CN112294599A - Training track generation model construction method, system and device based on human body parameters - Google Patents
Training track generation model construction method, system and device based on human body parameters Download PDFInfo
- Publication number
- CN112294599A CN112294599A CN202011192281.7A CN202011192281A CN112294599A CN 112294599 A CN112294599 A CN 112294599A CN 202011192281 A CN202011192281 A CN 202011192281A CN 112294599 A CN112294599 A CN 112294599A
- Authority
- CN
- China
- Prior art keywords
- human body
- training
- joints
- preset
- generation model
- 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
Links
- 238000012549 training Methods 0.000 title claims abstract description 79
- 238000010276 construction Methods 0.000 title claims description 13
- 238000000034 method Methods 0.000 claims abstract description 59
- 230000005021 gait Effects 0.000 claims abstract description 31
- 210000003141 lower extremity Anatomy 0.000 claims abstract description 20
- 210000001503 joint Anatomy 0.000 claims description 49
- 230000005484 gravity Effects 0.000 claims description 17
- 210000000629 knee joint Anatomy 0.000 claims description 13
- 210000004394 hip joint Anatomy 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 210000000544 articulatio talocruralis Anatomy 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 11
- 239000000126 substance Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 210000003414 extremity Anatomy 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 14
- 230000008569 process Effects 0.000 description 9
- 210000003423 ankle Anatomy 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 210000002683 foot Anatomy 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 210000001624 hip Anatomy 0.000 description 3
- 210000003692 ilium Anatomy 0.000 description 3
- 210000003127 knee Anatomy 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 210000000689 upper leg Anatomy 0.000 description 3
- 244000309466 calf Species 0.000 description 2
- 230000002490 cerebral effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 206010061296 Motor dysfunction Diseases 0.000 description 1
- 208000020339 Spinal injury Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H1/00—Apparatus for passive exercising; Vibrating apparatus; Chiropractic devices, e.g. body impacting devices, external devices for briefly extending or aligning unbroken bones
- A61H1/02—Stretching or bending or torsioning apparatus for exercising
- A61H1/0237—Stretching or bending or torsioning apparatus for exercising for the lower limbs
- A61H1/0255—Both knee and hip of a patient, e.g. in supine or sitting position, the feet being moved together in a plane substantially parallel to the body-symmetrical plane
- A61H1/0262—Walking movement; Appliances for aiding disabled persons to walk
-
- 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
- A61B5/112—Gait analysis
-
- 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
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
-
- 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
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
- A61B5/1122—Determining geometric values, e.g. centre of rotation or angular range of movement of movement trajectories
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5007—Control means thereof computer controlled
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2230/00—Measuring physical parameters of the user
- A61H2230/62—Posture
- A61H2230/625—Posture used as a control parameter for the apparatus
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Dentistry (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Engineering & Computer Science (AREA)
- Physiology (AREA)
- Geometry (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Epidemiology (AREA)
- Pain & Pain Management (AREA)
- Physical Education & Sports Medicine (AREA)
- Rehabilitation Therapy (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention belongs to the field of computers, and particularly relates to a method, a system and a device for constructing a training trajectory generation model based on human body parameters, aiming at solving the problem of single gait training trajectory of the existing lower limb rehabilitation robot. The method comprises the steps of constructing a training sample set based on an input feature set and a Fourier coefficient set; training a plurality of category regression models for the preset joints respectively based on the training sample set, and selecting the regression model with the minimum prediction error as an angle generation model of the corresponding joint; and combining the obtained angle models of the plurality of joints to obtain a training track generation model of the human body part containing the preset joints. The training track generation model constructed by the method can generate the differential training track based on the specific human body parameters of the user.
Description
Technical Field
The invention belongs to the field of computers, and particularly relates to a training trajectory generation model construction method, system and device based on human body parameters.
Background
At present, thanks to the development of modern medicine, the fatality rate of diseases such as cerebral apoplexy, cerebral trauma and spinal injury is greatly reduced; however, after acute treatment, most patients have sequelae such as lower limb motor dysfunction and the like, and need long-term rehabilitation training, mainly gait rehabilitation training. In the traditional gait rehabilitation training, a plurality of rehabilitation therapists are required to complete the training together. Under the condition that the resources of the domestic rehabilitation therapists are in short supply at present, the lower limb rehabilitation robot is often used for rehabilitation training of patients, and assists or actively drives the patients to carry out gait training. The gait tracks adopted by the lower limb rehabilitation robot are mainly the angle tracks of three joints of a hip, a knee and an ankle in the sagittal plane of a human body. The gait track data of the normal person during walking is collected and then used on the robot as a template for gait rehabilitation training of the patient. However, the gait tracks have individual differences, and have strong correlation with human body characteristics such as sex, age, height and other factors. According to the characteristics of the patient, the lower limb rehabilitation robot provides gait track training which is more suitable for the patient, and the improvement of the rehabilitation effect of the patient is promoted.
The invention provides a human body parameter-based personalized gait track generation method, which is characterized in that three joint angle curves of a hip, a knee and an ankle are fitted through Fourier series, fitted Fourier coefficients are adopted to replace gait tracks, and the method is applied to a lower limb rehabilitation robot; based on 14 human body parameters, modeling the relationship between the human body parameters and Fourier coefficients by a machine learning method, and further constructing an individualized gait track generation model based on the human body parameters.
Disclosure of Invention
In order to solve the above problems in the prior art, that is, to solve the problem of single gait training track of the existing lower limb rehabilitation robot, the first aspect of the present invention provides a training track generation model construction method based on human body parameters, comprising the following steps:
constructing a training sample set based on the input feature set and the Fourier coefficient set;
training a plurality of category regression models for the preset joints respectively based on the training sample set, and selecting the regression model with the minimum prediction error as an angle generation model of the corresponding joint;
combining the obtained angle models of the plurality of joints to obtain a training track generation model of the human body part containing the preset joints;
wherein the content of the first and second substances,
the input feature set comprises a plurality of human body feature category parameters of human bodies;
the Fourier coefficient set is a coefficient item in a joint angle function obtained by fitting through a Fourier series method based on test data of a preset joint;
the preset joints are joints included in the human body part of the track to be generated.
In some preferred embodiments, the input feature set is obtained by:
based on the initial sample set, acquiring an input feature set by adopting a maximum correlation minimum redundancy method; each sample in the initial sample set comprises parameters of an individual corresponding to a preset human body characteristic category.
In some preferred embodiments, the method for selecting the input feature set by using the maximum correlation minimum redundancy method includes:
step S110, calculating the set of Fourier coefficients through mutual information to obtain a characteristic sequence corresponding to each Fourier coefficient based on preset human body characteristics;
s120, sorting the features corresponding to the Fourier coefficients, and obtaining final feature sorting by calculating the mean value of the serial numbers;
and S130, based on the final feature sorting, sequentially adding preset human body features as alternative input feature sets in sequence, respectively modeling with the Fourier coefficient sets to obtain intermediate models, and selecting the alternative input feature set corresponding to the intermediate model with the minimum mean error as the selected input feature set.
In some preferred embodiments, the method for obtaining the feature ordering corresponding to each fourier coefficient by mutual information calculation based on preset human body features for the set of fourier coefficients includes:
step S111, selecting a Fourier coefficient from the Fourier coefficient set;
step S112, aiming at a single Fourier coefficient, calculating the mutual information between the single Fourier coefficient and each preset human body characteristic in sequence, and putting the preset human body characteristic corresponding to the maximum mutual information into a characteristic set D1The remaining set of features D2;
Step S113, for feature set D2Respectively calculating the features and feature set D1Average value of mutual information of each feature in (1);
step S114, selecting the feature set D corresponding to the maximum mutual information average value in step S1132Into feature set D1After the original signature sequence;
step S115, execute step S112 to step S114 until feature set D2If the number is null, generating a feature order corresponding to the corresponding Fourier coefficient;
step S116, selecting one of the remaining fourier coefficients in the set of fourier coefficients, and executing step S112 until all fourier coefficients in the set of fourier coefficients have obtained corresponding feature ranks.
In some preferred embodiments, the human body part comprising the preset joint is a lower limb of a human body; the preset joints comprise hip joints, knee joints and ankle joints.
In some preferred embodiments, the training trajectory generation model further includes a center of gravity calculation module corresponding to a joint angle;
the gravity center calculation module is configured to calculate the gravity center by using the geometrical relationship between the limbs and the joints based on the hip joint angle, the knee joint angle and the ankle joint angle.
In some preferred embodiments, the joint angle function f (t) obtained by fourier series fitting based on test data of a predetermined joint is
Wherein n is the order of the fit,at angular frequency, T is the gait cycle, a0,ai,bi(i ═ 1.., n) is a coefficient term.
In some preferred embodiments, the multiple category regression models include a support vector machine regression model, a random forest regression model.
The invention provides a training track generation model construction system based on human body parameters, which comprises a first unit, a second unit and a third unit, wherein the first unit is used for generating a training track;
the first unit is configured to construct a training sample set based on an input feature set and a Fourier coefficient set;
the second unit is configured to train multiple category regression models for preset joints respectively based on the training sample set, and select a regression model with the smallest prediction error as an angle generation model of a corresponding joint;
the third unit is configured to combine the obtained angle models of the plurality of joints to obtain a training track generation model of the human body part including the preset joints;
wherein the content of the first and second substances,
the input feature set comprises a plurality of human body feature category parameters of human bodies;
the Fourier coefficient set is a coefficient item in a joint angle function obtained by fitting through a Fourier series method based on test data of a preset joint;
the preset joints are joints included in the human body part of the track to be generated.
In a third aspect of the present invention, a processing apparatus is provided, which includes a processor, a storage device; a processor adapted to execute various programs; a storage device adapted to store a plurality of programs; the program is suitable for being loaded and executed by a processor to realize the human body parameter-based training track generation model construction method.
The invention has the beneficial effects that:
the training track generation model constructed based on the method can generate the differential training track based on the specific human body parameters of the user, the generated training track is more fit with the human body condition of the user, the training effect of the user can be improved, and the motion function of the user is further improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is a schematic flow chart of a training trajectory generation model construction method based on human body parameters according to an embodiment of the present invention;
FIG. 2 is a schematic view of a lower extremity joint angle in accordance with an embodiment of the present invention;
FIG. 3 is a simplified model of a lower limb according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The invention discloses a training track generation model construction method based on human body parameters, which comprises the following steps as shown in figure 1:
constructing a training sample set based on the input feature set and the Fourier coefficient set;
training a plurality of category regression models for the preset joints respectively based on the training sample set, and selecting the regression model with the minimum prediction error as an angle generation model of the corresponding joint;
combining the obtained angle models of the plurality of joints to obtain a training track generation model of the human body part containing the preset joints;
wherein the content of the first and second substances,
the input feature set comprises a plurality of human body feature category parameters of human bodies;
the Fourier coefficient set is a coefficient item in a joint angle function obtained by fitting through a Fourier series method based on test data of a preset joint;
the preset joints are joints included in the human body part of the track to be generated.
For the purpose of more clearly illustrating the present invention, reference is now made to the following detailed description of the various parts in one embodiment of the present invention taken in conjunction with the accompanying drawings.
The method for constructing the training trajectory generation model based on the human body parameters in the embodiment of the invention is explained by taking the lower limbs of the human body as an example, and can be also applied to the modeling of the training trajectory of other human body parts, such as the upper limbs.
Before the specific steps of this embodiment are explained, the acquisition and fitting of the gait trajectory of the lower limbs of the human body are explained.
As shown in fig. 2, the lower limb of the human body is schematically illustrated, and the hip joint angle, the knee joint angle and the ankle joint angle in the gait track are respectively defined. Angle of hip joint as curve of center of gravity (l)1) Connecting with the center of hip and knee joint (l)2) Angle of (a) in fig. 2hip(ii) a Knee joint angle is l2Connecting the knee ankle joint center line (l)3) Angle of (a) in fig. 2knee(ii) a Ankle joint angle thetaankleIs the center of the ankle joint3Perpendicular line (l) of4) And footParallel lines of surface (l)5) The included angle of (a).
Collecting different speeds (v) of normal person by using joint angle data measuring instrument1...vi) Angle data of three joints when walking down. For the collected angle data, firstly searching missing values in the data, and filling the missing values by using the average value of the front and rear 5 data points; and then carrying out noise filtering and smoothing on the angle curve by adopting a moving average method. Since the acquisition process involves data for multiple gait cycles, the data needs to be divided into cycles, with each cycle being labeled. The initial point of the gait cycle is the moment when one side heel just touches down.
The processed three-joint angle curve is composed of hundreds of discrete sampling points, and if discrete gait track data points are directly used, two problems are caused: on one hand, the difficulty of modeling is increased, and the complexity of a track generation model is too high due to the fact that hundreds of discrete points are predicted; on the other hand, the motor control at the joint of the lower limb rehabilitation robot is not facilitated.
In the invention, joint angle data are fitted by a Fourier series method (1), so that a function f (t) related to time t can be obtained, as shown in formula (1):
wherein n is the order of the fit,at angular frequency, T is the gait cycle, a0,ai,bi(i ═ 1.., n) is a coefficient term.
The order n is selected according to the absolute error value of the fitted curve and the original curve, through experimental tests, when the fitting order is 5, the error value is gradually reduced, meanwhile, the fitting errors of the three joints are all within 0.3 degrees, the complexity of the error and the fitting model is comprehensively considered, and finally, n is 5 to be used as the final fitting order. Therefore, after each joint track is fitted, 12 Fourier systems can be obtainedNumber (omega, a)0,ai,bi(i 1.., 5)), these coefficients are used as the substitute values of the trajectory to participate in the modeling of the individualized gait trajectory. Further, the joint angle trajectory can be reconstructed by generating 12 parameters from the human body features. In the control of the joint motor of the lower limb rehabilitation robot, the speed curve and the acceleration curve of the track are obtained by derivation of the reconstructed joint track equation, so that various motor control modes (position control and speed control) can be selected.
The embodiment of the method is a preferable embodiment of the method, and comprises the following steps:
and S100, acquiring an input feature set by adopting a maximum correlation minimum redundancy method based on the initial sample set.
Each sample in the initial sample set comprises parameters of an individual corresponding to the preset human body characteristic category. For the embodiment, by analyzing the anatomy of the lower limbs of the human body and investigating related data, 14 human body characteristics (preset human body characteristics) can be selected to perform gait track modeling, and the characteristics mainly include: gender, age, height, weight, ilium width, trochanter width on both sides of the hip, anterior superior iliac spine width, thigh length, calf length, knee joint diameter, ankle height, ankle width, foot length and foot width. And acquiring human body data based on preset human body characteristics, and constructing a first sample set by taking a group of data corresponding to each human body as a sample.
Based on the method of the present invention, the input feature set can be the above-mentioned 14 human body features, but the input features are too many, which brings complexity to the system and complexity to the data acquisition of the user. The invention takes two aspects into consideration again: one is that there may be a large correlation between 14 features, such as: ilium width and ilium anterior superior spine width; and secondly, in order to simplify the feature set, the time for measuring the features is reduced. In the embodiment of the invention, a maximum correlation minimum redundancy criterion (mRMR) is adopted to optimize the feature set, the redundancy among the features and the correlation between the features and Fourier coefficients are represented by mutual information, the calculation mode of the mutual information I (X, Y) is shown as a formula (2),
where X and Y are two feature attributes, X and Y are the feature attribute values of the sample, p (X) and p (Y) are edge probability distributions, and p (X, Y) is a joint probability distribution.
The input feature set is selected by adopting a maximum correlation minimum redundancy method, and the method can be realized by the following steps:
and step S110, calculating the Fourier coefficient set to obtain a characteristic sequence corresponding to each Fourier coefficient through mutual information based on preset human body characteristics.
The steps further include:
step S111, selecting one fourier coefficient from the set of fourier coefficients.
Sorting the coefficient items in the fourier coefficient set, and then sequentially selecting the following steps, for example, selecting the first sorted coefficient item for the first time; in step S116, the selection of each of the subsequent coefficient items is performed in sequence.
Step S112, aiming at a single Fourier coefficient, calculating the mutual information between the single Fourier coefficient and each preset human body characteristic in sequence, and putting the preset human body characteristic corresponding to the maximum mutual information into a characteristic set D1The remaining set of features D2。
Put into feature set D2The preset human body features can be arranged from big to small according to the size of the mutual information, and also can be randomly arranged out of order.
Step S113, for feature set D2Respectively calculating the features and feature set D1Average value of mutual information of each feature in (1).
In this step, the following steps D can be performed in sequence2Taking out a feature, and calculating the feature and the feature set D for the selected feature1The mutual information of each feature in the image is calculated, and then the average value is calculated to obtain the score of the featureiThe calculation formula is shown as formula (3),
wherein, i is 11(n1Is D1Number of features in (1), n2Is D2F denotes a feature, and Y denotes a fourier coefficient.
Step S114, selecting the feature set D corresponding to the maximum mutual information average value in step S1132Into feature set D1After the original signature sequence.
According to the feature set D calculated in step S1132Selecting the feature with the maximum score and inserting the feature into the feature set D1Follows the original feature sequence and updates the feature set D1Simultaneously from feature set D2Delete the feature and update the feature set D2。
Step S115, execute step S112 to step S114 until feature set D2And if the result is null, generating a feature order corresponding to the corresponding Fourier coefficient.
Step S116, selecting one of the remaining fourier coefficients in the set of fourier coefficients, and executing step S112 until all fourier coefficients in the set of fourier coefficients have obtained corresponding feature ranks.
And executing the step, wherein each Fourier coefficient corresponds to a characteristic ordering. In this embodiment, 12 fourier coefficients correspond to 12 feature orderings.
And step S120, sorting the features corresponding to the Fourier coefficients, and obtaining the final feature sorting by calculating the mean value of the serial numbers.
In 12 feature sequences, any feature corresponds to 12 serial numbers, and the serial numbers in the final feature sequence can be obtained by performing mean value calculation on the 12 serial numbers. If the calculated values of the two feature mean values are the same, according to the sequence of each coefficient item of a preset Fourier coefficient set, selecting the sequence of two features in the feature sequence corresponding to the first coefficient item (or other specified coefficient items) to determine the sequence of the two features in the final feature sequence.
And S130, based on the final feature sorting, sequentially adding preset human body features as alternative input feature sets in sequence, respectively modeling with the Fourier coefficient sets to obtain intermediate models, and selecting the alternative input feature set corresponding to the intermediate model with the minimum mean error as the selected input feature set.
The modeling is performed based on the candidate input feature set and the fourier coefficient set, and the method is preferably performed by the following method of step S200 and step S300.
The method for selecting the alternative input feature set comprises the steps of modeling the first-ranked features and the Fourier coefficient set for the first time in the final feature ranking, increasing the second-ranked features for the second time, modeling the second-ranked features and the Fourier coefficient set, and repeating the steps in the following steps, wherein one feature is sequentially increased in each modeling to construct the alternative input feature set.
For models respectively constructed for different candidate input feature sets, the mean error of the corresponding models is calculated by adopting 5-fold cross validation, and then the candidate input feature set corresponding to the intermediate model with the minimum mean error is selected as the selected input feature set.
Through experiments, when the candidate input feature set in this embodiment includes the first six features, the error of joint angle reconstruction is the smallest, so the first six features of the final feature order are selected as the input feature set in this embodiment.
And step S200, constructing a training track generation model.
Constructing a training sample set based on the input feature set and the Fourier coefficient set; training a plurality of category regression models for the preset joints respectively based on the training sample set, and selecting the regression model with the minimum prediction error as an angle generation model of the corresponding joint; combining the obtained angle models of the plurality of joints to obtain a training track generation model of the human body part containing the preset joints; the input feature set comprises a plurality of human body feature category parameters of human bodies; the Fourier coefficient set is a coefficient item in a joint angle function obtained by fitting through a Fourier series method based on test data of a preset joint; the preset joints are joints included in the human body part of the track to be generated. In the embodiment, the human body part comprising the preset joints is a lower limb of a human body; the preset joints comprise hip joints, knee joints and ankle joints.
In this embodiment, two regression modeling methods, which are a support vector machine regression model and a random forest regression model, are adopted. The input of both models is optimized feature subset (6 features in the input feature set), and the output is 12 Fourier coefficients (omega, a)0,ai,bi(i=1,...,5))。
And constructing a training sample set and a testing sample set based on the input feature set and the Fourier coefficient set. The method comprises the steps of training three joints by simultaneously adopting two regression models through a training sample set, obtaining two trained models for each joint, then carrying out calculation-as-is-prediction-error by utilizing a test sample set, respectively selecting one model with the minimum prediction error from the two trained models corresponding to each joint as an angle generation model corresponding to the joint, and constructing a final training track generation model based on the obtained angle generation models of the three joints.
Based on the obtained gait track generation model, when a new patient exists, only 6 human body characteristics need to be measured, and the corresponding Fourier coefficients are generated through the established personalized gait track generation model, so that the gait track is reconstructed.
And step S300, adjusting the dynamic gravity center.
In the embodiment, a gravity center calculation module corresponding to the joint angle is added in the gait track generation model. And the gravity center calculation module is configured to calculate the gravity center by utilizing the geometrical relationship of the limbs and the joints based on the hip joint angle, the knee joint angle and the ankle joint angle.
When the human body walks, the gravity center can also change along with the change of the joint angle. In the process of generating an individualized gait trajectory, it is important to provide a center of gravity change curve corresponding to a change in joint angle. Especially, the change of the gravity center influences the perception of the gait of the patient in the gait rehabilitation training. In the invention, the trajectory curve of the center of gravity is calculated by constructing and simplifying a human lower limb model and utilizing the geometrical relationship between limbs and joints on the basis of the existing hip, knee and ankle joint angles.
A simplified model of the lower limbs of the human body is shown in fig. 3, in which the thigh and the calf are simplified into two links and the foot is simplified into a triangle (the internal angle near the ankle is theta)foot). The lowest point of the heel is taken as a contact point with the ground, and the height h of the gravity center is h1、h2、h3Three parts of the composition are shown as a formula (4) to a formula (7),
h=h1+h2+h3 (4)
h1=lthigh·sin(θhip) (5)
h2=lcalf·sin(θhip-θknee) (6)
wherein lthighFor thigh length,. lcalfFor the lower leg being long, /)calfIs heel length, θhipAngle of hip joint, thetakneeAngle of knee joint, θankleAngle of ankle joint, θfootTo simplify the foot to a triangular inner corner adjacent the ankle after the triangle.
By substituting the angle data of the hip, knee and ankle joints in one gait cycle into the formula (4), the cycle change curve of the gravity center can be calculated.
The training track generation model construction system based on the human body parameters comprises a first unit, a second unit and a third unit;
the first unit is configured to construct a training sample set based on an input feature set and a Fourier coefficient set;
the second unit is configured to train multiple category regression models for preset joints respectively based on the training sample set, and select a regression model with the smallest prediction error as an angle generation model of a corresponding joint;
the third unit is configured to combine the obtained angle models of the plurality of joints to obtain a training track generation model of the human body part including the preset joints;
wherein the content of the first and second substances,
the input feature set comprises a plurality of human body feature category parameters of human bodies;
the Fourier coefficient set is a coefficient item in a joint angle function obtained by fitting through a Fourier series method based on test data of a preset joint;
the preset joints are joints included in the human body part of the track to be generated.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process and related description of the system described above may refer to the corresponding process in the foregoing method embodiments, and will not be described herein again.
It should be noted that, the training trajectory generation model construction system based on human body parameters provided in the foregoing embodiment is only illustrated by the division of the functional modules, and in practical applications, the functions may be allocated to different functional modules according to needs, that is, the modules or steps in the embodiment of the present invention are further decomposed or combined, for example, the modules in the foregoing embodiment may be combined into one module, or may be further split into multiple sub-modules, so as to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not to be construed as unduly limiting the present invention.
A storage device according to a third embodiment of the present invention stores a plurality of programs, which are suitable for being loaded and executed by a processor to implement the above-mentioned training trajectory generation model construction method based on human body parameters.
A processing apparatus according to a fourth embodiment of the present invention includes a processor, a storage device; a processor adapted to execute various programs; a storage device adapted to store a plurality of programs; the program is suitable for being loaded and executed by a processor to realize the human body parameter-based training track generation model construction method.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes and related descriptions of the storage device and the processing device described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section, and/or installed from a removable medium. The computer program, when executed by a Central Processing Unit (CPU), performs the above-described functions defined in the method of the present application. It should be noted that the computer readable medium mentioned above in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The terms "first," "second," and the like are used for distinguishing between similar elements and not necessarily for describing or implying a particular order or sequence.
The terms "comprises," "comprising," or any other similar term are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (10)
1. A training track generation model construction method based on human body parameters is characterized by comprising the following steps:
constructing a training sample set based on the input feature set and the Fourier coefficient set;
training a plurality of category regression models for the preset joints respectively based on the training sample set, and selecting the regression model with the minimum prediction error as an angle generation model of the corresponding joint;
combining the obtained angle models of the plurality of joints to obtain a training track generation model of the human body part containing the preset joints;
wherein the content of the first and second substances,
the input feature set comprises a plurality of human body feature category parameters of human bodies;
the Fourier coefficient set is a coefficient item in a joint angle function obtained by fitting through a Fourier series method based on test data of a preset joint;
the preset joints are joints included in the human body part of the track to be generated.
2. The method for constructing the training trajectory generation model based on the human body parameters according to claim 1, wherein the input feature set is obtained by:
based on the initial sample set, acquiring an input feature set by adopting a maximum correlation minimum redundancy method; each sample in the initial sample set comprises parameters of an individual corresponding to a preset human body characteristic category.
3. The method for constructing a training trajectory generation model based on human body parameters according to claim 2, wherein the method for selecting the input feature set by using the maximum correlation minimum redundancy method comprises the following steps:
step S110, calculating the set of Fourier coefficients through mutual information to obtain a characteristic sequence corresponding to each Fourier coefficient based on preset human body characteristics;
s120, sorting the features corresponding to the Fourier coefficients, and obtaining final feature sorting by calculating the mean value of the serial numbers;
and S130, based on the final feature sorting, sequentially adding preset human body features as alternative input feature sets in sequence, respectively modeling with the Fourier coefficient sets to obtain intermediate models, and selecting the alternative input feature set corresponding to the intermediate model with the minimum mean error as the selected input feature set.
4. The method for constructing the training trajectory generation model based on the human body parameters according to claim 3, wherein the method comprises the following steps of, for the Fourier coefficient set, obtaining the feature sequence corresponding to each Fourier coefficient through mutual information calculation based on preset human body features:
step S111, selecting a Fourier coefficient from the Fourier coefficient set;
step S112, aiming at a single Fourier coefficient, calculating the mutual information between the single Fourier coefficient and each preset human body characteristic in sequence, and putting the preset human body characteristic corresponding to the maximum mutual information into a characteristic set D1The remaining set of features D2;
Step S113, for feature set D2Respectively calculating the features and feature set D1Average value of mutual information of each feature in (1);
step S114, selecting the feature set D corresponding to the maximum mutual information average value in step S1132Into feature set D1After the original signature sequence;
step S115, execute step S112 to step S114 until feature set D2If the number is null, generating a feature order corresponding to the corresponding Fourier coefficient;
step S116, selecting one of the remaining fourier coefficients in the set of fourier coefficients, and executing step S112 until all fourier coefficients in the set of fourier coefficients have obtained corresponding feature ranks.
5. The method for constructing the training trajectory generation model based on the human body parameters according to any one of claims 1 to 4, wherein the human body part containing the preset joints is a lower limb of a human body; the preset joints comprise hip joints, knee joints and ankle joints.
6. The method for constructing a training trajectory generation model based on human body parameters according to claim 5, wherein the training trajectory generation model further comprises a center of gravity calculation module corresponding to joint angles;
the gravity center calculation module is configured to calculate the gravity center by using the geometrical relationship between the limbs and the joints based on the hip joint angle, the knee joint angle and the ankle joint angle.
7. The method for constructing a training trajectory generation model based on human body parameters as claimed in claim 5, wherein the joint angle function f (t) obtained by Fourier series fitting based on the test data of the preset joint is
8. The method for constructing a training trajectory generation model based on human body parameters according to any one of claims 1 to 4, wherein the multiple category regression models comprise a support vector machine regression model and a random forest regression model.
9. A training track generation model building system based on human body parameters is characterized by comprising a first unit, a second unit and a third unit;
the first unit is configured to construct a training sample set based on an input feature set and a Fourier coefficient set;
the second unit is configured to train multiple category regression models for preset joints respectively based on the training sample set, and select a regression model with the smallest prediction error as an angle generation model of a corresponding joint;
the third unit is configured to combine the obtained angle models of the plurality of joints to obtain a training track generation model of the human body part including the preset joints;
wherein the content of the first and second substances,
the input feature set comprises a plurality of human body feature category parameters of human bodies;
the Fourier coefficient set is a coefficient item in a joint angle function obtained by fitting through a Fourier series method based on test data of a preset joint;
the preset joints are joints included in the human body part of the track to be generated.
10. A processing device comprising a processor, a storage device; a processor adapted to execute various programs; a storage device adapted to store a plurality of programs; characterized in that the program is adapted to be loaded and executed by a processor to implement the method for constructing a training trajectory generation model based on human body parameters according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011192281.7A CN112294599B (en) | 2020-10-30 | 2020-10-30 | Training track generation model construction method, system and device based on human body parameters |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011192281.7A CN112294599B (en) | 2020-10-30 | 2020-10-30 | Training track generation model construction method, system and device based on human body parameters |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112294599A true CN112294599A (en) | 2021-02-02 |
CN112294599B CN112294599B (en) | 2021-09-07 |
Family
ID=74332911
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011192281.7A Active CN112294599B (en) | 2020-10-30 | 2020-10-30 | Training track generation model construction method, system and device based on human body parameters |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112294599B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113018091A (en) * | 2021-02-22 | 2021-06-25 | 中国科学院深圳先进技术研究院 | Exoskeleton rehabilitation robot sharing control system and method |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2074943A1 (en) * | 2007-12-27 | 2009-07-01 | Yoshihiro Yamaguchi | System and method for analyzing waves of electrocardiogram |
WO2011037980A2 (en) * | 2009-09-22 | 2011-03-31 | Bioptigen, Inc. | Systems for extended depth frequency domain optical coherence tomography (fdoct) and related methods |
CN106156524A (en) * | 2016-07-29 | 2016-11-23 | 东北大学 | A kind of online gait planning system and method for Intelligent lower limb power assisting device |
CN106914897A (en) * | 2017-03-31 | 2017-07-04 | 长安大学 | Inverse Solution For Manipulator Kinematics method based on RBF neural |
CN108081266A (en) * | 2017-11-21 | 2018-05-29 | 山东科技大学 | A kind of method of the mechanical arm hand crawl object based on deep learning |
CN109009148A (en) * | 2018-08-24 | 2018-12-18 | 广东工业大学 | A kind of gait function appraisal procedure |
CN109968355A (en) * | 2019-03-08 | 2019-07-05 | 北京工业大学 | A kind of method that humanoid robot gait's balance model is established |
CN109991979A (en) * | 2019-03-29 | 2019-07-09 | 华中科技大学 | A kind of lower limb robot gait planing method towards complex environment |
CN110710976A (en) * | 2019-10-14 | 2020-01-21 | 深圳市迈步机器人科技有限公司 | Storage medium for personalized gait generation method, control system and exoskeleton robot |
CN110801226A (en) * | 2019-11-01 | 2020-02-18 | 西安交通大学 | Human knee joint moment testing system method based on surface electromyographic signals and application |
CN111297629A (en) * | 2020-02-25 | 2020-06-19 | 中国科学院自动化研究所 | Rehabilitation training method for simulating going upstairs and downstairs and lower limb rehabilitation robot |
-
2020
- 2020-10-30 CN CN202011192281.7A patent/CN112294599B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2074943A1 (en) * | 2007-12-27 | 2009-07-01 | Yoshihiro Yamaguchi | System and method for analyzing waves of electrocardiogram |
WO2011037980A2 (en) * | 2009-09-22 | 2011-03-31 | Bioptigen, Inc. | Systems for extended depth frequency domain optical coherence tomography (fdoct) and related methods |
CN106156524A (en) * | 2016-07-29 | 2016-11-23 | 东北大学 | A kind of online gait planning system and method for Intelligent lower limb power assisting device |
CN106914897A (en) * | 2017-03-31 | 2017-07-04 | 长安大学 | Inverse Solution For Manipulator Kinematics method based on RBF neural |
CN108081266A (en) * | 2017-11-21 | 2018-05-29 | 山东科技大学 | A kind of method of the mechanical arm hand crawl object based on deep learning |
CN109009148A (en) * | 2018-08-24 | 2018-12-18 | 广东工业大学 | A kind of gait function appraisal procedure |
CN109968355A (en) * | 2019-03-08 | 2019-07-05 | 北京工业大学 | A kind of method that humanoid robot gait's balance model is established |
CN109991979A (en) * | 2019-03-29 | 2019-07-09 | 华中科技大学 | A kind of lower limb robot gait planing method towards complex environment |
CN110710976A (en) * | 2019-10-14 | 2020-01-21 | 深圳市迈步机器人科技有限公司 | Storage medium for personalized gait generation method, control system and exoskeleton robot |
CN110801226A (en) * | 2019-11-01 | 2020-02-18 | 西安交通大学 | Human knee joint moment testing system method based on surface electromyographic signals and application |
CN111297629A (en) * | 2020-02-25 | 2020-06-19 | 中国科学院自动化研究所 | Rehabilitation training method for simulating going upstairs and downstairs and lower limb rehabilitation robot |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113018091A (en) * | 2021-02-22 | 2021-06-25 | 中国科学院深圳先进技术研究院 | Exoskeleton rehabilitation robot sharing control system and method |
Also Published As
Publication number | Publication date |
---|---|
CN112294599B (en) | 2021-09-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kidziński et al. | Automatic real-time gait event detection in children using deep neural networks | |
Mundt et al. | Prediction of lower limb joint angles and moments during gait using artificial neural networks | |
Wilson et al. | Coordination variability and skill development in expert triple jumpers | |
CN105411593A (en) | Method and apparatus for recognizing gait task | |
CN108830848A (en) | The device and system of the sequence of the vascular condition parameter on blood vessel are determined using computer | |
CN104412269B (en) | The method and apparatus that nervimotion rehabilitation is carried out using interaction scenarios system | |
CN107389052A (en) | A kind of ankle pump motion monitoring system and terminal device | |
CN112294599B (en) | Training track generation model construction method, system and device based on human body parameters | |
Jiang et al. | Model-based data augmentation for user-independent fatigue estimation | |
Du et al. | RETRACTED: Research on the intelligent model of progress in physical education training based on motion sensor | |
Vieten et al. | The kinematics of cyclic human movement | |
Alghamdi | A novel deep learning method for predicting athletes’ health using wearable sensors and recurrent neural networks | |
CN109934179B (en) | Human body action recognition method based on automatic feature selection and integrated learning algorithm | |
Kwasnicki et al. | Assessing functional mobility after lower limb reconstruction: a psychometric evaluation of a sensor-based mobility score | |
KR20190120923A (en) | Method and system for walking ability prediction using foot characteristics information | |
CN115658877B (en) | Medicine recommendation method and device based on reinforcement learning, electronic equipment and medium | |
Yeung et al. | Personalised machine learning approach to estimating knee kinematics using only shank-mounted IMU | |
Kour et al. | Sensor technology with gait as a diagnostic tool for assessment of Parkinson’s disease: a survey | |
CN111951950A (en) | Three-dimensional data medical classification system, method and device based on deep learning | |
Wurdeman | Lyapunov exponent | |
Stancic et al. | New kinematic parameters for quantifying irregularities in the human and humanoid robot gait | |
Perl et al. | Sensors, monitoring, and model-based data analysis in sports, exercise and rehabilitation | |
Graves et al. | Hippocampal Codes for Real-World Human Navigation | |
Budzyńska et al. | Verification of Selected Gait Parameters Derived from Inertial Sensors Using Simple Smartphone Based Optical System | |
CN115299934B (en) | Method, device, equipment and medium for determining test action |
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 |