KR20230076322A - Method for assessment of motor function based on fuzzy inference - Google Patents

Abstract

The present invention relates to an exercise function evaluation method based on fuzzy reasoning, the method comprising the steps of: (a) obtaining human body information about the motion of the human body; (b) detecting, on the basis of the human body information, measurement-item-specific capability values in measurement items that are set respectively for a plurality of motions to be measured; (c) classifying the measurement-item-specific capability values and inputting the same into a fuzzy inference unit having a plurality of membership functions, wherein each of the membership functions is generated and registered for each evaluation item of a preset evaluation technique, and the measurement-item-specific capability values are classified according to the evaluation items and input into the corresponding membership functions; and (d) outputting an inference value of each membership function as an evaluation value of the corresponding evaluation item. Therefore, the motor functions of a patients can be more precisely measured on the basis of a fuzzy reasoning technique even while using evaluation items of a conventional exercise function evaluation technique such as the Fugl-Meyer assessment (FMA) technique.

Description

Motor function evaluation method based on fuzzy reasoning {METHOD FOR ASSESSMENT OF MOTOR FUNCTION BASED ON FUZZY INFERENCE}

The present invention relates to a motor function evaluation method based on fuzzy reasoning, and more particularly, in evaluating the motor function of a rehabilitation subject such as a patient, a motor function evaluation method capable of more accurate motor function evaluation using a fuzzy reasoning technique. It is about.

The Fugl-Meyer assessment (FMA) technique relates to a method for quantitatively evaluating the degree of functional recovery of stroke patients based on the recovery stage of motor ability after stroke.

The Fugle-Meier assessment has a sequential scoring system, where a score of 0 means that the stroke patient is unable to perform a specified upper limb movement, a score of 1 means he is partially performing, and a score of 2 is completely performing.

Such a Fugle-Meier evaluation technique is widely used in motor function evaluation because of its validity and reliability, but has several problems.

First, there is a problem that the consistency and objectivity of evaluation may be lowered because it varies according to the subjective judgment of the measurer.

Second, it is inconvenient to move to the evaluation space because the evaluation is conducted in a face-to-face manner involving the measurer.

In order to solve the above problems, a technology using a wearable sensor has been proposed, but the patient may feel foreign body sensation or discomfort. In addition, in the case of a patient with muscle contraction, it is difficult to use a glove-type sensor, which limits general-purpose measurement.

Accordingly, a motor function evaluation system using multiple sensors has been proposed. In this case, it is desirable to minimize the number of sensors. This is because the cost of the entire system can be reduced and the time for attaching the sensor can be reduced.

For example, the motor function evaluation system disclosed in Korean Patent Registration No. 10-1814293 proposes a function evaluation technique using a motion recognition sensor and a pressure sensor.

The motor function evaluation system disclosed in the Korean registered patent analyzes the motion to be measured for the human body based on human body information on the human body movement recognized through the motion recognition sensor and digitizes it, thereby performing Fugl-Meier evaluation (Fugl-Meier evaluation). A technique for evaluating motor function according to the meyer assessment (FMA) technique is disclosed.

However, since the score of each evaluation item is evaluated on a 3-point scale of 0, 1, and 2 according to the Fugl-Meyer assessment (FMA) technique, precise changes in the patient's motor function are measured. not enough to do To compensate for this, it is possible to consider developing a separate motor function evaluation method, but proposing a separate technique beyond the currently widely used Fugl-Meyer assessment (FMA) technique is also not realistic. There is a problem.

Korean Registered Patent Publication No. 10-1814293

The present invention has been devised in view of the above points, and an object of the present invention is to accurately evaluate the patient's motor function while using an existing motor function evaluation technique such as the Fugl-meyer assessment (FMA) technique. It is to provide a motor function evaluation method based on fuzzy reasoning that can measure changes.

An object of the present invention is to provide a motor function evaluation method based on fuzzy reasoning, comprising the steps of (a) obtaining human body information about a human body movement, and (b) performing a plurality of measurements based on the human body information. detecting a capability value for each measurement item in each measurement item set for a target motion; (c) classifying and inputting the capability value for each measurement item to a fuzzy inference unit having a plurality of membership functions; A function is created and registered for each evaluation item in a preset evaluation technique, and the ability value for each measurement item is classified by the evaluation item and inputted to the corresponding membership function (d) The inferred value of each membership function is corresponding It is achieved by a motor function evaluation method comprising the step of outputting evaluation values for evaluation items.

Here, the evaluation technique may include a Fugl-meyer assessment (FMA) technique.

In addition, the measurement items include a first reasoning type classified as fully performed, partially performed, or not performed, a second reasoning type classified as performed or not performed, and a third reasoning type classified as maintained or not maintained, ; The ability values for each measurement item corresponding to the first reasoning type are given as R1, R2, and R3 corresponding to complete performance, partial performance, and non-performance, respectively; The ability values for each measurement item corresponding to the second inference type are given as R4 and R5 corresponding to performance and non-performance, respectively; The ability values for each measurement item corresponding to the third reasoning type may be assigned as R6 and R7 corresponding to maintenance and non-maintenance, respectively.

And, a plurality of fuzzy rules for configuring the membership function are set for each of R1, R2, and R3; Established by AND or OR combination between measurement items belonging to the second reasoning type for R4 and R5; R6 and R7 may be set and generated by an OR combination between measurement items belonging to the third reasoning type.

Further, each of the membership functions may be generated by applying at least two of the plurality of fuzzy rules, and may be generated through aggregation of the applied fuzzy rules.

Further, among the fuzzy rules, in the case of an AND combination between the measurement items, a minimum value of an overlapping portion between the fuzzy rules may be calculated and combined with a maximum value of an overlapping portion between the fuzzy rules in the case of an OR combination.

The membership function may output the evaluation value as a value between 0 and 1 by performing de-fuzzification after combining the fuzz rules.

And, (e) mapping the evaluation value of each membership function to a value of 0, 1, or 2, which is an evaluation value according to a Fugl-Meyer assessment (FMA) technique.

According to the present invention, it is possible to more precisely measure a patient's motor function based on a fuzzy reasoning technique, while using evaluation items on an existing motor function evaluation technique such as the Fugl-meyer assessment (FMA) technique. A motor function evaluation method based on fuzzy reasoning is provided.

In addition, according to the present invention, by converting precise measurement results into evaluation scores on existing evaluation techniques such as the Fugl-meyer assessment (FMA) technique, fuzziness that can be easily checked by users familiar with existing techniques An inference-based motor function assessment method is provided.

1 and 2 are diagrams showing a schematic configuration of a motor function evaluation system according to an embodiment of the present invention;
3 is a diagram showing an example of the configuration of an exercise capacity evaluation unit according to an embodiment of the present invention;
4 to 7 are diagrams for explaining the configuration of a fuzzy reasoning unit according to an embodiment of the present invention.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, only these embodiments are intended to complete the disclosure of the present invention, and are common in the art to which the present invention belongs. It is provided to fully inform the person skilled in the art of the scope of the invention, and the invention is only defined by the scope of the claims.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first element mentioned below may also be the second element within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

The motor function evaluation system 100 according to an embodiment of the present invention is a system for analyzing motion characteristics of a patient with a brain disease, and may assign evaluation scores to a series of measurement target motions according to evaluation conditions. However, the application is not limited to patients with brain diseases, and can be applied to various fields where the motion characteristics of the human body can be analyzed.

1 and 2 are diagrams showing a schematic configuration of a motor function evaluation system 100 according to an embodiment of the present invention.

Referring to FIGS. 1 and 2, the motor function evaluation system 100 according to an embodiment of the present invention may include a sensing unit 110, a motor ability evaluation unit 130, and an image display unit 150. there is.

The sensing unit 110 acquires human body information including the movement of the human body and the holding state of the hand in real time. For example, the human body information may include motion information on movement, rotation, bending, or extension of the arm, shoulder, waist, or hand of the human body in a specific direction. In order to obtain such information, it is exemplified that the sensing unit 110 according to the embodiment of the present invention includes a motion recognition sensor 111 and a pressure sensor 112 .

As shown in FIG. 2 , the motion recognition sensor 111 may be disposed toward the human body and detect the position of a joint of the human body, the direction of a bone adjacent to a joint, or a gripping state of a hand. In addition, the pressure sensor 112 may be held in the hand of the human body and sense the gripping force of the hand.

According to the structure as described above, since it is possible to obtain pronation or supination motion of the forearm arm and bending angle information of the finger without using a glove-type sensor or an inertial measurement unit (IMU), the motor function evaluation system (100) ), cost can be saved by reducing the number of sensors used, and practical application in the clinical field is possible by significantly reducing the time for attaching sensors.

3 is a diagram showing an example of the configuration of the exercise capacity evaluation unit 130 according to an embodiment of the present invention.

Referring to FIG. 3, the exercise capacity evaluation unit 130 according to an embodiment of the present invention includes a data classification unit 131, a fuzzy inference unit 132, an image processing unit 135, a communication unit 136, and a main control unit. (134). In addition, the exercise capacity evaluation unit 130 according to an embodiment of the present invention may further include an output mapping unit 133 and a user input unit 137.

The data classification unit 131 according to an embodiment of the present invention classifies the sensing result of the sensing unit 110 received through the communication unit 136 for each measurement item set for a plurality of measurement target motions. For example, a motion to be measured may be analyzed from an image captured by the motion recognition sensor 111, and the corresponding dungeon may be classified for each measurement item.

Here, in the embodiment of the present invention, as an example, the Fugl-meyer assessment (FMA) technique is applied to motor function evaluation, each of the evaluation items on the Fugl-meyer assessment (FMA) technique An example is classifying the measurement items to be applied for according to the evaluation items.

The fuzzy inference unit 132 according to an embodiment of the present invention detects a capability value for a corresponding measurement item based on data classified by the measurement item by the data classification unit 131 . That is, the fuzzy inference unit 132 may detect a capability value for each measurement item.

Further, the fuzzy reasoning unit 132 inputs capability values for each measurement item to a plurality of pre-registered membership functions, and outputs inferred values, that is, output values, of each membership function as evaluation values.

In an embodiment of the present invention, it is exemplified that each membership function is generated and registered for each evaluation item on an evaluation technique, for example, the above-described Fugl-Meyer assessment (FMA) technique. In addition, it is exemplified that the ability values for each measurement item are classified according to evaluation items and input to a corresponding membership function.

Hereinafter, a plurality of membership functions registered in the fuzzy inference unit 132 according to an embodiment of the present invention will be described in detail.

Taking the Fugl-meyer assessment (FMA) technique as an example, evaluation items in the Fugl-meyer assessment (FMA) technique are composed of T1, T2, and T3.

T1 may be defined as "elbow extension during hand to knee", and exercise ability may be evaluated through an exercise to bring the affected upper limb to the affected ear in a sitting position.

T2 can be defined as "shoulder abduction 0-90°", and the ability to exercise by lifting the shoulder up to 90° while keeping the elbow straight and the forearm not rotated (a state between pronation and supination). this can be evaluated.

T3 may be defined as "shoulder abduction + internal rotation during hand to knee", and exercise ability may be evaluated through an exercise in which the upper extremity on the affected side is directed toward the unaffected knee in the T1 posture.

In an embodiment of the present invention, as described above, it is exemplified to configure a membership function by setting T1, T2, and T3 of the Fugl-Meyer assessment (FMA) technique as evaluation items, that is, membership corresponding to T1. For example, the function, membership function corresponding to T2, and membership function corresponding to T3 are registered in the fuzzy reasoning unit 132, and evaluation values for each of T1, T2, and T3 are output from each membership function.

Meanwhile, the capability value for each measurement item to be applied as an input of each membership function is detected for each measurement item as described above. Here, in an embodiment of the present invention, it is exemplified that measurement items are classified into a first reasoning type, a second reasoning type, and a third reasoning type.

The first inference type may include motions in which measurement target motions corresponding to measurement items can be classified as fully performed, partially performed, and unperformed (ie, not performed).

And, the second inference type may include actions in which measurement target actions corresponding to measurement items can be classified into performed and non-performed.

Finally, the third reasoning type may include motions in which measurement target motions corresponding to measurement items can be classified into maintenance and non-maintenance (ie, not maintained).

4 is a diagram for explaining fuzzy input variables of a membership function in the fuzzy reasoning unit 132 according to an embodiment of the present invention. As shown in FIG. 4, each evaluation item of the Fugl-Meyer assessment (FMA) technique is matched with at least one of the inference types, and each evaluation item has at least one measurement item as its input. can be used

And, as described above, it is exemplified that capability values for each measurement item corresponding to the first reasoning type are given as R1, R2, and R3 corresponding to complete performance, partial performance, and non-performance, respectively.

In addition, for example, the ability values for each measurement item corresponding to the second reasoning type are given as R4 and R5 corresponding to performance and non-performance, respectively, and the ability value for each measurement item corresponding to the third reasoning type is maintained and non-maintenance. For example, those assigned to R6 and R7 correspond to each other. Here, R1 to R7 become indices of fuzzy inputs of the membership function.

5 is a diagram showing an example of a fuzzy rule applied to a membership function according to an embodiment of the present invention.

As shown in FIG. 5, the fuzzy rule is set for each of the fuzzy inputs R1, R2, and R3, and is set by AND or OR combination between measurement items belonging to the second reasoning type for R4 and R5, It is exemplified that R6 and R7 are set and generated by an OR combination between measurement items belonging to the third reasoning type.

In addition, the output for each fuzzy rule is set to S1, S2, and S3. Corresponding to the Fugl-Meyer assessment (FMA) technique, S1 is 2 points, S2 is 1 point, and S3 is 0 points. set as an example.

6 is a diagram illustrating examples of membership functions corresponding to a first reasoning type, a second reasoning type, and a third reasoning type to be applied to each fuzzy rule.

In addition, it is exemplified that a membership function corresponding to each evaluation item is generated through aggregation of fuzzy rules applied to the corresponding evaluation item.

That is, the membership function of the evaluation item corresponding to T1 among the evaluation items is generated through the synthesis of membership functions corresponding to the three fuzzy rules shown in FIG. 5, and T2 is the synthesis of membership functions corresponding to the five fuzzy rules. T3 is created through the synthesis of membership functions corresponding to the five fuzzy rules.

7 is a diagram showing an example of synthesis for generating membership functions for evaluation items. In the embodiment of the present invention, it is assumed that, among fuzzy rules, in the case of an AND combination between measurement items, the minimum value of the overlapping portion between fuzzy rules is calculated and the maximum value of the overlapping portion between fuzzy rules is calculated and synthesized in the case of an OR combination.

And, in the embodiment of the present invention, after synthesizing the membership function for the fuzzy rule, de-fuzzification is performed to quantify the evaluation value. In an embodiment of the present invention, it is exemplified that the evaluation value is output as a value between 0 and 1.

Through the above process, when the capability value for each measurement item is input to the corresponding membership function of the fuzzy inference unit 132, through the fuzzy inference process, it is converted to a value between 0 and 1 for each membership function, that is, for each FMA evaluation item. It is output, and a more precise evaluation is possible than conventional FMA evaluation values expressed by any one of the values 0, 1, and 2.

Here, the output mapping unit 133 according to an embodiment of the present invention maps the evaluation value of each membership function to a value of 0, 1, or 2, which is an evaluation value according to the Fugl-Meyer assessment (FMA) technique. So, it can be output. That is, the main control unit 134 controls the output mapping unit 133 to map the evaluation value of the membership function to a value of 0, 1, or 2 either automatically or at a request of the user through the user input unit 137, and the image processing unit A corresponding image may be generated through (135) and displayed through the image display unit 150.

Through this, it is converted into an evaluation score on the existing evaluation technique and provided, so that even a user familiar with the existing technique can easily check it.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

100: motor function evaluation system
110: sensing unit 111: motion recognition sensor
112: pressure sensor 130: exercise ability evaluation unit
131: data classification unit 132: fuzzy reasoning unit
133: output mapping unit 134: main control unit
135: image processing unit 136: communication unit
137: user input unit 150: video display unit

Claims (8)

In the motor function evaluation method based on fuzzy reasoning,
(a) obtaining human body information about human body movements;
(b) detecting a capability value for each measurement item in each measurement item set for a plurality of measurement target motions based on the human body information;
(c) classifying and inputting the ability values for each measurement item to a fuzzy inference unit having a plurality of membership functions; The ability values for each measurement item are classified according to the evaluation item and input to the corresponding membership function.
(d) outputting an evaluation value for a corresponding evaluation item based on the inferred value of each membership function.
According to claim 1,
The method for evaluating motor function, characterized in that the evaluation technique comprises a Fugl-meyer assessment (FMA) technique.
According to claim 2,
The above measurement items are
A first reasoning type classified into fully performed, partially performed, and non-performed;
A second reasoning type classified as performed or not performed;
includes a third reasoning type classified as maintained or unmaintained;
The ability values for each measurement item corresponding to the first reasoning type are given as R1, R2, and R3 corresponding to complete performance, partial performance, and non-performance, respectively;
The ability values for each measurement item corresponding to the second inference type are given as R4 and R5 corresponding to performance and non-performance, respectively;
The motor function evaluation method, characterized in that the ability values for each measurement item corresponding to the third reasoning type are assigned as R6 and R7 corresponding to maintenance and non-maintenance, respectively.
According to claim 3,
A plurality of fuzzy rules for constructing the membership function
set for each of R1, R2, R3;
Established by AND or OR combination between measurement items belonging to the second reasoning type for R4 and R5;
The motor function evaluation method, characterized in that it is set and generated by an OR combination between measurement items belonging to the third reasoning type for R6 and R7.
According to claim 4,
Each of the above membership functions
The motor function evaluation method, characterized in that generated by applying at least two of the plurality of fuzzy rules, and generated through aggregation of the applied fuzzy rules.
According to claim 5,
Among the fuzzy rules, in the case of an AND combination between the measurement items, the minimum value of the overlapping portion between the fuzzy rules is calculated and synthesized.
According to claim 6,
The motor function evaluation method, characterized in that the membership function outputs the evaluation value as a value between 0 and 1 by de-fuzzification after synthesis between the fuzzy rules.
According to claim 7,
(e) mapping the evaluation value of each membership function to a value of 0, 1 or 2, which is an evaluation value according to a Fugl-meyer assessment (FMA) technique. Functional evaluation method.

Images