CN119818929B - Haptic information feedback processing device and method for upper limb rehabilitation training - Google Patents
Haptic information feedback processing device and method for upper limb rehabilitation trainingInfo
- Publication number
- CN119818929B CN119818929B CN202411860244.7A CN202411860244A CN119818929B CN 119818929 B CN119818929 B CN 119818929B CN 202411860244 A CN202411860244 A CN 202411860244A CN 119818929 B CN119818929 B CN 119818929B
- Authority
- CN
- China
- Prior art keywords
- upper limb
- rehabilitation training
- module
- limb rehabilitation
- feedback
- 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
Landscapes
- Rehabilitation Tools (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a tactile information feedback processing device and method for upper limb rehabilitation training, wherein the device comprises a virtual reality display module, a motion track acquisition module, an evaluation analysis module, a feedback processing module, an upper limb rehabilitation training module and a physiological information acquisition module, wherein the virtual reality display module is used for displaying scene information of the upper limb rehabilitation training to a user, the physiological information acquisition module is used for acquiring a physiological parameter information set of the upper limb rehabilitation training by the user, the motion track acquisition module is used for acquiring an upper limb motion track information set of the upper limb rehabilitation training by the upper limb rehabilitation training module, the evaluation analysis module is used for evaluating and judging the upper limb motion track information set and standard motion track information to obtain an evaluation analysis result, and the feedback processing module is used for performing feedback calculation processing to obtain a feedback output value.
Description
Technical Field
The invention relates to the field of exoskeleton robots and the field of intelligent control, in particular to a tactile information feedback processing device and method for upper limb rehabilitation training.
Background
With the aggravation of the aging degree of China society, patients with upper limb movement dysfunction caused by diseases such as cerebral apoplexy are continuously increasing. In addition, patients with nerve or limb injury due to industrial injury, traffic accident, disease, etc. are also significantly increased.
For recovery of patients with upper limb dyskinesia, rehabilitation training is important. In the conventional rehabilitation therapy, a rehabilitation therapist usually performs one-to-one rehabilitation therapy on a patient in a freehand manner, and individual therapeutic means, experience differences, subjective consciousness and fatigue degrees of the rehabilitation therapist directly affect the therapeutic effect. The traditional rehabilitation training has the defects of single function, high cost, long rehabilitation period, tedious process, poor initiative, incapability of accurately evaluating the rehabilitation state and the like of rehabilitation equipment, and has the defects of deficiency of rehabilitation doctors.
Along with the development of the upper limb rehabilitation training devices of various types, the upper limb rehabilitation training devices are gradually applied to the upper limb rehabilitation process, and a better effect is achieved. From the aspect of implementation, the current rehabilitation training device mainly provides a mechanical training environment for users, lacks expansion of training scenes and diversity of user stimulation, and leads to limited training effect and efficiency.
Disclosure of Invention
The invention mainly solves the problems that the current rehabilitation training device mainly provides a mechanical training environment for users, lacks expansion of training scenes and diversity of user stimulation, and causes limited training effect and efficiency.
The embodiment of the application discloses a tactile information feedback processing device for upper limb rehabilitation training, which is characterized by comprising a virtual reality display module, a motion trail acquisition module, an evaluation analysis module, a feedback processing module, an upper limb rehabilitation training module and a physiological information acquisition module;
The virtual reality display module is used for displaying scene information of upper limb rehabilitation training to a user;
the physiological information acquisition module is used for acquiring a physiological parameter information set of a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training;
The motion trail acquisition module is used for acquiring an upper limb motion trail information set of a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training;
the evaluation analysis module is connected with the motion trail acquisition module and is used for evaluating, judging and processing the upper limb motion trail information set and the standard motion trail information to obtain an evaluation analysis result;
The feedback processing module is connected with the physiological information acquisition module, the evaluation analysis module and the upper limb rehabilitation training module and is used for carrying out feedback calculation processing on a force value sequence, a physiological parameter information set and an evaluation analysis result applied by a user when the upper limb rehabilitation training module is used for carrying out upper limb rehabilitation training to obtain a feedback output value, wherein the feedback output value is used for adjusting the touch stimulation of the upper limb rehabilitation training module to the user, and the force value sequence is acquired by the upper limb rehabilitation training module.
The upper limb rehabilitation training module comprises a training platform and a pointing component for being held by a patient, wherein the training platform comprises a base and a support, the pointing component is movably connected to the support, a mechanical sensor is arranged on the pointing component and is used for measuring and obtaining a force value sequence applied by a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training, and a plurality of soft needle structures for generating touch stimulation are arranged on the surface of the pointing component.
The physiological parameter information set comprises a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence and a body temperature information sequence.
The motion trail acquisition module is realized by adopting an image acquisition and analysis sub-module or an accelerometer sensor arranged on the upper limb of the user;
the upper limb movement track information set comprises a plurality of movement vectors;
The image acquisition analysis sub-module comprises an image acquisition unit and an image analysis unit, wherein the image acquisition unit is used for acquiring images of a user when the upper limb rehabilitation training module is used for conducting upper limb rehabilitation training, and the image analysis unit is used for extracting upper limb parts of the images of the user when the upper limb rehabilitation training module is used for conducting upper limb rehabilitation training to obtain upper limb movement tracks, and an upper limb movement track information set is constructed and obtained by utilizing all acquired upper limb movement tracks.
The second aspect of the embodiment of the application discloses a haptic information feedback processing method for upper limb rehabilitation training, which is realized by using the haptic information feedback processing device for upper limb rehabilitation training, and comprises the following steps:
s1, displaying scene information of upper limb rehabilitation training to a user by utilizing the virtual reality display module;
S2, acquiring a physiological parameter information set of a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training by utilizing the physiological information acquisition module;
S3, performing evaluation and discrimination processing on the upper limb movement track information set and the standard movement track information by using an evaluation analysis module to obtain an evaluation analysis result;
And S4, carrying out feedback calculation processing on the force value sequence, the physiological parameter information set and the evaluation analysis result applied by the user when the upper limb rehabilitation training module is used for upper limb rehabilitation training by utilizing the feedback processing module, and obtaining a feedback output value.
The method for evaluating and judging the upper limb movement track information set and the standard movement track information by using the evaluation analysis module comprises the following steps of:
s31, representing the upper limb movement track information set as a movement track matrix, and representing the standard movement track information as a movement vector, wherein the row vector of the movement track matrix is upper limb movement track information;
s32, performing first difference calculation processing on the motion trail matrix and the motion vector to obtain a first evaluation result value;
s33, performing second difference calculation processing on the motion trail matrix and the motion vector to obtain a second evaluation result value;
And S34, carrying out weighted summation processing on the first evaluation result value and the second evaluation result value to obtain an evaluation analysis result.
The expression of the first difference calculation process is:
wherein omega j is a preset j importance weight, z ij is an element of an ith row and a jth column of the motion trail matrix, For the j-th element of the motion vector, z1 ij is the i-th row and j-th column of the standard matrix constructed by using the motion vector, s is the first evaluation result value, and M and N are the row dimension and the column dimension of the motion track matrix respectively.
The expression of the second difference calculation process is:
Wherein p i is an evaluation component of the ith row, M and N are row dimension and column dimension of the motion track matrix, z ij is an element of the ith row and the jth column of the motion track matrix, z1 ij is an element of the ith row and the jth column of the standard matrix constructed by using the motion vector, and p is a second evaluation result value.
The feedback processing module is used for performing feedback calculation processing on a force value sequence, a physiological parameter information set and the evaluation analysis result applied by a user when the upper limb rehabilitation training module is used for performing upper limb rehabilitation training, so as to obtain a feedback output value, and the feedback processing module comprises:
The standard parameter value set comprises a heart rate standard value, a blood pressure standard value, a blood oxygen saturation standard value and a body temperature standard value;
subtracting each sequence in the physiological parameter information set from a corresponding standard value to obtain a corresponding difference sequence, wherein the difference sequence comprises a heart rate difference sequence, a blood pressure difference sequence, a blood oxygen saturation difference sequence and a body temperature difference sequence;
constructing and obtaining a difference matrix by utilizing all the difference sequences;
Performing eigenvalue decomposition processing on the difference matrix to obtain a maximum eigenvalue and a corresponding eigenvector, wherein the p-th element of the eigenvector is v p;
Constructing and obtaining an optimal feedback polynomial by utilizing the difference matrix;
Subtracting the standard force value from the force value sequence to obtain a force difference sequence, wherein the p-th element of the force difference sequence is b p;
Substituting the median value into an optimal feedback polynomial to obtain a first feedback output component;
And calculating the first feedback output component, the force difference sequence, the maximum characteristic value and the evaluation analysis result by using a feedback fusion model to obtain a feedback output value.
The expression of the feedback fusion model is as follows:
Wherein, the For the cross entropy loss function, alpha 1 is the maximum characteristic value, ρ is the evaluation analysis result, m is the element number of the characteristic vector, eta and delta are preset weight values, and beta is the feedback output value.
The beneficial effects of the invention are as follows:
The invention solves the problems that the current rehabilitation training device mainly provides a mechanical training environment for users, lacks expansion of training scenes and diversity of user stimulation, and causes limited training effect and efficiency.
According to the method, the problem of how to improve the stimulation diversity of the user is solved, the tactile stimulation is introduced, the feedback calculation model of the tactile stimulation is built according to the training effect, and the accuracy and the efficiency of the rehabilitation training of the upper limbs of the user are improved by accurately calculating the feedback tactile stimulation.
According to the invention, by introducing the virtual reality display module, multiple types of virtual reality training scenes are provided, and the diversity of the training scenes is improved.
According to the invention, the evaluation analysis module is utilized to evaluate and judge the upper limb movement track information set and the standard movement track information, and when an evaluation analysis result is obtained, a first difference calculation processing model and a second difference calculation processing model are established, so that the extraction of different types of characteristic quantities is realized, and the characteristic quantities are fused, so that the accurate evaluation of the movement track is realized.
When the feedback calculation processing is carried out, the physiological parameter factors are considered, the physiological parameter factors are evaluated, the real-time performance and the accuracy of feedback are improved, and the accuracy of the tactile feedback value is ensured by fusing the strength evaluation result and the motion trail evaluation result.
Drawings
FIG. 1 is a schematic diagram of the apparatus of the present invention;
Fig. 2 is a flow chart of the implementation of the method of the present invention.
Detailed Description
For a better understanding of the present disclosure, an embodiment is presented herein.
FIG. 1 is a schematic diagram of the apparatus of the present invention, and FIG. 2 is a flow chart of the implementation of the method of the present invention.
Aiming at the problems that the current rehabilitation training device mainly provides a mechanical training environment for users, lacks of expansion of training scenes and diversity of user stimulation, and causes limitation of training effect and efficiency, the invention discloses a haptic information feedback processing device and method for upper limb rehabilitation training.
The embodiment of the application discloses a tactile information feedback processing device for upper limb rehabilitation training, which comprises a virtual reality display module, a motion track acquisition module, an evaluation analysis module, a feedback processing module, an upper limb rehabilitation training module and a physiological information acquisition module;
The virtual reality display module is used for displaying scene information of upper limb rehabilitation training to a user;
the physiological information acquisition module is used for acquiring a physiological parameter information set of a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training;
The motion trail acquisition module is used for acquiring an upper limb motion trail information set of a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training;
the evaluation analysis module is connected with the motion trail acquisition module and is used for evaluating, judging and processing the upper limb motion trail information set and the standard motion trail information to obtain an evaluation analysis result;
The feedback processing module is connected with the physiological information acquisition module, the evaluation analysis module and the upper limb rehabilitation training module and is used for carrying out feedback calculation processing on a force value sequence, a physiological parameter information set and the evaluation analysis result applied by a user when the upper limb rehabilitation training module is used for carrying out upper limb rehabilitation training to obtain a feedback output value;
the virtual reality display module can be realized by VR Class, pico and the like, and scene information displayed by the virtual reality display module can be specified according to user input quantity.
The upper limb rehabilitation training module comprises a training platform and a pointing component for being held by a patient, wherein the training platform comprises a base and a support, and the pointing component is movably connected to the support. The upper limb rehabilitation training device comprises an upper limb rehabilitation training module, a pointing component, a mechanical sensor and a plurality of soft needle-shaped structures, wherein the pointing component is provided with the mechanical sensor which is used for measuring and obtaining a force value sequence applied by a user when the upper limb rehabilitation training module is used for conducting upper limb rehabilitation training, and the surface of the pointing component is provided with the plurality of soft needle-shaped structures which are used for generating touch stimulation.
The physiological parameter information set comprises a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence and a body temperature information sequence;
The motion trail acquisition module is realized by adopting an image acquisition and analysis sub-module or an accelerometer sensor arranged on the upper limb of the user;
the upper limb movement track information set comprises a plurality of movement vectors;
The image acquisition and analysis sub-module comprises an image acquisition unit and an image analysis unit; the system comprises an image acquisition unit, an image analysis unit, an upper limb movement track acquisition unit and a lower limb movement track analysis unit, wherein the image acquisition unit is used for acquiring images of a user when the upper limb rehabilitation training module is used for performing upper limb rehabilitation training;
The evaluation analysis module performs evaluation and discrimination processing on the upper limb movement track information set and the standard movement track information to obtain an evaluation analysis result, and comprises the following steps:
The upper limb movement track information set is expressed as a movement track matrix, and standard movement track information is expressed as a movement vector;
performing first difference calculation processing on the motion trail matrix and the motion vector to obtain a first evaluation result value;
Performing second difference calculation processing on the motion trail matrix and the motion vector to obtain a second evaluation result value;
carrying out weighted summation processing on the first evaluation result value and the second evaluation result value to obtain an evaluation analysis result;
The expression of the first difference calculation process is:
wherein omega j is a preset j importance weight, z ij is an element of an ith row and a jth column of the motion trail matrix, For the j-th element of the motion vector, z1 ij is the i-th row and j-th column of the standard matrix constructed by using the motion vector, s is the first evaluation result value, and M and N are the row dimension and the column dimension of the motion track matrix respectively. Omega j, obtained through preset or obtained through calculating the variance value of each column of the motion trail matrix;
the expression of the second difference calculation process is:
Wherein p i is an evaluation component of the ith row, M and N are row dimension and column dimension of the motion track matrix, z ij is an element of the ith row and the jth column of the motion track matrix, z1 ij is an element of the ith row and the jth column of the standard matrix constructed by using the motion vector, and p is a second evaluation result value.
And the line vectors of the standard matrix constructed by using the motion vectors are motion vectors, and the dimension of the standard matrix is the same as that of the motion track matrix.
The feedback processing module performs feedback calculation processing on a force value sequence, a physiological parameter information set and the evaluation analysis result applied by a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training, so as to obtain a feedback output value, and the feedback processing module comprises:
The standard parameter value set comprises a heart rate standard value, a blood pressure standard value, a blood oxygen saturation standard value and a body temperature standard value;
subtracting each sequence in the physiological parameter information set from a corresponding standard value to obtain a corresponding difference sequence, wherein the difference sequence comprises a heart rate difference sequence, a blood pressure difference sequence, a blood oxygen saturation difference sequence and a body temperature difference sequence;
constructing and obtaining a difference matrix by utilizing all the difference sequences;
Performing eigenvalue decomposition processing on the difference matrix to obtain a maximum eigenvalue and a corresponding eigenvector, wherein the p-th element of the eigenvector is v p;
Constructing and obtaining an optimal feedback polynomial by utilizing the difference matrix;
Subtracting the standard force value from the force value sequence to obtain a force difference sequence, wherein the p-th element of the force difference sequence is b p;
Substituting the median value into an optimal feedback polynomial to obtain a first feedback output component;
calculating the first feedback output component, the force difference sequence, the maximum characteristic value and the evaluation analysis result by using a feedback fusion model to obtain a feedback output value;
the expression of the feedback fusion model is as follows:
Wherein, the For the cross entropy loss function, alpha 1 is the maximum characteristic value, ρ is the evaluation analysis result, m is the element number of the characteristic vector, eta and delta are preset weight values, and beta is the feedback output value.
Values of eta and delta can be 0.5 and 0.4.
The weights used for the weighted summation processing of the first evaluation result value and the second evaluation result value are 0.3 and 0.7.
Specifically, the amount of tactile stimulation determines the set density and radius of the soft needle-like structures of the surface of the pointing assembly.
The physiological information acquisition module can be realized through a health monitoring bracelet.
The pointing component is connected with the support of the training platform through a connecting rod mechanism, the connecting rod mechanism comprises at least one connecting rod unit, the connecting rod unit comprises a first connecting rod and a second connecting rod which are hinged and connected through a first hinge structure, the front end of the first connecting rod is connected with the support of the training platform through a central rotating shaft, and the pointing component is arranged at the rear end of the second connecting rod;
The accelerometer sensor is used for acquiring an upper limb movement track of a user when the upper limb rehabilitation training module is used for performing upper limb rehabilitation training, and constructing an upper limb movement track information set by using all acquired upper limb movement tracks;
The upper limb part extraction of the image of the user when the upper limb rehabilitation training module is used for upper limb rehabilitation training can be realized by adopting a SURF characteristic point detection algorithm or a corner detection algorithm or adopting OpenPose algorithm in OpenCV.
The soft needle-shaped structure can be a rubber strip-shaped structure.
The loss function may employ a cross entropy loss function.
And performing difference calculation processing on the motion trail matrix and the motion vector to obtain a first evaluation result value, wherein the method comprises the following steps:
Copying the row vector according to the column direction by taking the motion vector as a row vector to obtain a standard motion matrix, wherein the dimension of the standard motion matrix is the same as the dimension of the motion track matrix;
subtracting the motion trail matrix from the standard motion matrix to obtain a difference matrix;
performing characteristic average value calculation on the difference matrix to obtain an average value vector;
the expression of the characteristic mean value calculation is as follows:
Wherein b p is the p-th element of the mean value vector, A pq is the p-th row and q-th column elements of the difference matrix, and n is the column dimension of the difference matrix;
performing weight vector calculation on the difference matrix to obtain a weight vector;
The expression of the weight vector calculation is as follows:
V p is the p-th element of the time-aligned standard motion trail information, and f p is the p-th element of the weight vector;
carrying out weighted summation on the weight vector and the mean vector to obtain a first evaluation result value;
the second aspect of the embodiment of the application discloses a haptic information feedback processing method for upper limb rehabilitation training, which is realized by using the haptic information feedback processing device for upper limb rehabilitation training, and comprises the following steps:
s1, displaying scene information of upper limb rehabilitation training to a user by utilizing the virtual reality display module;
S2, acquiring a physiological parameter information set of a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training by utilizing the physiological information acquisition module;
S3, performing evaluation and discrimination processing on the upper limb movement track information set and the standard movement track information by using an evaluation analysis module to obtain an evaluation analysis result;
And S4, carrying out feedback calculation processing on the force value sequence, the physiological parameter information set and the evaluation analysis result applied by the user when the upper limb rehabilitation training module is used for upper limb rehabilitation training by utilizing the feedback processing module, and obtaining a feedback output value.
The step of carrying out evaluation and discrimination processing on the upper limb movement track information set and the standard movement track information to obtain an evaluation analysis result comprises the following steps:
The upper limb movement track information set is expressed as a movement track matrix, and standard movement track information is expressed as a movement vector;
performing first difference calculation processing on the motion trail matrix and the motion vector to obtain a first evaluation result value;
Performing second difference calculation processing on the motion trail matrix and the motion vector to obtain a second evaluation result value;
carrying out weighted summation processing on the first evaluation result value and the second evaluation result value to obtain an evaluation analysis result;
The expression of the first difference calculation process is:
wherein omega j is a preset j importance weight, z ij is an element of an ith row and a jth column of the motion trail matrix, For the j-th element of the motion vector, z1 ij is the i-th row and j-th column of the standard matrix constructed by using the motion vector, s is the first evaluation result value, and M and N are the row dimension and the column dimension of the motion track matrix respectively. Omega j, obtained through preset or obtained through calculating the variance value of each column of the motion trail matrix;
the expression of the second difference calculation process is:
Wherein p i is an evaluation component of the ith row, M and N are row dimension and column dimension of the motion track matrix, z ij is an element of the ith row and the jth column of the motion track matrix, z1 ij is an element of the ith row and the jth column of the standard matrix constructed by using the motion vector, and p is a second evaluation result value.
And the line vectors of the standard matrix constructed by using the motion vectors are motion vectors, and the dimension of the standard matrix is the same as that of the motion track matrix.
The feedback calculation processing is performed on the force value sequence, the physiological parameter information set and the evaluation analysis result applied by the user when the upper limb rehabilitation training module is used for upper limb rehabilitation training, so as to obtain a feedback output value, and the feedback calculation processing comprises the following steps:
The standard parameter value set comprises a heart rate standard value, a blood pressure standard value, a blood oxygen saturation standard value and a body temperature standard value;
subtracting each sequence in the physiological parameter information set from a corresponding standard value to obtain a corresponding difference sequence, wherein the difference sequence comprises a heart rate difference sequence, a blood pressure difference sequence, a blood oxygen saturation difference sequence and a body temperature difference sequence;
constructing and obtaining a difference matrix by utilizing all the difference sequences;
Performing eigenvalue decomposition processing on the difference matrix to obtain a maximum eigenvalue and a corresponding eigenvector, wherein the p-th element of the eigenvector is v p;
Constructing and obtaining an optimal feedback polynomial by utilizing the difference matrix;
Subtracting the standard force value from the force value sequence to obtain a force difference sequence, wherein the p-th element of the force difference sequence is b p;
Substituting the median value into an optimal feedback polynomial to obtain a first feedback output component;
calculating the first feedback output component, the force difference sequence, the maximum characteristic value and the evaluation analysis result by using a feedback fusion model to obtain a feedback output value;
the expression of the feedback fusion model is as follows:
Wherein, the For the cross entropy loss function, alpha 1 is the maximum characteristic value, ρ is the evaluation analysis result, m is the element number of the characteristic vector, eta and delta are preset weight values, and beta is the feedback output value.
Values of eta and delta can be 0.5 and 0.4.
The weights used for the weighted summation processing of the first evaluation result value and the second evaluation result value are 0.3 and 0.7.
Specifically, the amount of tactile stimulation determines the set density and radius of the soft needle-like structures of the surface of the pointing assembly.
The physiological information acquisition module can be realized through a health monitoring bracelet.
The pointing component is connected with the support of the training platform through a connecting rod mechanism, the connecting rod mechanism comprises at least one connecting rod unit, the connecting rod unit comprises a first connecting rod and a second connecting rod which are hinged and connected through a first hinge structure, the front end of the first connecting rod is connected with the support of the training platform through a central rotating shaft, and the pointing component is arranged at the rear end of the second connecting rod;
The accelerometer sensor is used for acquiring an upper limb movement track of a user when the upper limb rehabilitation training module is used for performing upper limb rehabilitation training, and constructing an upper limb movement track information set by using all acquired upper limb movement tracks;
The upper limb part extraction of the image of the user when the upper limb rehabilitation training module is used for upper limb rehabilitation training can be realized by adopting a SURF characteristic point detection algorithm or a corner detection algorithm or adopting OpenPose algorithm in OpenCV.
The soft needle-shaped structure can be a rubber strip-shaped structure.
The loss function may employ a cross entropy loss function.
And performing difference calculation processing on the motion trail matrix and the motion vector to obtain a first evaluation result value, wherein the method comprises the following steps:
Copying the row vector according to the column direction by taking the motion vector as a row vector to obtain a standard motion matrix, wherein the dimension of the standard motion matrix is the same as the dimension of the motion track matrix;
subtracting the motion trail matrix from the standard motion matrix to obtain a difference matrix;
performing characteristic average value calculation on the difference matrix to obtain an average value vector;
the expression of the characteristic mean value calculation is as follows:
Wherein b p is the p-th element of the mean value vector, A pq is the p-th row and q-th column elements of the difference matrix, and n is the column dimension of the difference matrix;
performing weight vector calculation on the difference matrix to obtain a weight vector;
The expression of the weight vector calculation is as follows:
V p is the p-th element of the time-aligned standard motion trail information, and f p is the p-th element of the weight vector;
carrying out weighted summation on the weight vector and the mean vector to obtain a first evaluation result value;
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (7)
1. The haptic information feedback processing device for upper limb rehabilitation training is characterized by comprising a virtual reality display module, a motion track acquisition module, an evaluation analysis module, a feedback processing module, an upper limb rehabilitation training module and a physiological information acquisition module;
The virtual reality display module is used for displaying scene information of upper limb rehabilitation training to a user;
the physiological information acquisition module is used for acquiring a physiological parameter information set of a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training;
The motion trail acquisition module is used for acquiring an upper limb motion trail information set of a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training;
the evaluation analysis module is connected with the motion trail acquisition module and is used for evaluating, judging and processing the upper limb motion trail information set and the standard motion trail information to obtain an evaluation analysis result;
The feedback processing module is connected with the physiological information acquisition module, the evaluation analysis module and the upper limb rehabilitation training module and is used for carrying out feedback calculation processing on a force value sequence, a physiological parameter information set and an evaluation analysis result applied by a user when the upper limb rehabilitation training module is used for carrying out upper limb rehabilitation training to obtain a feedback output value;
The evaluation analysis module performs evaluation and discrimination processing on the upper limb movement track information set and the standard movement track information to obtain an evaluation analysis result, and comprises the following steps:
The upper limb movement track information set is expressed as a movement track matrix, and standard movement track information is expressed as a movement vector;
performing first difference calculation processing on the motion trail matrix and the motion vector to obtain a first evaluation result value;
Performing second difference calculation processing on the motion trail matrix and the motion vector to obtain a second evaluation result value;
carrying out weighted summation processing on the first evaluation result value and the second evaluation result value to obtain an evaluation analysis result;
The expression of the first difference calculation process is:
wherein omega j is a preset j importance weight, z ij is an element of an ith row and a jth column of the motion trail matrix, Z1ij is the element of the ith row and the jth column of the standard matrix constructed by using the motion vector, s is a first evaluation result value, and M and N are the row dimension and the column dimension of the motion track matrix respectively;
the expression of the second difference calculation process is:
Wherein p i is an evaluation component of the ith row, M and N are row dimension and column dimension of the motion track matrix, z ij is an element of the ith row and the jth column of the motion track matrix, z1ij is an element of the ith row and the jth column of the standard matrix constructed by using the motion vector, and p is a second evaluation result value.
2. The tactile information feedback processing device for upper limb rehabilitation training according to claim 1, wherein the upper limb rehabilitation training module comprises a training platform and a pointing component for being held by a patient, the training platform comprises a base and a support, the pointing component is movably connected to the support, a mechanical sensor is arranged on the pointing component and is used for measuring and obtaining a force value sequence applied by a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training, and a plurality of soft needle structures for generating tactile stimulus are arranged on the surface of the pointing component.
3. The tactile information feedback processing apparatus for rehabilitation training of an upper limb according to claim 1, wherein the physiological parameter information set includes a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence.
4. The tactile information feedback processing device for upper limb rehabilitation training according to claim 1, wherein the motion trail acquisition module is realized by adopting an image acquisition and analysis sub-module or an accelerometer sensor arranged on the upper limb of the user;
the upper limb movement track information set comprises a plurality of movement vectors;
The image acquisition analysis sub-module comprises an image acquisition unit and an image analysis unit, wherein the image acquisition unit is used for acquiring images of a user when the upper limb rehabilitation training module is used for conducting upper limb rehabilitation training, and the image analysis unit is used for extracting upper limb parts of the images of the user when the upper limb rehabilitation training module is used for conducting upper limb rehabilitation training to obtain upper limb movement tracks, and an upper limb movement track information set is constructed and obtained by utilizing all acquired upper limb movement tracks.
5. A tactile information feedback processing method for upper limb rehabilitation training, characterized by being realized by the tactile information feedback processing apparatus for upper limb rehabilitation training according to any one of claims 1 to 4, comprising:
s1, displaying scene information of upper limb rehabilitation training to a user by utilizing the virtual reality display module;
S2, acquiring a physiological parameter information set of a user when the upper limb rehabilitation training module is used for upper limb rehabilitation training by utilizing the physiological information acquisition module;
S3, performing evaluation and discrimination processing on the upper limb movement track information set and the standard movement track information by using an evaluation analysis module to obtain an evaluation analysis result;
And S4, carrying out feedback calculation processing on the force value sequence, the physiological parameter information set and the evaluation analysis result applied by the user when the upper limb rehabilitation training module is used for upper limb rehabilitation training by utilizing the feedback processing module, and obtaining a feedback output value.
6. The method for processing haptic feedback information for rehabilitation training of an upper limb according to claim 5, wherein the feedback calculation processing is performed on a force value sequence, a physiological parameter information set and the evaluation analysis result applied by a user when the upper limb rehabilitation training is performed by the upper limb rehabilitation training module by using the feedback processing module to obtain a feedback output value, and the method comprises the following steps:
The standard parameter value set comprises a heart rate standard value, a blood pressure standard value, a blood oxygen saturation standard value and a body temperature standard value;
subtracting each sequence in the physiological parameter information set from a corresponding standard value to obtain a corresponding difference sequence, wherein the difference sequence comprises a heart rate difference sequence, a blood pressure difference sequence, a blood oxygen saturation difference sequence and a body temperature difference sequence;
constructing and obtaining a difference matrix by utilizing all the difference sequences;
Performing eigenvalue decomposition processing on the difference matrix to obtain a maximum eigenvalue and a corresponding eigenvector, wherein the p-th element of the eigenvector is v p;
Constructing and obtaining an optimal feedback polynomial by utilizing the difference matrix;
Subtracting the standard force value from the force value sequence to obtain a force difference sequence, wherein the p-th element of the force difference sequence is b p;
Substituting the median value into an optimal feedback polynomial to obtain a first feedback output component;
And calculating the first feedback output component, the force difference sequence, the maximum characteristic value and the evaluation analysis result by using a feedback fusion model to obtain a feedback output value.
7. The method for processing haptic information feedback for rehabilitation training of upper limbs according to claim 6, wherein the expression of the feedback fusion model is:
alpha 1 is the maximum eigenvalue, ρ is the evaluation analysis result, m is special,
The element number, eta and delta of the sign vector are preset weight values, and beta is a feedback output value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411860244.7A CN119818929B (en) | 2024-12-17 | 2024-12-17 | Haptic information feedback processing device and method for upper limb rehabilitation training |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411860244.7A CN119818929B (en) | 2024-12-17 | 2024-12-17 | Haptic information feedback processing device and method for upper limb rehabilitation training |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119818929A CN119818929A (en) | 2025-04-15 |
| CN119818929B true CN119818929B (en) | 2025-08-19 |
Family
ID=95307408
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411860244.7A Active CN119818929B (en) | 2024-12-17 | 2024-12-17 | Haptic information feedback processing device and method for upper limb rehabilitation training |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119818929B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150097333A (en) * | 2014-02-18 | 2015-08-26 | 경북대학교 산학협력단 | motion control system of haptic device for rehabilitation |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106491310B (en) * | 2016-11-17 | 2019-02-05 | 合肥工业大学 | An intelligent rehabilitation medical device |
| CN109568083B (en) * | 2018-12-15 | 2024-01-05 | 华南理工大学 | A multimodal interactive upper limb rehabilitation robot training system |
| CN110742775B (en) * | 2019-10-12 | 2022-04-12 | 东南大学 | Upper limb active and passive rehabilitation training robot system based on force feedback technology |
| CN112999011A (en) * | 2019-12-19 | 2021-06-22 | 沈阳新松机器人自动化股份有限公司 | Control method of upper and lower limb rehabilitation training device |
-
2024
- 2024-12-17 CN CN202411860244.7A patent/CN119818929B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150097333A (en) * | 2014-02-18 | 2015-08-26 | 경북대학교 산학협력단 | motion control system of haptic device for rehabilitation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119818929A (en) | 2025-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116261749B (en) | Methods and systems for recognizing user actions | |
| Islam et al. | Yoga posture recognition by detecting human joint points in real time using microsoft kinect | |
| CN103127691A (en) | Video generating apparatus and method | |
| CN101515199A (en) | Character input device based on eye tracking and P300 electrical potential of the brain electricity | |
| CN113869217B (en) | A method and system for obtaining image recognition data | |
| CN117476182A (en) | Cognitive decision-making assessment training system and method under instantaneous overweight and weightlessness conditions | |
| Yang et al. | Hand rehabilitation training system integrating non-contact and contact triboelectric nanogenerators for enhanced gesture and handwriting recognition | |
| KR102350320B1 (en) | Customized health care system using electric stimulation device and method thereof | |
| CN119818930B (en) | Fusion feedback processing device and method for lower limb rehabilitation training | |
| US20230337989A1 (en) | Motion data display method and system | |
| CN119818929B (en) | Haptic information feedback processing device and method for upper limb rehabilitation training | |
| CN117785627A (en) | Ergonomic evaluation methods, devices, electronic equipment and media for virtual and real integration | |
| Hidayat et al. | LOVETT scalling with MYO armband for monitoring finger muscles therapy of post-stroke people | |
| CN113288087B (en) | Virtual-real linkage experimental system based on physiological signals | |
| KR102826085B1 (en) | Apparatus abnormal muscle synergy correction training and method of correcting muscle synergy correction using the same | |
| CN119680177B (en) | Fusion feedback processing device and method for upper limb rehabilitation training | |
| CN117137434A (en) | Intelligent physique detection system based on multiple sensors and detection method thereof | |
| Yang et al. | Wushu movement evaluation method based on Kinect | |
| CN119680176B (en) | Haptic information feedback processing device and method for lower limb rehabilitation training | |
| Deng et al. | Advancing biomedical engineering through a multi-modal sensor fusion system for enhanced physical training. | |
| Fadzli et al. | Preliminary study on muscle force estimation using musculoskeletal model for upper limb rehabilitation with assistive device for home setting | |
| CN110507336B (en) | Personalized method for cervical vertebra monitoring and correcting | |
| CN119249361B (en) | Analysis method based on leg training data and training chair | |
| CN113100708A (en) | Quantitative evaluation system for human body balance function | |
| Wang | The Application System of Intelligent Wearable Devices in Physical Education |
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 |