KR102279799B1 - Bio-impedance Based Real Time Body Weight Estimation Method, Apparatus and Computer-readable Medium - Google Patents

Abstract

The present invention relates to a bioimpedance-based real-time weight prediction method, apparatus, and computer readable medium, and more particularly, to derive a change in body composition through continuous bioimpedance measurement of a user's body, and to determine weight based on the change in body composition. The present invention relates to a bioimpedance-based real-time weight prediction method, apparatus, and computer-readable medium capable of predicting a user's weight without measurement by a scale by predicting a change.

Description

Bio-impedance Based Real Time Body Weight Estimation Method, Apparatus and Computer-readable Medium

The present invention relates to a bioimpedance-based real-time weight prediction method, apparatus, and computer readable medium, and more particularly, to derive a change in body composition through continuous bioimpedance measurement of a user's body, and to determine weight based on the change in body composition. The present invention relates to a bioimpedance-based real-time weight prediction method, apparatus, and computer-readable medium capable of predicting a user's weight without measurement by a scale by predicting a change.

Worldwide, the number of obese people is increasing due to unhealthy eating habits and lack of exercise. Numerous studies have shown that obesity can cause various chronic diseases, such as atherosclerosis and heart failure, as well as diseases related to the brain. The cost of products and services related to weight loss or medical expenses due to obesity-related diseases is more than 30 trillion dollars per year.

Accordingly, many companies such as Fitbit, Garmin, Jawbone, Nike, Samsung, Microsoft, LG, Apple, etc. are using the smart band/watch’s built-in sensor-based step counter, mileage tracker, altimeter, etc. It has launched a variety of health care devices that provide functionalities. In such a health management device, food intake from a diary through manual input, monitoring of vital signs using physiological sensors, and various other functions to support a healthier lifestyle are provided, and the market for such devices has rapidly increased. . However, most devices focus on monitoring body activity rather than weight changes, eating habits and other daily habits related to weight gain and weight loss.

Many fitness center obesity management programs require users to regularly record their daily food intake patterns, weight changes, and types of exercise. The main device used to check weight trends is a scale, which helps to track the absolute change in weight over time. However, keeping track of your weight can be daunting, and you often forget that you need to measure your weight on a regular basis.

As described above, various methods have been proposed to predict body weight without directly measuring the weight with a scale. Methods for estimating weight by estimating dimensions such as height and waist circumference of a subject by receiving image information, or algorithms for estimating weight by directly inputting numerical values such as waist circumference and thigh circumference have been proposed, but depending on the location of the shooting, etc. It can be difficult to estimate the dimensions, and when using a linear statistical method from a large database obtained from the population to predict body weight, errors due to individual differences appear large.

As another method, a method of calculating weight change by deriving energy intake and consumption from meals and physical activity has been proposed, but it is difficult to accurately analyze energy intake from food or energy consumption due to physical activity because it varies greatly between individuals. There are disadvantages.

delete

Korean Patent Laid-Open Patent No. 10-2019-0119916 (Apparatus and method for predicting body shape change, published on October 23, 2019)

The present invention derives a change in body composition through continuous bioimpedance measurement of a user's body, and predicts a change in body weight based on the change in body composition, thereby predicting a user's weight without measurement by a scale. Real-time weight prediction based on bioimpedance An object of the present invention is to provide a method, an apparatus and a computer readable medium.

In order to solve the above problems, the present invention provides a bioimpedance-based real-time weight prediction method, comprising: an initial information input step of inputting initial information about a user's body; a bioimpedance measuring step of measuring the bioimpedance of the user's body by applying an electric current to the user's body; a body composition information deriving step of deriving measured body composition information from the user's bioimpedance; correlation between body composition information and body weight; the initial information; and the measured body composition information; a weight prediction step of deriving predicted weight information based on It provides a bioimpedance-based real-time weight prediction method comprising a.

In the present invention, the initial information, the user's profile information; the measured initial body composition information of the user; and the measured initial weight information of the user; may include.

In the present invention, the weight prediction step includes: a body composition change deriving step of deriving a body composition change from the initial body composition information and the measured body composition information; a weight change deriving step of deriving a weight change based on the correlation between the body composition information and the body weight and the body composition change; and a predicted weight deriving step of deriving predicted weight information from the initial weight information and the weight change. may include.

In the present invention, the body composition information includes body fat (Fat Mass, FM); Fat-Free Mass (FFM); Soft Lean Mass (SLM); and total body water (TBW); and one or more of the following, and the correlation between the body composition information and the body weight may include a correlation between one or more items of the body composition information and body fat.

In the present invention, the correlation between the body composition information and body weight is

may include a relational expression of

In the present invention, the bioimpedance measurement step, the body composition information deriving step, and the weight prediction step may be repeatedly performed according to a preset time period.

In the present invention, the bioimpedance-based real-time weight prediction method includes: a measured weight input step of measuring a user's weight and inputting measured weight information; and a correlation updating step of revising and updating the correlation based on the measured weight information and the predicted weight information. may further include.

In the present invention, the bioimpedance-based real-time weight prediction method includes: a weight input notification step of displaying a notification to the user to measure the weight when the measured weight input step is not performed for a preset time; may further include.

In the present invention, the correlation updating step includes: a parameter correction step of modifying the correlation parameters based on the measured weight information and the predicted weight information; and an initial information updating step of updating the initial information based on the measured weight information; may include.

In order to solve the above problems, the present invention provides a bioimpedance-based real-time weight prediction device, comprising: an initial information input unit for inputting initial information about a user's body; a bioimpedance measuring unit measuring the bioimpedance of the user's body by applying an electric current to the user's body; a body composition information derivation unit for deriving measured body composition information from the user's bioimpedance; correlation between body composition information and body weight; the initial information; and the measured body composition information; a weight prediction unit for deriving predicted weight information based on It provides a bioimpedance-based real-time weight prediction device comprising a.

In order to solve the above problems, the present invention provides a bioimpedance-based real-time weight prediction method as a computer-readable medium, wherein the computer-readable medium includes instructions for causing a computing device to perform the following steps , and the steps include: an initial information input step of inputting initial information about the user's body; a bioimpedance measuring step of measuring the bioimpedance of the user's body by applying an electric current to the user's body; a body composition information deriving step of deriving measured body composition information from the user's bioimpedance; correlation between body composition information and body weight; the initial information; and the measured body composition information; a weight prediction step of deriving predicted weight information based on It provides a computer-readable medium comprising a.

According to an embodiment of the present invention, it is possible to exhibit the effect of predicting the current weight through bioimpedance measurement by a wearable device or the like without measuring the weight on the scale.

According to an embodiment of the present invention, it is possible to exhibit the effect of increasing the accuracy of the predicted weight by continuously inputting the measured weight.

According to an embodiment of the present invention, it is possible to increase the accuracy of the predicted weight by adjusting the parameters for predicting the weight according to the user.

According to an embodiment of the present invention, when the measured weight is not input, it is possible to display the effect of continuously receiving the measured weight by notifying the user.

1 is a diagram schematically illustrating a process of deriving body composition information based on bioimpedance according to an embodiment of the present invention.
2 is a flowchart schematically illustrating steps of a bioimpedance-based real-time weight prediction method according to an embodiment of the present invention.
3 is a diagram schematically illustrating body composition information according to an embodiment of the present invention.
4 is a diagram schematically illustrating a configuration of initial information according to an embodiment of the present invention.
5 is a diagram schematically illustrating detailed steps of the weight prediction step according to an embodiment of the present invention.
6 is a diagram schematically illustrating a process of a weight prediction step according to an embodiment of the present invention.
7 is a diagram schematically illustrating a process of a correlation update step according to an embodiment of the present invention.
8 is a flowchart schematically illustrating detailed steps of a correlation update step according to an embodiment.
9 is a diagram schematically illustrating a process of an initial information update step according to an embodiment of the present invention.
10 is a diagram schematically illustrating an internal configuration of an apparatus for predicting weight according to an embodiment of the present invention.
11 is a diagram illustrating an example of an internal configuration of a computing device according to an embodiment of the present invention.

Hereinafter, various embodiments and/or aspects are disclosed with reference to the drawings. In the following description, for purposes of explanation, numerous specific details are set forth to provide a thorough understanding of one or more aspects. However, it will also be recognized by one of ordinary skill in the art that such aspect(s) may be practiced without these specific details. The following description and accompanying drawings set forth in detail certain illustrative aspects of one or more aspects. These aspects are illustrative, however, and some of the various methods in principles of the various aspects may be employed, and the descriptions set forth are intended to include all such aspects and their equivalents.

Further, various aspects and features will be presented by a system that may include a number of devices, components and/or modules, and the like. It is also noted that various systems may include additional devices, components, and/or modules, etc. and/or may not include all of the devices, components, modules, etc. discussed with respect to the drawings. must be understood and recognized.

As used herein, “embodiment”, “example”, “aspect”, “exemplary”, etc. may not be construed as an advantage or advantage in any aspect or design described above over other aspects or designs. . The terms '~part', 'component', 'module', 'system', 'interface', etc. used below generally mean a computer-related entity, for example, hardware, hardware A combination of and software may mean software.

Also, the terms "comprises" and/or "comprising" mean that the feature and/or element is present, but excludes the presence or addition of one or more other features, elements and/or groups thereof. should be understood as not

Also, terms including an ordinal number, such as first, second, etc., may be used to describe various elements, but the elements are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

In addition, in the embodiments of the present invention, unless otherwise defined, all terms used herein, including technical or scientific terms, are generally understood by those of ordinary skill in the art to which the present invention belongs. have the same meaning as Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in an embodiment of the present invention, an ideal or excessively formal meaning is not interpreted as

1 is a diagram schematically illustrating a process of deriving body composition information based on bioimpedance according to an embodiment of the present invention.

In the present invention, the weight is predicted based on body composition information. The human body consists of water, fat, muscle, etc., and each component has a different resistivity value. Fat has a resistivity of 20-25 Ω·m, skeletal muscle has a specific resistance of 6-10 Ω·m, and blood has a specific resistance of 1.6-2 Ω·m.

Using this, it is possible to estimate the body composition by measuring the impedance that appears when a small amount of alternating current is applied to the human body. Water in the body can be measured with very high accuracy by such a measurement, but direct measurement is difficult because fat acts like an insulator with respect to alternating current.

1 shows a method of deriving body composition information by measuring bioimpedance in an embodiment of the present invention. In an embodiment of the present invention, an electrode or the like may be attached or contacted to a person's wrist or ankle to apply a current, and the impedance of the body may be measured through the voltage and current appearing. Such an operation may be performed through the bioimpedance measuring unit 200 . At this time, the measurement may be performed while changing the frequency of the applied current.

Thereafter, body composition information may be derived based on the measured bioimpedance information. For this, the user's profile information such as age, gender, and height may be further input. Such an operation may be performed through the body composition information derivation unit 300 .

2 is a flowchart schematically illustrating steps of a bioimpedance-based real-time weight prediction method according to an embodiment of the present invention.

Referring to FIG. 2 , a bioimpedance-based real-time weight prediction method according to an embodiment of the present invention includes an initial information input step of inputting initial information on the body of a user 10 ( S100 ); a bioimpedance measurement step (S200) of measuring the bioimpedance of the body of the user (10) by applying an electric current to the body of the user (10); a body composition information deriving step (S300) of deriving measured body composition information from the bioimpedance of the user (10); correlation between body composition information and body weight; the initial information; and the measured body composition information; a weight prediction step of deriving predicted weight information based on (S400); A measured weight input step of measuring the user's weight and inputting the measured weight information (S500); and a correlation updating step (S600) of correcting and updating the correlation based on the measured weight information and the predicted weight information; may include.

In the initial information input step ( S100 ), initial information about the user's body, which is basic information for estimating the weight, is received. The initial information may include information such as age or height that may indicate individual characteristics of the user, and weight and body composition information at a specific point in time for predicting the weight. In an embodiment of the present invention, a method of deriving a change in body composition based on the body composition information measured at the specific point in time and subsequently measured body composition information, and deriving a change in body weight based on the change in body composition, is currently weight can be predicted. In this case, the weight and body composition information of the initial information needs to be information measured at the same time point. In addition, the weight and body composition information includes information of the measured time, and when a change in body composition and a change in body weight are derived thereafter, a change amount may be derived based on the information of the time.

In the bioimpedance measurement step (S200), after the initial information input step (S200), the bioimpedance of the user 10 is measured at the time of estimating the weight. In the bioimpedance measuring step ( S200 ), the bioimpedance of the user 10 is measured through the bioimpedance measuring unit 200 as shown in FIG. 1 . In an embodiment of the present invention, the bioimpedance measuring unit 200 may be a component of a wearable device. In this embodiment, the weight of the user 10 can be predicted by measuring the bioimpedance just by the user 10 wearing the wearable device.

In the body composition information deriving step ( S300 ), the measured body composition information of the user 10 is derived based on the bioimpedance of the user 10 measured in the bioimpedance measuring step ( S200 ). In an embodiment of the present invention, the initial information may be used to derive the measured body composition information of the user 10 . In an embodiment of the present invention, the measured body composition information may include information on the amount of body composition constituting the body of the user 10 and date information on which the bioimpedance is measured. By including the measured date information as described above, it is possible to derive the body change according to the time of the user 10 and to allow the user 10 to easily manage the weight.

The weight prediction step (S400) may derive the predicted weight information by predicting the current weight based on the measured body composition information and the initial information derived in the body composition information deriving step (S300). In an embodiment of the present invention, a change in body composition is derived based on the measured body composition information and the initial information, a change in body weight is derived from a change in the body composition, and predicted weight information based on the change in body weight and the initial information. to derive In order to derive a change in body weight from the change in body composition, the correlation between body composition information and body weight may be used in the weight prediction step ( S400 ). In general, since body fat (FM) cannot be determined from bioimpedance, body weight cannot be directly determined from the bioimpedance, but in the present invention, body weight is predicted using the correlation between body composition information and body weight excluding the body fat (FM). .

In an embodiment of the present invention, the bioimpedance measuring step (S200), the body composition information deriving step (S300), and the weight prediction step (S400) may be repeatedly performed according to a preset time period. As described above, the weight information predicted by being repeatedly performed according to a preset time period is stored according to time, so that the user can check the change trend of the weight and easily manage the weight.

In addition, the bioimpedance measuring step (S200), the body composition information deriving step (S300), and the weight prediction step (S400) may be performed according to the preset time period and may also be performed by a user's input. As this is performed by the user's input, when the user wants to check the current predicted weight, the derived current predicted weight can be checked.

The measured weight input step ( S500 ) receives measured weight information including the actual weight value of the user 10 . In this measurement weight input step (S500), the user 10 may input the measured value after measuring the weight, or automatically measured in conjunction with a smart scale measuring the user's 10 weight. You can also input a value. In this way, by receiving the actual weight information of the user 10 in the measured weight input step (S500), an error in the predicted weight of the user 10 is derived, and based on this, the weight prediction of the user 10 is By updating the necessary information, it is possible to reduce the error of the predicted weight. The measured weight information may include information on the measured weight value of the user 10 and information on the date on which the weight was measured.

In the correlation updating step (S600), the correlation is corrected and updated based on the measured weight information received in the measured weight input step (S500). The measured weight information is the actual weight of the user 10 , and an error of the predicted weight information derived in the weight prediction step ( S400 ) may be derived using this. Based on the error information, the correlation between the body composition information and the body weight is corrected so that the correlation between the body composition information and the body weight can be more accurately predicted, and the error is reduced by updating the correlation.

In an embodiment of the present invention, in the correlation updating step (S600), the parameter of the correlation equation that minimizes the prediction error derived based on the measured weight information input in the measured weight input step (S500) is derived and updated. You can modify the correlation in this way.

In an embodiment of the present invention, when the measuring weight input step (S500) is not performed for a preset time, a weight input notification step (not shown) of displaying a notification to the user to measure the weight; may further include. In the weight prediction step ( S400 ) according to an embodiment of the present invention, a weight change is predicted based on the initial information. In the case of such a prediction, it may have high accuracy with respect to short-term changes, but in the case of long-term changes, the accuracy may be lowered due to accumulated errors, and if the user experiences a sudden weight change, the accuracy of the prediction may be lowered. It is necessary to input the measured weight and to be able to correct it. Therefore, in the weight prediction method of the present invention, when the measuring weight input step S500 is not performed for a preset time (for example, a month or a period in which the bioimpedance measuring step is repeated 200 times), the user can hear and see Alternatively, it is possible to increase the accuracy of prediction by notifying the user to perform the measurement weight input step S500 through tactile information or the like.

3 is a diagram schematically illustrating body composition information according to an embodiment of the present invention.

Referring to Figure 3, the weight is composed of lean mass (Fat-Free Mass, FFM) and body fat (Fat Mass, FM), and the lean mass (FFM) is muscle mass (Soft Lean Mass, SLM) and minerals ( Minerals), the muscle mass (SLM) is composed of total body water (TBW) and protein (Protein), and the body water amount (TBW) is intracellular water (Intra-Cellular Water, ICW) and cells It is composed of Extra-Cellular Water (ECW).

In an embodiment of the present invention, the body composition information derived based on bioimpedance may include: body fat (Fat Mass, FM); Fat-Free Mass (FFM); Soft Lean Mass (SLM); and total body water (TBW); It may include one or more of

In an embodiment of the present invention, in the body composition information deriving step ( S300 ), the lean body mass (FFM) of the user 10 may be derived by the following equation.

In the above formula, a, b, c, and d may vary depending on the bioimpedance measurement method (position of the electrode, applied current, frequency, etc.). As in the above formula, information such as age, gender, and height of the user 10 is required in order to derive the body composition of the user 10, so it is preferable that the age, gender, and height information of the user 10 are included in the initial information. .

In addition to lean body mass (FFM), body water mass (TBW) and muscle mass (SLM) can also be derived in a similar way.

4 is a diagram schematically illustrating a configuration of initial information according to an embodiment of the present invention.

Referring to FIG. 4 , in an embodiment of the present invention, the initial information 20 includes: profile information 21 of a user 10; the measured initial body composition information 22 of the user 10; and the measured initial weight information 22 of the user 10; may include.

The profile information 21 may include information such as age, gender and height of the user 10 . Such information may be used to derive body composition information of the user 10 from the measured bioimpedance information.

The initial weight information 22 is used as information for predicting the current weight. In an embodiment of the present invention, in the weight prediction step (S400), predicted weight information is derived based on the initial weight information 22 and weight change. In order to increase the accuracy of prediction, accurate weight information by measurement is required. It needs to be entered.

The initial body composition information 23 is used as information for predicting the current weight. In an embodiment of the present invention, in the weight prediction step (S400), the body composition change is derived based on the body composition information derived based on the initial body composition information 23 and the bioimpedance measured in the bioimpedance measurement step (S200). will do The initial body composition information 23 may be directly input by the user, or the user's body composition may be derived and input through the same process as in the bioimpedance measurement step S200 and the body composition information deriving step S300. .

Date information including the input date of the initial information 20 may be stored in the initial information 20 . Such date information may be stored in each of the initial weight information 22 or the initial body composition information 23 with the measurement date of the body weight or the measurement date of the body composition, or collectively for the entire initial information 20 . The date written as . Such date information is compared with the date information on which the bioimpedance measurement step (S200) is performed, and the measured body composition derived from the initial information 20 and the body composition information deriving step (S300) and the weight prediction step (S400). It is possible to grasp the temporal flow between the information and the predicted weight information, so that it can be used for weight prediction or the user can grasp the predicted weight according to the passage of time.

5 is a diagram schematically illustrating detailed steps of the weight prediction step according to an embodiment of the present invention.

Referring to FIG. 5 , the weight prediction step (S400) according to an embodiment of the present invention includes: a body composition change deriving step (S410) of deriving a body composition change from the initial body composition information and the measured body composition information; a weight change deriving step (S420) of deriving a weight change based on the correlation between the body composition information and the body weight and the body composition change; and a predicted weight deriving step (S430) of deriving predicted weight information from the initial weight information and the weight change. may include.

In the body composition change deriving step ( S410 ), the amount of change in the body composition information is derived by comparing the initial body composition information with the measured body composition information. In the body composition change deriving step (S410), the amount of change in the measured body composition information based on the initial body composition information included in the initial information input in the initial information input step (S100) and the bioimpedance measured in the bioimpedance measuring step (S200) By deriving it, it is possible to derive the difference in body composition between the time point of the initial information input step (S100) and the time point of the bioimpedance measurement step (S200).

The weight change deriving step (S420) derives a weight change from the body composition change. To this end, the correlation between body composition information and body weight is used in the weight change deriving step (S420). Since body fat (FM) cannot be directly derived from the bioimpedance measured in the bioimpedance measuring step (S200), in an embodiment of the present invention, the body fat (FM) is based on body composition information other than the body fat (FM). , and the weight is predicted by deriving the weight from it.

In an embodiment of the present invention, in the weight change deriving step (S420), the body fat (FM) and body weight are not directly derived, but the body fat (FM) change and the body weight change are derived based on the body composition change, and the weight change and initial weight are derived. weight is estimated based on

In the predicted weight deriving step (S430), predicted weight information is derived based on the weight change. The weight change is derived from the difference in body composition between the time point of the initial information input step (S100) and the time point of the bioimpedance measurement step (S200). Similarly, the time point of the initial information input step (S100) and the bioimpedance measurement step (S200) ) represents the change in body weight between time points. Accordingly, predicted weight information including the predicted weight at the time of the bioimpedance measurement step (S200) can be derived from the weight change and the initial weight information including the weight information in the initial information input step (S100).

6 is a diagram schematically illustrating a process of a weight prediction step according to an embodiment of the present invention.

Referring to FIG. 6 , in the body composition change deriving step S410 , a body composition change 40 is derived based on the initial body composition information 23 of the initial information 20 and the measured body composition information 30 .

Thereafter, in the weight change deriving step ( S420 ), a weight change 50 is derived from the body composition change 40 . In this case, the weight change 50 may be derived using the correlation 90 between the body composition information and the body weight. In an embodiment of the present invention, the correlation 90 between the body composition information and the body weight may include a correlation between one or more items of the body composition information and body fat. By the bioimpedance measurement as in the present invention, body fat (FM) among body composition information cannot be directly derived. Therefore, it is necessary to indirectly derive the body fat FM based on the correlation between one or more items of the body composition information and the body fat FM. Based on such a correlation, changes in body fat (FM) can be derived from changes in body composition, and body weight is expressed as the sum of lean mass (FFM) and body fat (FM) in body composition information, so the change in lean mass (FFM) And it is possible to derive a change in body weight from the change in body fat (FM). That is, in an embodiment of the present invention, the correlation 90 between the body composition information and the body weight may include the correlation between the body composition change 40 and the weight change 50 .

In an embodiment of the present invention, the correlation 90 between the body composition information and the body weight may include the following relational expression.

Such a relational expression is an expression derived by modeling the ratio of the muscle mass (SLM) to the body weight (W) as a function of the initial body fat (F). According to the above relational expression, the amount of change of the body weight W with respect to time is expressed as a function of the amount of change of the muscle mass SLM with respect to time.

According to such a relational expression, it is possible to derive change information of the body weight W based on the change information of the muscle mass SLM without information on the change of body fat.

7 is a diagram schematically illustrating a process of a correlation update step according to an embodiment of the present invention.

Referring to FIG. 7 , in an embodiment of the present invention, in the correlation updating step S600 , error information 80 is first derived based on the predicted weight information 60 and the measured weight information 70 . Thereafter, the correlation 90 between the body composition information and the body weight may be updated based on the derived error information 80 . In more detail, the parameters of the relational expression of the correlation 90 between the body composition information and the body weight may be updated and updated.

In an embodiment of the present invention, the correlation between the body composition information and the body weight may include the following relational expression.

At this time, since the ratio of body fat to muscle mass is different for each individual, the change in body weight appears in different ways. Therefore, in order to derive an accurate weight change, it is necessary to derive parameters based on continuously measured weight and body composition information and user profile information.

를 도출하기 위해,

에서 잔차를

로 계산하고,

의 측정 오차가 고정 분산

를 따른다고 할 때, 카이-제곱 방법에 의해 최적화할 수 있다. 그 결과 카이-제곱 함수를 최소화시키는 파라미터

를 하기와 같이 도출할 수 있다.The measured body weight and body composition information may be used to model the correlation between the body composition information and the body weight, such as the above relational expression. Such data are as follows: SLM _k = {slm _k1 , slm _k2 , slm _k3 , … , slm _kn } and F = {f _k1 , f _k2 , … , f _kn } may appear. Here, k represents the number of measured data, and slm _i and f _i represent muscle mass (SLM) and body fat (FM) of the i-th data, respectively. At this time, the initial parameter of the relation

to derive,

the residual from

calculated as,

The measurement error of the fixed variance

, it can be optimized by the chi-square method. The resulting parameter that minimizes the chi-square function

can be derived as follows.

와 같이 평균 최종 모델 파라미터를 도출하여 모델을 완성할 수 있다.In an embodiment of the present invention to improve the accuracy of the model parameter estimates as described above, by repeating the parameter estimation process based on a randomly-synthesized data set generated by the ^{_{D o s (o = 1,}} 2, ..., m) Monte Carlo estimation can be applied. In an embodiment of the present invention, synthetic data sets D ₁ ^s , D ₂ ^s , D ₃ ^s , . . . Based on , D _m ^s _{, the Monte Carlo parameters a 1} ^s , a ₂ ^s , a ₃ ^s , … that minimize the chi-square function. , a _m ^s , and the parameters

The model can be completed by deriving the average final model parameters as

8 is a flowchart schematically illustrating detailed steps of a correlation update step according to an embodiment.

Referring to FIG. 8 , in an embodiment of the present invention, the correlation updating step (S600) includes a parameter correction step (S610) of modifying the correlation parameters based on the measured weight information and the predicted weight information; and an initial information updating step (S620) of updating the initial information based on the measured weight information; may include.

The parameter correction step (S610) derives error information 80 based on the predicted weight information 60 and the measured weight information 70 as in the process shown in FIG. This may be performed as a method of updating the correlation 90 between the body composition information and the body weight based on the information.

In the initial information update step (S620), the initial information is updated based on the measured weight information received in the measured weight input step (S500). In the weight prediction step (S400), the current weight is predicted based on the initial information. If the initial information is maintained without being updated, an error due to a long-term change increases and the accuracy of prediction is lowered. Therefore, when the measured weight information of the user 10 is input in the measured weight input step ( S500 ), the initial information is updated based on this, so that the accuracy of prediction can be improved.

In an embodiment of the present invention, in the initial information updating step (S620), the initial weight information is updated based on the measured weight of the measured weight information, and the user profile information is also updated based on the date of the measured weight information. can In an embodiment of the present invention, the user profile information may include the user's age, and the user's age may be the age at which the initial information is input. Based on this, the age of the user on the date the weight is measured may be derived and updated.

9 is a diagram schematically illustrating a process of an initial information update step according to an embodiment of the present invention.

Referring to FIG. 9 , as shown in FIG. 7 , in an embodiment of the present invention, the parameter updating step S610 of the correlation updating step S600 is based on the predicted weight information 60 and the measured weight information 70 first. Error information 80 is derived. Thereafter, the correlation 90 between the body composition information and the body weight may be updated based on the derived error information 80 . In more detail, the parameters of the relational expression of the correlation 90 between the body composition information and the body weight may be updated and updated.

In addition, in the initial information update step (S620) of the correlation update step (S600), the initial weight information 22 may be updated based on the measured weight information 70 .

10 is a diagram schematically illustrating an internal configuration of an apparatus for predicting weight according to an embodiment of the present invention.

Referring to FIG. 10 , the bioimpedance-based real-time weight prediction apparatus 1000 according to an embodiment of the present invention includes an initial information input unit 100 for inputting initial information about a user's body; a bioimpedance measuring unit 200 for measuring the bioimpedance of the user's body by applying an electric current to the user's body; a body composition information derivation unit 300 for deriving measured body composition information from the user's bioimpedance; correlation between body composition information and body weight; the initial information; and the measured body composition information; a weight prediction unit 400 for deriving predicted weight information based on ; a measured weight input unit 500 for measuring the user's weight and inputting measured weight information; and a correlation update unit 600 for updating and correcting the correlation based on the measured weight information and the predicted weight information. may include.

The initial information input unit 100 , the bioimpedance measurement unit 200 , the body composition information extraction unit 300 , the weight prediction unit 400 , the measured weight input unit 500 , and the correlation update unit 600 ) Each of the above-described initial information input step (S100), the bioimpedance measurement step (S200), the body composition information deriving step (S300), the weight prediction step (S400), the measured weight input step (S500) and the correlation By performing the same steps as the relationship update step (S600), it is possible to derive the predicted weight.

In this case, the weight prediction apparatus 1000 may be configured by a wearable device. The wearable device may be any one of a smart watch, a smart glass, a smart band, and a head mounted display (HMD), and is preferably a smart watch.

11 is a diagram illustrating an example of an internal configuration of a computing device according to an embodiment of the present invention.

11, the computing device 11000 includes at least one processor 11100, a memory 11200, a peripheral interface 11300, an input/output subsystem ( An I/O subsystem) 11400 , a power circuit 11500 , and a communication circuit 11600 may include at least one or more. In this case, the computing device 11000 may correspond to a bioimpedance-based real-time weight prediction device.

The memory 11200 may include, for example, a high-speed random access memory, a magnetic disk, an SRAM, a DRAM, a ROM, a flash memory, or a non-volatile memory. have. The memory 11200 may include a software module, an instruction set, or other various data necessary for the operation of the computing device 11000 .

In this case, access to the memory 11200 from other components such as the processor 11100 or the peripheral interface 11300 may be controlled by the processor 11100 .

Peripheral interface 11300 may couple input and/or output peripherals of computing device 11000 to processor 11100 and memory 11200 . The processor 11100 may execute a software module or an instruction set stored in the memory 11200 to perform various functions for the computing device 11000 and process data.

The input/output subsystem 11400 may couple various input/output peripherals to the peripheral interface 11300 . For example, the input/output subsystem 11400 may include a controller for coupling a peripheral device such as a monitor, keyboard, mouse, printer, or a touch screen or sensor as needed to the peripheral interface 11300 . According to another aspect, input/output peripherals may be coupled to peripheral interface 11300 without going through input/output subsystem 11400 .

The power circuit 11500 may supply power to all or some of the components of the terminal. For example, the power circuit 11500 may include a power management system, one or more power sources such as batteries or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator, or a power source. It may include any other components for creation, management, and distribution.

The communication circuit 11600 may enable communication with another computing device using at least one external port.

Alternatively, as described above, if necessary, the communication circuit 11600 may include an RF circuit to transmit and receive an RF signal, also known as an electromagnetic signal, to enable communication with other computing devices.

This embodiment of FIG. 11 is only an example of the computing device 11000, and the computing device 11000 may omit some components shown in FIG. 11 or further include additional components not shown in FIG. 11, or 2 It may have a configuration or arrangement that combines two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor in addition to the components shown in FIG. 11 , and various communication methods (WiFi, 3G, LTE) are provided in the communication circuit 11600 . , Bluetooth, NFC, Zigbee, etc.) may include a circuit for RF communication. Components that may be included in the computing device 11000 may be implemented in hardware, software, or a combination of both hardware and software including an integrated circuit specialized for one or more signal processing or applications.

Methods according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded in a computer-readable medium. In particular, the program according to the present embodiment may be configured as a PC-based program or an application dedicated to a mobile terminal. The application to which the present invention is applied may be installed in the user terminal through a file provided by the file distribution system. As an example, the file distribution system may include a file transmission unit (not shown) that transmits the file according to a request of the user terminal.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

Software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computing devices, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

According to an embodiment of the present invention, it is possible to exhibit the effect of predicting the current weight through bioimpedance measurement by a wearable device or the like without measuring the weight on the scale.

According to an embodiment of the present invention, it is possible to exhibit the effect of increasing the accuracy of the predicted weight by continuously inputting the measured weight.

According to an embodiment of the present invention, it is possible to increase the accuracy of the predicted weight by adjusting the parameters for predicting the weight according to the user.

According to an embodiment of the present invention, when the measured weight is not input, it is possible to display the effect of continuously receiving the measured weight by notifying the user.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible from the above description by those skilled in the art. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result. Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (9)

As a bioimpedance-based real-time weight prediction method,
an initial information input step of inputting initial information including weight and body composition information at the same specific point in time of the user's body;
a bioimpedance measuring step of measuring the bioimpedance of the user's body by applying an electric current to the user's body;
a body composition information deriving step of deriving measured body composition information from the user's bioimpedance; and
correlation between body composition information and body weight; weight and body composition information and the measured body composition information at a specific point in time of the initial information; a weight prediction step of deriving predicted weight information based on
a measured weight input step of measuring the user's weight and inputting measured weight information; and
a correlation updating step of revising and updating the correlation based on the measured weight information and the predicted weight information; including,
The correlation update step is
a parameter correction step of deriving error information based on the measured weight information and the predicted weight information, and correcting the parameters of the correlation by updating the correlation between the body composition information and the body weight based on the derived error information; and
and an initial information update step of updating the weight information of the initial information based on the measured weight information received in the measured weight input step;
The weight prediction step is
a body composition change deriving step of deriving a body composition change from the body composition information of the initial information and the measured body composition information;
a weight change deriving step of deriving a weight change based on the correlation between the body composition information and the body weight and the body composition change; and
a predicted weight deriving step of deriving predicted weight information from the weight information of the initial information and the weight change; including,
The correlation is

contains the relation of
The parameter modified in the parameter modification step corresponds to α and β of the relational expression, a bioimpedance-based real-time weight prediction method.
delete delete The method according to claim 1,
The body composition information is
Fat Mass (FM);
Fat-Free Mass (FFM);
Soft Lean Mass (SLM); and
Total Body Water (TBW); comprising at least one of
The correlation between the body composition information and body weight is
A bioimpedance-based real-time weight prediction method comprising a correlation between at least one item of the body composition information and body fat.
delete delete The method according to claim 1,
The bioimpedance-based real-time weight prediction method comprises:
a weight input notification step of displaying a notification to the user to measure the weight when the measured weight input step is not performed for a preset time; Further comprising, bioimpedance-based real-time weight prediction method.
As a bioimpedance-based real-time weight prediction device,
an initial information input unit for inputting initial information including weight and body composition information at the same specific point in time of the user's body;
a bioimpedance measuring unit measuring the bioimpedance of the user's body by applying an electric current to the user's body;
a body composition information derivation unit for deriving measured body composition information from the user's bioimpedance; and
correlation between body composition information and body weight; weight and body composition information at a specific time of the initial information; and the measured body composition information; a weight prediction unit for deriving predicted weight information based on
a measured weight input unit for measuring the user's weight and inputting measured weight information; and
a correlation update unit that corrects and updates the correlation based on the measured weight information and the predicted weight information; including,
The correlation update unit,
a parameter correction step of modifying a parameter of the correlation by deriving error information based on the measured weight information and the predicted weight information, and updating the correlation between the body composition information and the body weight based on the derived error information; and
performing an initial information update step of updating the weight information of the initial information based on the measured weight information input from the measured weight input unit;
The weight prediction unit,
a body composition change deriving step of deriving a body composition change from the body composition information of the initial information and the measured body composition information;
a weight change deriving step of deriving a weight change based on the correlation between the body composition information and the body weight and the body composition change; and
a predicted weight deriving step of deriving predicted weight information from the weight information of the initial information and the weight change; do,
The correlation is

contains the relation of
wherein the parameter modified by the parameter modification step corresponds to α and β of the relational expression, a bioimpedance-based real-time weight prediction apparatus.
A computer-readable medium for providing a bioimpedance-based real-time weight prediction method, the computer-readable medium storing instructions for causing a computing device to perform the following steps,
The steps are:
an initial information input step of inputting initial information including weight and body composition information at the same specific point in time of the user's body;
a bioimpedance measuring step of measuring the bioimpedance of the user's body by applying an electric current to the user's body;
a body composition information deriving step of deriving measured body composition information from the user's bioimpedance;
correlation between body composition information and body weight; weight and body composition information at a specific time of the initial information; and the measured body composition information; a weight prediction step of deriving predicted weight information based on
a measured weight input step of measuring the user's weight and inputting measured weight information; and
a correlation updating step of revising and updating the correlation based on the measured weight information and the predicted weight information; including,
The correlation update step is
a parameter correction step of modifying a parameter of the correlation by deriving error information based on the measured weight information and the predicted weight information, and updating the correlation between the body composition information and the body weight based on the derived error information; and
and an initial information update step of updating the weight information of the initial information based on the measured weight information received in the measured weight input step;
The weight prediction step is
a body composition change deriving step of deriving a body composition change from the body composition information of the initial information and the measured body composition information;
a weight change deriving step of deriving a weight change based on the correlation between the body composition information and the body weight and the body composition change; and
a predicted weight deriving step of deriving predicted weight information from the weight information of the initial information and the weight change; including,
The correlation is

contains the relation of
The parameter modified in the parameter modifying step corresponds to α, and β of the relational expression.

Images