Breath rate and hear rate calibration system and method based on RADAR signal using Attention Network

Abstract

A non-contact RADAR signal-based respiratory rate and heart rate correction system utilizing an Attention Network is disclosed. The non-contact RADAR signal-based respiratory rate and heart rate correction system utilizing the Attention Network may comprise a Frequency Modulated Continuous Wave (FMCW) radar sensor that generates a biosignal containing a patient's respiratory information and heart rate information in a non-contact manner, an Attention Network that generates a correction biosignal by removing noise from the biosignal and selecting respiratory-related patterns and heart rate-related patterns, and a signal processing module that calculates the respiratory rate and heart rate by analyzing the correction biosignal.

Description

Technology Field

[0001] The present invention relates to an absorption and heart rate correction system, and more specifically, to a non-contact RADAR signal-based respiratory rate and heart rate correction system utilizing an Attention Network that can significantly reduce measurement errors by removing noise from non-contact RADAR signals measured by FMCW radar and correcting respiratory rate and heart rate. Background Technology

[0002] Conventional patient monitoring systems primarily measured patients' vital signs using contact sensors. However, this method not only caused discomfort to patients but also posed a risk of skin infection due to the sensors' contact with the skin. To address these issues, non-contact single sensors, such as cameras and radar, were introduced; however, these sensors were vulnerable to external noise and lacked accuracy, limiting their practical clinical application. In particular, for measurements such as heart rate and respiratory rate, the accuracy dropped significantly when using non-contact sensors, making them difficult to use in applications like telemedicine. For instance, when using FMCW radar to measure a patient's respiratory rate and heart rate non-contactually, noise caused low measurement precision, making it difficult to obtain accurate readings. The problem to be solved

[0003] The problem that the present invention aims to solve is to provide a non-contact RADAR signal-based respiratory rate and heart rate correction system utilizing an Attention Network that can significantly reduce measurement errors by removing noise from non-contact RADAR signals measured by MCW radar, etc., and correcting respiratory rate and heart rate. means of solving the problem

[0004] A non-contact RADAR signal-based respiratory rate and heart rate correction system utilizing an Attention Network according to an embodiment of the present invention for achieving the above objective may comprise a Frequency Modulated Continuous Wave (FMCW) radar sensor that generates a biosignal including a patient's respiratory information and heart rate information in a non-contact manner, an Attention Network that generates a correction biosignal by removing noise from the biosignal and selecting respiratory-related patterns and heart rate-related patterns, and a signal processing module that calculates the respiratory rate and heart rate by analyzing the correction biosignal. Effects of the invention

[0005] A non-contact RADAR signal-based respiratory rate and heart rate correction system utilizing an Attention Network according to one embodiment of the technical concept of the present invention has the advantage of enabling more precise measurements by correcting heart rate and respiratory rate through the Attention Network by precisely processing meaningful parts of the signal or removing noise from respiratory and heart rate information generated by an FMCW radar sensor. Experimentally, it was confirmed that when the non-contact RADAR signal-based respiratory rate and heart rate correction system utilizing an Attention Network according to one embodiment of the technical concept of the present invention is applied, the measurement error of heart rate and respiratory rate is reduced from the existing 20% ​​to less than 10% compared to the conventional case, thus having the advantage of significantly increasing data reliability. In addition, the non-contact RADAR signal-based respiratory rate and heart rate correction system utilizing an Attention Network according to one embodiment of the technical concept of the present invention has the advantage of enhancing patient convenience through non-contact measurement and enabling real-time monitoring in the medical field. Brief explanation of the drawing

[0006] A brief description of each drawing is provided to help to more fully understand the drawings cited in the detailed description of the present invention. FIG. 1 is a block diagram of a non-contact RADAR signal-based respiratory rate and heart rate correction system (100) utilizing an Attention Network according to one embodiment of the technical concept of the present invention. Specific details for implementing the invention

[0007] In order to fully understand the present invention, the operational advantages of the present invention, and the objectives achieved by the implementation of the present invention, reference should be made to the accompanying drawings illustrating preferred embodiments of the present invention and the contents described therein.

[0008] The present invention will be described in detail below by explaining preferred embodiments of the invention with reference to the attached drawings. Identical reference numerals in each drawing indicate identical components.

[0009] FIG. 1 is a block diagram of a non-contact RADAR signal-based respiratory rate and heart rate correction system (100) utilizing an Attention Network according to one embodiment of the technical concept of the present invention.

[0010] Referring to FIG. 1, a non-contact RADAR signal-based respiratory rate and heart rate correction system (100) utilizing an Attention Network may be equipped with a Frequency Modulated Continuous Wave (FMCW) radar sensor (110), an Attention Network (120), and a signal processing module (130).

[0011] The FMCW radar sensor (110) can generate a biosignal including the patient's respiration information and heart rate information in a non-contact manner. The biosignal may include the patient's respiration rate information, heart rate information, etc., measured in a non-contact manner. However, if the present invention can generate a biosignal including the patient's respiration information and heart rate information in a non-contact manner, a different type of sensor may be used instead of the FMCW radar sensor.

[0012] The Attention Network (120) receives the biosignal generated by the FMCW radar sensor (110), removes noise from the biosignal, and selects breathing-related patterns and heart rate-related patterns to generate a corrected biosignal, and can operate based on artificial intelligence. That is, the Attention Network (120) can extract meaningful patterns related to breathing and heart rate from the biosignal and remove irrelevant data or noise. Through such operation, the corrected biosignal from which noise has been removed from the biosignal may be a signal in which only breathing-related patterns and heart rate-related patterns are selected. As described above, if it is possible to generate a corrected biosignal by removing noise from the biosignal and selecting only breathing-related patterns and heart rate-related patterns, various other artificial intelligence modules, in addition to the Attention Network, may be applied.

[0013] The signal processing module (130) receives the corrected biosignal from the Attention Network (120), analyzes it, and can calculate the patient's respiratory rate and heart rate from the corrected biosignal. Since the corrected biosignal is a signal in which noise is removed and respiratory-related patterns and heart rate-related patterns are emphasized, the patient's respiratory rate and heart rate calculated from such corrected biosignal have high accuracy.

[0014] As described above, the best embodiments have been disclosed in the drawings and specification. Specific terms have been used herein, but they are used only for the purpose of describing the invention and are not intended to limit the meaning or the scope of the invention as described in the claims. Therefore, those skilled in the art will understand that various modifications and equivalent alternative embodiments are possible therefrom. Accordingly, the true technical scope of protection of the invention should be determined by the technical spirit of the appended claims.

Claims

Claim 1 A non-contact RADAR signal-based respiratory rate and heart rate correction system utilizing an Attention Network, characterized by comprising: a Frequency Modulated Continuous Wave (FMCW) radar sensor that generates a biosignal including a patient's respiratory information and heart rate information in a non-contact manner; an Attention Network that generates a corrected biosignal by removing noise from the biosignal and selecting respiratory-related patterns and heart rate-related patterns; and a signal processing module that calculates the respiratory rate and heart rate by analyzing the corrected biosignal.

Images