JP2022191688A - Determination device, determination method, computer program and recording medium - Google Patents

Abstract

To determine whether a living body sound is detected correctly, while keeping cost down.SOLUTION: A determination device (20) determines whether a living body sound is detected correctly by a living body sound detection device (10), having a first sensor (11) for acquiring first sound information containing the living body sound when detecting the living body sound of an object (1), and a second sensor (12) arranged in a position separated from the object more than the first sensor and acquiring second sound information containing the sound around the object. The determination device includes: acquisition means (21a, 21b) for acquiring the first sound information and the second sound information; extraction means (24a, 24b) for extracting a first low frequency component being the low frequency component contained in the first sound information, and a second low frequency component being the low frequency component contained in the second sound information; and determination means (27) for determining whether the living body sound detection device detects the living body sound correctly, on the basis of results of comparison between the first low frequency component and the second low frequency component.SELECTED DRAWING: Figure 1

Description

The present invention relates to a technical field of a determination device, a determination method, a computer program, and a recording medium for determining whether a body sound detection device correctly detects body sounds of a target.

As this type of device, for example, one or a plurality of contact detection sensor pairs are arranged around an auscultatory sound sensor in a chestpiece, and auscultatory sound is detected based on the contact detection results of the paired contact detection sensors. A device for determining whether or not a contact state can be acquired appropriately has been proposed (see Patent Document 1).

International Publication No. 2016/143116

In the technique described in Patent Document 1, it is necessary to prepare at least one contact detection sensor pair (that is, two contact detection sensors) separately from the auscultatory sound sensor. There is a problem.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems. An object of the present invention is to provide a program and a recording medium.

In order to solve the above problems, the determination device of the present invention includes a first sensor that acquires first sound information including the body sound when detecting body sounds of a target, and a sensor that is further away from the target than the first sensor. and a body sound detecting device disposed at a position and having a second sensor that acquires second sound information including ambient sound of the target, and determining whether the body sound is correctly detected, Acquisition means for acquiring first sound information and said second sound information; Based on the extraction means for extracting a second low-frequency component, and the result of comparison between the first low-frequency component and the second low-frequency component, the body sound detecting device correctly detects the body sound. and determination means for determining whether or not there is.

In order to solve the above problems, the determination method of the present invention includes a first sensor that acquires first sound information including the body sound when body sounds of a target are detected; and a second sensor that is arranged at a position and acquires second sound information including ambient sound of the target. an acquisition step of acquiring first sound information and the second sound information; extracting a first low frequency component that is a low frequency component contained in the first sound information; and extracting a low frequency component contained in the second sound information The body sound detecting device correctly detects the body sound based on an extraction step of extracting a second low frequency component, and a comparison result between the first low frequency component and the second low frequency component. and a determining step of determining whether or not there is.

In order to solve the above problems, the computer program of the present invention provides a first sensor that acquires first sound information including the body sound when body sound of a target is detected, and a sensor that is further away from the target than the first sensor. the computer of the determination device for determining whether the body sound detection device having a second sensor arranged at a position and acquiring second sound information including the ambient sound of the target is correctly detecting the body sound; Acquisition means for acquiring first sound information and said second sound information; Based on the extraction means for extracting a second low-frequency component, and the result of comparison between the first low-frequency component and the second low-frequency component, the body sound detecting device correctly detects the body sound. It functions as determination means for determining whether or not there is.

A recording medium of the present invention records the above-described computer program of the present invention in order to solve the above problems.

The operation and other advantages of the present invention will become apparent from the detailed description that follows.

It is a figure which shows the structure of the determination apparatus which concerns on an Example. It is a flowchart which shows operation|movement of the determination apparatus which concerns on an Example.

(Determination device)
An embodiment relating to a determination device will be described. A determination device according to an embodiment determines whether a body sound detection device correctly detects body sounds of a target. A body sound detection device has a first sensor and a second sensor. The first sensor acquires first sound information including the body sound when the body sound of the target is detected. The second sensor is arranged at a position farther from the target than the first sensor when the body sound of the target is detected. A second sensor acquires second sound information including ambient sound of the object.

Here, the first sound information mainly includes sound information related to body sounds, but may also include sound information related to sounds around the object. The second sound information mainly includes sound information related to sounds around the object, but may also include sound information related to body sounds. By the way, the sound information related to the surrounding sounds of the object that can be included in the first sound information becomes noise for the sound information related to body sounds. The noise included in the first sound information can be removed or reduced by referring to the second sound information mainly including sound information related to the surrounding sound of the object. Note that the method of removing or reducing noise is not an essential feature of the determination device, so the description thereof will be omitted.

The judging device comprises acquisition means, extraction means, and judgment means. The acquisition means acquires the first sound information and the second sound information from the body sound detection device. The extraction means extracts a first low frequency component, which is a low frequency component included in the first sound information. The extraction means also extracts a second low-frequency component, which is a low-frequency component included in the second sound information. Since the existing technology can be applied to the method of extracting the low-frequency component from the sound information, detailed description thereof will be omitted. The determining means determines whether or not the body sound detecting device correctly detects the target body sound based on the comparison result between the first low frequency component and the second low frequency component.

As described above, the second sound information acquired by the second sensor may also include information related to body sounds. This is because when the body sound detection device is in proper contact with the target, the body sound-related vibrations propagate throughout the body sound detection device and are detected by the second sensor. Also, the frequency associated with body sounds is relatively low. When the body sound detection device is in proper contact with the object, the second low frequency component is relatively similar to the first low frequency component because the second sound information contains information related to the body sound. On the other hand, when the body sound detection device is not in proper contact with the object, the second low frequency component is relatively deviated from the first low frequency component. Therefore, by comparing the first low-frequency component and the second low-frequency component, it is possible to determine whether or not the body sound detection device correctly detects the target body sound.

As described above, the second sound information obtained by the second sensor can be used, for example, to remove or reduce noise contained in the first sound information obtained by the first sensor. That is, in the determination device, the second sound information used for noise removal, for example, is also used to determine whether the body sound detection device correctly detects the target body sound. In other words, the determination device does not need to provide a body sound detection device with a dedicated member in order to determine whether the body sound detection device correctly detects the target body sound. Therefore, according to the determination device, it is possible to determine whether the body sound detection device correctly detects the target body sound while suppressing the cost.

(Determination method)
An embodiment relating to a determination method will be described. A determination method according to an embodiment determines whether a body sound detection device correctly detects body sounds of a target. Since the configuration of the body sound detection device is the same as that of the embodiment relating to the determination device described above, the description thereof will be omitted.

The determination method includes an acquisition step, an extraction step and a determination step. In the obtaining step, the first sound information and the second sound information are obtained. In the extracting step, a first low-frequency component, which is a low-frequency component included in the first sound information, is extracted. Also, in the extracting step, a second low-frequency component, which is a low-frequency component included in the second sound information, is extracted. In the determination step, it is determined whether or not the body sound detection device correctly detects the body sound based on the comparison result between the first low frequency component and the second low frequency component.

According to the determination method, it is possible to determine whether the body sound detection device correctly detects the target body sound while suppressing the cost, like the determination device according to the above-described embodiment.

(computer program)
An embodiment relating to a computer program will be described. A computer program according to an embodiment acquires first sound information and second sound information for a computer of a determination device that determines whether a body sound detection device correctly detects body sounds when target body sounds are detected. Acquisition means, extracting means for extracting a first low-frequency component, which is a low-frequency component contained in the first sound information, and extracting a second low-frequency component, which is a low-frequency component contained in the second sound information; It also functions as determination means for determining whether or not the body sound detection device correctly detects body sounds based on the result of comparison between the first low frequency component and the second low frequency component. Note that the configuration of the body sound detection device is the same as that of the above embodiment of the determination device, so the description thereof will be omitted.

According to the computer program, the computer program can be read from a recording medium such as RAM (Random Access Memory), CD-ROM (Compact Disc Read Only Memory), DVD-ROM (DVD Read Only Memory), etc. The determination device according to the above-described embodiment can be realized relatively easily by reading it into a computer that constitutes the determination device and executing it, or by downloading the computer program via a communication means and then executing it. can do. As a result, it is possible to determine whether the body sound detection device correctly detects the target body sound while suppressing the cost, like the determination device according to the above-described embodiment.

Here, a recording medium such as a CD-ROM, a DVD-ROM, or the like on which the computer program is recorded corresponds to an embodiment of the recording medium.

An embodiment of the determination device will be described with reference to FIGS. 1 and 2. FIG. In this embodiment, a determination device 20 for determining whether the body sound detection device 10 is correctly detecting body sounds in a system for continuously monitoring the body sounds of the subject 1 will be described.

The body sound detection device 10 has a first sensor 11 and a second sensor 12 . The first sensor 11 and the second sensor 12 may be sensors capable of acquiring body sounds, such as microphones and acceleration sensors. When the body sound of the subject 1 is detected, the first sensor 11 is arranged closer to the subject 1 than the second sensor 12 (in other words, the second sensor 12 is located farther from the subject 1 than the first sensor 11). position), the body sound detection device 10 is attached to the subject 1 .

The first sensor 11 acquires first sound information including body sounds of the subject 1 . The second sensor 12 acquires second sound information including sounds around the subject 1 . Here, the first sound information and the second sound information may be digital audio such as WAVE format.

The determination device 20 includes acquisition units 21a and 21b, frequency conversion units 22a and 22b, power conversion units 23a and 23b, low frequency acquisition units 24a and 24b, a correlation coefficient calculation unit 25, a threshold processing unit 26, and a detection unit 27. configured as follows. The acquisition unit 21 a acquires the first sound information acquired by the first sensor 11 . The acquisition unit 21 b acquires the second sound information acquired by the second sensor 12 .

The first sound information acquired by the acquisition unit 21a is sent to the frequency conversion unit 22a. The frequency conversion unit 22a applies frequency conversion processing to the first sound information. The frequency conversion unit 22a sends the first sound information subjected to frequency conversion processing to the power conversion unit 23a. The power conversion unit 23a performs power conversion processing on the first sound information that has been subjected to the frequency conversion processing. As a result, a power spectrum (that is, a graph showing the sound pressure level for each frequency) is generated for the first sound information.

Similarly, the second sound information acquired by the acquisition unit 21b is sent to the frequency conversion unit 22b. The frequency conversion unit 22b applies frequency conversion processing to the second sound information. The frequency conversion unit 22b sends the frequency-converted second sound information to the power conversion unit 23b. The power conversion unit 23b performs power conversion processing on the second sound information that has been subjected to the frequency conversion processing. As a result, a power spectrum relating to the second sound information is generated.

Since various existing modes can be applied to the frequency conversion process and the power conversion process, detailed description thereof will be omitted.

The low-frequency acquisition unit 24a acquires (extracts) low-frequency components (for example, components with frequencies of several hundred hertz or less) from the power spectrum related to the first sound information. Similarly, the low frequency acquisition unit 24b acquires (extracts) low frequency components from the power spectrum of the second sound information. The low-frequency component acquired by the low-frequency acquisition unit 24a is referred to as "first low-frequency component". The low-frequency component acquired by the low-frequency acquisition unit 24b is called "second low-frequency component".

The correlation coefficient calculator 25 calculates the correlation coefficient using the first low frequency component, the second low frequency component, and the following equation.

where “r” is the correlation coefficient, “x _i ” is the i th data value of the first low frequency component, and “y _i ” is the i th data value of the second low frequency component. , "n" is the total number of data contained in the first and second low frequency components. " _x -bar" is the mean value of the first low-frequency component, "y-bar" is the mean value of the second low-frequency component, "sx" is the standard deviation of the first low-frequency component, and "s _y " is the standard deviation of the second low frequency component and " _sxy " is the covariance of the first and second low frequency components.

When the body sound detection device 10 is in proper contact with the subject 1 , for example, heart sounds (that is, body sounds) of the subject 1 are transmitted to both the first sensor 11 and the second sensor 12 . Here, heart sounds mainly consist of low-frequency components of several hundred hertz or less. Therefore, when the body sound detection device 10 is in proper contact with the subject 1, both the first and second low frequency components contain components derived from heart sounds. As a result, when the body sound detection device 10 is in proper contact with the subject 1, the above correlation coefficient r becomes a relatively large value.

On the other hand, if the body sound detection device 10 is not in proper contact with the subject 1 , for example, heart sounds of the subject 1 are less likely to be transmitted to the first sensor 11 and the second sensor 12 . As a result, each of the first and second low-frequency components derived from heart sounds becomes relatively small. As a result, when the body sound detection device 10 is not in proper contact with the subject 1, the above-described correlation coefficient r becomes a relatively small value.

The threshold processor 26 compares the correlation coefficient r calculated by the correlation coefficient calculator 25 with a predetermined threshold. Here, the "predetermined threshold value" is a value that determines whether the body sound detection device 10 is in proper contact with the subject 1, and is set in advance as a fixed value or as a variable value according to some physical quantity or parameter. . Such a predetermined threshold value may be set based on the relationship obtained by obtaining, for example, the relationship between the degree of contact of the body sound detection device 10 with the subject 1 and the correlation coefficient r through experiments or simulations. .

The threshold processing unit 26 sends, to the detection unit 27, information indicating the magnitude relationship between the correlation coefficient r and the predetermined threshold, for example. The detection unit 27 determines that the body sound detection device 10 is not in proper contact with the subject 1 when the correlation coefficient r is smaller than a predetermined threshold. That is, it is determined that the body sound detection device 10 has not correctly detected the body sound of the subject 1 . Thereby, the detection unit 27 detects an inappropriate contact state of the body sound detection device 10 . In this case, the detection unit 27 emits a warning sound or displays a warning message, for example. Note that the detection unit 27 does not need to perform any special operation when the correlation coefficient r is greater than the predetermined threshold.

The operation of the determination device 20 will be explained with reference to the flowchart of FIG. In the process of step S101 in FIG. 2, the acquisition unit 21a acquires the first sound information acquired by the first sensor 11, and the acquisition unit 21b acquires the second sound information acquired by the second sensor 12. . In the processing of step S102, the frequency conversion unit 22a performs frequency conversion processing on the first sound information, and the frequency conversion unit 22b performs frequency conversion processing on the second sound information.

In the processing of step S103, the power conversion unit 23a performs power conversion processing on the frequency-converted first sound information, and the power conversion unit 23b performs power conversion on the frequency-converted second sound information. process. In the processing of step S104, the low frequency acquisition unit 24a acquires (extracts) the first low frequency component described above, and the low frequency acquisition unit 24b acquires (extracts) the second low frequency component described above.

In the process of step S105, the correlation coefficient calculator 25 calculates the correlation coefficient r. In the process of step S<b>106 , the threshold processing unit 26 sends information indicating the magnitude relationship between the correlation coefficient r and the predetermined threshold to the detection unit 27 . In the process of step S107, when the correlation coefficient r is smaller than the predetermined threshold, the detection unit 27 determines that the body sound detection device 10 is not in proper contact with the subject 1. That is, the detection unit 27 determines that the body sound detection device 10 does not correctly detect the body sounds of the subject 1 . At this time, since the detection unit 27 detects an inappropriate contact state of the body sound detection device 10 (step S107: Yes), for example, it emits a warning sound or displays a warning message (step S108).

In the processing of step S107, when the correlation coefficient r is larger than the predetermined threshold, the detection unit 27 determines that the body sound detection device 10 is in proper contact with the subject 1. That is, the detection unit 27 determines that the body sound detection device 10 correctly detects body sounds of the subject 1 . In this case, since an inappropriate contact state of body sound detection device 10 is not detected (step S107: No), the operation shown in FIG. 2 ends. Note that the operation shown in FIG. 2 is repeated at a predetermined cycle.

In the present embodiment, the "subject 1" corresponds to an example of the "subject", the "acquisition units 21a and 21b" correspond to an example of the "acquisition means", and the "low frequency acquisition units 24a and 24b" correspond to the "extraction means". , and the "detection unit 27" corresponds to an example of the "determination unit."

The present invention is not limited to the above-described embodiments, and can be modified as appropriate within the scope not contrary to the gist or idea of the invention that can be read from the scope of claims and the entire specification. A determination method, a computer program, and a recording medium are also included in the technical scope of the present invention.

DESCRIPTION OF SYMBOLS 1... Subject, 10... Body sound detection apparatus, 11... 1st sensor, 12... 2nd sensor, 20... Determination apparatus, 21a, 21b... Acquisition part, 22a, 22b... Frequency conversion part, 23a, 23b... Power conversion part , 24a, 24b ... low frequency acquisition unit, 25 ... correlation coefficient calculation unit, 26 ... threshold value processing unit, 27 ... detection unit

Claims (6)

A first sensor that acquires first sound information including the body sound when detecting body sounds of a target, and a second sensor that is arranged at a position further from the target than the first sensor and includes sounds around the target. A determination device for determining whether a body sound detection device having a second sensor that acquires sound information correctly detects the body sound,
acquisition means for acquiring the first sound information and the second sound information;
an extracting means for extracting a first low-frequency component, which is a low-frequency component contained in the first sound information, and extracting a second low-frequency component, which is a low-frequency component contained in the second sound information;
determination means for determining whether or not the body sound detection device correctly detects the body sound based on a comparison result between the first low frequency component and the second low frequency component;
A determination device comprising: The determining means calculates a correlation coefficient between the first low frequency component and the second low frequency component as the comparison result,
The determination means determines that the body sound detection device does not correctly detect the body sound when the correlation coefficient is smaller than a predetermined threshold, and the body sound when the correlation coefficient is greater than the predetermined threshold. The determination device according to claim 1, wherein it is determined that the detection device correctly detects the body sound. A first sensor that acquires first sound information including the body sound when detecting body sounds of a target, and a second sensor that is arranged at a position further from the target than the first sensor and includes sounds around the target. A determination method for determining whether a body sound detection device having a second sensor that acquires sound information correctly detects the body sound, comprising:
an acquisition step of acquiring the first sound information and the second sound information;
an extracting step of extracting a first low-frequency component, which is a low-frequency component contained in the first sound information, and extracting a second low-frequency component, which is a low-frequency component contained in the second sound information;
a determination step of determining whether or not the body sound detection device correctly detects the body sound based on a comparison result between the first low frequency component and the second low frequency component;
A determination method comprising: The determining step includes a calculating step of calculating a correlation coefficient between the first low frequency component and the second low frequency component as the comparison result,
In the determining step, it is determined that the body sound detection device does not correctly detect the body sound when the correlation coefficient is smaller than a predetermined threshold, and the body sound when the correlation coefficient is greater than the predetermined threshold. 4. The determination method according to claim 3, wherein it is determined that the detection device correctly detects the body sound. A first sensor that acquires first sound information including the body sound when detecting body sounds of a target, and a second sensor that is arranged at a position further from the target than the first sensor and includes sounds around the target. a computer of a determination device for determining whether a body sound detection device having a second sensor for acquiring sound information correctly detects the body sound,
acquisition means for acquiring the first sound information and the second sound information;
an extracting means for extracting a first low-frequency component, which is a low-frequency component contained in the first sound information, and extracting a second low-frequency component, which is a low-frequency component contained in the second sound information;
determination means for determining whether or not the body sound detection device correctly detects the body sound based on a comparison result between the first low frequency component and the second low frequency component;
A computer program characterized by functioning as 6. A recording medium on which the computer program according to claim 5 is recorded.

Images