CN111383733B - Motion monitoring and correcting method, device, equipment and storage medium based on knee joint motion signals - Google Patents
Motion monitoring and correcting method, device, equipment and storage medium based on knee joint motion signals Download PDFInfo
- Publication number
- CN111383733B CN111383733B CN201811646080.2A CN201811646080A CN111383733B CN 111383733 B CN111383733 B CN 111383733B CN 201811646080 A CN201811646080 A CN 201811646080A CN 111383733 B CN111383733 B CN 111383733B
- Authority
- CN
- China
- Prior art keywords
- knee joint
- motion
- movement
- signals
- information
- 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
- 210000000629 knee joint Anatomy 0.000 title claims abstract description 358
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 230000006378 damage Effects 0.000 claims abstract description 64
- 238000013507 mapping Methods 0.000 claims abstract description 42
- 230000001133 acceleration Effects 0.000 claims description 50
- 238000005259 measurement Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 10
- 210000000988 bone and bone Anatomy 0.000 claims description 9
- 210000004417 patella Anatomy 0.000 claims description 7
- 208000028722 Abnormality of the knee Diseases 0.000 claims 3
- 238000005452 bending Methods 0.000 claims 3
- 210000004872 soft tissue Anatomy 0.000 claims 3
- 210000001519 tissue Anatomy 0.000 claims 3
- 238000012549 training Methods 0.000 abstract description 12
- 230000036544 posture Effects 0.000 description 41
- 230000006870 function Effects 0.000 description 28
- 210000003127 knee Anatomy 0.000 description 12
- 230000006735 deficit Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000001228 spectrum Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 244000309466 calf Species 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 210000000689 upper leg Anatomy 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000009525 mild injury Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009528 severe injury Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Physical Education & Sports Medicine (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a motion monitoring and correcting method based on knee joint motion signals, which comprises the following steps: acquiring knee joint movement signals, knee joint posture information and movement time data; generating knee joint movement information according to the knee joint movement signals and the knee joint posture information, and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information; reading a preset mapping table, searching standard time data, standard motion signals and maximum error allowable values corresponding to the damaged grade of the knee joint to be detected in the preset mapping table, and calculating an actual error value according to the motion signals to be detected and the standard motion signals; and when the motion time data is compared to be larger than the standard time data and the actual error value is larger than the maximum error allowable value, sending a first alarm signal, wherein the first alarm signal is used for reminding a user to stop motion. The method can remind the user to train in a correct training mode, and avoid deviation.
Description
Technical Field
The invention belongs to the field of intelligent medical treatment, and particularly relates to a knee joint movement signal-based movement monitoring and correcting method, device and equipment and a storage medium.
Background
Knee joint is one of the joints of the human body with the most complex functions and structures. Because the knee joint bears almost the whole weight of the human body in the motion process of the human body, the knee joint is easy to damage, the damaged knee joint is slower to recover, and great pain is brought to the patient.
In the current treatment, when external force correction or electromyographic signal stimulation correction is carried out, a patient is required to perform proper movement so as to achieve the purpose of quick recovery, however, as the patient cannot know the movement rule of the patient himself, if the movement posture or movement time is not noticed in movement, the load of the knee joint is increased, the treatment effect is not achieved, and secondary injury to the knee joint is possibly caused.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a method, a device, equipment and a storage medium for motion monitoring and correction based on knee joint motion signals. The technical problems to be solved by the invention are realized by the following technical scheme:
the embodiment of the invention provides a motion monitoring and correcting method based on knee joint motion signals, which comprises the following steps:
acquiring knee joint movement signals, knee joint posture information and movement time data;
generating knee joint movement information according to the knee joint movement signals and the knee joint posture information, and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information;
reading a preset mapping table, searching standard time data, standard motion signals and maximum error allowable values corresponding to the damaged grades of the knee joint to be detected in the preset mapping table, and calculating actual error values according to the motion signals to be detected and the standard motion signals, wherein the preset mapping table comprises mapping relations between the standard damaged grades and the standard time data, the standard motion signals and the maximum error allowable values;
and when the motion time data is compared to be larger than the standard time data and the actual error value is larger than the maximum error allowable value, sending a first alarm signal, wherein the first alarm signal is used for reminding a user to stop motion.
In one specific embodiment, the method further comprises: and when the motion time data is smaller than the standard time data and the actual error value is larger than the maximum error allowable value, sending a second alarm signal, wherein the second alarm signal is used for reminding a user to adjust the motion gesture.
In one embodiment, obtaining the damage level of the knee joint to be measured according to the knee joint motion information includes:
the knee joint movement information is brought into a pre-trained model to obtain a classification result;
and obtaining the damage grade of the knee joint to be detected according to the classification result.
In one embodiment, the knee motion signal includes at least one of a characteristic value of the knee motion signal in a time domain and a characteristic value of the knee motion signal in a frequency domain.
In a specific embodiment, the knee posture information includes a characteristic value of a joint angle of the knee joint and a characteristic value of an acceleration of the knee joint, the characteristic value of the joint angle of the knee joint includes a difference value of the joint angle of the knee joint in the preset measurement period, and the characteristic value of the acceleration of the knee joint includes a difference value of the acceleration of the knee joint in the preset measurement period.
In one embodiment, the pre-trained model is obtained by:
acquiring a preset number of knee joint movement information samples, wherein each knee joint movement information sample comprises characteristic information of a knee joint movement signal, posture information of a knee joint and a preset classification result;
inputting the preset number of knee joint movement information samples into an original model, and calculating a loss function value;
and if the loss function value is smaller than a preset function threshold value, obtaining the pre-trained model.
The invention also provides a motion monitoring and correcting device based on the knee joint motion signal, which comprises:
the data acquisition module is used for acquiring knee joint movement signals, knee joint posture information and movement time data;
the data processing module is connected with the data acquisition module and is used for generating knee joint movement information according to the knee joint movement signals and the knee joint posture information and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information;
the storage module is connected with the data processing module and used for storing a preset mapping table, wherein the preset mapping table comprises a mapping relation between a standard damaged grade and standard time data, a standard motion signal and a maximum error allowable value;
the data processing module is further used for reading the preset mapping table, searching standard time data, standard motion signals and maximum error allowable values corresponding to the damaged grade of the knee joint to be detected in the preset mapping table, and calculating actual error values according to the motion signals to be detected and the standard motion signals;
and the comparison module is connected with the data processing module and the data acquisition module and is used for transmitting a first alarm signal when the motion time data are larger than the standard time data and the actual error value is larger than the maximum error allowable value, and the first alarm signal is used for reminding a user to stop moving.
In a specific embodiment, the comparison module is further configured to compare that the motion time data is smaller than the standard time data and the actual error value is greater than the maximum error allowable value, and send a second alarm signal, where the second alarm signal is used to remind the user to adjust the motion gesture.
The invention also provides a knee joint movement signal-based movement monitoring and correcting device, which comprises a collector, a memory and a processor, wherein the memory stores a computer program, and the collector realizes the following steps when executing the computer program: acquiring knee joint movement signals, knee joint posture information and movement time data;
the processor, when executing the computer program, performs the steps of: generating knee joint movement information according to the knee joint movement signals and the knee joint posture information, and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information; reading a preset mapping table, searching standard time data, standard motion signals and maximum error allowable values corresponding to the damaged grades of the knee joint to be detected in the preset mapping table, and calculating actual error values according to the motion signals to be detected and the standard motion signals, wherein the preset mapping table comprises mapping relations between the standard damaged grades and the standard time data, the standard motion signals and the maximum error allowable values; and when the motion time data is compared to be larger than the standard time data and the actual error value is larger than the maximum error allowable value, sending a first alarm signal, wherein the first alarm signal is used for reminding a user to stop motion.
The invention also provides a computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor realizes the steps of the above method.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the knee joint movement signal-based movement monitoring and correcting method, whether the user has the problem of overlarge movement posture deviation or overlong movement time can be judged by collecting the data of the knee joint movement information and the like of the user, and the movement data of the user is monitored, so that the user is reminded to train in a correct training mode, and the deviation is avoided.
2. According to the knee joint movement signal-based movement monitoring and correcting method, a pre-trained model is used to obtain a classification result; based on the classification result, the damage degree of the knee joint is determined, so that a corresponding maximum error allowable value is set according to the damage degree of the knee joint, and the motion information of a user can be intuitively obtained, so that the user can be correctly trained according to the state of the knee joint, and the forward promotion effect is achieved.
Drawings
FIG. 1 is a flow chart of a method for motion monitoring and correction based on knee joint motion signals according to an embodiment of the present invention;
fig. 2 is a block diagram of a motion monitoring and correcting device based on knee joint motion signals according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to specific examples, but embodiments of the present invention are not limited thereto.
Example 1
Referring to fig. 1, fig. 1 is a flowchart of a motion monitoring and correcting method based on a knee joint motion signal according to an embodiment of the present invention, including:
s1, acquiring knee joint movement signals, knee joint posture information and movement time data;
s2, generating knee joint movement information according to the knee joint movement signals and the knee joint posture information, and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information;
the step is required to be performed in a human body movement state, that is, in a human body movement state, knee joint movement information generated by a knee joint of the human body is acquired, wherein the knee joint movement information comprises characteristic information of a knee joint movement signal, posture information of the knee joint and the like.
The knee joint movement information is a movement signal and a posture signal generated in the middle of the patella during extension and flexion movements of the knee joint, wherein the movement signal includes a vibration signal acquired by an acceleration sensor. When a human body moves, the knee joint is also in a moving state, and the joint mode of bones and the compression degree of bones in the knee joint are different according to the different postures and movement speeds of the human body, so that the state of the knee joint in the moving state of the human body is different from the state of the knee joint in the static state such as the lying or sitting posture of the human body.
The motion signal to be detected refers to a motion signal detected by a patient to be corrected, the motion signal comprises a vibration signal acquired by an acceleration sensor, and the standard motion signal refers to a motion signal of the patient under normal conditions. It is worth mentioning that, in order to enable signal comparison, the signal types of the standard motion signal and the motion signal to be measured are identical.
Meanwhile, the knee joint motion signals generated by the damaged knee joint in the motion state are greatly different from the knee joint motion signals generated by the undamaged knee joint in the motion state, and the characteristic information of the knee joint motion signals generated based on the knee joint motion signals generated by the knee joint can intuitively and accurately embody the characteristics of the knee joint motion signals.
Specifically, the characteristic information of the knee joint motion signal may be a characteristic value of the knee joint motion signal in a time domain and/or a frequency domain, for example, the characteristic value of the knee joint motion signal in the time domain may be an average value, a root mean square, or the like, the characteristic value of the knee joint motion signal in the frequency domain may be a frequency spectrum, an energy spectrum, a power spectrum, or the like, and the characteristic value of the knee joint motion signal in the time-frequency domain may be a wavelet packet transform coefficient or the like. Thus, the characteristic information of the knee joint movement signal can intuitively embody the characteristics of the knee joint movement signal from the time domain and the frequency domain respectively.
In addition, the knee joint motion signal is acquired, meanwhile, the posture information of the knee joint can be acquired, and the posture information of the knee joint can be generated based on the speed, the acceleration, the joint angle, the height of the knee joint from the ground and the like of the knee joint, so that the posture information of the knee joint can be embodied.
Specifically, since the velocity, acceleration, joint angle, etc. of the knee joint have a great influence on the manner of coupling of bones in the knee joint and the degree of compression of the bones, and when the human body falls from a height, a great instantaneous pressure is generated on the knee joint, a great difference is also generated in the knee joint motion signal generated by the knee joint when the posture of the knee joint is different.
In this step, the knee joint movement signal and the posture information of the knee joint corresponding to the knee joint movement signal may be obtained, so as to determine the damage degree of the knee joint based on the knee joint movement signal and the posture information of the knee joint corresponding to the knee joint movement signal, so that the accuracy of the finally determined damage degree of the knee joint may be improved by generating the knee joint movement signal and the posture condition corresponding to the knee joint movement signal by the knee joint.
The posture information of the knee joint may be generated based on the joint angle of the knee joint, the acceleration of the knee joint, and the height of the knee joint from the ground.
Specifically, the joint angle of the knee joint may be calculated by the inclination angle of the thigh with the vertical direction and the inclination angle of the calf with the vertical direction, and the acceleration of the knee joint may be measured by a biaxial acceleration sensor provided on the thigh and the calf, or by a biaxial acceleration sensor provided in the vicinity of the knee joint.
Because the joint angle of the knee joint and the acceleration of the knee joint have great influence on the joint mode of each bone in the knee joint and the compression degree of each bone, knee joint movement information generated by the knee joint is also greatly different under the condition that the joint angle of the knee joint and the acceleration of the knee joint are different, therefore, knee joint movement signals can be acquired, and gesture information corresponding to the knee joint movement signals generated by the knee joint can be obtained, so that the damage degree of the knee joint is determined based on the joint angle and the acceleration of the knee joint, and the accuracy of the finally determined damage degree of the knee joint is improved.
Since in a normal case, the knee joint movement information may include movement signals, posture signals, etc. within one measurement period for reflecting signal parameters of the knee joint characteristics, characteristic values of the joint angles and characteristic values of the accelerations may be calculated based on the joint angles and the accelerations of the knee joint within the one measurement period, so that the calculated characteristic values of the joint angles and characteristic values of the accelerations may be reflected in posture change conditions of the knee joint within the one preset measurement period. Then, in order to improve the accuracy of the finally determined degree of damage of the knee joint, the characteristic value of the joint angle and the characteristic value of the acceleration may be used as the posture information of the knee joint.
For example, a joint angle is randomly obtained from the joint angles of the knee joint in the preset measurement period as a characteristic value of the joint angle, and an acceleration is randomly obtained from the accelerations of the knee joint in the preset measurement period as a characteristic value of the accelerations. For another example, the average value of the joint angles of the knee joint in a preset measurement period may be taken as the characteristic value of the joint angles, and the average value of the joint accelerations of the knee joint in a preset measurement period may be taken as the characteristic value of the accelerations. For another example, a variance value of a joint angle of the knee joint in a preset measurement period may be taken as a characteristic value of the joint angle, and a variance value of a joint acceleration of the knee joint in a preset measurement period may be taken as a characteristic value of the acceleration.
Of course, according to the actual situation, the characteristic values in statistics such as the difference value and the mean square difference value of the joint angle and the acceleration can be calculated as the characteristic value of the joint angle and the characteristic value of the acceleration based on the joint angle and the acceleration of the knee joint in a preset measurement period.
S3, reading a preset mapping table, searching standard time data, standard motion signals and maximum error allowable values corresponding to the damaged grades of the knee joint to be detected in the preset mapping table, and calculating actual error values according to the motion signals to be detected and the standard motion signals, wherein the preset mapping table comprises mapping relations between the standard damaged grades and the standard time data, the standard motion signals and the maximum error allowable values;
the standard time data, the standard motion signal and the maximum error allowable value in the preset mapping table are all determined according to standard damaged grades, firstly, a plurality of groups of data are obtained in advance through a method similar to the steps S1 and S2, the standard damaged grades are formed through a neural network training mode, each damaged grade corresponds to different standard time data and the maximum error allowable value, the standard time data refers to the optimal time length of each training under the damaged grade, and the maximum error allowable value refers to the deviation percentage of the actual motion signal and the standard motion signal.
And S4, when the motion time data is compared to be larger than the standard time data and the actual error value is larger than the maximum error allowable value, a first alarm signal is sent, and the first alarm signal is used for reminding a user to stop motion.
The error is larger when the data of a item are compared independently, so that the alarm reminding is carried out only when the data of the item are judged to be met simultaneously, and the alarm reminding is carried out only when the data of the item are disconnected and met simultaneously, thereby improving the alarm accuracy.
According to the knee joint movement signal-based movement monitoring and correcting method, whether the user has the problem of overlarge movement posture deviation or overlong movement time can be judged by collecting the data of the knee joint movement information and the like of the user, and the movement data of the user is monitored, so that the user is reminded to train in a correct training mode, and the deviation is avoided.
In one specific embodiment, the method further comprises: and when the motion time data is smaller than the standard time data and the actual error value is larger than the maximum error allowable value, sending a second alarm signal, wherein the second alarm signal is used for reminding a user to adjust the motion gesture. According to the above conclusion, when the exercise time does not exceed the standard time but exceeds the maximum error allowable value, no significant negative effect occurs, that is, if the deviation of the action posture is too large, although the exercise takes place, the effect is not very obvious, so in this case, the user should be reminded to adjust the exercise posture, rather than directly stop the exercise until the user cannot adjust to the correct posture and the time exceeds the standard time, and the user is reminded to stop the exercise again, so as not to have negative effect, and the recovery of the knee joint of the user is affected.
In one embodiment, obtaining the damage level of the knee joint to be measured according to the knee joint motion information includes:
the knee joint movement information is brought into a pre-trained model to obtain a classification result;
and obtaining the damage grade of the knee joint to be detected according to the classification result.
Here it is specifically described how the level of damage to the knee joint is obtained.
In this step, the obtained knee joint movement information may be input into a pre-trained model to obtain a classification result, so as to determine the degree of damage of the knee joint based on the classification result.
The pre-trained model can be an intelligent algorithm model such as a support vector machine (Support Vector Machine, SVM) model, a neural network model and the like.
In particular, the SVM model may be a radial basis function (Radial Basis Function, RBF) kernel based SVM model. Of course, other kernel functions may be selected according to the actual situation, for example, a polynomial kernel function, a laplace kernel function, a Sigmoid kernel function, and the like.
Specifically, the pre-trained SVM model may be a two-class SVM model, the corresponding classification results are two classes, and the damage degree of the knee joint corresponding to the two classes of classification results is respectively undamaged and damaged; the pre-trained SVM model can also be a multi-classification SVM model, the corresponding classification results can be at least three types, the damage degree of knee joints corresponding to the classification results can be undamaged and damaged respectively, wherein damage can be at least classified into mild damage, severe damage and the like.
Of course, the classification results corresponding to the multi-classification SVM model may be four, five or more, and in general, the damage may be subdivided, so that the finally determined damage degree of the knee joint is more accurate.
And determining the damage degree of the knee joint based on the classification result.
In this step, the degree of damage of the knee joint may be determined based on the obtained classification result and a preset expected value corresponding to the degree of damage set when training the model.
For example, when the pre-trained model is a two-class SVM model, the expected value of the classification result corresponding to the knee joint motion signal generated by the undamaged knee joint is set to be 1, and the expected value of the classification result corresponding to the knee joint motion signal generated by the damaged knee joint is set to be-1 when the original two-class SVM model is trained, then the knee joint can be determined to be undamaged when the classification result is 1, and the knee joint can be determined to be damaged when the classification result is-1.
For example, when the model is a multi-classification SVM model, the degree of impairment corresponding to the classification result may be set to include non-impairment and impairment, the impairment including primary impairment, secondary impairment, tertiary impairment and quaternary impairment; then, when training the multi-classification SVM model, the expected value of the classification result corresponding to the knee joint motion signal generated by the undamaged knee joint may be set to be 1, the expected value of the classification result corresponding to the knee joint motion signal generated by the first-stage damaged knee joint may be set to be-1, the expected value of the classification result corresponding to the knee joint motion signal generated by the second-stage damaged knee joint may be set to be-2, the expected value of the classification result corresponding to the knee joint motion signal generated by the third-stage damaged knee joint may be set to be-3, and the expected value of the classification result corresponding to the knee joint motion signal generated by the fourth-stage damaged knee joint may be set to be-4; then, when the classification result is 1, it can be determined that the knee joint is not damaged, when the classification result is-1, it can be determined that the knee joint is damaged at one stage, when the classification result is-2, it can be determined that the knee joint is damaged at two stages, when the classification result is-3, it can be determined that the knee joint is damaged at three stages, and when the classification result is-4, it can be determined that the knee joint is damaged at four stages.
According to the knee joint movement signal-based movement monitoring and correcting method, a pre-trained model is used to obtain a classification result; based on the classification result, the damage degree of the knee joint is determined, so that a corresponding motion time threshold and a motion error threshold are set according to the damage degree of the knee joint, and motion information of a user can be intuitively obtained, so that the user can be correctly trained according to the state of the knee joint, and the forward promotion effect is achieved.
In one embodiment, the knee motion signal includes at least one of a characteristic value of the knee motion signal in a time domain and a characteristic value of the knee motion signal in a frequency domain.
Specifically, the characteristic values of the knee joint motion signal in the time domain may include an average value of the knee joint motion signal, a root mean square of the knee joint motion signal, a standard deviation of the knee joint motion signal, and the like, wherein the time domain characteristics of the knee joint motion signal are calculated for the knee joint motion signal in a preset measurement time period, the characteristic values of the knee joint motion signal in the frequency domain may include a frequency spectrum, an energy spectrum, a power spectrum, a cepstrum, and the like of the knee joint motion signal, and the characteristic values of the knee joint motion signal in the time-frequency domain may be wavelet packet transformation coefficients and the like.
It will be appreciated that the characteristic values of the knee motion signal in the time domain and the characteristic values of the knee motion signal in the frequency domain can characterize the knee motion signal from the time domain and the frequency domain, respectively.
In a specific embodiment, the knee posture information includes a characteristic value of a joint angle of the knee joint and a characteristic value of an acceleration of the knee joint, the characteristic value of the joint angle of the knee joint includes a difference value of the joint angle of the knee joint in the preset measurement period, and the characteristic value of the acceleration of the knee joint includes a difference value of the acceleration of the knee joint in the preset measurement period.
Because the difference value is used to describe the difference between the maximum value and the minimum value of the variable in the range, the difference value of the joint angle and the difference value of the acceleration can be used as the characteristic value of the joint angle and the characteristic value of the acceleration respectively, it can be understood that the characteristic value of the joint angle and the characteristic value of the acceleration can reflect the movement condition of the joint angle and the acceleration, when the characteristic value of the joint angle and the characteristic value of the acceleration are larger, the movement of the knee joint can be illustrated to be more intense in the preset measurement time period, and when the characteristic value of the joint angle and the characteristic value of the acceleration are smaller, the movement of the knee joint can be illustrated to be more gentle in the preset measurement time period. In this way, based on the posture information including the characteristic value of the joint angle and the characteristic value of the acceleration, the accuracy of determining the degree of damage of the knee joint can be improved.
In one embodiment, the pre-trained model is obtained by:
acquiring a preset number of knee joint movement information samples, wherein each knee joint movement information sample comprises characteristic information of a knee joint movement signal, posture information of a knee joint and a preset classification result;
in this step, a preset number of knee joint movement information samples may be obtained for training an original model, where each of the knee joint movement information samples may include characteristic information of a knee joint movement signal, posture information of the knee joint, and a preset classification result; the model can be an SVM model, and can also be other intelligent algorithm models.
Specifically, the degree of damage of the knee joint in the knee joint movement information sample is known, and a preset classification result corresponding to each degree of damage can be set in advance.
For example, the preset classification result corresponding to the undamaged state is set to be 1, the preset classification result corresponding to the damaged state is set to be-2, the preset classification result corresponding to the damaged state is set to be-3, and the preset classification result corresponding to the damaged state is set to be-4; then, if the degree of damage of the knee joint in the knee joint movement information sample a is not damaged, the preset classification result in the knee joint movement information sample a is 1, and if the degree of damage of the knee joint in the knee joint movement information sample B is two-stage damaged, the preset classification result in the knee joint movement information sample B is-2.
It will be appreciated that the greater the number of presets and the greater the difference between the knee joint motion information samples, the more advantageous it is to train out a model that can accurately determine the degree of knee joint damage.
Inputting the preset number of knee joint movement information samples into an original model, calculating a loss function value, and judging whether the loss function value is smaller than a preset function threshold.
In the step, when intelligent algorithms such as a neural network model are adopted, whether the model is trained is judged through a loss function, if the loss function value is smaller than a preset function threshold value, the model training is finished, and the method can be used for determining the damage degree of the knee joint based on knee joint motion information. The obtained preset number of knee joint movement information samples can be input into an original model, so that the original model is trained by using the preset number of knee joint movement information samples, and the loss function value of a preset loss function is used for measuring the training degree of the model; judging whether the loss function value is smaller than a preset function threshold, if yes, indicating that the model is trained, if not, indicating that the model is not trained, and further requiring to continue training through iteration.
The original model may be a two-class SVM model or a multi-class SVM model, which may be specifically determined according to the actual situation.
Therefore, according to the training method of the model in the embodiment of the invention, the original model can be trained by using the preset number of knee joint movement information samples, so that a trained model is obtained, and the trained model is used for accurately determining the damage degree of the knee joint based on the knee joint movement information.
Referring to fig. 2, the present invention also provides a motion monitoring and correcting device based on knee joint motion signals, comprising:
the data acquisition module 1 is used for acquiring knee joint movement signals, knee joint posture information and movement time data;
the data acquisition module may be an acceleration sensor for acquiring the knee joint movement signal in a movement state of the human body. It will be appreciated that the knee joint motion signal generated by a damaged knee joint may be distinguished from the knee joint motion signal generated by an undamaged knee joint, and thus the knee joint motion signal of the human body may be acquired using an acceleration sensor.
In practical applications, in order to improve accuracy of the measured knee joint motion signals, the acceleration sensor may be plural. The acceleration sensor may specifically be a micro accelerometer, and of course, may also be other sensors having a function of measuring vibration signals.
Knee posture information is also collected by a sensor, such as a gyroscope or other sensor with a posture information measuring function.
The data processing module 2 is connected with the data acquisition module 1 and is used for generating knee joint movement information according to the knee joint movement signals and the knee joint posture information and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information;
the data processing module may be a processor capable of receiving and processing the data, for example, a micro processor such as an MCU, an FPGA, etc., it is worth mentioning that such a processor generally also has a storage unit with a data storage function and a communication unit with a data receiving or transmitting function, however, because the data volume is large, if the data is processed while the data is stored, the data processing efficiency is affected due to too large bandwidth occupied by the data processing module, so the external storage module is used to store the data, and the preset mapping table is stored in the storage module 3, where the preset mapping table includes a mapping relationship between a standard damage level and standard time data, a standard motion signal, and a maximum error allowable value;
the data processing module 2 is further configured to read the preset mapping table, search standard time data, a standard motion signal and a maximum error allowable value corresponding to the damaged level of the knee joint to be detected in the preset mapping table, and calculate an actual error value according to the motion signal to be detected and the standard motion signal;
the comparison module 4 is connected with the data processing module 2 and the data acquisition module 1 and is used for transmitting a first alarm signal when the motion time data are compared to be larger than the standard time data and the actual error value is larger than the maximum error allowable value, and the first alarm signal is used for reminding a user to stop motion.
The comparison function of the comparison module can be independently a comparator, and the function of the comparison module can be embedded into the data processing module to complete the comparison function, and when the comparison module is independently a comparator, the comparison data is simpler and the precision requirement is not high, so that the common comparator is adopted.
In a specific embodiment, the comparison module is further configured to send a second alarm signal when the motion time data is greater than the standard time data and the actual error value is less than the standard time data, where the second alarm signal is used to remind the user to adjust the motion gesture.
In a specific application, in order to facilitate the use of a user, the device can be externally connected with a communication module, and a better reminding effect is achieved by sending the alarm signal to an intelligent terminal through the communication module, for example, if the terminal is a wearable intelligent device such as an intelligent watch, an audible and visual alarm or a vibration alarm can be set, and of course, besides the alarm signal, all acquired or processed data can be stored, and a certain analysis or display is performed, so that the user perceives the process of each movement visually. The specific communication manner and the display method can be implemented by applying the prior art, and are not described herein.
The invention also provides a knee joint movement signal-based movement monitoring and correcting device, which comprises a collector, a memory and a processor, wherein the memory stores a computer program, and the collector realizes the following steps when executing the computer program: acquiring knee joint movement signals, knee joint posture information and movement time data;
the processor, when executing the computer program, performs the steps of: generating knee joint movement information according to the knee joint movement signals and the knee joint posture information, and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information; reading a preset mapping table, searching standard time data, standard motion signals and maximum error allowable values corresponding to the damaged grades of the knee joint to be detected in the preset mapping table, and calculating actual error values according to the motion signals to be detected and the standard motion signals, wherein the preset mapping table comprises mapping relations between the standard damaged grades and the standard time data, the standard motion signals and the maximum error allowable values; and when the motion time data is compared to be larger than the standard time data and the actual error value is larger than the maximum error allowable value, sending a first alarm signal, wherein the first alarm signal is used for reminding a user to stop motion.
The invention also provides a computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor realizes the steps of the above method.
The functions described in this embodiment, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computing device readable storage medium. Based on such understanding, a portion of the present disclosure that contributes to the prior art or a portion of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is a further detailed description of the invention in connection with the preferred embodiments, and it is not intended that the invention be limited to the specific embodiments described. It will be apparent to those skilled in the art that several simple deductions or substitutions may be made without departing from the spirit of the invention, and these should be considered to be within the scope of the invention.
Claims (7)
1. A method of motion monitoring and correction based on knee joint motion signals, comprising:
acquiring knee joint movement signals, knee joint posture information and movement time data; the knee joint movement signals are used for reflecting movement damage and tissue abnormality of the knee joint, and the knee joint movement signals comprise vibration signals acquired by the acceleration sensor; the vibration signal is a signal which is transmitted by the vibration generated by bones and soft tissues in the knee joint through the middle part of the patella when the knee joint stretches and bends; the knee joint posture information is generated based on information representing the knee joint posture including the speed, the acceleration, the joint angle and the height of the knee joint from the ground;
generating knee joint movement information according to the knee joint movement signals and the knee joint posture information, and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information; the knee joint movement information is obtained by a movement signal and a posture signal generated in the middle of a patella when the knee joint moves in extension and bending; the knee joint movement information comprises characteristic information of knee joint movement signals and knee joint posture information; obtaining the damage grade of the knee joint to be detected according to the knee joint movement information, wherein the method comprises the following steps: the knee joint movement information is brought into a pre-trained model to obtain a classification result; obtaining the damage grade of the knee joint to be detected according to the classification result; wherein the knee joint damage degree corresponding to the classification result comprises damage without damage and damage with different degrees;
reading a preset mapping table, searching standard time data, standard motion signals and maximum error allowable values corresponding to the damaged grades of the knee joint to be detected in the preset mapping table, and calculating actual error values according to the motion signals to be detected and the standard motion signals, wherein the preset mapping table comprises mapping relations between the standard damaged grades and the standard time data, the standard motion signals and the maximum error allowable values;
and when the motion time data is compared to be larger than the standard time data and the actual error value is larger than the maximum error allowable value, sending a first alarm signal, wherein the first alarm signal is used for reminding a user to stop motion.
2. The knee joint motion signal based motion monitoring correction method of claim 1, further comprising: and when the motion time data is smaller than the standard time data and the actual error value is larger than the maximum error allowable value, sending a second alarm signal, wherein the second alarm signal is used for reminding a user to adjust the motion gesture.
3. The knee joint motion signal-based motion monitoring correction method according to claim 1, wherein the knee joint posture information includes a characteristic value of a joint angle of the knee joint including an extreme value of a joint angle of the knee joint in the preset measurement period and a characteristic value of an acceleration of the knee joint including an extreme value of an acceleration of the knee joint in the preset measurement period.
4. A knee joint motion signal based motion monitoring and correction device comprising:
the data acquisition module is used for acquiring knee joint movement signals, knee joint posture information and movement time data; the knee joint movement signals are used for reflecting movement damage and tissue abnormality of the knee joint, and the knee joint movement signals comprise vibration signals acquired by the acceleration sensor; the vibration signal is a signal which is transmitted by the vibration generated by bones and soft tissues in the knee joint through the middle part of the patella when the knee joint stretches and bends; the knee joint posture information is generated based on information representing the knee joint posture including the speed, the acceleration, the joint angle and the height of the knee joint from the ground;
the data processing module is connected with the data acquisition module and is used for generating knee joint movement information according to the knee joint movement signals and the knee joint posture information and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information; the knee joint movement information is obtained by a movement signal and a posture signal generated in the middle of a patella when the knee joint moves in extension and bending; the knee joint movement information comprises characteristic information of knee joint movement signals and knee joint posture information; obtaining the damage grade of the knee joint to be detected according to the knee joint movement information, wherein the method comprises the following steps: the knee joint movement information is brought into a pre-trained model to obtain a classification result; obtaining the damage grade of the knee joint to be detected according to the classification result; wherein the knee joint damage degree corresponding to the classification result comprises damage without damage and damage with different degrees;
the storage module is connected with the data processing module and used for storing a preset mapping table, wherein the preset mapping table comprises a mapping relation between a standard damaged grade and standard time data, a standard motion signal and a maximum error allowable value;
the data processing module is further configured to read the preset mapping table, search standard time data, standard motion signals and maximum error allowable values corresponding to the damaged level of the knee joint to be detected in the preset mapping table, and calculate actual error values according to the motion signals to be detected and the standard motion signals;
and the comparison module is connected with the data processing module and the data acquisition module and is used for transmitting a first alarm signal when the motion time data are larger than the standard time data and the actual error value is larger than the maximum error allowable value, and the first alarm signal is used for reminding a user to stop moving.
5. The knee joint motion signal based motion monitoring and correction device of claim 4, wherein the comparison module is further configured to compare the motion time data to be less than the standard time data and the actual error value to be greater than the maximum error tolerance value, send a second alert signal, the second alert signal being configured to alert a user to adjust the motion profile.
6. A knee joint movement signal based movement monitoring and correction device comprising a collector, a memory and a processor, the memory storing a computer program, characterized in that,
the collector implements the following steps when executing the computer program: acquiring knee joint movement signals, knee joint posture information and movement time data; the knee joint movement signals are used for reflecting movement damage and tissue abnormality of the knee joint, and the knee joint movement signals comprise vibration signals acquired by the acceleration sensor; the vibration signal is a signal which is transmitted by the vibration generated by bones and soft tissues in the knee joint through the middle part of the patella when the knee joint stretches and bends; the knee joint posture information is generated based on information representing the knee joint posture including the speed, the acceleration, the joint angle and the height of the knee joint from the ground;
the processor, when executing the computer program, performs the steps of: generating knee joint movement information according to the knee joint movement signals and the knee joint posture information, and obtaining the damage grade of the knee joint to be detected according to the knee joint movement information; reading a preset mapping table, searching standard time data, standard motion signals and maximum error allowable values corresponding to the damaged grades of the knee joint to be detected in the preset mapping table, and calculating actual error values according to the motion signals to be detected and the standard motion signals, wherein the preset mapping table comprises mapping relations between the standard damaged grades and the standard time data, the standard motion signals and the maximum error allowable values; when the motion time data is compared to be larger than the standard time data and the actual error value is larger than the maximum error allowable value, a first alarm signal is sent, and the first alarm signal is used for reminding a user to stop motion; the knee joint movement information is obtained by a movement signal and a posture signal generated in the middle of a patella when the knee joint moves in extension and bending; the knee joint movement information comprises characteristic information of knee joint movement signals and knee joint posture information; obtaining the damage grade of the knee joint to be detected according to the knee joint movement information, wherein the method comprises the following steps: the knee joint movement information is brought into a pre-trained model to obtain a classification result; obtaining the damage grade of the knee joint to be detected according to the classification result; wherein the degree of damage of the knee joint corresponding to the classification result comprises damage which is not damaged and damage with different degrees.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811646080.2A CN111383733B (en) | 2018-12-29 | 2018-12-29 | Motion monitoring and correcting method, device, equipment and storage medium based on knee joint motion signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811646080.2A CN111383733B (en) | 2018-12-29 | 2018-12-29 | Motion monitoring and correcting method, device, equipment and storage medium based on knee joint motion signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111383733A CN111383733A (en) | 2020-07-07 |
| CN111383733B true CN111383733B (en) | 2024-02-02 |
Family
ID=71218312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811646080.2A Active CN111383733B (en) | 2018-12-29 | 2018-12-29 | Motion monitoring and correcting method, device, equipment and storage medium based on knee joint motion signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111383733B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537179B (en) * | 2021-09-16 | 2021-12-24 | 南通嘉蒂体育用品有限公司 | Running data processing method based on digital processing |
| CN117357063B (en) * | 2023-10-08 | 2024-03-26 | 中国人民解放军海军特色医学中心 | Meniscus injury grade assessment system and method based on physiological signals |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014150780A2 (en) * | 2013-03-15 | 2014-09-25 | Jointvue, Llc | Determination of joint condition based on vibration analysis |
| CN104706359A (en) * | 2015-04-01 | 2015-06-17 | 深圳柔微传感科技有限公司 | Method and smart garment for achieving real-time monitoring of motion |
| CN108852364A (en) * | 2018-07-09 | 2018-11-23 | 深圳德创健康科技有限责任公司 | Monitor the object wearing device of movement information of knee |
| CN108888265A (en) * | 2018-05-23 | 2018-11-27 | 四川斐讯信息技术有限公司 | A kind of movement method for early warning and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180028109A1 (en) * | 2016-07-27 | 2018-02-01 | Andrew TESNOW | System and method for a wearable knee injury prevention |
-
2018
- 2018-12-29 CN CN201811646080.2A patent/CN111383733B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014150780A2 (en) * | 2013-03-15 | 2014-09-25 | Jointvue, Llc | Determination of joint condition based on vibration analysis |
| CN104706359A (en) * | 2015-04-01 | 2015-06-17 | 深圳柔微传感科技有限公司 | Method and smart garment for achieving real-time monitoring of motion |
| CN108888265A (en) * | 2018-05-23 | 2018-11-27 | 四川斐讯信息技术有限公司 | A kind of movement method for early warning and device |
| CN108852364A (en) * | 2018-07-09 | 2018-11-23 | 深圳德创健康科技有限责任公司 | Monitor the object wearing device of movement information of knee |
Non-Patent Citations (1)
| Title |
|---|
| 基于多重分形的膝关节摆信号特征提取与分类;徐一平等;《信号处理》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111383733A (en) | 2020-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111383763B (en) | Knee joint movement information processing method, device, equipment and storage medium | |
| KR101970700B1 (en) | Apparatus and method of brain-computer interface for device controlling based on brain signal | |
| CN111383733B (en) | Motion monitoring and correcting method, device, equipment and storage medium based on knee joint motion signals | |
| EP3298955A1 (en) | Method and system for determining postural balance of a person | |
| WO2020056071A1 (en) | Wearable sensor device and analysis platform for objective outcome assessment in spinal diseases technical field | |
| US11127181B2 (en) | Avatar facial expression generating system and method of avatar facial expression generation | |
| CN110659677A (en) | Human body falling detection method based on movable sensor combination equipment | |
| Sun et al. | Human gait modeling and gait analysis based on Kinect | |
| CN104269025A (en) | Wearable type single-node feature and position selecting method for monitoring outdoor tumble | |
| WO2014153665A1 (en) | System and method for monitoring a subject | |
| CN111383755B (en) | Knee joint disease evaluation system based on Internet of things cloud server | |
| Zhang et al. | Upper limb motion capturing and classification for unsupervised stroke rehabilitation | |
| CN111374672A (en) | Intelligent knee pad and knee joint injury early warning method | |
| Sang et al. | Human activity recognition and monitoring using smartphones | |
| CN111382636B (en) | Knee joint movement signal processing method, device, equipment and storage medium | |
| CN111382641A (en) | Body state recognition method and motion guidance system of motion sensing game | |
| CN116491935B (en) | Exercise health monitoring method, system and medium of intelligent wearable equipment | |
| KR20140073294A (en) | Apparatus and method for real-time emotion recognition using pulse rate change | |
| Cheng et al. | A fall detection algorithm based on pattern recognition and human posture analysis | |
| Hamdi et al. | Lower limb gait activity recognition using Inertial Measurement Units for rehabilitation robotics | |
| WO2019115432A1 (en) | Determining whether a hypothesis concerning a signal is true | |
| CN111743668B (en) | Prosthesis control method, device, electronic equipment and storage medium | |
| CN111436939B (en) | Method, system, device and medium for identifying sign signals based on deep learning | |
| KR102268445B1 (en) | Apparatus for estimation of gait stability based on inertial information and method thereof | |
| CN111166345A (en) | Three-dimensional motion detection method, device and equipment and readable storage medium |
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 |