Apparatus, system, and method for monitoring rehabilitation exercise

Abstract

The present invention relates to an apparatus for monitoring rehabilitation exercise. The apparatus for monitoring rehabilitation exercise, according to embodiments of the present invention, comprises: at least one sensor attached to a patient's body to measure the state of muscle movement; at least one processor that receives an electrical signal from the sensor to determine the exercise state of the patient; and a memory storing instructions processed by the processor, wherein the instructions include threshold information that distinguishes between and determines muscle contraction, muscle relaxation, and muscle stiffness of the patient.

Description

Device, system and method for monitoring rehabilitation exercise

[0001] The present invention relates to a device, system and method for monitoring rehabilitation exercise, and more particularly, to a system and method capable of accurately monitoring the exercise of a rehabilitation patient through surface electromyography signals and strain sensor data.

[0002] Rehabilitation exercises are effective only when performed with proper technique and posture, so it's necessary to guide patients and monitor their progress. However, frequent hospital visits for expert guidance can be a significant burden for patients with physical disabilities.

[0003] Additionally, even if a patient visits a hospital, there are limitations in accurate diagnosis because the evaluation of motor status relies on the therapist's subjective assessment and the patient's self-report.

[0004] Therefore, a monitoring system and method that can accurately track and guide the patient's exercise status is needed.

[0005] The problems that the present invention seeks to solve are as follows.

[0006] First, it is to collect detailed data related to muscle activity to accurately understand the patient's movement patterns.

[0007] Second, it is to evaluate the treatment effect based on the patient's accurate exercise data and establish a personalized rehabilitation plan.

[0008] Third, it is to prevent injuries and increase treatment effectiveness through proper technique and posture education.

[0009] The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the description below.

[0010] In order to achieve the above task, a device according to various embodiments of the present invention comprises a device for monitoring rehabilitation exercise, comprising: at least one sensor attached to a patient's body to measure a muscle movement state; at least one processor that receives an electrical signal from the sensor to determine the patient's movement state; and a memory that stores a command processed by the processor, wherein the command includes threshold value information for distinguishing and determining muscle contraction, muscle relaxation, and muscle stiffness of the patient.

[0011] Specific details of other embodiments are included in the detailed description and drawings.

[0012] According to the present invention, one or more of the following effects are achieved.

[0013] First, by collecting detailed data related to muscle activity, we can accurately identify the patient's movement patterns.

[0014] Second, it provides data for evaluating treatment effects and establishing personalized rehabilitation plans based on the patient's accurate exercise data.

[0015] Third, we provide accurate monitoring methods and systems to prevent injuries and improve treatment effectiveness through proper technique and posture education.

[0016] The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

[0017] Figure 1 is a block diagram showing components of a monitoring system (200) according to various embodiments of the present invention.

[0018] Figure 2 is a flowchart showing signal analysis of a monitoring device (100) and a monitoring system (200) according to various embodiments of the present invention.

[0019] Figure 3 is a flowchart showing a command generation method of a monitoring device (100) and a monitoring system (200) according to various embodiments of the present invention.

[0020] Figure 4a is a flowchart showing the threshold value readjustment of a server (80) according to various embodiments of the present invention.

[0021] Figure 4b is a flowchart showing the threshold value readjustment of a server (80) according to various embodiments of the present invention.

[0022] Figure 4c is a flowchart showing the threshold value readjustment of a server (80) according to various embodiments of the present invention.

[0023] Figure 5 illustrates threshold value calculation and dynamic threshold value adjustment of a monitoring device (100) and a monitoring system (200) according to various embodiments of the present invention.

[0024] Figure 6 illustrates an example of a monitoring device (100) and a monitoring system (200) interpreting and judging a signal according to various embodiments of the present invention.

[0025] Figure 7 illustrates another example of a monitoring device (100) and a monitoring system (200) interpreting and judging a signal according to various embodiments of the present invention.

[0026] FIG. 8 illustrates another example of a monitoring device (100) and a monitoring system (200) interpreting and judging signals according to various embodiments of the present invention.

[0027] The terms used in the embodiments of this specification have been selected from widely used, current terms, taking into account the functions of the present disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, the applicant may arbitrarily select terms, and in such cases, their meanings will be described in detail in the description of the relevant embodiments. Therefore, the terms used in this specification should not be defined simply as names of terms, but rather based on the meanings of the terms and the overall content of the present disclosure.

[0028] Hereinafter, the present invention will be described with reference to the drawings.

[0029] Figure 1 is a block diagram showing components of a monitoring system (200) according to various embodiments of the present invention. Figure 2 is a flowchart showing signal analysis of a monitoring device (100) and a monitoring system (200) according to various embodiments of the present invention.

[0030] Referring to FIGS. 1 and 2, a monitoring device (100) according to various embodiments of the present invention includes a monitoring device (100) for monitoring rehabilitation exercise, which includes at least one sensor attached to a patient's body to measure a muscle movement state; at least one processor (10) that receives an electrical signal from the sensor to determine a patient's movement state; and a memory (50) that stores instructions processed by the processor (10), wherein the instructions include threshold value information for distinguishing and determining muscle contraction, muscle relaxation, and muscle stiffness of the patient.

[0031] In addition, a monitoring device (100) according to various embodiments of the present invention includes a monitoring device (100) for monitoring rehabilitation exercise, which is attached to a patient's body and measures a muscle movement state; at least one processor (10) that receives an electrical signal from the sensor and determines the patient's movement state; and a memory (50) that stores a command processed by the processor (10), wherein the command includes threshold value information for distinguishing and determining muscle contraction, muscle relaxation, and muscle tremors of the patient.

[0032] In addition, a monitoring device (100) according to various embodiments of the present invention includes, in a monitoring device (100) for monitoring rehabilitation exercise, at least one sensor attached to a patient's body to measure a muscle movement state; a processor (10) that receives an electrical signal from the sensor and distinguishes and determines at least one of muscle contraction, muscle relaxation, muscle stiffness, and muscle tremors of the patient; and a command for driving the processor (10).

[0033] In one embodiment, the monitoring device (100) can detect muscle movement of a patient using at least one sensor attached to the patient. In one embodiment, the monitoring device (100) detects muscle movement status using various sensors attached to the muscles. The various sensors may be, for example, an EMG sensor (20), a strain gauge (40), and an IMU (30). The IMU (30) may include an acceleration sensor (31), a gyroscope (32), and a geomagnetic sensor (33).

[0034] The processor (10) can execute one or more instructions of a program stored in the memory (50). The processor (10) may be composed of hardware components that perform arithmetic, logic, and input / output operations and signal processing. The processor (10) may be composed of at least one of, for example, a central processing monitoring device (100), a microprocessor (10), a graphic processing unit (10), application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), and field programmable gate arrays (FPGAs), but is not limited thereto. In one embodiment, the processor (10) may be composed of a communication processor (CP).

[0035] The processor (10) includes a counting unit (11) that counts and / or cumulatively counts various numbers, a command generation unit (11) that generates a control command (e.g., a command generation unit to be provided to the patient), and a judgment unit (13) that determines the patient's exercise status and threshold value reset.

[0036] The signal analysis process of the monitoring device (100) and the monitoring system (200) according to various embodiments of the present invention includes the steps of artifact removal and estimation (S21), frequency filter (S22), rectification (S23), fixed threshold value setting (S24), onset-offset detection (S25), windowing (S26), dynamic threshold value adjustment (S27), windowing (S28), and feature extraction (S29). In order to remove artifacts, outliers can be removed through a Kalman filter and replaced with estimated values.

[0037] The fixed threshold value setting (S24) step can perform a test for a predetermined time to measure the “mean + a (standard deviation)” to determine background noise.

[0038] The dynamic threshold adjustment (S27) step adjusts the threshold if it exceeds a certain standard based on the variability of the signal after measurement.

[0039] Figure 3 is a flowchart showing a command generation method of a monitoring device (100) and a monitoring system (200) according to various embodiments of the present invention.

[0040] Referring to FIG. 3, a method according to various embodiments of the present invention includes a step of determining whether a predetermined section before Ttemp_onset remains below a threshold value in a method for monitoring rehabilitation exercise; a step of generating a contraction command (S31); a step of determining whether a predetermined section after Ttemp_onset remains above a threshold value; a step of generating a relaxation command (S33); a step of determining whether at least one of a predetermined time, the number of contraction commands generated, and the number of relaxation commands generated reaches a reference value; and a step of transmitting a determination result value to a server (80).

[0041] The monitoring device (100) includes a communication module (60) and transmits information to the monitoring system (200) via the Internet (70).

[0042] In one embodiment, the monitoring device (100) can recognize the patient's muscle movements using at least one sensor attached to the patient. In one embodiment, the monitoring device (100) can recognize whether the patient has initiated exercise, failed to initiate exercise, completed exercise, failed to complete exercise, whether the patient has muscle stiffness, and whether the patient has muscle contraction using various sensors attached to the muscles.

[0043] By utilizing a strain gauge (40), an IMU (30), and an EMG sensor (20) according to one embodiment of the present invention, isometric and isotonic movements can be distinguished. Each sensor can measure changes in muscle length, force generation, and electrical activity. The processor (10) analyzes the measured data.

[0044] The strain gauge (40) detects the force or tension generated when a muscle contracts. If the processor (10) determines that tension is generated but the muscle length does not change, it determines that the movement is isometric. If the force is generated and the muscle length changes, it determines that the movement is isotonic.

[0045] The IMU (30) (Inertial Measurement Unit) measures changes in joint position (acceleration, angular velocity, direction) during exercise. When muscle length changes, changes can also be observed in the angle and movement of the joint. If the processor (10) confirms that the joint angle is fixed through the IMU (30) data, it determines that the exercise is isometric. If changes in the joint angle or movement occur, it determines that the exercise is isotonic.

[0046] The EMG sensor (20) (electromyography sensor) measures the electrical activity of muscles (muscle activity). The EMG sensor (20) determines the intensity and duration of muscle contraction. The processor (10) determines that if the EMG signal remains constant, it is an isometric exercise, and if the EMG signal fluctuates (contraction and relaxation patterns), it can determine that it is an isotonic exercise.

[0047] More specifically, the processor (10) can determine that the movement is isometric if a continuous tension is measured from the strain gauge (40), no change in movement of muscles and / or joints is measured from the IMU (30), and a continuous and stable muscle activity pattern is measured from the EMG sensor (20).

[0048] The processor (10) can determine that the movement is isotonic if the strain gauge (40) measures changes in force size (muscle contraction and relaxation), the IMU (30) measures changes in joint angle or movement, and the EMG sensor (20) measures changes in muscle activity pattern along the length.

[0049] A device according to one embodiment of the present invention can analyze a movement state by integrating a strain gauge (40), an IMU (30), and an EMG sensor (20).

[0050] Machine learning algorithms can automatically classify isometric and isotonic movements by learning data from the various sensors mentioned above.

[0051] The processor (10) can store rehabilitation treatment data by providing real-time feedback to the server (80) to determine whether the patient is performing the correct exercise. The server (80) can design exercise programs and measure performance, and output reports on muscle efficiency analysis and training optimization.

[0052] The processor (10) determines that when muscle contraction occurs, the muscle has shortened its length or generated force, and can determine the patient's condition as one of exercise initiation, isotonic exercise, and isometric exercise.

[0053] The processor (10) determines that when muscle relaxation occurs, muscle activity stops and force is no longer generated, and can determine the patient's condition as one of the end of isometric exercise, the end of isometric exercise, or the end of exercise.

[0054] Muscle stiffness is an abnormal condition in which muscles remain in a persistent state of tension and do not relax. If the processor (10) determines that tension occurs but muscle length does not change, it determines that the exercise is isometric.

[0055] The processor (10) determines that muscle stiffness occurs when the isometric movement state exceeds a predetermined time. The processor (10) can command the generation of a warning signal. If the processor (10) determines that muscle stiffness occurs, it can command the transmission of a warning signal to a terminal carried by the patient and / or guardian. The communication module (60) can transmit a signal to the server (80) or the terminal of the patient or guardian according to the command of the processor (10).

[0056] In one embodiment, various sensors detect muscle contraction and relaxation, and the processor (10) determines whether exercise has begun, whether exercise has failed to begin, whether exercise has been completed, whether exercise has failed to complete, whether muscle stiffness has occurred, and whether muscle contraction has occurred. The processor (10) can monitor the patient's condition in real time by counting and / or cumulatively counting the number of each event.

[0057] The judgment unit (13) can compare and / or calculate the signal received by the sensor, the accumulated counting number, the threshold value, the minimum threshold value, the maximum threshold value, the set time, the number of contraction commands generated, and the number of relaxation commands generated, and reset the threshold value based on the value.

[0058] A monitoring system (200) according to various embodiments of the present invention includes a server (80) that receives and stores information determined from a monitoring device (100), and the server (80) readjusts a threshold value set for a patient based on the determined information.

[0059] The server (80) can recognize the patient's movement pattern using the monitoring device (100). In one embodiment, the server (80) can include a deep neural network model (DNN) that includes information acquired by various sensors and learned model parameters. The deep neural network model can be composed of an artificial intelligence model that includes at least one of, for example, a convolutional neural network model, a recurrent neural network (RNN), a support vector machine (SVM), linear regression, logistic regression, naive Bayes classification, a random forest, a decision tree, or a k-nearest neighbor algorithm.

[0060] The server (80) can acquire label values ​​regarding the patient's exercise performance pattern by performing learning that inputs the patient's exercise status acquired through the sensor as input data into a deep neural network model. The server (80) can recognize the patient's exercise pattern based on the acquired label values. The monitoring device (100) can patternize each element of, for example, whether the patient started exercise, whether the patient failed to start exercise, whether the patient completed exercise, whether the patient failed to complete exercise, whether the patient had muscle stiffness, and whether the patient had muscle contraction, and can recognize each pattern by associating it with the cause and degree of injury.

[0061] Figure 4a is a flowchart illustrating threshold value readjustment of a server (80) according to various embodiments of the present invention. Figure 4b is a flowchart illustrating threshold value readjustment of a server (80) according to various embodiments of the present invention. Figure 4c is a flowchart illustrating threshold value readjustment of a server (80) according to various embodiments of the present invention.

[0062] Referring to FIGS. 4A, 4B, and 4C, a method according to various embodiments of the present invention includes a step of receiving at least two of the number of times a contraction command is generated, the number of times an exercise is initiated, the number of times an exercise is initiated and failed, the number of times an exercise is completed, the number of times an exercise is completed and failed, the number of times a relaxation command is generated, the number of times a muscle is stiffened, and the number of times a muscle is contracted; a step of accumulating and storing the received number of times; and a step of readjusting a minimum threshold value and a maximum threshold value, which are criteria for determining whether an exercise has been initiated, whether an exercise has been completed, whether a muscle is stiffened, and whether a muscle is contracted, based on the result of the accumulated count. A processor (10) performs each of the above steps.

[0063] The processor (10) can readjust the minimum and maximum threshold values. Based on the results received by the sensor, the processor (10) can readjust the threshold values ​​by determining whether the exercise evaluation result is unattainable, has a high risk of injury, or has insufficient exercise effects. The threshold value readjustment and the exercise evaluation result may also be performed by another processor (not shown) present in the server (80).

[0064] FIG. 5 illustrates threshold value calculation and dynamic threshold value adjustment of a monitoring device (100) and a monitoring system (200) according to various embodiments of the present invention. FIG. 6 illustrates an example of a monitoring device (100) and a monitoring system (200) interpreting and judging a signal according to various embodiments of the present invention. FIG. 7 illustrates another example of a monitoring device (100) and a monitoring system (200) interpreting and judging a signal according to various embodiments of the present invention. FIG. 8 illustrates another example of a monitoring device (100) and a monitoring system (200) interpreting and judging a signal according to various embodiments of the present invention.

[0065] Referring to FIGS. 5, 6, 7 and 8, conditions for motion onset detection according to various embodiments of the present invention include: selecting a time (Ttemp_onset) that starts below a threshold value and exceeds the threshold value; a predetermined section before Ttemp_onset that remains below the threshold value; a predetermined section after Ttemp_onset that remains above the threshold value; if the condition is not met, selecting the next Ttemp_onset and repeating; if the condition is met, Ttemp_onset = Tonset.

[0066] Conditions for motion onset detection according to various embodiments of the present invention are as follows.

[0067] Select a time (Ttemp_onset) that starts below the threshold and exceeds the threshold, a set interval before Ttemp_onset must remain below the threshold, a set interval after Ttemp_onset must remain above the threshold, if the condition is not met, select the next Ttemp_onset and repeat, if the condition is met, Ttemp_onset = Tonset.

[0068] Conditions for motion onset detection according to various embodiments of the present invention are as follows.

[0069] A method for monitoring rehabilitation exercise using a device including at least one sensor, a processor, and a memory, the method comprising: a step of determining whether a predetermined section prior to a Tonset, which is a point in time at which exercise ends, remains below a threshold value; a step of generating a contraction command for instructing a patient to contract a muscle; and a step of determining a point in time at which a condition is satisfied that the immediately preceding predetermined section remains below the threshold value and the immediately following predetermined section remains above the threshold value, based on the point in time at which the contraction command is generated, as a Tonset.

[0070] Conditions for motion onset detection according to various embodiments of the present invention may be as follows.

[0071] Select a time (Ttemp_onset) that starts below the threshold and exceeds the threshold; a set interval before Ttemp_onset must remain below the threshold; a set interval after Ttemp_onset must remain above the threshold; if the condition is not met, select the next Ttemp_onset and repeat; if the condition is met, determine Ttemp_onset = Tonset.

[0072] The command is configured so that the processor (10) can determine that movement has begun if the signal received by the sensor is greater than a minimum threshold value.

[0073] The command is configured so that the processor (10) can determine muscle stiffness if the signal received by the sensor is greater than or equal to a minimum threshold value and remains above the minimum threshold value for a predetermined period of time.

[0074] The command is configured so that the processor (10) can determine muscle stiffness if the signal received by the sensor is greater than or equal to a maximum threshold value and is maintained at the maximum threshold value for a predetermined period of time.

[0075] The command is configured so that the processor (10) can determine muscle stiffness when the signal received by the sensor is greater than or equal to a maximum threshold value and remains greater than or equal to a minimum threshold value for a predetermined period of time.

[0076] The command is configured so that the processor (10) can determine that the movement initiation has failed if the signal received by the sensor is below a minimum threshold value.

[0077] The command is configured so that the processor (10) can determine that the movement is complete when the maximum value of the signal received by the sensor exceeds the maximum threshold value.

[0078] The command is configured so that the processor (10) can determine that the movement has failed to complete if the maximum value of the signal received by the sensor is less than the maximum threshold value.

[0079] A monitoring device (100) according to various embodiments of the present invention comprises: at least one sensor attached to a patient's body for measuring a muscle movement state; at least one processor (10) for receiving an electrical signal from the sensor and determining a patient's movement state; and a memory (50) for storing commands processed by the processor (10), wherein the commands include threshold value information for distinguishing and determining muscle contraction, muscle relaxation, and muscle tremors of the patient.

[0080] The command is that the signal received by the sensor vibrates up and down based on a threshold value, and if the cycle of the up and down vibration area is within a set value, it is judged as muscle tremor.

[0081] The processor (10) according to various embodiments of the present invention can determine the achievement rate and performance rate.

[0082] Attainment Rate: Number of times the target threshold is reached / Number of attempts

[0083] Performance Rate: Number of times the default threshold is exceeded / Number of attempts

[0084] Target threshold: th_max

[0085] Default threshold: th_min

[0086] The processor (10) calculates the achievement rate and the performance rate at the offset after the relaxation command.

[0087] Commands according to various embodiments of the present invention may include the following configuration for interval definition.

[0088] t_mi: time of message interval (waiting time until the next message, contraction command message if onset does not exist within the interval after contraction command, relaxation command message if onset exists within the interval after contraction command, relaxation command message if offset does not exist within the interval after relaxation command)

[0089] Commands according to various embodiments of the present invention may include configuration for interval definition.

[0090] T_nci: time of next contract interval (waiting time until the next contraction message when an offset occurs after a relaxation command)

[0091] Commands according to various embodiments of the present invention may include configuration for interval definition.

[0092] T_ooi: time of on / offset interval (minimum interval for determining onset / offset)

[0093] According to the invention as described above, the following effects are achieved.

[0094] First, it enables accurate monitoring of the exercise status of rehabilitation patients who have difficulty in muscle contraction and relaxation.

[0095] In addition, according to the present invention, subjective judgment can be excluded, and it is possible to accurately determine how long, how strongly, and what type of exercise a patient should perform in rehabilitation exercise, thereby prescribing quantified exercise.

[0096] Additionally, as the patient's achievement and performance rate are fed back to the medical staff in real time, the prescription can be changed and the current condition can be reflected to provide effective rehabilitation exercise.

[0097] Additionally, the patient's burden is reduced as the rehabilitation exercise status can be monitored remotely via the Internet.

[0098] Additionally, raw data from fusion signals can be used as metrics for machine learning to evaluate and predict the quality of exercise.

[0099] Although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and various modifications can be made by a person skilled in the art to which the invention pertains without departing from the gist of the present invention as claimed in the claims. Furthermore, such modifications should not be understood individually from the technical idea or prospect of the present invention.

Claims

1. In a device for monitoring rehabilitation exercise, At least one sensor attached to the patient's body to measure muscle movement status; At least one processor that receives an electrical signal from the sensor and determines the patient's movement status; and Includes a memory that stores instructions processed by the processor, The above command is, A device comprising threshold information for distinguishing between muscle contraction, muscle relaxation and muscle stiffness of the patient.

2. In paragraph 1, The above command is, A device configured such that if a signal received by the sensor is greater than a minimum threshold value, the processor determines that movement has begun.

3. In paragraph 1, The above processor, A device that analyzes the patient's muscle information obtained through the above sensor and determines that the patient is performing isometric exercise if it determines that tension is generated in the muscle but the muscle length does not change.

4. In paragraph 1, The above processor, A device that analyzes the patient's muscle information obtained through the above sensor and determines that the patient is undergoing isotonic exercise if it determines that tension is generated in the muscle and that the muscle length has changed at the same time.

5. In paragraph 1, The above processor, A device that analyzes muscle information obtained through the above sensor and determines the patient's condition as one of exercise initiation, isotonic exercise, or isometric exercise when muscle contraction occurs.

6. In paragraph 1, The above processor, A device that analyzes muscle information obtained through the above sensor and determines the patient's condition as one of the following: end of isometric exercise, end of isometric exercise, or end of exercise when muscle relaxation occurs.

7. In paragraph 1, The above processor, A device that analyzes muscle information obtained through the above sensor and determines that tension occurs in the muscle but the muscle length does not change, thereby determining it as isometric exercise, and if the isometric exercise state exceeds a set period of time, it determines it as muscle stiffness.

8. In paragraph 1, The above processor, A device that analyzes muscle information obtained through the above sensor and generates a command to transmit an alarm sound to a patient or guardian when a state in which tension is generated in the muscle but the muscle length does not change exceeds a set period of time.

9. In paragraph 1, The above command is, A device configured such that if a signal received by the sensor is greater than or equal to a minimum threshold value and remains above the minimum threshold value for a predetermined period of time, the processor determines that there is muscle stiffness.

10. In paragraph 1, The above command is, A device configured such that if a signal received by the sensor is greater than or equal to a maximum threshold value and remains greater than or equal to the minimum threshold value for a predetermined period of time, the processor determines that there is muscle stiffness.

11. In paragraph 1, The above command is, A device configured such that if a signal received by the sensor is below a minimum threshold value, the processor determines that the movement has failed.

12. In paragraph 1, The above command is, A device configured such that when the maximum value of the signal received by the sensor exceeds a maximum threshold value, the processor determines that the movement is completed.

13. In paragraph 1, The above command is, A device configured such that if the maximum value of the signal received by the sensor is less than or equal to a maximum threshold value, the processor determines that the exercise has failed to complete.

14. In a device for monitoring rehabilitation exercise, At least one sensor attached to the patient's body to measure muscle movement status; At least one processor that receives an electrical signal from the sensor and determines the patient's movement status; and Includes a memory that stores instructions processed by the processor, The above command is, A device configured such that if a signal received by the sensor vibrates up and down based on the threshold value and the period of the up and down vibration area is within a set value, the processor determines that it is a muscle tremor.

15. A method for monitoring rehabilitation exercise utilizing a device including at least one sensor, a processor and a memory, A step of receiving at least two of the following: number of contraction command generation times, number of movement initiation times, number of movement initiation failures, number of movement completion times, number of movement completion failures, number of relaxation command generation times, number of muscle stiffening times, and number of muscle contractions; A step of accumulating and storing the number of times received; and A method including a step of readjusting the minimum threshold value and the maximum threshold value, which are criteria for determining whether the exercise has been started, whether the exercise has been completed, whether the muscle has been stiffened, and whether the muscle has been contracted, based on the accumulated count result.

Images