CN108937847B - Method for evaluating human body movement coordination - Google Patents
Method for evaluating human body movement coordination Download PDFInfo
- Publication number
- CN108937847B CN108937847B CN201710362928.8A CN201710362928A CN108937847B CN 108937847 B CN108937847 B CN 108937847B CN 201710362928 A CN201710362928 A CN 201710362928A CN 108937847 B CN108937847 B CN 108937847B
- Authority
- CN
- China
- Prior art keywords
- phase
- coordination
- human body
- phase space
- motion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—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
- A61B5/103—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
- A61B5/1116—Determining posture transitions
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Physiology (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Neurology (AREA)
- Neurosurgery (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method for evaluating human motion coordination, which comprises the steps of reconstructing phase space according to time sequence sequences of acceleration signals of different human parts, performing denoising processing, and respectively predicting other phase spaces according to a local manifold characteristic structure of any one phase space to obtain coordination indexes of the human parts; finally, a human body movement coordination matrix is constructed and formed, and the trace of the movement coordination matrix is used as the movement coordination index of the human body; and comparing and matching the result of the motion coordination index of the human body with the result of different human bodies in the database, and outputting the motion coordination level among different parts of the human body and the overall motion coordination level. The invention solves the problem that the coordination degree of different areas of the human body in the motion process cannot be objectively quantified, thereby making up the blank of the objective quantification of the coordination of the human body at present.
Description
Technical Field
The invention relates to a method for evaluating human motion coordination.
Background
Along with the popularization of the digital health strategy, people pay more and more attention to daily exercise data, and the data can enable people to know the self exercise state in the exercise process. The human body coordination evaluation has great significance, on one hand, the evaluation can reflect the human body movement adaptive capacity from the system perspective, and on the other hand, the evaluation can also provide a target for daily exercise of the masses.
The coordination in the human body movement process refers to the fact that in the specific movement process, the matching degree of different areas is obtained by analyzing the movement states of different areas of the human body. However, because human coordination is a brand-new concept, no clear objective quantitative standard exists for human movement evaluation coordination at home and abroad. At present, the human tone evaluation method mainly adopts a subjective evaluation method and a dynamic equilibrium evaluation method for evaluation. The subjective evaluation method is judged according to the states of the limbs of the body of the subject in the process of movement and is mainly carried out in the form of a special household scale, but the evaluation standard is not uniform easily, is influenced by subjective factors easily, and cannot carry out objective evaluation on coordination. The dynamic equilibrium evaluation method indirectly reflects the coordination degree according to the statistical indexes of the overall motion of the human body, and cannot directly reflect the coordination degree of different areas of the human body in the motion process.
Disclosure of Invention
The invention aims to solve the problem that the coordination degree of different areas of a human body in the motion process cannot be objectively quantified, and further make up the blank of the current objective quantification of human body coordination.
In order to achieve the above object, the present invention provides a method for evaluating human motion coordination based on phase space analysis, which can analyze the coupling degree of four limbs, the waist and abdomen area and the upper trunk of a human body and output the result of evaluating human motion coordination, and the method comprises the following steps:
step 1: and acquiring a human body motion posture signal and preprocessing the human body motion posture signal. The human body posture signal acquisition module is responsible for recording acceleration signals of a human body worn on the left wrist, the right wrist, the left ankle, the right ankle, the neck and the waist and abdomen in real time in the motion process to form a 6-path time sequence Si(i=1,2,…,6);
Step 2: the signal preprocessing module carries out phase space reconstruction on each path of acceleration signals obtained by recording and completes denoising processing to obtain 6 high-dimensional phase space attractors A corresponding to the acceleration signals of 6 parts of the human body in the motion processi(i=1,2,…,6);
And step 3: the time sequence performs phase space and limb coordination analysis of individual movements. The motion coordination index analysis module is used for analyzing any phase space AiFor other phase spaces Aj(i not equal to j) are respectively predicted to obtain AijFurther by AijAnd AjCorrelation coefficient C between spatially corresponding time seriesijObtaining the coordination indexes of the human body parts; finally, a human body movement harmony matrix C ═ C is constructed and formedijFourthly, the trace of the motion coordination matrix C is used as the motion coordination index of the human body;
and 4, step 4: and performing overall harmony evaluation on the input motion data, and outputting harmony results of different areas of the human body. And comparing and matching the motion coordination index result of the human body with results of different human bodies in the database, and outputting the motion coordination level and the overall motion coordination level of different parts of the human body.
Has the advantages that:
firstly, reconstructing phase space according to time sequence sequences of acceleration signals of different human body parts, completing denoising processing, and then respectively predicting other phase spaces according to a local manifold characteristic structure of any one phase space to obtain harmony indexes of the human body parts; and finally, constructing and forming a human body motion coordination matrix, taking the trace of the motion coordination matrix as the overall motion coordination index of the human body, comparing and matching the result of the motion coordination index of the human body with the result of different human bodies in the database, and outputting the motion coordination level and the overall motion coordination level of different parts of the human body. The invention has the following advantages:
1. the method reflects the self-adaptive capacity of human body movement from the system perspective, comprehensively considers the phase space characteristics of each path of signal, and can effectively evaluate the overall coordination in the human body movement process. Therefore, the method can simultaneously obtain the results of the comparison of the coupling degrees between the left wrist, the right wrist, the left ankle, the right ankle, the neck and the waist and abdomen, can provide a large amount of information for evaluating the human body coordination, and further fills the blank of objective quantification of the human body coordination at present.
2. The invention provides the coupling degree analysis among all paths of signals, so that the coordination evaluation can be carried out on different regions of a human body, 0-100% evaluation results are output, the higher the numerical value is, the higher the coordination degree of the different regions is, and the objective and quantitative basis can be conveniently provided for the daily exercise of the masses.
3. The method has good robustness and operation speed, and can quickly, comprehensively and accurately evaluate the harmony evaluation index of a person under a specific task.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
The present invention will be described below with reference to specific examples, but the present invention is not limited thereto.
FIG. 1 is a schematic system flow diagram of the method of the present invention.
First, the present invention establishes a basic record of the subject based on the inputted name, sex, age, height, weight, and medical history. Before the human body moves, signal acquisition modules for measuring acceleration data of relevant areas are placed on the left wrist, the right wrist, the left ankle, the right ankle, the neck and the waist and abdomen of the human body. Then the human body walks for at least 20 minutes according to the straight line, and the body posture signal acquisition module is responsible for recording the acceleration signals of the left and right wrists, the left and right ankles, the neck and the waist and abdomen worn by the human body in real time during the movement process to form a 6-path time sequence Si(i ═ 1,2, …, 6). The collection time is 1 minute to 15 minutes, and the sampling frequency is adjustable from 100Hz to 300 Hz. And then the signal preprocessing module carries out regularization denoising on each path of recorded acceleration signals. The signal preprocessing module can adopt a regularization denoising method to carry out a constraint optimization strategy, for example, the regularization denoising method is used for optimizing by calculating the Lyapunov index of each path of acceleration signal as a regularization term condition; argmin | | f-f0| | + λ L, wherein L is the Lyapunov index; or the entropy indexes of all paths of acceleration signals are calculated to be used as regular term conditions for optimization; argmin | | f-f0| | + λ En, wherein En is information entropy; or the phase space denoising is finished by adopting a local manifold projection method or principal component analysis based on the phase space octave geometry.
The motion coordination index analysis module obtains a high-dimensional phase space of each signal by reconstructing the phase space of each de-noised signal, and obtains 6 high-dimensional phase space attractors A corresponding to the acceleration signals of 6 parts of the human body in the motion processi(i ═ 1,2, …, 6); and adopting a Takens phase space reconstruction method, wherein the embedding dimension and the delay time are determined by a correlation dimension and mutual information method.
Any two phase spaces are used for mapping coverage prediction of local manifold structure, the motion coordination index is used for predicting the phase spaces of acceleration signals of different human body parts in pairs on the premise of keeping the characteristics of the local manifold structure of the phase spaces, and further the correlation between the actual signal result and the passing phase space prediction result is further usedThe coefficient is used as the coordination index between different parts of the human body; wherein the local manifold feature of the phase space is a phase point x in the phase spaceiThe relative position relationship of nearest neighbors within the Euclidean distance range; for any phase point x in the reconstruction phase spaceiSelect and x in order from small to largeiThe nearest k phase points form a neighborhood point group xip(p ═ 1,2, …, k); wherein the selection range of k is m +1 to 2m, and m is the embedding dimension of the reconstruction phase space; phase point xiPartial manifold structure of (2):
wherein, WipIs a phase point xiPhase point x within neighborhood point groupipWeight coefficient of (d):
dipis a phase separation point xiAnd xipEuclidean distance, di1Is a phase separation point xiAnd xipThe minimum euclidean distance.
The method for predicting the phase space of the acceleration signals of different human body parts in pairs is to predict a certain phase space AiAny one of phase points x iniRespectively applied to other phase spaces A according to own local manifold characteristic structurej(i ≠ j), the corresponding predicted phase point is obtained:
traverse AiAll phase points in, all predicted phase points xjComposition AiTo AjPredicted phase space A ofij;
The coordination among different parts of the human body is a predicted phase space AijCorresponding time series SijAnd the original reconstruction phase space AjCorresponding time series S of acceleration signalsjMake pairwise correlationSexual analysis to obtain correlation coefficient CijAs an index of coordination between the two sites; finally, a human body movement harmony matrix C ═ C is constructed and formedijAnd taking the trace of the motion coordination matrix C as the overall motion coordination index of the human body.
The motion coordination level output module comprises a crowd database with different motion coordination degrees, and provides the level of coordination among different parts of the testee in the recorded crowd by comparing and matching the motion coordination indexes of individuals in the database.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make numerous possible variations and modifications to the present invention, or modify equivalent embodiments, using the methods and techniques disclosed above, without departing from the scope of the present invention. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (6)
1. A method for evaluating human motion coordination, comprising the steps of:
1) recording acceleration signals of different parts of a human body in the motion process in real time to form a time sequence Si,i=1,2,…,n;
2) Performing phase space reconstruction on the time sequence of the acceleration signal of each part and completing denoising processing to obtain a high-dimensional phase space attractor corresponding to the acceleration signal;
3) on the premise of maintaining the local manifold structure characteristics of the phase space, the phase spaces of the acceleration signals of different human body parts are predicted pairwise, and the prediction method is to predict a certain phase space AiAny one of phase points x iniRespectively applied to other phase spaces A according to the characteristics of local manifold structuresjObtaining a corresponding predicted phase point: traverse AiAll phase points in the phase, all predicted phase points constitute AiTo AjPredicted phase space A ofij;
4) Predicting the phase space AijCorresponding time series SijAnd the original reconstruction phase space AjCorresponding time series S of acceleration signalsjPerforming pairwise correlation analysis to obtain correlation coefficient CijAs an index of motor coordination between different parts; constructing and forming a human body movement harmony matrix C ═ { C ═ CijAnd the trace of the motion coordination matrix C is used as the overall motion coordination index of the human body;
5) comparing and matching the motion coordination indexes among different parts in the step 4) and the overall motion coordination indexes of the human body with results of different human bodies in the database, and outputting the motion coordination levels among different parts of the human body and the overall motion coordination levels.
2. The method for evaluating the movement coordination of the human body according to claim 1, wherein the acceleration signals in step 1) are taken from the left wrist, the right wrist, the left ankle, the right ankle, the neck and the abdomen of the human body.
3. The method for evaluating human motion coordination according to claim 1, wherein the optimization in step 2) is performed by calculating lyapunov exponent of each acceleration signal as a regularization term condition.
4. The method for evaluating human motion coordination according to claim 1, wherein the optimization in step 2) is performed by calculating entropy indexes of the acceleration signals of each path as a regularization term condition.
5. The method for evaluating human motion coordination according to claim 1, wherein the phase space denoising in step 2) is performed by using a local manifold projection method or principal component analysis based on a phase space octave geometry.
6. The method of evaluating human movement coordination according to claim 1, characterized by the steps ofStep 3) the local manifold structure of the phase space is characterized by a certain phase point x in the phase spaceiThe relative position relationship of nearest neighbors within the Euclidean distance range; for any phase point x in the reconstruction phase spaceiSelect and x in order from small to largeiThe nearest k phase points form a neighborhood point group xipP is 1,2, …, k; wherein the selection range of k is m +1 to 2m, and m is the embedding dimension of the reconstruction phase space; phase point xiPartial manifold structure of (2):
wherein, wipIs a phase point xiPhase point x within neighborhood point groupipWeight coefficient of (d):
dipis a phase separation point xiAnd xipEuclidean distance, di1Is a phase separation point xiAnd xipThe minimum euclidean distance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710362928.8A CN108937847B (en) | 2017-05-22 | 2017-05-22 | Method for evaluating human body movement coordination |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710362928.8A CN108937847B (en) | 2017-05-22 | 2017-05-22 | Method for evaluating human body movement coordination |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108937847A CN108937847A (en) | 2018-12-07 |
CN108937847B true CN108937847B (en) | 2020-10-09 |
Family
ID=64462578
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710362928.8A Active CN108937847B (en) | 2017-05-22 | 2017-05-22 | Method for evaluating human body movement coordination |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108937847B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103064821A (en) * | 2012-12-26 | 2013-04-24 | 中国科学技术大学 | Method and device for analyzing dynamic signals |
CN104933488A (en) * | 2015-06-30 | 2015-09-23 | 中国铁道科学研究院通信信号研究所 | Fault rate prediction method of ATP (Automatic Train Protection) vehicle-mounted equipment |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6442421B1 (en) * | 2000-04-27 | 2002-08-27 | Centre National De La Recherche Scientifique | Method for the medical monitoring in real time of a patient from the analysis of electroencephalograms to characterize and differentiate between physiological or pathological conditions, and a method for anticipating epileptic seizures |
EP2007277A4 (en) * | 2006-04-18 | 2010-06-02 | Susan Mirow | Method and apparatus for analysis of psychiatric and physical conditions |
CN102567638B (en) * | 2011-12-29 | 2018-08-24 | 无锡微感科技有限公司 | A kind of interactive upper limb healing system based on microsensor |
US9478147B2 (en) * | 2012-05-17 | 2016-10-25 | The University Of Connecticut | Methods and apparatus for interpersonal coordination analysis and training |
US20140288878A1 (en) * | 2013-03-15 | 2014-09-25 | Aliphcom | Identification of motion characteristics to determine activity |
CN103400154B (en) * | 2013-08-09 | 2016-08-10 | 电子科技大学 | A kind of based on the human motion recognition method having supervision Isometric Maps |
CN104757968A (en) * | 2014-08-08 | 2015-07-08 | 沈阳工业大学 | Statistical evaluation method for intermediate data of paroxysmal conditions of children's absence epilepsy |
CN104748961A (en) * | 2015-03-30 | 2015-07-01 | 中国矿业大学 | Gear fault diagnosis method based on SVD decomposition and noise reduction and correlation EEMD entropy features |
CN105203645B (en) * | 2015-06-08 | 2018-03-13 | 中国铁路总公司 | A kind of high-speed switch crackle hurt intelligent detecting method based on vibration signal fusion |
US10244990B2 (en) * | 2015-09-30 | 2019-04-02 | The Board Of Trustees Of The University Of Alabama | Systems and methods for rehabilitation of limb motion |
-
2017
- 2017-05-22 CN CN201710362928.8A patent/CN108937847B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103064821A (en) * | 2012-12-26 | 2013-04-24 | 中国科学技术大学 | Method and device for analyzing dynamic signals |
CN104933488A (en) * | 2015-06-30 | 2015-09-23 | 中国铁道科学研究院通信信号研究所 | Fault rate prediction method of ATP (Automatic Train Protection) vehicle-mounted equipment |
Also Published As
Publication number | Publication date |
---|---|
CN108937847A (en) | 2018-12-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105167742B (en) | A kind of fetal weight adaptive estimation method and system | |
CN111728590A (en) | Individual cognitive ability prediction method and system based on dynamic function connection | |
CN111643321B (en) | Exoskeleton joint angle prediction method and system based on sEMG signals | |
Li et al. | Abnormal sitting posture recognition based on multi-scale spatiotemporal features of skeleton graph | |
CN110269605B (en) | Electrocardiosignal noise identification method based on deep neural network | |
CN116110597B (en) | Digital twinning-based intelligent analysis method and device for patient disease categories | |
CN109567313B (en) | Intelligent insole with biological characteristic recognition function | |
CN111798980A (en) | Complex medical biological signal processing method and device based on deep learning network | |
CN114550299A (en) | System and method for evaluating daily life activity ability of old people based on video | |
CN114155952A (en) | Senile dementia illness auxiliary analysis system for elderly people | |
CN116935009B (en) | Operation navigation system for prediction based on historical data analysis | |
CN116186561B (en) | Running gesture recognition and correction method and system based on high-dimensional time sequence diagram network | |
CN108937847B (en) | Method for evaluating human body movement coordination | |
CN110801228B (en) | Brain effect connection measurement method based on neural network prediction | |
CN112768074A (en) | Artificial intelligence-based serious disease risk prediction method and system | |
CN113197558A (en) | Heart rate and respiratory rate detection method and system and computer storage medium | |
CN115147768B (en) | Fall risk assessment method and system | |
CN113869090A (en) | Fall risk assessment method and device | |
Vijayvargiya et al. | PC-GNN: Pearson Correlation-Based Graph Neural Network for Recognition of Human Lower Limb Activity Using sEMG Signal | |
CN116543455A (en) | Method, equipment and medium for establishing parkinsonism gait damage assessment model and using same | |
CN105138835B (en) | Human body composition Forecasting Methodology based on physiologic information entropy | |
CN114202772B (en) | Reference information generation system and method based on artificial intelligence and intelligent medical treatment | |
CN113283465B (en) | Diffusion tensor imaging data analysis method and device | |
CN113255462A (en) | Gait scoring method, system, computer program product and readable storage medium | |
CN108926326B (en) | Method for evaluating dynamic balance control capability of human body along with motion platform |
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 |