CN111227796A - Balance obstacle quantitative evaluation method and system based on multi-mode fusion of support vector machine - Google Patents
Balance obstacle quantitative evaluation method and system based on multi-mode fusion of support vector machine Download PDFInfo
- Publication number
- CN111227796A CN111227796A CN202010033220.XA CN202010033220A CN111227796A CN 111227796 A CN111227796 A CN 111227796A CN 202010033220 A CN202010033220 A CN 202010033220A CN 111227796 A CN111227796 A CN 111227796A
- Authority
- CN
- China
- Prior art keywords
- vector machine
- support vector
- balance
- lower limb
- parameters
- 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.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4005—Detecting, measuring or recording for evaluating the nervous system for evaluating the sensory system
- A61B5/4023—Evaluating sense of balance
-
- 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]
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Neurology (AREA)
- Neurosurgery (AREA)
- Physiology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of balance obstacle assessment, in particular to a balance obstacle quantitative assessment method and system based on multi-mode fusion of a support vector machine. The method comprises the following steps: acquiring multi-mode parameters of lower limb balance; establishing a support vector machine classifier to train the acquired lower limb balance multi-mode parameters; and (4) adopting a support vector machine classifier to perform classification output. In the balance disorder quantitative evaluation method and system based on the multi-mode fusion of the support vector machine, gait kinematic parameters are collected by a dynamic catcher, dynamic parameters of gait are obtained by a plantar pressure sensor, electromyographic signals of lower limb movement are obtained by an electromyographic signal collecting device, the support vector machine is trained on the basis of multi-mode data with definite levels by combining a balance scale guide, a disease classification guide and a clear level, the three aspects of convergence speed, stability and classification effect are evaluated, and quantitative evaluation is realized.
Description
Technical Field
The invention relates to the technical field of balance obstacle assessment, in particular to a balance obstacle quantitative assessment method and system based on multi-mode fusion of a support vector machine.
Background
From the physiological point of view, the balance function control is an integration processing of information from various aspects such as proprioception, vision, and vestibular system in muscles, tendons, and joints by a multi-level nerve center including vestibular nuclei, brainstem network, spinal cord, cerebellum, and cerebral cortex, and the body is regulated by a muscle tissue related to the balance function, so that the body maintains a stable center of gravity on a sole limited support plane.
At present, whether a patient has balance disorder (a reference line is determined) and the condition with the balance disorder is graded according to the Berg clinical scale, so that a plurality of items need to be referred, the boundary is not obvious, the grading effect is poor, and quantitative evaluation cannot be achieved.
Disclosure of Invention
The invention aims to provide a balance obstacle quantitative evaluation method and system based on multi-mode fusion of a support vector machine, so as to solve the problems in the background technology.
In order to solve the above technical problem, an object of the present invention is to provide a method for quantitatively evaluating a balance fault under multi-modal fusion based on a support vector machine, which includes the following steps:
s1, collecting and obtaining lower limb balance multi-mode parameters;
s2, establishing a support vector machine classifier to train the acquired lower limb balance multi-modal parameters;
and S3, adopting a support vector machine classifier to perform classification output.
Preferably, in S1, the method for acquiring the multi-modal parameters of lower limb balance includes an electromyographic signal processing and feature extraction method, a motion capture feature extraction method, and a human plantar pressure center feature extraction method.
Preferably, the electromyographic signal processing and feature extracting method includes the steps of:
s1.1, performing baseline removal and denoising on the surface electromyography signals by using empirical mode decomposition;
s1.2, performing feature extraction on the surface myoelectric signal by using the basic scale entropy (the basic scale entropy has the advantage of strong anti-noise interference capability of approximate entropy, and the calculation complexity is close to the approximate entropy and the sample entropy is small due to the adoption of a dynamic programming method).
The electromyographic signal (EMG) is a weak signal with the amplitude not more than 5 millivolts, and the noise interference of the surface electromyographic signal (sEMG) comprises the following components:
crosstalk of muscle groups near the electrodes;
acquiring the interference of the equipment;
power supply interference, environmental interference, etc.
Preferably, the motion capture feature extraction method includes the steps of:
s2.1, obtaining three-dimensional coordinates of corresponding nodes of the human body by utilizing a motion capture system (multiple points);
and S2.2, deducing first-order characteristics and second-order characteristics of the three-dimensional coordinates of the key parts.
Preferably, the method for extracting the human body plantar pressure center features comprises the following steps:
s3.1, calculating a track area, wherein the track area refers to the area of an area covered by a pressure center in one experimental period, and is a common characteristic for evaluating balance capacity because the track area can reflect the swing range of a body;
s3.2, calculating a left-right gravity center distribution ratio and a front-back gravity center distribution ratio, wherein if the geometric center of the pressure platform is taken as the origin of coordinates, the left-right gravity center distribution ratio and the front-back gravity center distribution ratio respectively refer to the ratio of the number of the pressure centers distributed on the left and the right of the longitudinal axis and the ratio of the number of the pressure centers distributed on the upper and the lower of the horizontal axis;
s3.3, calculating the track length of COP, wherein the calculation formula is as follows:
the left and right trajectory length calculation formula of COP:
the calculation formula of the front and back trajectory length of COP is as follows:
x and y are coordinate values of the pressure center, and n is the sampling frequency × t.
S3.4, calculating the moving swing diameter, wherein the moving swing diameter refers to the maximum deviation range of the pressure center, and can be divided into a left moving swing diameter, a right moving swing diameter and a front moving swing diameter and a rear moving swing diameter according to the deviation direction of the gravity center, the moving swing diameter and the gravity center are similar in distribution ratio, and the moving swing diameter can be divided into the left moving swing diameter, the right moving swing diameter and the front moving swing diameter and the rear moving swing diameter, which are respectively:
Dx＝xmax-xmin；
Dy＝ymax-ymin；
where xmax refers to the maximum deflection of the center of pressure in the positive direction of the abscissa and xmin refers to the maximum deflection of the center of pressure in the negative direction of the abscissa; similarly, ymax and ymin represent the maximum deflection of the center of pressure in the forward and reverse directions of the longitudinal axis, respectively.
Preferably, in S2, the method for training multi-modal parameters of lower limb balance includes the following steps:
s4.1, the working principle of the support vector machine is to find the maximum interval and finally convert the maximum interval into a problem of solving the optimal solution by convex quadratic programming, and the formula is as follows:
s.t.yi(wTxi+b)≥1,i＝1,2,...,m.
w represents the coefficient of the classification hyperplane, b is a constant;
s4.2, because some samples can not find a hyperplane in the low dimension, two types of samples can be correctly divided, and at the moment, the original sample needs to be mapped to a higher linear separable dimension for division through a mapping function phi (x);
s4.3, phi (x) can appear in the solving processi)Tφ(xj) For the inner product after the sample is mapped to the feature space, the feature space dimension may be very high or even infinite, the calculation is difficult, and a kernel function is introduced to avoid the problem;
the kernel function is of many kinds, and may be constructed by selecting a linear kernel, a polynomial kernel gaussian kernel, a laplacian kernel, a Sigmoid kernel, or the like.
All samples meet constraint conditions and are difficult to realize, the interval is maximized in a real task, meanwhile, some samples are allowed to not meet the constraint, the samples are only required to be few enough, the interval between two heterogeneous support vectors is called as soft interval, in mathematical solution w and b, a loss function is introduced, commonly used substitution loss functions comprise change loss, exponential loss, contrast loss and the like, and the change loss function is used in the method:
lhinge(z)＝max(0,1-z)。
preferably, in S3, the method for the support vector machine classifier to output the classification includes: when a new sample is classified and predicted by using the soft interval SVM, if the new sample is classified and predicted to be a positive class, otherwise, the new sample is classified and predicted to be a negative class.
Another object of the present invention is to provide a system for quantitative assessment of balance impairment based on multi-modal fusion of support vector machines, comprising:
a parameter acquisition module: the system is used for acquiring and obtaining multi-mode parameters of lower limb balance;
a support vector machine training module: the system is used for establishing a support vector machine classifier to train the acquired lower limb balance multi-modal parameters;
a classification output module: the support vector machine classifier is used for classifying and outputting.
The present invention also provides a device for quantitative assessment of balance fault under multi-modal fusion based on support vector machine, comprising a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method for quantitative assessment of balance fault under multi-modal fusion based on support vector machine as described above when executing the computer program.
The fourth objective of the present invention is to provide a computer-readable storage medium, wherein at least one program is stored in the storage medium, and the at least one program is executed by the processor to implement the steps of the method for quantitative assessment of balance fault under multi-modal fusion based on support vector machine as described in any one of the above.
Compared with the prior art, the invention has the beneficial effects that: in the balance disorder quantitative evaluation method and system based on the multi-mode fusion of the support vector machine, gait kinematic parameters are collected by a dynamic catcher, gait kinetic parameters are obtained by a plantar pressure sensor, electromyographic signals of lower limb movement are obtained by an electromyographic signal collecting device, multi-mode data characteristics obtained by the three modes are extracted, a balance scale guide and a disease classification guide are combined, the support vector machine with different linear kernels, multi-term kernels, Gaussian kernels and the like is trained on the basis of multi-mode data with definite disease labeling and grade definition, and the convergence speed, the stability and the classification effect are evaluated to realize quantitative evaluation.
Drawings
FIG. 1 is an overall flow diagram of the present invention;
FIG. 2 is a flow chart of the electromyographic signal processing and feature extraction method of the present invention;
FIG. 3 is a flow chart of a motion capture feature extraction method of the present invention;
FIG. 4 is a flow chart of the method for extracting the center characteristics of human plantar pressure according to the present invention;
FIG. 5 is a flow chart of a lower limb balance multi-modal parameter training of the present invention;
fig. 6 is a schematic structural diagram of the device for quantitatively evaluating the balance fault based on the multi-modal fusion of the support vector machine.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1-6, the present invention provides a technical solution:
the invention provides a balance obstacle quantitative evaluation method based on support vector machine multi-mode fusion, which comprises the following steps:
s1, collecting and obtaining lower limb balance multi-mode parameters;
s2, establishing a support vector machine classifier to train the acquired lower limb balance multi-modal parameters;
and S3, adopting a support vector machine classifier to perform classification output.
In this embodiment, in S1, the method for acquiring the multi-modal parameters of lower limb balance includes an electromyographic signal processing and feature extraction method, a motion capture feature extraction method, and a human plantar pressure center feature extraction method.
Further, the electromyographic signal processing and feature extraction method comprises the following steps:
s1.1, performing baseline removal and denoising on the surface electromyography signals by using empirical mode decomposition;
s1.2, performing feature extraction on the surface myoelectric signal by using the basic scale entropy (the basic scale entropy has the advantage of strong anti-noise interference capability of approximate entropy, and the calculation complexity is close to the approximate entropy and the sample entropy is small due to the adoption of a dynamic programming method).
Wherein, the electromyographic signal (EMG) is a weak signal with the amplitude not more than 5 millivolts, and the noise interference of the surface electromyographic signal (sEMG) comprises:
crosstalk of muscle groups near the electrodes;
acquiring the interference of the equipment;
power supply interference, environmental interference, etc.
Specifically, the motion capture feature extraction method includes the steps of:
s2.1, obtaining three-dimensional coordinates of corresponding nodes of the human body by utilizing a motion capture system (multiple points);
and S2.2, deducing first-order characteristics and second-order characteristics of the three-dimensional coordinates of the key parts.
It is worth to be noted that the human plantar pressure center feature extraction method comprises the following steps:
s3.1, calculating a track area, wherein the track area refers to the area of an area covered by a pressure center in one experimental period, and is a common characteristic for evaluating balance capacity because the track area can reflect the swing range of a body;
s3.2, calculating a left-right gravity center distribution ratio and a front-back gravity center distribution ratio, wherein if the geometric center of the pressure platform is taken as the origin of coordinates, the left-right gravity center distribution ratio and the front-back gravity center distribution ratio respectively refer to the ratio of the number of the pressure centers distributed on the left and the right of the longitudinal axis and the ratio of the number of the pressure centers distributed on the upper and the lower of the horizontal axis;
s3.3, calculating the track length of COP, wherein the calculation formula is as follows:
the left and right trajectory length calculation formula of COP:
the calculation formula of the front and back trajectory length of COP is as follows:
x and y are coordinate values of the pressure center, and n is the sampling frequency × t.
S3.4, calculating the moving swing diameter, wherein the moving swing diameter refers to the maximum deviation range of the pressure center, and can be divided into a left moving swing diameter, a right moving swing diameter and a front moving swing diameter and a rear moving swing diameter according to the deviation direction of the gravity center, the moving swing diameter and the gravity center are similar in distribution ratio, and the moving swing diameter can be divided into the left moving swing diameter, the right moving swing diameter and the front moving swing diameter and the rear moving swing diameter, which are respectively:
Dx＝xmax-xmin；
Dy＝ymax-ymin；
where xmax refers to the maximum deflection of the center of pressure in the positive direction of the abscissa and xmin refers to the maximum deflection of the center of pressure in the negative direction of the abscissa; similarly, ymax and ymin represent the maximum deflection of the center of pressure in the forward and reverse directions of the longitudinal axis, respectively.
Still further, in S2, the method for training multi-modal parameters of lower limb balance includes the following steps:
s4.1, the working principle of the support vector machine is to find the maximum interval and finally convert the maximum interval into a problem of solving the optimal solution by convex quadratic programming, and the formula is as follows:
s.t.yi(wTxi+b)≥1,i＝1,2,...,m.
w represents the coefficient of the classification hyperplane, b is a constant;
s4.2, because some samples can not find a hyperplane in the low dimension, two types of samples can be correctly divided, and at the moment, the original sample needs to be mapped to a higher linear separable dimension for division through a mapping function phi (x);
s4.3, phi (x) can appear in the solving processi)Tφ(xj) For the inner product after the sample is mapped to the feature space, the feature space dimension may be very high or even infinite, the calculation is difficult, and a kernel function is introduced to avoid the problem;
it should be noted that there are many kinds of kernel functions, and a linear kernel, a polynomial kernel gaussian kernel, a laplacian kernel, a Sigmoid kernel, or the like can be selected and configured.
All samples meet constraint conditions and are difficult to realize, the interval is maximized in a real task, meanwhile, some samples are allowed to not meet the constraint, the samples are only required to be few enough, the interval between two heterogeneous support vectors is called as soft interval, in mathematical solution w and b, a loss function is introduced, commonly used substitution loss functions comprise change loss, exponential loss, contrast loss and the like, and the change loss function is used in the method:
lhinge(z)＝max(0,1-z)。
in S3, the method for supporting the vector machine classifier to perform classification output includes: when a new sample is classified and predicted by using the soft interval SVM, if the new sample is classified and predicted to be a positive class, otherwise, the new sample is classified and predicted to be a negative class.
Another object of the present invention is to provide a system for quantitative assessment of balance impairment based on multi-modal fusion of support vector machines, comprising:
a parameter acquisition module: the system is used for acquiring and obtaining multi-mode parameters of lower limb balance;
a support vector machine training module: the system is used for establishing a support vector machine classifier to train the acquired lower limb balance multi-modal parameters;
a classification output module: the support vector machine classifier is used for classifying and outputting.
It should be noted that the functions of the parameter acquisition module, the support vector machine training module, and the classification output module are specifically described in the description of the method portion corresponding to each module, and are not described herein again.
Referring to fig. 6, a schematic structural diagram of a device for quantitative evaluation of balance fault based on multi-modal fusion of support vector machines according to an embodiment of the present invention is shown, where the device includes a processor, a memory, and a bus.
The processor comprises one or more processing cores, the processor is connected with the processor through a bus, the memory is used for storing program instructions, and when the processor executes the program instructions in the memory, the balance obstacle quantitative evaluation method based on the support vector machine multi-modal fusion is realized.
Alternatively, the memory may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
In addition, the present invention further provides a computer-readable storage medium, in which at least one program is stored, and the at least one program is executed by the processor to implement the steps of the method for quantitative assessment of balance fault under multi-modal fusion based on support vector machine as described in any one of the above.
Optionally, the present invention further provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the steps of the method for quantitative assessment of balance fault based on multi-modal fusion of support vector machines in the above aspects.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by hardware related to instructions of a program, where the program may be stored in a computer readable storage medium, and the above mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A balance obstacle quantitative evaluation method based on support vector machine multi-mode fusion comprises the following steps:
s1, collecting and obtaining lower limb balance multi-mode parameters;
s2, establishing a support vector machine classifier to train the acquired lower limb balance multi-modal parameters;
and S3, adopting a support vector machine classifier to perform classification output.
2. The method for quantitatively evaluating the balance fault under the multimodal fusion based on the support vector machine according to claim 1, is characterized in that: in S1, the method for acquiring the multi-modal parameters of lower limb balance includes an electromyographic signal processing and feature extraction method, a motion capture feature extraction method, and a human plantar pressure center feature extraction method.
3. The method for quantitatively evaluating the balance fault under the multimodal fusion based on the support vector machine according to claim 2, is characterized in that: the electromyographic signal processing and feature extraction method comprises the following steps:
s1.1, performing baseline removal and denoising on the surface electromyography signals by using empirical mode decomposition;
s1.2, extracting the features of the surface myoelectric signals by using the basic scale entropy.
4. The method for quantitatively evaluating the balance fault under the multimodal fusion based on the support vector machine according to claim 2, is characterized in that: the motion capture feature extraction method comprises the following steps:
s2.1, obtaining three-dimensional coordinates of corresponding nodes of the human body by utilizing a motion capture system (multiple points);
and S2.2, deducing first-order characteristics and second-order characteristics of the three-dimensional coordinates of the key parts.
5. The method for quantitatively evaluating the balance fault under the multimodal fusion based on the support vector machine according to claim 2, is characterized in that: the method for extracting the human body plantar pressure center features comprises the following steps:
s3.1, calculating the area of the track;
s3.2, calculating a left-right gravity center distribution ratio and a front-back gravity center distribution ratio;
s3.3, calculating the track length of COP, wherein the calculation formula is as follows:
the left and right trajectory length calculation formula of COP:
the calculation formula of the front and back trajectory length of COP is as follows:
x and y are coordinate values of the pressure center, and n is the sampling frequency x t;
s3.4, calculating the moving swing diameter, wherein the formula is as follows:
Dx＝xmax-xmin；
Dy＝ymax-ymin；
where xmax refers to the maximum deflection of the center of pressure in the positive direction of the abscissa and xmin refers to the maximum deflection of the center of pressure in the negative direction of the abscissa; ymax and ymin represent the maximum deflection of the center of pressure in the forward and reverse directions of the longitudinal axis, respectively.
6. The method for quantitatively evaluating the balance fault under the multimodal fusion based on the support vector machine according to claim 1, is characterized in that: in S2, the method for training multi-modal lower limb balance parameters includes the following steps:
s4.1, searching a maximum interval, converting the maximum interval into convex quadratic programming and solving an optimal solution, wherein the formula is as follows:
s.t.yi(wTxi+b)≥1,i＝1,2,...,m.
w represents the coefficient of the classification hyperplane, b is a constant;
s4.2, mapping the original sample through a mapping function phi (x);
s4.3, introducing a kernel function.
7. The method for quantitatively evaluating the balance fault under the multimodal fusion based on the support vector machine according to claim 1, is characterized in that: in S3, the method for supporting the vector machine classifier to output the classification includes: judgment of wTxi+b>And if 0 is true, predicting the class as a positive class, otherwise, predicting the class as a negative class.
8. A balance obstacle quantitative evaluation system based on support vector machine multi-mode fusion comprises:
a parameter acquisition module: the system is used for acquiring and obtaining multi-mode parameters of lower limb balance;
a support vector machine training module: the system is used for establishing a support vector machine classifier to train the acquired lower limb balance multi-modal parameters;
a classification output module: the support vector machine classifier is used for classifying and outputting.
9. The utility model provides a balanced obstacle quantitative evaluation device based on under support vector machine multimode fusion which characterized in that: the method comprises a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to realize the steps of the method for quantitatively evaluating the balance obstacle under the multi-modal fusion based on the support vector machine according to any one of claims 1 to 4.
10. A computer-readable storage medium, wherein at least one program is stored in the storage medium, and the at least one program is executed by the processor to implement the steps of the method for quantitative assessment of balance impairment based on support vector machine multimodal fusion according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033220.XA CN111227796A (en) | 2020-01-13 | 2020-01-13 | Balance obstacle quantitative evaluation method and system based on multi-mode fusion of support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033220.XA CN111227796A (en) | 2020-01-13 | 2020-01-13 | Balance obstacle quantitative evaluation method and system based on multi-mode fusion of support vector machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111227796A true CN111227796A (en) | 2020-06-05 |
Family
ID=70880812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010033220.XA Pending CN111227796A (en) | 2020-01-13 | 2020-01-13 | Balance obstacle quantitative evaluation method and system based on multi-mode fusion of support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111227796A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114533041A (en) * | 2022-01-24 | 2022-05-27 | 西安交通大学 | Automatic assessment method for spinal cord injury limb dysfunction based on clustering |
| CN116766207A (en) * | 2023-08-02 | 2023-09-19 | 中国科学院苏州生物医学工程技术研究所 | Robot control method based on multi-mode signal motion intention recognition |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017058913A1 (en) * | 2015-09-28 | 2017-04-06 | Case Western Reserve University | Wearable and connected gait analytics system |
| CN107368752A (en) * | 2017-07-25 | 2017-11-21 | 北京工商大学 | A kind of depth difference method for secret protection based on production confrontation network |
-
2020
- 2020-01-13 CN CN202010033220.XA patent/CN111227796A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017058913A1 (en) * | 2015-09-28 | 2017-04-06 | Case Western Reserve University | Wearable and connected gait analytics system |
| CN107368752A (en) * | 2017-07-25 | 2017-11-21 | 北京工商大学 | A kind of depth difference method for secret protection based on production confrontation network |
Non-Patent Citations (2)
| Title |
|---|
| 王新栋: "平衡能力感知的多角度刺激与测量评估研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
| 许国根等: "《模式识别与智能计算的MATLAB实现 第2版》", 31 July 2017, 北京航空航天大学出版社 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114533041A (en) * | 2022-01-24 | 2022-05-27 | 西安交通大学 | Automatic assessment method for spinal cord injury limb dysfunction based on clustering |
| CN116766207A (en) * | 2023-08-02 | 2023-09-19 | 中国科学院苏州生物医学工程技术研究所 | Robot control method based on multi-mode signal motion intention recognition |
| CN116766207B (en) * | 2023-08-02 | 2024-05-28 | 中国科学院苏州生物医学工程技术研究所 | Robot control method based on multi-mode signal motion intention recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3617815B1 (en) | Work support device, work support method, and work support program | |
| Benalcázar et al. | Hand gesture recognition using machine learning and the Myo armband | |
| Li et al. | An automatic user-adapted physical activity classification method using smartphones | |
| CN109069066A (en) | Wearable and connection gait analysis system | |
| CN111227796A (en) | Balance obstacle quantitative evaluation method and system based on multi-mode fusion of support vector machine | |
| CN110991268A (en) | Depth image-based Parkinson hand motion quantization analysis method and system | |
| CN112733772B (en) | Method and system for detecting real-time cognitive load and fatigue degree in warehouse picking task | |
| CN108634969B (en) | Emotion detection device, emotion detection system, emotion detection method, and storage medium | |
| Silva et al. | One lead ECG based personal identification with feature subspace ensembles | |
| CN107480635B (en) | Glance signal identification method and system based on bimodal classification model fusion | |
| Aghagolzadeh et al. | Latent state-space models for neural decoding | |
| Nguyen et al. | Unsupervised clustering of free-living human activities using ambulatory accelerometry | |
| Aarthy et al. | RETRACTED ARTICLE: Time series real time naive bayes electrocardiogram signal classification for efficient disease prediction using fuzzy rules | |
| Radmand et al. | Investigation of optimum pattern recognition methods for robust myoelectric control during dynamic limb movement | |
| Merdjanovska et al. | Cross-database generalization of deep learning models for arrhythmia classification | |
| Fattah et al. | Basic hand action classification based on surface EMG using autoregressive reflection coefficient | |
| Wu et al. | Classification and simulation of process of linear change for grip force at different grip speeds by using supervised learning based on sEMG | |
| CN111297366B (en) | Data processing method and diagnosis device for assisting disease diagnosis based on daily necessities | |
| US20090012921A1 (en) | Method for identifying a person's posture | |
| CN110801227A (en) | Method and system for testing three-dimensional color block obstacle based on wearable equipment | |
| CN111134670A (en) | Multi-mode balance obstacle quantitative evaluation method and system based on generation countermeasure network | |
| CN108926814B (en) | Personalized human body balance training system | |
| CN110403631A (en) | A kind of Noninvasive intracranial pressure measurement method based on continuous ultrasound image | |
| Gupta et al. | Optimization of Data Quality Related EMG Feature Extraction Parameters to Increase Hand Movement Classification Accuracy | |
| He et al. | Simulation system for myoelectric hand prosthesis using augmented reality |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |