KR101125672B1 - Method for measuring exercise pattern and apparatus for measuring exercise quantity using the method - Google Patents

Abstract

An exercise pattern analysis method and an exercise amount calculating device using the same are provided.
A method of analyzing a motion pattern according to an embodiment includes determining a motion pattern using a vector magnitude calculation step of calculating a vector magnitude of three-axis acceleration, a standard deviation calculation step of obtaining a standard deviation of the calculated vector sizes, and a standard deviation. The exercise pattern determination step is included.
Therefore, the present invention can monitor the physical activity according to the motion of a person in real time to analyze the exercise pattern and calculate the amount of exercise using the analyzed exercise pattern.

Description

Method for measuring exercise pattern and apparatus for measuring exercise quantity using the method

The present invention relates to an exercise pattern analysis method and an exercise amount calculating device using the same, and more specifically, an exercise pattern analysis by analyzing physical activity according to a human motion in real time and calculating an exercise amount using the analyzed exercise pattern. It relates to a pattern analysis method and a momentum calculation device using the same.

As the industrial development and the aging age have recently come, the number of the elderly and the disabled living alone is increasing, and it is difficult to take care of the elderly, the disabled or the patients alone for 24 hours.

Therefore, there is a need for a device that monitors physical activity in real time to enable rapid emergency treatment in case of emergency by monitoring their operation 24 hours without having to care for them 24 hours.

In addition, there is a need for a device that monitors physical activity that can be supervised by a central computer in real time without attaching it to a general public who is exercising in a fitness center or the like, without directly observing the exercise prescriber.

Conventionally, an expensive three-dimensional motion analyzer has been developed to analyze the amount of exercise according to a movement pattern, but this is limited to space-time constraints such as being available only in a laboratory and inconvenient to carry.

In addition, the development of a smart phone equipped with a pedometer improved the convenience of carrying, but it was possible to analyze only the fragmentary exercise patterns such as walking and running, there was a limit to measure more precise exercise amount.

An object of the present invention is to provide an exercise pattern analysis method for analyzing an exercise pattern represented by a human motion through standard deviations of human motion sizes.

Another object of the present invention is to provide an exercise amount calculating device for calculating an exercise amount using the analyzed exercise pattern.

The object of the present invention is not limited to the above-mentioned object, and other objects not mentioned will be clearly understood by those skilled in the art from the following description.

In accordance with an aspect of the present invention for achieving the above object, the momentum calculation device, the acceleration sensor unit for detecting the acceleration generated by the movement of the subject, the acceleration sensor unit for calculating the magnitude of the detected acceleration, The standard deviation of the magnitudes is calculated, and includes a signal analyzer for determining a movement pattern of the subject based on the calculated standard deviation, and an exercise amount calculation unit for calculating an exercise amount with reference to the exercise pattern determined by the signal analyzer.

On the other hand, the signal analyzer calculates the magnitude of the plurality of accelerations stored in the first array, the memory module including a first array in which the acceleration is divided into a plurality of units stored in the second array included in the memory module The module may include a standard deviation calculation module for calculating a standard deviation of the magnitudes of the plurality of accelerations stored in the second array, and a motion pattern determination module for analyzing the motion pattern based on the standard deviation.

The signal analyzer may further include a threshold generation module configured to sense a change in the exercise pattern analyzed by the exercise pattern determination module, generate a threshold including a change point of the exercise pattern and information of the exercise pattern, and store the threshold in the memory module. have.

Meanwhile, when the memory module receives the threshold from the threshold generation module, the memory module may delete the acceleration and the magnitude of the acceleration stored in the first array and the second array.

The exercise pattern may include at least one of a static exercise pattern and a dynamic exercise pattern.

In addition, the static exercise pattern may include at least one of lying down, sitting, and standing, and the dynamic exercise pattern may be at least one of walking, climbing, stepping down, fast walking, running, and skipping.

In addition, the acceleration may be characterized in that it is detected periodically.

According to another aspect of the present invention, a method of analyzing a motion pattern includes a motion pattern using a three-axis acceleration sensor that detects a three-axis motion signal composed of acceleration in the X-axis direction, acceleration in the Y-axis direction, and acceleration in the Z-axis direction. How to analyze it.

The motion pattern analysis method includes the steps of: the acceleration detected by the movement of the subject is divided into a plurality of units and stored in the form of a first array; the magnitude of the acceleration stored in the first array is calculated to calculate a vector size stored in the second array; And a storage step, a standard deviation calculation step of calculating a standard deviation of the magnitudes of the accelerations stored in the second array, and a movement pattern determination step of determining a motion pattern using the calculated standard deviation.

The method may further include a step of sensing a change in the exercise pattern determined in the exercise pattern determination step, and generating a threshold point including a change point of the exercise pattern and information on the exercise pattern, and storing the threshold point.

The exercise pattern may include at least one of a static exercise pattern and a dynamic exercise pattern.

In addition, the static exercise pattern may include at least one of lying down, sitting, and standing, and the dynamic exercise pattern may be characterized in that at least one of walking, climbing stairs, descending stairs, fast walking, jumping and skipping.

Also. Acceleration may be characterized in that it is detected periodically.

According to the present invention, it is possible to analyze the movement pattern represented by the movement of the person through the standard deviation of the movement size of the person, it is possible to accurately analyze the movement pattern. In addition, according to the present invention, it is possible to further distinguish the exercise pattern, such as lying down, sitting, standing, walking, climbing the stairs, going down the stairs, fast walking, running and jumping rope.

In addition, it is possible to calculate the exercise amount by using the exercise pattern analyzed by the above analysis method, it is possible to calculate the exercise amount more accurately.

In addition, after attaching the present inventors exercise amount calculating device to the elderly, disabled people or patients living alone can be connected to the server to enable rapid emergency measures in an emergency.

In addition, by attaching the exercise amount calculating device of the present inventor to a general person exercising in a fitness center, etc., the exercise prescriber can directly monitor and manage from a central computer.

1 is a schematic block diagram of an exercise amount calculating device according to an embodiment of the present invention.
FIG. 2 is a schematic block diagram of the signal analyzer shown in FIG. 1.
Figure 3 is a flow chart of the exercise pattern analysis method according to another embodiment of the present invention.
FIG. 4 is a flowchart illustrating a movement pattern classification step shown in FIG. 3.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various forms, and only the present embodiments are intended to complete the disclosure of the present invention, and the general knowledge in the art to which the present invention pertains. It is provided to fully convey the scope of the invention to those skilled in the art, and the present invention is defined only by the scope of the claims.

1 is a schematic block diagram of an exercise amount calculating device according to an embodiment of the present invention.

The exercise amount calculating apparatus 100 according to the present exemplary embodiment includes a three-axis acceleration sensor unit 110, a signal amplifier 120, a filtering unit 130, a signal analyzer 140, and an exercise amount calculating unit 150. .

The three-axis acceleration sensor unit 110 is mounted on the subject to measure and output the acceleration of the X, Y, Z axis. The three-axis acceleration sensor unit 110 separately measures the three-dimensional acceleration of the X, Y, and Z axes. That is, the three-axis acceleration sensor unit 110 can be said to detect the three-axis acceleration consisting of the acceleration in the X-axis direction, the acceleration in the Y-axis direction and the acceleration in the Z-axis direction.

In addition, the three-axis acceleration can be detected periodically every 0.1 seconds, the detection period may be implemented in a period other than 0.1 seconds.

The signal amplifier 120 amplifies the three-axis acceleration that is the output of the three-axis acceleration sensor unit 110 and transmits it to the filtering unit 130.

The filtering unit 130 removes unnecessary noise components from the amplified three-axis acceleration received from the signal amplifier 120. The filtering unit 130 may use a low pass filter that removes unnecessary high frequency noise components in order to express the characteristics of the acceleration signal of the subject of the momentum calculator 100.

The signal analyzer 140 analyzes the motion pattern from the 3-axis acceleration from which the noise component is removed from the filter 130. In detail, the signal analyzer 140 may determine whether the motion pattern performed by the subject from the 3-axis acceleration is a static motion pattern or a dynamic motion pattern.

In addition, the signal analysis unit 140 1) if the static movement pattern can determine which movement pattern of lying down, sitting and standing, and 2) if the dynamic movement pattern walking, climbing stairs, descending stairs, fast walking, It is possible to determine which exercise pattern is skipping and skipping.

In addition, the signal analyzer 140 may display the determined exercise pattern on a monitor screen.

Hereinafter, the process of the signal analysis unit 140 to determine the movement pattern will be described in detail with reference to FIG. 2 is a detailed block diagram of the signal analyzer 140 shown in FIG. 1.

As shown in FIG. 2, the signal analyzer 140 may include a memory module 141, a vector size calculation module 142, a standard deviation calculation module 143, a motion pattern determination module 144, and a threshold point generation module 145. ).

The memory module 141 stores the periodically measured three-axis acceleration in the form of an array. Although the measurement period of the three-axis acceleration may be 0.1 second, it can be realized that other periods other than 0.1 seconds.

In addition, the measured three-axis acceleration may be divided and stored in units of a specific number. The specific number may vary according to the memory capacity of the memory module 141.

According to an exemplary embodiment, the memory module 141 divides and stores the three-axis acceleration measured by a measurement period of 0.1 second into ten units. That is, the 'three' three-axis acceleration is stored in chronological order.

For example, if the time at which the 3-axis acceleration starts to be measured is 9 o'clock and measured at the interval of 0.1 second, the 10-axis acceleration measured from 9 o'clock to 9 o'clock, which is 1 second after 9 o'clock, is measured. Store in That is, the three-axis acceleration is divided into units of one second until the time to complete the measurement to store the three-axis acceleration.

The memory module 141 may be implemented as a cache memory. That is, when the movement pattern is determined from the three-axis acceleration stored in the array form divided by units, the three-axis acceleration from which the movement pattern is determined is deleted, and the new three-axis acceleration is stored in the array in which the three-axis acceleration was stored.

The vector size calculation module 142 calculates the vector size of the three-axis acceleration stored in an array form by dividing the memory module 141 into a specific number of units. The calculation of the vector size is to calculate the square root for each of the three-axis accelerations and square them. This is represented by the following equation (1).

In Equation 1, X represents acceleration in the X-axis direction, Y represents acceleration in the Y-axis direction, and Z represents acceleration in the Z-axis direction.

The vector size calculation module 142 transmits the calculated vector size to the memory module 141, and the memory module 141 has a three-axis acceleration corresponding to the vector size received from the vector size calculation module 142. Save with. That is, the vector size is also stored in the form of an array in a specific number of units similar to the three-axis acceleration.

For example, the vector magnitude of the 3-axis acceleration measured at 9 o'clock is stored together in an array in which the 3-axis acceleration is stored. That is, the vector size is calculated from the ten three-axis accelerations measured at 0.1 second intervals from 9 o'clock to 9 o'clock 1 second when the three-axis acceleration starts to be measured. The calculated vector size is transmitted to the memory module 141 again and divided into 10 pieces together with the 3-axis acceleration corresponding to the vector size and stored in an array form.

The standard deviation calculation module 143 calculates the standard deviation of the vector sizes stored in the array form by dividing the memory module 141 into a certain number of units. The standard deviation is calculated using a formula for obtaining a standard deviation, as shown in Equation 2 below.

는 메모리 모듈(141)에 특정 갯수의 단위로 나누어 저장된 벡터크기들에 해당하고, m은 특정 갯수의 단위로 나누어 저장된 벡터크기들의 평균을 나타낸다. 또한, n은 상기 특정 갯수에 해당한다. 상술한 바와 같이 일 실시예에 따라 n은 10이지만, 메모리 모듈(141)의 메모리 용량에 따라 n값은 변화할 수 있다.In Equation 2,

Denotes the vector sizes stored in the memory module 141 in units of a specific number, and m denotes an average of the vector sizes stored in units of a specific number. In addition, n corresponds to the specific number. As described above, n is 10 according to an embodiment, but n may vary according to the memory capacity of the memory module 141.

For example, the standard deviation is calculated at intervals of one second by calculating the standard deviation from the calculated ten vector sizes from 9:00 to 9: 1.

The exercise pattern determination module 144 determines the exercise pattern of the subject based on the standard deviation calculated by the standard deviation calculation module 143. Hereinafter, the method of determining the exercise pattern according to the standard deviation calculated by the exercise pattern determination module 144 will be described in detail.

1) If the standard deviation is less than '2.0', the exercise pattern determination module 144 determines the exercise pattern of the subject as "lie down, sit",

2) If the standard deviation is more than '2.0' and less than '2.5', the exercise pattern determination module 144 determines the exercise pattern of the subject as "standing",

3) If the standard deviation is greater than '2.5' and less than '35', the exercise pattern determination module 144 determines the exercise pattern of the subject as "walking, going down stairs",

4) If the standard deviation is greater than or equal to '35' and less than '80', the exercise pattern determination module 144 judges the exercise pattern of the subject as "climbing up, walking fast",

5) If the standard deviation is '80' or more, the exercise pattern determination module 144 determines the exercise pattern of the subject as "skip, skipping."

Here, the values of '2.0', '2.5', '35' and '80' correspond to the values obtained in the repetitive experiment, and it is natural that these values can be replaced with other values.

For example, if the standard deviation obtained based on the vector sizes stored in the memory module 141 based on a certain number of units falls between '35' and '80', the motion at that time is "climbing" or "fast walking". To judge.

The threshold point generation module 145 generates a threshold point by sensing whether the exercise pattern changes based on the exercise pattern determined by the exercise pattern determination module 144. The critical point is a point in time at which the movement pattern changes. Therefore, when a threshold including the movement pattern change time and the information of the movement pattern at that time is generated, the threshold is transmitted to and stored in the memory module 141. That is, by sensing whether the movement pattern determined from the standard deviation of the vector size calculated at a specific unit time interval is changed, the time at the time of change and the movement pattern at that time are stored, and the amount of exercise is calculated using the movement pattern.

For example, it is assumed that the subject performs a 'walking' from 9:00 to 9:10 and 'walks quickly' from 9:10.

According to an exemplary embodiment, the memory module 141 divides three-axis accelerations from 9 o'clock to 9:10 into 10 units and stores them in an array. The 3-axis acceleration can be measured at a period of 0.1 second, so the 3-axis acceleration of 1 second is stored in the array. The vector size calculation module 142 calculates the vector size of the three-axis acceleration stored in each unit in the memory module 141. The standard deviation calculation module 143 calculates the standard deviation from the stored vector size divided into ten units.

The exercise pattern determination module 144 determines an exercise pattern based on the calculated standard deviation, and the threshold point generation module 145 senses a change in the exercise pattern at 9:10 as the time when there is a change in the exercise pattern. will be. Therefore, the threshold generation module 145 generates a threshold including the information that the exercise of 'walking' is performed from 9 to 9:10 and starts to 'walk quickly' from 9:10 and the memory module 141 is generated. Will be sent.

When the threshold point generated by the threshold point generation module 145 is stored in the memory module 141, all of the three-axis acceleration and the vector size stored in the memory module 141 are deleted, and the newly measured three-axis acceleration is stored based on this. Repeat the same process to calculate the information of the exercise pattern.

The exercise amount calculating unit 150 calculates and stores the exercise amount for the exercise pattern determined by the signal analyzer 140 as a calorie.

The exercise amount calculating unit 150 calculates the amount of exercise using METs (Metabolic Equinalents) scores stored in the exercise database, the weight of the subject and the exercise time. The momentum calculation operation is as shown in Equation 3 below.

METs is the intensity index of physical activity according to the exercise pattern, W is the weight of the subject (in kg), and T is the exercise time of the subject.

The METs Index is a standardized index designed to make calorie consumption according to physical activity readily available on site and to allow comparisons between studies related to physical activity. 1 METs are equal to resting metabolic rate, and the higher the intensity of physical activity according to exercise pattern, the higher the METs index.

The METs index is stored in the momentum database in table form along with the exercise pattern. Exercise patterns may include lying, sitting, standing, walking, climbing stairs, descending stairs, walking fast, jumping, and skipping rope.

T is an exercise time value converted in hours. T is equal to a value obtained by converting the movement pattern change time sensed by the threshold generation module 145 into units of time. For example, if the time at which the exercise pattern is changed from 9 o'clock to 9 o'clock is sensed as 9:10, T is calculated as 1/6.

Hereinafter, the calculation of the exercise amount using Equation 3 will be described by way of example.

If an 80 kg subject has "walked" for 20 minutes, the exercise amount of the subject is calculated as 88 Kcal by 3.3 METs * 80 kg * (20 minutes / 60 minutes).

3 is a flowchart of a method of analyzing a motion pattern according to another embodiment of the present invention, and FIG. 4 is a flowchart of a motion pattern determination step shown in FIG. 3.

The method for analyzing a motion pattern includes storing a three-axis acceleration including an acceleration in the X-axis direction, an acceleration in the Y-axis direction, and an acceleration in the Z-axis direction (S100), and calculating and storing the vector magnitude of the three-axis acceleration. (S200), the standard deviation calculation step of obtaining the standard deviation of the calculated vector sizes (S300) and the step of determining the exercise pattern using the standard deviation (S400), the step of determining whether there is a change in the exercise pattern (S500) and the exercise If there is a change in the pattern, a step of generating a threshold point and storing it is included.

Storing the three-axis acceleration (S100) is in the process of the three-axis acceleration sensor unit 110 provided in the momentum calculation device 100 mounted on the subject to convert the acceleration of the X, Y, Z axis into an electrical signal to output Is performed by. Naturally, the 3-axis acceleration can be measured repeatedly every 0.1 seconds and can be measured at intervals other than 0.1 seconds.

In addition, the periodically measured three-axis acceleration is divided into a specific number of units and stored in an array form. According to an embodiment, the measured three-axis acceleration is configured in a unit of 10 each and stored for each unit. Therefore, since the three-axis acceleration was measured at a period of 0.1 second, the three-axis acceleration for one second is stored in an array form. The unit of '10' may vary according to memory capacity, and storing the 3-axis acceleration in the variable unit is also included in the scope of the present invention.

In the calculating and storing of the vector size (S200), the vector size is calculated from the three-axis acceleration stored in an array form by dividing the unit into a specific number, and the calculated vector size is stored in an array form with the corresponding three-axis acceleration. Step.

The standard deviation calculating step (S300) is a step of calculating standard deviation from vector sizes stored in an array form by dividing the data into a specific number of units.

Exercise pattern determination step (S400) determines the movement pattern of lying, sitting, standing, walking, going down stairs, climbing stairs, fast walking, running and skipping based on the standard deviation calculated in the standard deviation calculation step (S300). . That is, since the standard deviation calculated from the vector sizes stored in the specific unit corresponds to the standard deviation of the three-axis acceleration vector size for a specific time, the motion pattern determination step (S400) determines what the motion pattern is during the specific time. Judging.

If the standard deviation calculated in the standard deviation calculation step S300 is less than 2 (S410), the current operation is determined to be "lie down, sit". Here, '2' used as a standard deviation reference value is obtained from a repeated experiment.

In the standing division step (S440), if the standard deviation calculated in the standard deviation calculation step (S300) is greater than '2' (S410) and less than '2.5' (S430), the current operation is determined as "standing". Here, '2' and '2.5' used as standard deviation reference values are obtained from repeated experiments.

If the standard deviation calculated in the standard deviation calculation step (S300) is greater than '2.5' (S430) and less than '35' (S450), the current operation is "walking, descending stairs". Go ". The '2.5' and '35' used as standard deviation reference values are obtained from repeated experiments.

Ascending stairs, walking fast (S480) is the standard deviation calculated in the standard deviation calculation step (S300) is greater than '35' (S450) and less than '80' (S470), the current operation is "step climbing, fast Walk ". Here, '35' and '80' used as standard deviation reference values are obtained from repeated experiments.

If the standard deviation calculated in the standard deviation calculation step S300 is greater than '80' (S470), the current operation is determined to be "skip, skipping rope". Here, '80' used as a standard deviation reference value is obtained from a repeated experiment.

Determining whether the exercise pattern changes (S500) is a step of determining whether there is a change in the exercise pattern determined in the exercise pattern determination step (S400).

If there is a change in the exercise pattern, and generates a critical point including the time and information of the exercise pattern at the time when the change in the exercise pattern (S600). For example, if the exercise of 'walking' is performed from 9:00 to 9:10, the time of 9:00 and 9:10 and the movement pattern at that time are stored together.

The exercise amount calculating device 100 described so far may be used to be attached to an elderly person, a disabled person or a patient, and in this case, the exercise amount calculating device 100 transmits information on the amount of exercise to the management server, and the emergency management server may emergency. You can ask the relief agency for first aid.

In addition, the exercise amount calculating apparatus 100 may be attached to and used by a general person exercising in a fitness center. In this case, the exercise amount calculating apparatus 100 transmits information on the amount of exercise to a central computer so that the exercise prescriber does not directly observe the center. Management supervision can be made from a computer.

On the other hand, it is also possible to implement a separate exercise pattern analysis apparatus by separating only the signal analysis unit 140 constituting the exercise amount calculating apparatus 100, the case of the exercise pattern analysis apparatus implemented as described above is also within the protection scope of the present invention. Of course it is included.

In the above embodiment, it is assumed that the movement pattern of the subject is determined based on the magnitude of the calculated standard deviation, which is merely an example for convenience of description. In determining the movement pattern, it is of course possible not only to consider the magnitude of the standard deviation, but also to refer to other elements of the standard deviation. For example, it is of course possible to determine the movement pattern based on other factors such as the rate of change of the standard deviation or the pattern.

In addition, it is also possible to calculate the exercise amount by referring to the exercise pattern in another manner without using Equation 3 presented in the embodiment as calculating the exercise amount with reference to the exercise pattern.

Those skilled in the art will appreciate that the present invention can be embodied in other specific forms without changing the technical spirit or essential features thereof. For example, a program for realizing a signal analysis method for classifying a motion pattern of the present invention may be implemented in various forms such as a form of a recording medium in which a program is recorded. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. The scope of the present invention is indicated by the scope of the following claims rather than the above description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents are included in the scope of the present invention. Should be interpreted.

100: momentum output device
110: 3-axis acceleration sensor
120: signal amplifier
130: filtering unit
140: signal analysis unit
150: momentum calculation unit

Claims (12)

An acceleration sensor unit mounted on the subject to detect an acceleration generated by the movement of the subject;
A signal analyzer for calculating the magnitude of the detected acceleration, calculating the standard deviation of the calculated magnitudes, and determining a movement pattern of the subject based on the calculated standard deviation; And
And an exercise amount calculating unit calculating an exercise amount by referring to the exercise pattern determined by the signal analyzing unit.
The signal analysis unit,
A memory module including a first array in which the acceleration is divided into a plurality of units and stored;
A vector size calculation module for calculating magnitudes of the plurality of accelerations stored in the first array and storing the magnitudes of the accelerations in a second array included in the memory module;
A standard deviation calculation module for calculating a standard deviation of the magnitudes of the plurality of accelerations stored in the second array; And
And an exercise pattern determination module analyzing the exercise pattern based on the standard deviation.
delete The method according to claim 1,
The signal analysis unit
And a threshold point generation module configured to sense a change in the exercise pattern analyzed by the exercise pattern determination module, to generate a threshold point including a change point of the exercise pattern and information of the exercise pattern, and to store the threshold point in a memory module. .
The method according to claim 3,
The memory module
Receiving a threshold point from the threshold generation module, the momentum calculation apparatus, characterized in that for removing the acceleration and the magnitude of the acceleration stored in the first array and the second array.
The method according to claim 1,
The exercise pattern is
An exercise amount calculating apparatus comprising at least one of a static exercise pattern and a dynamic exercise pattern.
The method according to claim 5,
The static movement pattern is
At least one of lying down, sitting and standing,
The dynamic movement pattern
An exercise amount calculating device, characterized in that at least one of walking, climbing stairs, descending stairs, fast walking, running and skipping.
The method according to claim 1,
The momentum calculation device, characterized in that the acceleration is detected periodically.
Storing acceleration in the form of a first array divided into a plurality of units, the acceleration detected by the movement of the subject;
Calculating and storing a vector size in which the magnitude of the acceleration stored in the first array is calculated and stored in the second array;
A standard deviation calculation step of calculating a standard deviation of the magnitudes of the accelerations stored in the second array; And
And a motion pattern determination step of determining a motion pattern using the calculated standard deviation.
The method according to claim 8,
And detecting a change in the exercise pattern determined in the exercise pattern determination step, generating a threshold point including a change point of the exercise pattern and information on the exercise pattern, and storing the threshold point.
The method according to claim 8,
The exercise pattern is
An exercise pattern analysis method comprising at least one of a static exercise pattern and a dynamic exercise pattern.
The method according to claim 10,
The static movement pattern is
At least one of lying down, sitting and standing,
The dynamic movement pattern
Exercise pattern analysis method, characterized in that at least one of walking, climbing stairs, going down stairs, fast walking, running and skipping.
The method according to claim 8,
The acceleration is
Movement pattern analysis method characterized in that it is detected periodically.

Images