogram and motion recording and analyzing system
CN103519819A (en) Gait analysis method and gait analysis system
CN105496416A (en) Human motion state recognition method and device
CN102551735B (en) Blood oxygen measuring instrument
CN107753026A (en) For the intelligent shoe self-adaptive monitoring method of backbone leg health
CN104146712A (en) Wearable plantar pressure detection apparatus and plantar pressure detection and attitude prediction method
CN106805980A (en) A kind of gait analysis system and analysis method
Song et al. Speed estimation from a tri-axial accelerometer using neural networks
CN106166071A (en) The acquisition method of a kind of gait parameter and equipment
CN101953682A (en) Heartbeat detection method based on cuff device
CN105943206A (en) Prosthetic hand control method based on MYO armlet
CN106123911A (en) A kind of based on acceleration sensor with the step recording method of angular-rate sensor
CN107273677A (en) A kind of multi-channel nerve function quantitative evaluation system
CN108958482B (en) Similarity action recognition device and method based on convolutional neural network
CN106730766A (en) A kind of evaluation method of the adult motor's load based on heart rate data
CN106388786A (en) Processing method acquiring data based on intelligent ring
CN103785157A (en) Human body motion type identification accuracy improving method
CN107469326A (en) Swimming monitoring method and device for wearable equipment and wearable equipment
CN105435438A (en) Exercise analysis device and exercise analysis method
CN106108879A (en) A kind of evaluation methodology of students in middle and primary schools' physical training sports load based on heart rate data
CN109805935A (en) A kind of intelligent waistband based on artificial intelligence hierarchical layered motion recognition method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant