KR20220109157A - Electronic device and method for acquiring data from seismocardiogram signal - Google Patents

Abstract

According to the present invention, an electronic device includes: a sensor which acquires SCG signals from a part of a subject's body; and a processor which receives an SCG signal from the sensor, inputs the received SCG signal to a plurality of band-pass filters to obtain a plurality of SCG signals divided by frequency band, and generates a fiducial point estimation model for a subject's heartbeat through deep learning based on a plurality of SCG signals. In addition to this, various embodiments identified through the specification are possible. Accordingly, the blood pressure may be measured through the included components without adding a separate hardware component for measuring blood pressure.

Description

ELECTRONIC DEVICE AND METHOD FOR ACQUIRING DATA FROM SEISMOCARDIOGRAM SIGNAL

Various embodiments according to the present disclosure relate to an electronic device and method for learning SCG signals acquired through a sensor and acquiring data based on a learning result.

Recently, as the number of hypertensive patients increases, the number of people who manage their health through regular blood pressure measurement in daily life is increasing. However, the cuff blood pressure monitor that measures the blood pressure of a subject by increasing the pressure of the cuff is not easy to carry and has disadvantages that the measured blood pressure may vary depending on the way the cuff is worn. Accordingly, the demand for a cuffless type blood pressure monitor is increasing.

In estimating blood pressure using the cuffless method, it is important whether the blood pressure monitor can accurately measure a pulse transit time (PTT). A conventional blood pressure monitor utilizes signal data acquired through an electrocardiogram (ECG) sensor and a photoplethysmogram (PPG) sensor to measure a pulse wave transmission time.

Recently, research on a method for measuring blood pressure through an electronic device such as a smart phone that a user is already using is being conducted. In particular, research to improve the accuracy of the blood pressure measurement result while considering the price point by not adding a separate part for acquiring the biosignal is continuing.

Patent Document 1: Korean Patent Publication No. 10-1674997

Various embodiments according to the present disclosure provide an electronic device that performs deep learning on SCG signals acquired through a sensor and acquires data based on a result of the deep learning.

The technical problems to be achieved by the present disclosure are not limited to the technical problems as described above, and other technical problems may be inferred from the following embodiments.

According to an embodiment, an electronic device receives an SCG signal from a sensor and a sensor for acquiring an SCG signal from a body part of a subject, and divides the received SCG signal into a plurality of band-pass filters for each frequency band The method may include a processor for acquiring a plurality of SCG signals and generating a fiducial point estimation model for a heartbeat of a subject through deep learning based on the plurality of SCG signals.

In an embodiment, the processor may detect an aortic valve opening point during the heartbeat of the subject through the reference point estimation model.

In an embodiment, the processor may determine the pulse transit time of the subject through the detected aortic valve opening point.

In an embodiment, deep learning may be implemented through a deep neural network algorithm.

In an embodiment, the processor may input a plurality of SCG signals to an input neuron of a deep neural network algorithm, and output data about a reference point to an output neuron.

In an embodiment, the deep neural network algorithm may include at least one dense layer and a bi-directional LSTM layer.

In an embodiment, the plurality of band filters may include band filters having different frequency bandwidths in the range of 0.8 Hz to 50 Hz.

An operation method of an electronic device according to an embodiment includes an operation of receiving an SCG signal obtained from a body part of a subject through a sensor, and inputting the received SCG signal into a plurality of band-pass filters to divide the signal for each frequency band. It may include an operation of acquiring a plurality of SCG signals, and an operation of generating a fiducial point estimation model for a heartbeat of a subject through deep learning based on the plurality of SCG signals. .

In an embodiment, the method of operating the electronic device may further include detecting an aortic valve opening point during a heartbeat of the subject through a reference point estimation model.

In an embodiment, the method of operating the electronic device may further include determining a pulse transit time of the subject through the detected aortic valve opening point.

In an embodiment, deep learning may be implemented through a deep neural network algorithm.

In an embodiment, the method of operating the electronic device may further include inputting a plurality of SCG signals to an input neuron of a deep neural network algorithm, and outputting data about a reference point to an output neuron. have.

In an embodiment, the deep neural network algorithm may include at least one dense layer and a bi-directional LSTM layer.

In an embodiment, the plurality of band filters may include band filters having different frequency bandwidths in the range of 0.8 Hz to 50 Hz.

It may include a computer-readable recording medium in which a program for executing the method of operating the electronic device according to an embodiment in a computer is recorded.

Since the electronic device according to various embodiments of the present disclosure can measure blood pressure through pre-included components without adding a separate hardware component for measuring blood pressure, cost-effectiveness can be improved. .

1 is a block diagram of an electronic device according to an embodiment.
2A is a diagram illustrating a method of acquiring a signal through an electronic device according to an embodiment.
2B is a diagram illustrating a method of acquiring different signals through a sensor of an electronic device according to an embodiment.
3 is a graph illustrating an SCG signal obtained through a sensor of an electronic device according to an exemplary embodiment.
4 is a flowchart illustrating an electronic device generating a reference point estimation model from an SCG signal, according to an embodiment.
5 illustrates a data flow of an SCG signal obtained by an electronic device according to an embodiment.
6 illustrates an algorithm of a deep neural network learned in an electronic device according to an embodiment.
7 is a graph illustrating an electronic device detecting a reference point through a reference point estimation model, according to an exemplary embodiment.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art to which the present disclosure pertains can easily implement them. However, the present disclosure may be implemented in several different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present disclosure in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

The terms used in the present disclosure have been described as general terms currently used in consideration of the functions mentioned in the present disclosure, but may mean various other terms depending on the intention or precedent of a person skilled in the art, the emergence of new technology, etc. can Therefore, the terms used in the present disclosure should not be construed only as names of terms, but should be interpreted based on the meaning of the terms and the contents of the present disclosure.

In addition, the terms used in the present disclosure are only used to describe specific embodiments, and are not intended to limit the present disclosure. Expressions in the singular include the plural meaning unless the context clearly means the singular. In addition, throughout the specification, when a part is "connected" with another part, it is not only "directly connected" but also "electrically connected" with another element interposed therebetween. include Also, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated.

The above and similar referents used in this specification, particularly in the claims, may refer to both the singular and the plural. Further, the described steps may be performed in any suitable order, unless there is a description explicitly designating the order of the steps describing the method according to the present disclosure. The present disclosure is not limited according to the order of description of the described steps.

Phrases such as “in some embodiments” or “in one embodiment” appearing in various places in this specification are not necessarily all referring to the same embodiment.

Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented in any number of hardware and/or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors, or by circuit configurations for a predetermined function. Also, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented as an algorithm running on one or more processors. Also, the present disclosure may employ prior art for electronic configuration, signal processing, and/or data processing, and the like. Terms such as mechanism, element, means and configuration may be used broadly and are not limited to mechanical and physical configurations.

In addition, the connecting lines or connecting members between the components shown in the drawings only exemplify functional connections and/or physical or circuit connections. In an actual device, a connection between components may be represented by various functional connections, physical connections, or circuit connections that are replaceable or added.

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

1 is a block diagram of an electronic device according to an embodiment.

Referring to FIG. 1 , the electronic device 100 may include a sensor 110 and a processor 120 .

In an embodiment, the sensor 110 may acquire a biosignal of a subject. For example, the sensor 110 may include at least one of an inertial sensor (IMU sensor) and an optical sensor.

In an embodiment, the inertial sensor may acquire a heartbeat signal through vibration caused by a movement of a heart valve. The heartbeat signal may include a seismocardiogram (SCG) signal including key reference points of a cardiac cycle. The processor 120 detects the aortic valve opening (AO) point, the aortic valve closing (AC) point, and the mitral valve closing (MC) point through the main reference points of the cardiac cycle. can do.

In an embodiment, the optical sensor may emit a light-emitting diode (LED) light to a body part (eg, a finger) of the subject, and may receive the reflected light to obtain an optical blood flow measurement signal.

In an embodiment, the processor 120 may acquire biometric data from the biosignal acquired through the sensor 110 . In an embodiment, the processor 120 may acquire a pulse transit time (PTT) through the heartbeat signal received from the inertial sensor and the optical blood flow measurement signal received from the optical sensor. For example, the processor 120 may acquire a time difference between a specific point of the heartbeat signal and a specific point of the photoblood flow measurement signal, and determine the time difference as a pulse wave transmission time. The pulse wave transmission time means a time for which the pulsatile pressure wave is transmitted from the aortic valve to the peripheral region, and may correspond to biometric data related to the subject's blood pressure.

In an embodiment, the processor 120 may generate a fiducial point estimation model for a heartbeat by performing deep learning based on the biosignal acquired through the sensor 110 . For example, the processor 120 may generate the reference point estimation model through the SCG signal obtained through the inertial sensor. The fiducial point may mean an aortic valve opening (AO) point required to obtain a pulse wave transmission time.

In an embodiment, deep learning may be a set of algorithms for learning a method of obtaining a fiducial point to be extracted from signal data input to a neural network based on artificial intelligence. For example, deep learning may include a deep neural network (DNN), and the deep neural network may include an input neuron, an output neuron, and a plurality of hidden layers. In this case, the hidden layer may include a dense layer and a bi-directional long-short term memory layer (LSTM). A detailed description thereof will be described later with reference to FIG. 6 .

2A is a diagram illustrating a method of acquiring a signal through an electronic device according to an embodiment. 2B is a diagram illustrating a method of acquiring different signals through a sensor of an electronic device according to an embodiment.

Referring to FIG. 2A , the electronic device 100 may obtain a biosignal from a body part 210 of a subject 200 (eg, a user of the electronic device).

For example, when at least one region of the front portion of the electronic device 100 comes in contact with a body part corresponding to the vicinity of the heart of the subject 200 , the processor (eg, the processor 120 of FIG. 1 ) may include a sensor (eg: A heartbeat signal may be acquired from an inertial sensor among the sensors 110 of FIG. 1 .

For example, when at least one region of the rear surface of the electronic device 100 comes into contact with a body part corresponding to the fingertip of the subject 200 , the processor 120 receives the optical blood flow measurement signal from the optical sensor among the sensors 110 . can be obtained

Referring to FIG. 2B , the electronic device 100 may include an inertial sensor 205 and an optical sensor 215 . In this case, the optical sensor 215 may be included in a camera module (not shown) of the electronic device 100 .

In an embodiment, the inertial sensor 205 may acquire a heartbeat signal from the body part 220 corresponding to the heart area among the chest 200(a) of the subject. In an embodiment, the optical sensor 215 may acquire the optical blood flow measurement signal from the body part 230 corresponding to the fingertip of the subject's hand 200(b). In an embodiment, the inertial sensor 205 and the optical sensor 215 may acquire a heartbeat signal and an optical blood flow measurement signal in parallel, respectively.

FIG. 2B illustrates the electronic device 100 being separated from the subject's body parts 220 and 230 for convenience of explanation, but the electronic device 100 is in contact with the subject's body parts 220 and 230, respectively. In this state, it is possible to obtain a heartbeat signal and an optical blood flow measurement signal.

3 is a graph illustrating an SCG signal obtained through a sensor of an electronic device according to an exemplary embodiment.

Referring to FIG. 3 , a processor (eg, the processor 120 of FIG. 1 ) may receive an SCG signal from a sensor (eg, the sensor 110 of FIG. 1 ). The peaks of the SCG signal may indicate the occurrence of mechanical events such as heart contraction and blood ejection.

In an embodiment, the SCG signal received by the processor 120 may include main reference points. For example, the main reference points included in the SCG signal may include mitral valve closing (MC), isovolumetric moment (IM), aortic valve opening (AO), maximal acceleration (MA), and aortic valve closing (AC). .

In an embodiment, the processor 120 may extract main reference points from the received SCG signal. As an SCG signal having a substantially low signal to noise ratio is received, it may be difficult for a conventional electronic device to extract reference points of the SCG signal. The processor 120 of the electronic device (eg, the electronic device 100 of FIG. 1 ) according to the present disclosure determines the main reference points through a fiducial point estimation model generated by deep learning on the SCG signal. can be extracted.

In an embodiment, the SCG signal received by the processor 120 may change according to a location of a sensor (eg, the inertial sensor 205 of FIG. 2B ). For example, the SCG signal obtained when the inertial sensor 205 is disposed in a first region (eg, the central part) of the subject's body part (eg, the body part 220 of FIG. 2 ) may include the inertial sensor 205 ) may be different from the SCG signal obtained when the subject's body part 220 is disposed in the second region (eg, the lower part). In this case, relative amplitudes of reference points included in each SCG signal obtained in the first region and the second region may be different from each other. For example, the relative amplitude of the AO point of the SCG signal obtained in the second area may be smaller than the relative amplitude of the AO point of the SCG signal obtained in the first area. At this time, the processor 120 extracts each AO point of the SCG signal obtained in the first region and the second region through a fiducial point estimation model generated by performing deep learning on the SCG signal. can do.

4 is a flowchart illustrating an electronic device generating a reference point estimation model from an SCG signal, according to an embodiment. 5 illustrates a data flow of an SCG signal obtained by an electronic device according to an embodiment. In the description of FIGS. 4 and 5 , contents corresponding to, identical to, or similar to those described above may be omitted. In the description of FIG. 4 , it will be described with reference to FIG. 5 .

Referring to FIG. 4 , a processor (eg, the processor 120 of FIG. 1 ) may receive an SCG signal obtained from a body part of a subject in operation 400 . In one embodiment, the processor 120 obtains from a body part (eg, body part 220 of FIG. 2B ) corresponding to the vicinity of the subject's heart through an inertial sensor (eg, the inertial sensor 205 of FIG. 2B ). An SCG signal may be received. The SCG signal may correspond to the raw SCG signal 500 of FIG. 5 .

According to an embodiment, the processor 120 may obtain a plurality of divided SCG signals by inputting the SCG signal to a plurality of band filters in operation 410 .

In an embodiment, the plurality of band filters may include band filters having different frequency bandwidths in the range of 0.8 Hz to 50 Hz. The plurality of band filters 510 of FIG. 5 may include N band filters, such as a first band filter, a second band filter, and a third band filter to an N-th band filter. For example, when N=3, the first band filter may have a bandwidth of 0.8 Hz to 10 Hz, the second band filter may have a bandwidth of 10 Hz to 35 Hz, and the third band filter may have a bandwidth of 35 Hz to 50 Hz. This is only an example, and the number and bandwidth of band filters may be variously changed according to a design of a manufacturer.

In an embodiment, the processor 120 may obtain the N SCG signals divided for each frequency band by inputting the raw SCG signal 500 of FIG. 5 to the plurality of band filters 510 . In an embodiment, the processor 120 divides the raw SCG signal 500 for each frequency band and performs learning, thereby preventing deterioration of estimation performance and excessive use of memory.

According to an embodiment, the processor 120 may generate a fiducial point estimation model through deep learning based on a plurality of SCG signals in operation 420 .

In an embodiment, deep learning may be implemented through the algorithm of a deep neural network (DNN) 520 of FIG. 5 . For example, the deep neural network 520 may include an input neuron, an output neuron, at least one dense layer, and a bi-directional LSTM layer. A detailed description thereof will be described later with reference to FIG. 6 .

In an embodiment, the processor 120 may input a plurality of SCG signals obtained from the plurality of bandpass filters 510 of FIG. 5 as input neurons of the deep neural network. In an embodiment, before inputting the plurality of SCG signals to the input neurons, the processor 120 may apply knowledge about the characteristics of the SCG signals (eg, a signal pattern corresponding to a reference point) to the deep neural network. By applying the knowledge of the characteristics of the SCG signal to the deep neural network, the learning performance of the deep neural network may be increased.

In an embodiment, the processor 120 may generate the reference point estimation model 530 for the heartbeat of the subject by repeating learning through the deep neural network 520 . The processor 120 may extract a reference point from the SCG signal received from the sensor based on the generated reference point estimation model 530 . Also, even after generating the reference point estimation model 530 , the processor 120 may continuously update the reference point estimation model 530 by repeating operations 400 to 420 of FIG. 4 .

6 illustrates an algorithm of a deep neural network learned in an electronic device according to an embodiment.

Referring to FIG. 6 , the deep neural network 520 may include an input neuron, at least one dense layer, a bi-directional LSTM layer, and an output neuron.

In an embodiment, the size of the SCG signal input to the input neuron may be determined according to a batch size, a sequence length, and the number of filters. For example, when the batch size is 3, the sequence length is 10, and the number of filters is 5, the size of the input signal may be expressed as 'shape=(3, 10, 5)'.

In an embodiment, the deep neural network 520 may include a bidirectional LSTM layer including a forward learning layer and a backward learning layer. For example, when a plurality of SCG signals divided for each frequency band are input to an input neuron of the deep neural network 520 , the input signals may be transmitted to a first density layer including five neurons. Signals transferred to the first density layer may be transferred to the bidirectional LSTM layer, and forward time series learning and reverse time series learning may be performed in parallel on the transferred signals in the bidirectional LSTM layer.

As the deep neural network 520 includes the bidirectional LSTM layer, the learning performance of the deep neural network 520 may not deteriorate even if the sequence length is long or the depth is deep. In particular, the deep neural network 520 may generate a reference point estimation model with substantially improved accuracy by performing forward and backward time series learning in parallel. Through this, the electronic device (eg, the electronic device 100 of FIG. 1 ) that has performed learning through the deep neural network 520 receives the main information from the SCG signal acquired through the sensor (eg, the inertial sensor 205 of FIG. 2B ). Reference points can be accurately extracted.

In an embodiment, signals output from the bidirectional LSTM layer may be transmitted to the second density layer. For example, signals on which time series learning in the forward direction is performed and signals on which time series learning in the reverse direction is performed may be connected and transmitted to the second density layer. As another example, signals on which time-series learning in the forward direction is performed and signals on which time-series learning in the reverse direction is performed may be combined and then transferred to the second density layer. As another example, an average value of signals on which time series learning in the forward direction is performed and signals on which time series learning in the reverse direction is performed may be transferred to the second density layer.

In an embodiment, the bidirectional LSTM layer and the dense layer may be added after the second dense layer intersects. For example, the hidden layer between the input neuron and the output neuron is a first dense layer, a bidirectional LSTM layer, a second dense layer, a bidirectional LSTM layer, a third dense layer, a bidirectional LSTM layer, ?? , a bidirectional LSTM layer, and an nth density layer. In this case, the hidden layer may include n dense layers and n-1 bidirectional LSTM layers.

In an embodiment, data learned through at least one dense layer and a bidirectional LSTM layer may be output to an output neuron. In this case, the learned data may refer to data about a reference point for the subject's heartbeat.

와 같이 표현될 수 있다.In an embodiment, the output neuron may express the learned data through one-hot encoding. The output neuron may apply '1' to a portion corresponding to the reference point and express '0' to the remaining portion that does not correspond to the reference point. For example, if the sequence length is 10 and the learned reference point, the aortic valve opening (AO), is extracted in the second, the shape of the output neuron is

can be expressed as

7 is a graph illustrating an electronic device detecting a reference point through a reference point estimation model, according to an exemplary embodiment.

Referring to FIG. 7 , a processor (eg, the processor 120 of FIG. 1 ) may acquire an SCG signal from a body part of a subject through an inertial sensor (eg, the inertial sensor 205 of FIG. 2B ). The processor 120 extracts the reference points 700, 705, 710, and 715 for the heartbeat of the subject through the reference point estimation model (eg, the reference point estimation model 530 of FIG. 5) generated based on deep learning. can For example, the processor 120 may extract the reference point through a reference point estimation model generated through learning, rather than extracting the reference point based on the amplitude corresponding to the reference point indicating the aortic valve opening (AO) point.

In an embodiment, the processor 120 may acquire an optical blood flow signal from a body part of the subject through an optical sensor (eg, the optical sensor 215 of FIG. 2B ). The processor 120 may acquire the feature points 720 , 725 , 730 , and 735 based on a change in the amplitude of the optical blood flow signal. For example, the processor 120 may determine and obtain a point at which the amplitude of the optical blood flow signal abruptly increases as a feature point.

In an embodiment, the processor 120 is configured to obtain the reference points 700 , 705 , 710 , and 715 extracted through the reference point estimation model 530 and the feature points 720 , 725 , 730 obtained based on the amplitude change of the optical blood flow signal. , 735) may be determined as the pulse wave transmission time. For example, the processor 120 may calculate a time difference between the first reference point 700 and the first feature point 720 to obtain the pulse wave propagation time 740 .

Meanwhile, the above-described embodiment can be written as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable medium. In addition, the structure of the data used in the above-described embodiment may be recorded in a computer-readable medium through various means. In addition, the above-described embodiment may be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. For example, methods implemented as a software module or algorithm may be stored in a computer-readable recording medium as computer-readable codes or program instructions.

Computer-readable media may be any recording media that can be accessed by a computer, and may include volatile and nonvolatile media, removable and non-removable media. The computer-readable medium may include a magnetic storage medium, for example, a ROM, a floppy disk, a hard disk, and the like, and an optically-readable medium, for example, a storage medium such as a CD-ROM or DVD, but is not limited thereto. . In addition, computer-readable media may include computer storage media and communication media.

In addition, a plurality of computer-readable recording media may be distributed in network-connected computer systems, and data stored in the distributed recording media, for example, program instructions and codes, may be executed by at least one computer. have.

The specific implementations described in the present disclosure are merely exemplary, and do not limit the scope of the present disclosure in any way. For brevity of the specification, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted.

The description of the present disclosure described above is for illustration, and those of ordinary skill in the art to which the present disclosure pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present disclosure. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and likewise components described as distributed may also be implemented in a combined form.

Those of ordinary skill in the art related to the embodiments of the present disclosure will understand that it may be implemented in a modified form within a range that does not deviate from the essential characteristics of the description.

The present disclosure can apply various transformations and can have various embodiments, and the present disclosure is not limited by the specific embodiments described in the specification, and all transformations and equivalents included in the spirit and scope of the present disclosure It should be understood that alternatives are included in the present disclosure. Therefore, the disclosed embodiments should be understood in an illustrative rather than a restrictive sense.

The scope of the present disclosure is indicated by the claims rather than the detailed description of the invention, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present disclosure.

As used herein, terms such as “…unit”, “…module”, etc. mean a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software. can

"...part" and "...module" are stored in an addressable storage medium and may be implemented by a program that can be executed by a processor.

For example, "...part", "...module" refer to components such as software components, object-oriented software components, class components and task components, processes, and functions. may be implemented by fields, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, database, data structures, tables, arrays and variables have.

Claims (15)

a sensor for acquiring an SCG signal from a body part of the subject; and
Receiving the SCG signal from the sensor, inputting the received SCG signal to a plurality of band-pass filters to obtain a plurality of SCG signals divided for each frequency band, and based on the plurality of SCG signals An electronic device comprising: a processor for generating a fiducial point estimation model for the heartbeat of the subject through deep learning. According to claim 1,
The processor is configured to detect an aortic valve opening point during the heartbeat of the subject through the reference point estimation model. 3. The method of claim 2,
The processor is configured to determine a pulse transit time of the subject through the detected aortic valve opening point. According to claim 1,
The deep learning is implemented through a deep neural network algorithm, the electronic device. 5. The method of claim 4,
The processor is
An electronic device for inputting the plurality of SCG signals to an input neuron of the deep neural network algorithm, and outputting data about a reference point to an output neuron. 5. The method of claim 4,
The deep neural network algorithm comprises at least one dense layer and a bi-directional LSTM layer, the electronic device. According to claim 1,
The plurality of band filters includes band filters having different frequency bandwidths in the range of 0.8 Hz to 50 Hz. receiving an SCG signal obtained from a body part of a subject through a sensor;
obtaining a plurality of SCG signals divided for each frequency band by inputting the received SCG signal to a plurality of band-pass filters; and
and generating a fiducial point estimation model for the heartbeat of the subject through deep learning based on the plurality of SCG signals. 9. The method of claim 8,
The method of operating an electronic device, further comprising: detecting an aortic valve opening point during a heartbeat of the subject through the reference point estimation model. 10. The method of claim 9,
The method of operating an electronic device, further comprising the operation of determining a pulse transit time of the subject through the detected aortic valve opening point. 9. The method of claim 8,
The deep learning is implemented through a deep neural network algorithm, the operating method of the electronic device. 12. The method of claim 11,
The method of operating an electronic device, further comprising: inputting the plurality of SCG signals to an input neuron of the deep neural network algorithm, and outputting data about a reference point to an output neuron. 12. The method of claim 11,
The method of operating an electronic device, wherein the deep neural network algorithm includes at least one dense layer and a bi-directional LSTM layer. 9. The method of claim 8,
The method of operating an electronic device, wherein the plurality of band filters include band filters having different frequency bandwidths in the range of 0.8 Hz to 50 Hz. A computer-readable recording medium recording a program for executing the method according to claim 8 in a computer.

Images