Non-contact breathing guidance system for facilitating real-time feedback

Abstract

Systems and methods are provided for closed-loop, non-contact respiratory guidance that provide quantified alignment feedback data in real time. In one embodiment, the computer-implemented method may include receiving, by a computing system operably coupled to one or more processors, input data including respiratory data indicative of an entity's respiration. The computer-implemented method may include converting, by the computing system, the respiratory data to an entity respiratory signal such that the entity respiratory signal tracks the entity's respiration in real time. The computer-implemented method may include comparing, by the computing system, the entity respiratory signal to a suggested respiratory signal indicative of a suggested respiration. The computer-implemented method may include providing, by the computing system, alignment feedback data to the entity in real time based at least in part on the entity's respiration. The alignment feedback data may be indicative of an alignment between the entity respiratory signal and the suggested respiratory signal.

Description

Technical Field

[0001] The present disclosure generally relates to a guided breathing system. More particularly, the present disclosure relates to a closed-loop non-contact guided breathing system that provides real-time feedback.

Background Art

[0002] A guided breathing system provides a breathing exercise that may include a proposed breathing pattern for an entity to attempt to mimic. For example, such a system can monitor an entity's breathing, output a proposed breathing pattern, and / or provide feedback regarding the entity's breathing. The feedback can include, for example, biometric feedback that may indicate the entity's breathing rate, heart rate, and / or movement.

Summary of the Invention

[0003] Aspects and advantages of embodiments of the present disclosure are partially shown in the following description, or can be learned from the description, or can be learned through the practice of the embodiments.

[0004] According to an exemplary embodiment, a computing system can include one or more processors and one or more non-transitory computer-readable storage media that store instructions that, when executed by the one or more processors, cause the computing system to perform operations. The operations can include receiving input data that includes breathing data indicative of an entity's breathing, converting the breathing data into an entity breathing signal such that the entity breathing signal tracks the entity's breathing in real time, comparing the entity breathing signal to a proposed breathing signal indicative of a proposed breathing, and / or providing alignment feedback data to the entity in real time based at least in part on the entity's breathing. The alignment feedback data can indicate an alignment of the entity breathing signal and the proposed breathing signal.

[0005] According to another exemplary embodiment, a computer implementation may include: receiving input data, including respiration data indicating the respiration of an entity, by a computing system operably coupled to one or more processors; converting the respiration data into an entity respiration signal by the computing system so that the entity respiration signal tracks the entity's respiration in real time; comparing the entity respiration signal with a proposed respiration signal indicating proposed respiration; and / or providing the entity with alignment feedback data in real time, at least in part, based on the entity's respiration. The alignment feedback data may indicate the alignment between the entity respiration signal and the proposed respiration signal.

[0006] According to another exemplary embodiment, the computing system may include one or more processors and one or more non-temporary computer-readable storage media that, when executed by one or more processors, store instructions causing the computing system to perform actions. The operation may include receiving a continuous chirp-radar signal containing respiration data indicating the respiration of an entity. The continuous chirp-radar signal may include a plurality of chirps. The operation may further include converting the continuous chirp-radar signal into an entity respiration amplitude signal so that the entity respiration amplitude signal tracks the respiration of the entity in real time. The signal amplitude of the entity respiration amplitude signal may be generated when each of the plurality of chirps is received. The operation may further include comparing the entity respiration amplitude signal with a proposed respiration signal indicating a proposed respiration. The operation may further include providing the entity with alignment feedback data in real time, at least in part, based on the entity's respiration. The alignment feedback data may indicate the alignment between the entity respiration amplitude signal and the proposed respiration signal.

[0007] These and other features, aspects and advantages of the various embodiments of this disclosure will be better understood by referring to the following description and the appended claims. The appended drawings incorporated herein and forming part of this specification illustrate exemplary embodiments of this disclosure and, together with modes for carrying out the invention, illustrate the relevant principles.

[0008] A detailed discussion of embodiments for those skilled in the art is given herein with reference to the accompanying drawings. [Brief explanation of the drawing]

[0009] [Figure 1] A data flow diagram of an exemplary, non-limiting data flow process according to one or more exemplary embodiments of the present disclosure is shown. [Figure 2] A data flow diagram of an exemplary, non-limiting data flow process according to one or more exemplary embodiments of the present disclosure is shown. [Figure 3] A data flow diagram of an exemplary, non-limiting data flow process according to one or more exemplary embodiments of the present disclosure is shown. [Figure 4] A data flow diagram of an exemplary, non-limiting data flow process according to one or more exemplary embodiments of the present disclosure is shown. [Figure 5A] A diagram illustrating an exemplary, non-limiting signal evaluation process according to one or more exemplary embodiments of the present disclosure is shown. [Figure 5B] A diagram illustrating an exemplary, non-limiting signal evaluation process according to one or more exemplary embodiments of the present disclosure is shown. [Figure 6] The following diagrams illustrate exemplary, non-limiting alignment feedback data according to one or more exemplary embodiments of the present disclosure. [Figure 7] A block diagram of an exemplary, non-limiting computing system according to one or more exemplary embodiments of the present disclosure is shown. [Figure 8] A flowchart illustrating an exemplary, non-limiting computerized implementation according to one or more exemplary embodiments of the present disclosure is shown. [Figure 9] A flowchart illustrating an exemplary, non-limiting computerized implementation according to one or more exemplary embodiments of the present disclosure is shown. [Figure 10A] The following diagrams illustrate exemplary, non-limiting alignment feedback data according to one or more exemplary embodiments of the present disclosure. [Figure 10B] The following diagrams illustrate exemplary, non-limiting alignment feedback data according to one or more exemplary embodiments of the present disclosure. [Modes for carrying out the invention]

[0010] Embodiments of the present disclosure are shown here in detail, with one or more embodiments illustrated in the drawings. Each embodiment is provided for illustrative purposes of the present disclosure and is not intended to limit the present disclosure. In fact, it will be apparent to those skilled in the art that various modifications and variations can be made in the present disclosure without departing from the scope or spirit of the present disclosure. For example, features illustrated or described as part of one embodiment can be used in conjunction with another embodiment to create yet another embodiment. Accordingly, the present invention is intended to cover modifications and variations that fall within the scope of the appended claims and their equivalents.

[0011] Where used herein, the term “entity” means a human being, a user, an end user, a consumer, and / or another type of entity that can carry out one or more embodiments of the Disclosure, as described herein, shown in the accompanying drawings, and / or included in the accompanying claims. Where used herein, the terms “or” and “and / or” are intended to be generally inclusive, that is (i.e.), “A or B” or “A and / or B” are intended to mean “A or B or both.” Where used herein, terms such as “first,” “second,” and “third” may be used interchangeably to distinguish one component or entity from another, and are not intended to imply the location, functionality, or importance of any individual component or entity. Where used herein, when the terms “about” and / or “approximately” are used in conjunction with a number, they mean within 10 percent of the number indicated. Where used herein, the terms “couple,” “couples,” “coupled,” and / or “coupling” refer to chemical bonds (e.g., chemical bonds), communicative bonds, electrical bonds and / or electromagnetic bonds (e.g., capacitive bonds, inductive bonds, direct bonds and / or linkage bonds, etc.), mechanical bonds, operative bonds, optical bonds, and / or physical bonds.

[0012] Illustrative aspects of this disclosure relate to a closed-loop, non-contact breathing guidance system that can provide real-time, quantified alignment feedback to an entity (e.g., a human) attempting to mimic a proposed breathing pattern (e.g., a proposed breathing pattern) recommended by the system. The quantified alignment feedback may indicate the extent to which the entity's breathing aligns with the proposed breathing. Where used herein, a “closed-loop” breathing guidance system can describe a system that, for example, receives first input data indicating the entity’s breathing at a first time (T1), provides the entity with a first proposed breathing pattern at least in part based on the first input data, and receives second input data indicating the entity’s breathing at a second time (T2) after the first time (T1) (e.g., a subsequent time), while the entity is attempting to mimic (e.g., simulate) the first proposed breathing pattern, and / or provides the entity with a second proposed breathing pattern at least in part based on the second input data. In some embodiments, such a closed-loop process can continue indefinitely while the entity is practicing the technology disclosed in one or more embodiments described herein.

[0013] According to one or more exemplary embodiments of the present disclosure, the computing systems described herein can facilitate non-contact breathing guidance with real-time quantified alignment feedback. For example, to facilitate such non-contact breathing guidance with real-time quantified alignment feedback, the computing systems according to the exemplary embodiments described herein can perform operations including, but not limited to, receiving input data which may include and / or constitute breathing data indicating the breathing of an entity; converting the breathing data into an entity breathing signal so that the entity breathing signal tracks the breathing of the entity in real time; comparing the entity breathing signal with a proposed breathing signal indicating a proposed breathing; and / or providing the entity with alignment feedback data in real time based at least in part on the breathing of the entity. In some embodiments, the alignment feedback data may indicate the alignment between the entity breathing signal and the proposed breathing signal. For example, in the exemplary embodiments described herein, as will be described in more detail below, the alignment feedback data may be generated based on comparing the entity breathing signal with a proposed breathing signal which may indicate a proposed breathing. For example, in some embodiments, the alignment feedback data may be associated with the difference between the entity breathing signal and the proposed breathing signal. In at least one embodiment, alignment feedback data may be associated, for example, with the difference in amplitude, frequency, and / or phase between the entity breathing signal and the proposed breathing signal.

[0014] To perform the operations described above and / or other operations described herein, the computing system according to the exemplary embodiments of this disclosure may include one or more processors and / or one or more non-temporary computer-readable storage media, which may be coupled (e.g., communicatively, operationally, etc.) and / or associated. In these exemplary embodiments or other exemplary embodiments, one or more non-temporary computer-readable storage media may, when executed by one or more processors, store instructions that cause the computing system (e.g., via one or more processors) to perform the operations described above and / or other operations described herein to facilitate non-contact breathing guidance with real-time quantified alignment feedback.

[0015] According to one or more exemplary embodiments of the present disclosure, a computing system may receive input data which may include and / or constitute respiration data that may indicate the respiration of an entity (for example, which may indicate the current real-time respiration pattern of an entity). In at least one embodiment, such input data and / or respiration data may include and / or constitute, for example, radar data indicating the respiration of an entity, high-frequency radar data indicating the respiration of an entity, sonar data indicating the respiration of an entity, acoustic data indicating the respiration of an entity, video data indicating the respiration of an entity, time-series data indicating the respiration of an entity, and / or other input data and / or respiration data which may indicate the respiration of an entity.

[0016] In some embodiments, the computing system may receive a combination of different types of input data, which may constitute a specific type of and / or form a specific type of breathing data that may indicate the breathing of an entity. For example, in these embodiments or other embodiments, the computing system may receive radar data indicating the breathing of an entity, sonar data indicating the breathing of an entity, and video data indicating the breathing of an entity.

[0017] In one embodiment, the computing system may receive input data in the form of a continuous chirp-radar signal (e.g., a frequency-modulated continuous wave (FMCW) radar signal) which may include and / or constitute respiration data that may indicate the respiration of an entity. In this embodiment or another embodiment, the continuous chirp-radar signal may include and / or constitute a plurality of chirps.

[0018] In one or more exemplary embodiments, a computing system may receive the input data and / or respiratory data described above from one or more non-contact sources and / or devices that may be included in, coupled to, and / or associated with (e.g., communicatively, operatively, etc.) the computing system. In at least one embodiment, such one or more non-contact sources and / or devices may capture, collect, and / or otherwise obtain such input data and / or respiratory data without physically engaging the entity (e.g., without contacting the entity). For example, in one or more embodiments, the computing system may include, but is not limited to, a radar device (e.g., a high-frequency radar, a real-time motion tracking radar, etc.), a sonar device, a camera device, an audio device (e.g., a microphone, etc.), and / or another non-contact source and / or device that may capture, collect, and / or otherwise obtain such input data and / or respiratory data without physically engaging the entity. In at least one embodiment, the computing system may receive the continuous chirp radar signal described above from a high-frequency radar (e.g., an FMCW radar) and / or a real-time motion tracking radar.

[0019] In at least one embodiment of the present disclosure, based at least in part on (e.g., in response to) receiving the above-described input data and / or breath data, the computing system may convert the breath data into an entity breath signal so that the entity breath signal can track the entity's breathing in real time. For example, in some embodiments, upon receiving the input data and / or breath data (e.g., immediately upon receiving the input data and / or breath data, in real time), the computing system may convert the breath data into an entity breath amplitude signal so that the entity breath amplitude signal can track (e.g., mimic, simulate, replicate, etc.) the entity's breathing in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) and / or synchronize with the entity's breathing by implementing (e.g., running, operating, etc.) a tracking algorithm such as a phase tracking algorithm having relatively low latency.

[0020] Where used herein, the “relatively low latency” of the phase tracking algorithm described above may mean latency that is lower (e.g., less) than the latency of other phase tracking algorithms, latency that is defined as low according to standards and / or protocols relevant to the art of signal processing, latency that is considered low by those skilled in the art of signal processing, latency that is not perceptible to entities as defined herein (e.g., not perceptible to humans), latency that is low enough to allow entities as defined herein (e.g., humans) to perceive the conversion of the respiratory data described above to entity respiratory signals as occurring in real time (e.g., live, instantaneously, etc.), and / or latency that is shorter than a defined time (e.g., less than about 5 seconds, less than about 1 second, less than about 500 milliseconds (ms), less than about 100 ms, less than about 10 ms, etc.).

[0021] In one or more embodiments, where a computing system receives input data and / or respiratory data in the form of the continuous chirped radar signal described above (e.g., in the form of an FMCW radar signal that can be provided by, for example, a high-frequency radar, an FMCW radar, a real-time motion tracking radar, etc.), the computing system can convert the continuous chirped radar signal into an entity respiratory amplitude signal such that the entity respiratory amplitude signal can track the respiration of the entity in real time. In these one or more embodiments, the signal amplitude of the entity respiratory amplitude signal can be generated (e.g., by the computing system) upon reception of each of a plurality of chirps. For example, in these embodiments or other embodiments, upon receiving the continuous chirped radar signal (e.g., immediately upon receiving the continuous chirped radar signal, in real time), the computing system implements (e.g., executes, operates, etc.) the above-described phase tracking algorithm with relatively low latency so that the entity respiratory amplitude signal can track (e.g., mimic, simulate, replicate, etc.) the respiration of the entity in real time (e.g., live, in parallel, and / or simultaneously with the respiration of the entity) and / or be synchronized with the respiration of the entity, and can convert the continuous chirped radar signal into an entity respiratory amplitude signal.

[0022] To facilitate the above-described conversion of a continuous chirp-radar signal to such an entity breathing amplitude signal according to one or more embodiments, upon receiving multiple chirps of the continuous chirp-radar signal (e.g., immediately upon receiving multiple chirps of the continuous chirp-radar signal, in real time), the computing system may implement the above-described phase-tracking algorithm with relatively low latency (e.g., run, operate, etc.) to generate the signal amplitude of the entity breathing amplitude signal. For example, in one embodiment, upon receiving a new chirp among the multiple chirps (e.g., immediately upon receiving a chirp that has not been previously received, in real time), the computing system may implement the phase-tracking algorithm with relatively low latency to generate a new local amplitude of the entity breathing amplitude signal (e.g., a local amplitude that has not been previously generated). In this embodiment, the new local amplitude may correspond to a new chirp. In this way, the computing system according to the exemplary embodiment can convert each chirp of a plurality of chirps, and thus the continuous chirp player signal, into an entity breathing amplitude signal that can track (e.g., mimic, simulate, replicate, etc.) the breathing of an entity in real time (e.g., live, in parallel, and / or simultaneously with the breathing of the entity) and / or synchronize with the breathing of the entity.

[0023] To further facilitate the above-described conversion of a continuous char plater signal to such entity breathing amplitude signals according to at least one embodiment of the present disclosure, upon receiving a continuous char plater signal (e.g., immediately upon receiving the continuous char plater signal, in real time), the computing system may perform one or more of the following operations by implementing the above-described phase tracking algorithm having relatively low latency (e.g., run, operate, etc.):

[0024] In one embodiment, the computing system may remove noise data from a continuous char plater signal by implementing a phase-tracking algorithm with relatively low latency (e.g., using an exponential filter and / or exponential smoothing process). In this embodiment, the noise data may and / or consist of data that can indicate at least one motion corresponding to one or more second entities (e.g., the motion of an object and / or another person).

[0025] In one embodiment, a computing system may implement a relatively low-latency phase-tracking algorithm to map a range that may be associated with a continuous char radar signal (e.g., using an exponential filter and / or exponential smoothing process). In this embodiment, the range may include and / or constitute at least a portion of the entity's respiratory data. In some embodiments, the range may include and / or constitute a spatial range that may be associated with and / or adjacent to the entity. For example, in some embodiments, the range may be defined as the distance between the entity and a radar device that captures, collects, and / or otherwise acquires the entity's respiratory data. For example, in at least one embodiment, the range may be defined, for example, as the distance from the entity's chest to the radar device. In one embodiment, the range may be defined as a distance of about 1 meter (m) between the entity's chest and the radar device. In at least one embodiment, the range may include one or more range bins that may include and / or constitute at least a portion of the entity's respiratory data. For example, in one embodiment, one or more range bins may be defined as distance intervals along the range described above. For example, in this embodiment or another embodiment, each of one or more range bins may be defined as a distance of about 3 centimeters (cm) along a 1-meter range between the chest of the entity and the radar.

[0026] In one embodiment, the computing system may normalize the ranges to a range probability map that may and / or constitute a plurality of range bins (e.g., one or more range bins as described above) by implementing a relatively low-latency phase-tracking algorithm. In this embodiment, each of the plurality of range bins may and / or constitute at least a portion of the respiratory data. As used herein, the “range probability map” may constitute a vector (e.g., range_map / sum(range_map)) obtained by dividing each range bin value by the sum of all range bin values.

[0027] In one embodiment, a computing system may implement a phase-tracking algorithm with relatively low latency to apply one or more inertia functions to a range probability map and / or range bins to determine a center of mass that can correspond to the range probability map and / or range bins. In an embodiment, the computing system may implement a phase-tracking algorithm to apply inertia as an element-wise low-pass filter. In this embodiment or another embodiment, the range probability map is updated over time and should not be changed frequently. In this embodiment or another embodiment, the effect of inertia can eliminate sudden motion artifacts. In this embodiment or another embodiment, the center of mass may constitute the expected value of the probability map after inertia application. For example, the center of mass may describe and / or constitute the range with the highest probability of accurately describing the chest region of the entity. In some embodiments, the center of mass may constitute the range bin with the highest probability (e.g., compared to all other range bins) of accurately describing the chest region of the entity and / or the chest motion of the entity during respiration. In at least one embodiment, the computing system may implement a phase tracking algorithm to "lock" the phase values ​​of the center of mass (e.g., "lock" the phase values ​​of a particular range bin that has the highest probability of accurately describing the thoracic region of the entity and / or the thoracic motion of the entity during respiration).

[0028] In one embodiment, the computing system may perform a relatively low-latency phase-tracking algorithm to extract phase data that can correspond to the center of mass. In this embodiment, the phase data may represent a wrapped phase signal that can correspond to the center of mass. Note that in some embodiments, the original range map may be computed from the continuous char plater signal by obtaining the absolute components of the Fast Fourier Transform (FFT). In some embodiments, the phase components of the FFT may be set aside (e.g., held, saved, stored). In some embodiments, the dimensions of the range map may be the same as the dimensions of the phase map, since they are derived from the same FFT as the phase map. In some embodiments, to extract phase data that can correspond to the center of mass, the computing system may perform a relatively low-latency phase-tracking algorithm to extract (e.g., read out) specific phase values ​​in the corresponding highest-probability user chest range bins identified in the previous steps described above.

[0029] In one embodiment, the computing system may implement a relatively low-latency phase-tracking algorithm to perform a signal-phase unwrapping process on the phase data and / or wrapped phase signal to obtain a continuous phase signal (e.g., an unwrapped phase signal that can correspond to the center of mass) that can correspond to the center of mass. In some embodiments, when calculating the phase for each chirp, the phase value is between negative π (-π or -¶) and positive π (+π or +¶). In some embodiments, the phase value fluctuates over time within this range (e.g., between -π (-¶) and +π (+¶)) based on the entity's breathing frequency. However, in some embodiments, for example, there may be a “wrapping” effect when the phase value is π-0.1 (¶-0.1), and as the entity breathes deeply and the phase value increases, the phase value should bounce back to -π (-¶) because it cannot represent a value greater than +π (+¶). Therefore, in some embodiments, the "smoothness" of the entity's breathing can be utilized (e.g., exploited), and whenever there is this abrupt bounce from -π(-¶) to π(¶) or from π(¶) to -π(-¶), it can be interpreted as wrapping behavior, and the ends can be "stitched" to reconstruct a smooth breathing signal. For example, in at least one embodiment, a phase tracking algorithm with relatively low latency can perform the above signal phase unwrapping process on a one-dimensional (1D) phase time series that can be obtained from the previous steps described above, by implementing a phase unwrapping algorithm such as Itoh's phase unwrapping algorithm.

[0030] In one embodiment, the computing system may implement a relatively low-latency phase-tracking algorithm to apply a filter to a continuous phase signal to obtain an entity respiration amplitude signal. In this embodiment, the filter may be operable to remove data that may indicate defined entity movements that may be associated with the entity's respiration (e.g., subtle movements the entity makes during inhalation and / or exhalation).

[0031] According to at least one embodiment described herein, based at least in part on (e.g., in response to) converting the above-described respiration data and / or continuous char plater signals into the above-described entity respiration signals and / or entity respiration amplitude signals, the computing system may compare the entity respiration signals and / or entity respiration amplitude signals with a proposed respiration signal that may represent a proposed respiration (e.g., a proposed respiration pattern that may be defined and / or recommended by the computing system). For example, in one exemplary embodiment, the computing system may compare the entity respiration signals and / or entity respiration amplitude signals with such a proposed respiration signal to determine the extent to which the entity respiration signals and / or entity respiration amplitude signals align with the proposed respiration signal. In one exemplary embodiment, the computing system may compare the entity respiration signals and / or entity respiration amplitude signals with a proposed respiration signal that may be generated by the computing system. In this exemplary embodiment or another exemplary embodiment, such a proposed respiration signal may represent a proposed respiration (e.g., a proposed respiration pattern) that may be defined and / or recommended by the computing system. In this exemplary embodiment or another exemplary embodiment, the computing system may define and / or recommend such proposed respiration and / or generate such proposed respiration signals based at least in part on one or more attributes and / or biometrics that may correspond to an entity (e.g., the entity's age, weight, height, real-time heart rate and / or mean heart rate, real-time blood pressure and / or mean blood pressure, etc.).

[0032] To facilitate the above-described comparison between the entity breathing signal and / or entity breathing amplitude signal and the proposed breathing signal, and / or to determine the extent to which the entity breathing signal and / or entity breathing amplitude signal align with the proposed breathing signal, the computing system according to the exemplary embodiment may implement an alignment algorithm (e.g., can be executed, can operate, etc.). For example, in at least one embodiment, the computing system may implement an alignment algorithm to which a spectral similarity process may be applied to compare the entity breathing signal and / or entity breathing amplitude signal with the proposed breathing signal, and / or to determine the extent to which the entity breathing signal and / or entity breathing amplitude signal align with the proposed breathing signal. In this embodiment, the extent to which the entity breathing signal and / or entity breathing amplitude signal align with the proposed breathing signal may be expressed as an alignment score, which may range, for example, from a value of about zero (0) to a value of about 1. In this embodiment, a value of zero (0) may indicate relatively poor alignment (e.g., non-alignment), and / or a value of 1 may indicate relatively good alignment (e.g., perfect alignment). In this way, the computing system according to the exemplary embodiments described herein can determine an alignment score that can indicate the degree of alignment between the entity respiration signal and / or the entity respiration amplitude signal and the proposed respiration signal.

[0033] Where used herein, in some embodiments, “alignment” between an entity breathing signal (e.g., an entity breathing amplitude signal) and a proposed breathing signal may occur when the entity breathing signal (e.g., an entity breathing amplitude signal) is visually and / or mathematically in phase or nearly in phase with the proposed breathing signal. Where used herein, the “degree” of alignment between an entity breathing signal (e.g., an entity breathing amplitude signal) and a proposed breathing signal may describe, for example, how close (or not) the entity breathing signal (e.g., an entity breathing amplitude signal) is in phase or nearly in phase with the proposed breathing signal, visually and / or mathematically.

[0034] To determine the alignment score described above in accordance with at least one embodiment of the present disclosure, the computing system may perform (e.g., execute, operate, etc.) the alignment algorithm described above to perform one or more of the following operations. For example, in one embodiment, the computing system may perform the alignment algorithm to compute a spectral vector of the respiration data for phase invariance by computed a first spectral vector that may correspond to the entity's respiration data and / or entity respiration signal (e.g., entity respiration amplitude signal), and a second spectral vector that may correspond to proposed respiration data (e.g., data indicating proposed respiration that may be defined and / or recommended by the computing system as described above) and / or a proposed respiration signal; compute a first L2-normalized spectral vector and a second L2-normalized spectral vector, respectively, by applying a normalization function, for example, an L2 normalization function, to the first and second spectral vectors; compute an alignment score of the first and second L2-normalized spectral vectors using a dot product operation; and / or apply a softmax function to the alignment score to improve the dynamic range associated with the alignment score.

[0035] In one or more embodiments, each of the spectral vectors described above may constitute an absolute FFT of a signal (e.g., an absolute FFT value corresponding to a phase signal, an amplitude signal, etc.). For example, in one embodiment, the first spectral vector described above may constitute an absolute FFT (e.g., an absolute FFT value) of the continuous phase signal described above (e.g., an unwrapped phase signal corresponding to a center of mass) that can be obtained using the phase unwrapping algorithm described above (e.g., using Itoh's phase unwrapping algorithm). In at least one embodiment, the L2 normalization function described above may include dividing each element of the spectral vector by the L2 norm (=energy) of the entire vector (e.g., to obtain an L2 normalized vector). In one embodiment, the dot product operation described above may include taking the dot product of two such normalized vectors (e.g., two L2 normalized vectors), which may include taking the element-wise product between the two vectors and summing them all up. In some embodiments, such a dot product is maximized to 1 if the two normalized vectors are exactly the same. For example, a denormalized vector can be expressed as dot(a / ||a||,a / ||a||)=dot(a,a) / ||a||^2=||a||^2 / ||a||^2=1, and the dot product is minimized when the two normalized vectors look different. Thus, in some embodiments, the dot product is a measure of similarity between an entity's breathing (e.g., an entity's breathing pattern) and a proposed breathing (e.g., a proposed breathing pattern). In some exemplary embodiments of this disclosure, the dot product and / or such measure of similarity between an entity's breathing and a proposed breathing is described as the degree to which the entity's breathing aligns with the proposed breathing.

[0036] In one or more embodiments described herein, a computing system may provide an entity with alignment feedback data in real time, at least in part, based on the entity's respiration. In one or more embodiments, the alignment feedback data may indicate the alignment between the entity's respiration signal and / or entity respiration amplitude signal and the proposed respiration signal. For example, in one or more embodiments, at least in part, based on (e.g., in response to) receiving the above-described input data (e.g., a continuous char plater signal), which may include and / or constitute respiration data that may indicate the entity's respiration, the computing system may (e.g., in real time as soon as such input data is received) implement the above-described phase tracking algorithm having relatively low latency to convert the respiration data into an entity respiration signal (e.g., an entity respiration amplitude signal), implement the above-described alignment algorithm to compare the entity respiration signal (e.g., an entity respiration amplitude signal) with the proposed respiration signal and / or determine an alignment score corresponding to such a signal, and / or provide the entity with the alignment score and / or other alignment feedback data in real time (e.g., live, in parallel, and / or concurrently with the entity's respiration) in response to the entity's respiration. In one or more of these embodiments, the computing system may perform such actions in real time while an entity is performing a guided breathing exercise which is defined by the computing system and / or communicated to the entity based on, for example, the proposed breathing described above and / or a proposed breathing signal which may be defined and / or generated by the computing system as described above. For example, in one or more of these embodiments, the computing system may perform such actions in real time while the entity is attempting to align its breathing with the proposed breathing and / or align its entity breathing signal (e.g., an entity breathing amplitude signal) with the proposed breathing signal.

[0037] In additional embodiments and / or alternative embodiments of the present disclosure, a computing system may provide an entity with alignment feedback data that may include and / or constitute alignment visualizations that may include entity breathing signals (e.g., entity breathing amplitude signals) and / or proposed breathing signals. For example, in this additional embodiment and / or alternative embodiment, the computing system may provide an alignment visualization to an entity that may include and / or constitute visualizations of entity breathing signals (e.g., entity breathing amplitude signals) overlaid on and / or adjacent to (e.g., superimposed on and / or adjacent to) the proposed breathing signal. In one embodiment, such alignment visualization may include and / or constitute images (e.g., still images) of entity breathing signals (e.g., entity breathing amplitude signals) overlaid on and / or adjacent to (e.g., superimposed on and / or adjacent to) the proposed breathing signal. In another embodiment, such alignment visualization may include and / or constitute video (e.g., live video, real-time video) of entity breathing signals (e.g., entity breathing amplitude signals) overlaid on and / or adjacent to (e.g., superimposed on and / or adjacent to) the proposed breathing signal.

[0038] In some embodiments, the computing system may provide the entity with one or more other types of alignment feedback data that can indicate the alignment between the entity's breathing signal and the proposed breathing signal. For example, in these or other embodiments, the computing system may provide such alignment feedback data to the entity in the form of, for example, audio data (e.g., digital voice, buzzer, audible alarm, etc.), text data, numerical data, and / or alphanumeric data (e.g., letters, numbers, words, written messages, push notifications, etc.), graphic data (e.g., symbols, signs, icons, emojis, etc.), tactile data (e.g., vibration of a device associated with the entity, such as a smartphone or wearable computing device), visual data (e.g., light having an intensity that correlates with the degree of alignment and / or changes depending on the degree of alignment), and / or other forms of data. In these or other embodiments, the computing system may provide such one or more other types of alignment feedback data to the entity in real time in response to the entity's breathing (e.g., live, in parallel, and / or simultaneously with the entity's breathing).

[0039] In at least one embodiment, the computing system may provide the alignment feedback data described above to an entity via a network such as a local area network (LAN), a wireless and / or wired network, a wide area network (WAN), a personal area network (PAN), a wireless personal area network (WPAN), and / or another network. In this or another embodiment, the computing system may provide the alignment feedback data to an entity via, for example, a monitor and / or screen that may be coupled to, included in, and / or otherwise associated with the computing system, a monitor and / or screen that may be coupled to, included in, and / or otherwise associated with a computing device (e.g., a wearable computing device, a computer, a smartphone, a tablet, etc.) that may be associated with an entity.

[0040] Exemplary embodiments of this disclosure provide several technical effects, advantages, and / or improvements in computing technology. For example, by facilitating non-contact respiratory guidance with real-time quantified alignment feedback as stipulated in the exemplary embodiments of this disclosure, the computing system can thereby eliminate one or more contact-based components (e.g., devices, hardware, software, etc.) and / or processes (e.g., workflows) used to acquire, capture, and / or collect entity respiratory data in other ways. In another example, by implementing the above-described phase-tracking algorithm having relatively low latency (e.g., compared to other phase-tracking algorithms) and converting the respiratory data into entity respiratory signals (e.g., entity respiratory amplitude signals) as described above, the computing system according to the exemplary embodiments can thereby improve the processing speed, performance, and / or efficiency of one or more processors capable of performing such conversion. In this embodiment, by improving the processing speed, performance, and / or efficiency of such one or more processors, the computing system can thereby reduce the computational costs associated with such one or more processors. In another example, by comparing an entity respiration signal (e.g., an entity respiration amplitude signal) with a proposed respiration signal in real time and / or providing the entity with alignment feedback in real time according to the exemplary embodiments of the present disclosure, the computing system can thereby eliminate the use of one or more memory devices for storing the aforementioned input data and / or respiration data that may indicate the entity's respiration. In this embodiment, by eliminating the use of one or more memory devices for storing such data, the computing system according to the exemplary embodiments can thereby increase the available storage capacity of such one or more memory devices and / or reduce the operating costs associated with such one or more memory devices.

[0041] Figure 1 shows a data flow diagram of an exemplary, non-limiting data flow process 100 according to one or more exemplary embodiments of the present disclosure. A computing system described herein may implement the data flow process 100 to facilitate a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time, according to an exemplary embodiment of the present disclosure. For example, a user computing device 710 and / or a server component system 740, described later and shown in Figure 7, may implement the data flow process 100 to facilitate a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time, according to an exemplary embodiment of the present disclosure.

[0042] As shown in the exemplary embodiment shown in Figure 1, the data flow process 100 may include inputting input data 102 to a tracking algorithm 104. In this embodiment, the data flow process 100 may further include inputting the output of the tracking algorithm 104 to an alignment algorithm 106 which may output alignment feedback data 108. In at least one embodiment, a user computing device 710 and / or a server component system 740, described later with reference to Figure 7, may provide alignment feedback data 108 in real time, at least in part, based on receiving the input data 102 by implementing the tracking algorithm 104 and / or the alignment algorithm 106.

[0043] The input data 102 may include and / or consist of breathing data (not shown) that may indicate the entity's breathing (for example, the entity's current real-time breathing pattern). For example, the input data 102 may include and / or consist of radar data indicating the entity's breathing, high-frequency radar data indicating the entity's breathing, sonar data indicating the entity's breathing, acoustic data indicating the entity's breathing, video data indicating the entity's breathing, time-series data indicating the entity's breathing, and / or other data that may indicate the entity's breathing.

[0044] In some embodiments, the input data 102 may include and / or constitute a combination of different types of input data, each of which may include and / or constitute a specific type of respiration data that may indicate the respiration of an entity. For example, the input data 102 may include and / or constitute a combination of radar data indicating the respiration of an entity, sonar data indicating the respiration of an entity, and video data indicating the respiration of an entity.

[0045] In at least one embodiment, the input data 102 may include and / or constitute a continuous chirp radar signal, such as a frequency-modulated continuous wave (FMCW) radar signal, which may include and / or constitute breathing data that may indicate the breathing of an entity, for example. In this embodiment or another embodiment, the continuous chirp radar signal and / or FMCW radar signal may include and / or constitute a plurality of chirps.

[0046] In at least one embodiment, the input data 102 and / or the respiratory data described above may be obtained from one or more non-contact sources and / or devices that can capture, collect, and / or otherwise acquire the input data 102 and / or respiratory data without physically engaging with the entity (e.g., without touching the entity). For example, the input data 102 and / or respiratory data may be obtained from radar devices (e.g., high-frequency radar, real-time motion tracking radar, etc.), sonar devices, camera devices, audio devices (e.g., microphones, etc.), and / or other non-contact sources and / or devices that can capture, collect, and / or otherwise acquire the input data 102 and / or respiratory data without physically engaging with the entity. In at least one embodiment in which the input data 102 includes and / or constitutes the continuous char radar signal (e.g., FMCW radar signal) described above, such continuous char radar signal may be obtained from a high-frequency radar (e.g., FMCW radar) and / or real-time motion tracking radar.

[0047] The tracking algorithm 104 may include and / or configure a phase tracking algorithm having relatively low latency (for example, compared to other phase tracking algorithms). In one embodiment, the tracking algorithm 104 may convert the breathing data of the input data 102 into an entity breathing signal so that the entity breathing signal can track (e.g., mimic, simulate, replicate, etc.) the entity's breathing in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) and / or synchronize with the entity's breathing. In another embodiment, the tracking algorithm 104 may convert the breathing data of the input data 102 into an entity breathing amplitude signal so that the entity breathing amplitude signal can track (e.g., mimic, simulate, replicate, etc.) the entity's breathing in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) and / or synchronize with the entity's breathing. Details describing how the tracking algorithm 104 can convert the breathing data of the input data 102 into an entity breathing signal so that the entity breathing signal can track (e.g., mimic, simulate, replicate, etc.) the entity's breathing in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) and / or synchronize with the entity's breathing are given below with reference to the exemplary embodiment shown in Figure 2.

[0048] In embodiments where the input data 102 includes and / or constitutes the continuous chirp radar signal (e.g., FMCW radar signal) described above, the tracking algorithm 104 may convert the continuous chirp radar signal into an entity breathing amplitude signal so that the entity breathing amplitude signal can track (e.g., mimic, simulate, replicate, etc.) the entity's breathing in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) and / or synchronize with the entity's breathing. In this embodiment, the tracking algorithm 104 may generate a signal amplitude of the entity breathing amplitude signal when each of a plurality of chirps is received. For example, when a new chirp of a plurality of chirps is received (e.g., as soon as a previously unreceived chirp is received in real time), the tracking algorithm 104 may generate a new local amplitude of the entity breathing amplitude signal (e.g., a previously ungenerated local amplitude). The new local amplitude may correspond to a new chirp. In this way, the tracking algorithm 104 can convert each chirp of the multiple chirps, and thus the continuous chirp-radar signal, into an entity breathing amplitude signal that can track (e.g., mimic, simulate, replicate, etc.) the entity's breathing in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) and / or synchronize with the entity's breathing. Further details describing how the tracking algorithm 104 can convert the continuous chirp-radar signal into an entity breathing amplitude signal so that the entity breathing amplitude signal can track (e.g., mimic, simulate, replicate, etc.) the entity's breathing in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) and / or synchronize with the entity's breathing are given below with reference to the exemplary embodiment shown in Figure 4.

[0049] Alignment algorithm 106 may include, constitute, and / or apply a spectral similarity process for comparing an entity breathing signal and / or entity breathing amplitude signal with a proposed breathing signal, and / or determining the degree to which the entity breathing signal and / or entity breathing amplitude signal are aligned with the proposed breathing signal. The degree to which the entity breathing signal and / or entity breathing amplitude signal are aligned with the proposed breathing signal may be expressed as an alignment score, which may range, for example, from a value of approximately zero (0) to a value of approximately 1. For example, a value of zero (0) may indicate relatively poor alignment (e.g., non-alignment), and / or a value of 1 may indicate relatively good alignment (e.g., perfect alignment). In this way, alignment algorithm 106 may determine an alignment score that can indicate the degree of alignment between the entity breathing signal and / or entity breathing amplitude signal and the proposed breathing signal. Details describing how the alignment algorithm 106 may compare entity respiration signals and / or entity respiration amplitude signals with proposed respiration signals and / or determine the alignment score described above are given below with reference to the exemplary embodiment shown in Figure 3.

[0050] The proposed breathing signal described above may represent a proposed breathing pattern. In one embodiment, the proposed breathing signal may represent a proposed breathing pattern that can be defined and / or recommended by, for example, a user computing device 710 and / or a server component system 740. In this embodiment or another, the proposed breathing and / or proposed breathing signal may be defined, generated and / or recommended based at least in part on one or more attributes and / or biometrics that may correspond to an entity (e.g., the entity's age, weight, height, real-time heart rate and / or mean heart rate, real-time blood pressure and / or mean blood pressure, etc.).

[0051] The alignment feedback data 108 may include and / or consist of one or more other types of alignment feedback data that can indicate the alignment of the alignment score and / or entity breathing signal and / or entity breathing amplitude signal with the proposed breathing signal. In embodiments in which the user computing device 710 and / or server component system 740 perform the data flow process 100, the user computing device 710 and / or server component system 740, as described later, may generate such one or more other types of alignment feedback data based at least in part on (e.g., using) the alignment score. For example, the user computing device 710 and / or server component system 740 may generate such one or more other types of alignment feedback data such that the one or more other types of alignment feedback data correlates with and / or corresponds to the alignment score.

[0052] Alignment feedback data 108 may include and / or constitute audio data (e.g., digital voice, buzzer, audible alarm, etc.), text data, numerical data, and / or alphanumeric data (e.g., letters, numbers, words, written messages, push notifications, etc.), graphic data (e.g., symbols, signs, icons, emojis, etc.), haptic data (e.g., vibrations of a device associated with an entity, such as a smartphone or wearable computing device), visual data (e.g., light having an intensity that correlates with the degree of alignment and / or changes depending on the degree of alignment), and / or other forms of data. In one or more embodiments, alignment feedback data 108 may include and / or constitute alignment visualizations which may include entity breathing signals (e.g., entity breathing amplitude signals) and / or proposed breathing signals. For example, such alignment visualizations may include and / or constitute visualizations of entity breathing signals (e.g., entity breathing amplitude signals) overlaid on and / or adjacent to (e.g., superimposed on and / or adjacent to) proposed breathing signals. In one embodiment, such alignment visualization may include and / or constitute an image (e.g., a still image) of an entity breathing signal (e.g., an entity breathing amplitude signal) overlaid on and / or adjacent to (e.g., superimposed on and / or adjacent to) the proposed breathing signal. In another embodiment, such alignment visualization may include and / or constitute a video (e.g., live video, real-time video) of an entity breathing signal (e.g., an entity breathing amplitude signal) overlaid on and / or adjacent to (e.g., superimposed on and / or adjacent to) the proposed breathing signal.

[0053] In embodiments in which the user computing device 710 and / or the server component system 740 perform the data flow process 100, the user computing device 710 and / or the server component system 740, as described later, may provide the entity with alignment feedback data 108 in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) based at least partially on (e.g., in response to) the entity's breathing. For example, based at least in part on (e.g., in response to) receiving input data 102 (e.g., a continuous char plater signal), the user computing device 710 and / or server component system 740 may (e.g., immediately after receiving input data 102, in real time) implement a tracking algorithm 104 to convert the respiration data into an entity respiration signal (e.g., an entity respiration amplitude signal), implement an alignment algorithm 106 to compare the entity respiration signal (e.g., an entity respiration amplitude signal) with a proposed respiration signal and / or determine an alignment score corresponding to such a signal and / or provide the entity with alignment feedback data 108 (e.g., an alignment score, the alignment visualization described above, etc.) in real time in response to the entity's respiration (e.g., live, in parallel, and / or simultaneously with the entity's respiration). In at least one embodiment, the user computing device 710 and / or the server component system 740 may perform such actions in real time while an entity is performing a guided breathing exercise defined by the user computing device 710 and / or the server component system 740 and / or communicated to the entity, based on the proposed breathing and / or proposed breathing signals described above, which may be defined and / or generated by the user computing device 710 and / or the server component system 740 as described above.For example, the user computing device 710 and / or the server component system 740 may perform such operations in real time while the entity is attempting to align its respiration with a proposed respiration and / or align an entity respiration signal (e.g., an entity respiration amplitude signal) with the proposed respiration signal.

[0054] Figure 2 shows a data flow diagram of an exemplary, non-limiting data flow process 200 according to one or more exemplary embodiments of the present disclosure. Computing systems described herein may implement the data flow process 200 that facilitates a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time, according to exemplary embodiments of the present disclosure. For example, a user computing device 710 and / or a server component system 740, described later and shown in Figure 7, may implement the tracking algorithm 104 (e.g., run, operate, etc.) to implement the data flow process 200 that facilitates a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time, according to exemplary embodiments of the present disclosure.

[0055] The dataflow process 200 may include and / or configure a dataflow process for data flowing through the tracking algorithm 104. For example, the dataflow process 200 may include and / or configure a dataflow process for input data 102 and / or the respiration data described above, passing through the tracking algorithm 104. More specifically, in the exemplary embodiment shown in Figure 2, the dataflow process 200 may include and / or configure a dataflow process for input data 102 and / or respiration data passing through the tracking algorithm 104 to convert respiration data into an entity respiration signal 214 so that the entity respiration signal 214 can track (e.g., mimic, simulate, replicate, etc.) the entity's respiration in real time (e.g., live, in parallel, and / or simultaneously with the entity's respiration) and / or synchronize with the entity's respiration. In at least one embodiment described herein, the entity respiration signal 214 may include and / or configure an entity respiration amplitude signal.

[0056] As shown in the exemplary embodiment in Figure 2, in 202, the tracking algorithm 104 may remove clutter from the input data 102. For example, the tracking algorithm 104 may use an exponential filter and / or exponential smoothing process to remove noise data from the input data 102 and / or breathing data. The noise data may include and / or consist of data that can indicate at least one movement (e.g., the movement of an object and / or another person) corresponding to one or more second entities.

[0057] In 204, the tracking algorithm 104 may use an exponential filter and / or exponential smoothing process to map a range that may be associated with the input data 102 and / or respiratory data. The range may include and / or constitute at least a portion of the entity's respiratory data.

[0058] In 206, the tracking algorithm 104 may normalize the ranges into a range probability map which may and / or constitute a plurality of range bins. Each of the plurality of range bins may and / or constitute at least a portion of the respiratory data.

[0059] In 208, the tracking algorithm 104 can apply one or more inertia functions to a range probability map and / or multiple range bins to determine a center of mass that can correspond to the range probability map and / or multiple range bins.

[0060] In 210, the tracking algorithm 104 may extract phase data (e.g., from a probability map) that may correspond to the center of mass. The phase data may represent a phase signal (e.g., a wrapped phase signal or an unwrapped phase signal) that may correspond to the center of mass.

[0061] In 212, the tracking algorithm 104 may apply a filter to the phase signal to acquire and output an entity respiration signal 214 (e.g., an entity respiration amplitude signal). The filter may be operable to remove data that may indicate defined entity movements that may be associated with the entity's respiration (e.g., subtle movements the entity makes during inhalation and / or exhalation).

[0062] In embodiments where the input data 102 includes and / or constitutes a combination of different types of input data, each having different types of respiratory data as described above, the tracking algorithm 104 may perform the operations described above with respect to each different type of input data to convert all of the different types of respiratory data into an entity respiratory signal 214. For example, in embodiments where the input data 102 includes and / or constitutes a combination of, for example, radar data indicating the entity's breathing, sonar data indicating the entity's breathing, and video data indicating the entity's breathing, the tracking algorithm 104 may perform the operations described above with respect to each different type of input data to convert all of the different types of respiratory data into an entity respiratory signal 214. For example, in these embodiments, the tracking algorithm 104 may convert all of the different types of respiratory data into a single entity respiratory signal 214 such that the entity respiratory signal 214 may include, constitute, and / or consider all of such different types of respiratory data.

[0063] Figure 3 shows a data flow diagram of an exemplary, non-limiting data flow process 300 according to one or more exemplary embodiments of the present disclosure. Computing systems described herein may implement the data flow process 300 that facilitates a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time, according to exemplary embodiments of the present disclosure. For example, a user computing device 710 and / or a server component system 740, described later and shown in Figure 7, may implement the alignment algorithm 106 (e.g., run, operate, etc.) to implement the data flow process 300 that facilitates a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time, according to exemplary embodiments of the present disclosure.

[0064] The data flow process 300 may include and / or constitute a data flow process for data flowing through the alignment algorithm 106. For example, the data flow process 300 may include and / or constitute a data flow process for entity breathing signals 214 (e.g., entity breathing amplitude signals) through the alignment algorithm 106. More specifically, in the exemplary embodiment shown in Figure 3, the data flow process 300 may include and / or constitute a data flow process for entity breathing signals 214 through the alignment algorithm 106 for comparing the entity breathing signals 214 with the proposed breathing signals and / or for determining the degree to which the entity breathing signals 214 are aligned with the proposed breathing signals. That is, for example, the data flow process 300 may include and / or constitute a data flow process for entity breathing signals 214 through the alignment algorithm 106 for determining an alignment score 310.

[0065] As shown in the exemplary embodiment shown in Figure 3, in 302, the alignment algorithm 106 may calculate the spectral vector of the respiratory data for phase invariance by calculating a first spectral vector that may correspond to the entity's respiratory data and / or the entity's respiratory signal 214 (e.g., the entity's respiratory amplitude signal), and by calculating a second spectral vector that may correspond to the proposed respiratory data (e.g., data indicating proposed respiration) and / or the corresponding proposed respiratory signal. In at least one embodiment, the proposed respiratory data and / or the corresponding proposed respiratory signal may be defined, generated, and / or recommended by the user computing device 710 and / or the server component system 740, for example, as described above.

[0066] In 304, the alignment algorithm 106 can calculate the first normalized spectral vector and the second normalized spectral vector by applying a normalization function to the first and second spectral vectors, respectively. For example, the alignment algorithm 106 can calculate the first L2 normalized spectral vector and the second L2 normalized spectral vector by applying an L2 normalization function to the first and second spectral vectors, respectively.

[0067] In 306, the alignment algorithm 106 can calculate the alignment scores of the first and second L2-normalized spectral vectors. For example, the alignment algorithm 106 can calculate the alignment scores of the first and second L2-normalized spectral vectors by performing a dot product operation.

[0068] In 308, the alignment algorithm 106 may apply a softmax function to the alignment score to obtain and output an alignment score 310. The alignment algorithm 106 may also apply a softmax function to improve the dynamic range associated with the alignment score 310.

[0069] Figure 4 shows a data flow diagram of an exemplary, non-limiting data flow process 400 according to one or more exemplary embodiments of the present disclosure. Computing systems described herein may implement the data flow process 400 that facilitates a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time, according to exemplary embodiments of the present disclosure. For example, a user computing device 710 and / or a server component system 740, described later and shown in Figure 7, may implement the tracking algorithm 104 (e.g., run, operate, etc.) to implement the data flow process 400 that facilitates a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time, according to exemplary embodiments of the present disclosure.

[0070] The dataflow process 400 may include and / or configure a dataflow process for data flowing through the tracking algorithm 104. The dataflow process 400 may include and / or configure exemplary non-limiting alternative embodiments of the dataflow process 200 described above and shown in Figure 2. For example, the dataflow process 400 may include and / or configure a dataflow process for the continuous charr rider signal 402 going through the tracking algorithm 104, rather than the input data 102. More specifically, in the exemplary embodiment shown in Figure 4, the dataflow process 400 may include and / or configure a dataflow process for the continuous charr rider signal 402 via the tracking algorithm 104 to convert the continuous charr rider signal 402 into an entity breathing amplitude signal 418 so that the entity breathing amplitude signal 418 can track (e.g., mimic, simulate, replicate, etc.) the entity's breathing in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) and / or be synchronized with the entity's breathing.

[0071] As shown in the exemplary embodiment in Figure 4, in 404, the tracking algorithm 104 may remove clutter from the continuous char plater signal 402. For example, the tracking algorithm 104 may use an exponential filter and / or exponential smoothing process to remove noise data from the continuous char plater signal 402. The noise data may include and / or consist of data that can indicate at least one motion (e.g., the motion of an object and / or another person) corresponding to one or more second entities.

[0072] In 406, the tracking algorithm 104 may use an exponential filter and / or exponential smoothing process to map a range that may be associated with the continuous chirp render signal 402. The range may include and / or constitute at least a portion of the entity's breathing data.

[0073] In 408, the tracking algorithm 104 may normalize the ranges into a range probability map which may and / or constitute a plurality of range bins. Each of the plurality of range bins may and / or constitute at least a portion of the respiratory data.

[0074] In 410, the tracking algorithm 104 can apply one or more inertia functions to a range probability map and / or multiple range bins to determine a center of mass that can correspond to the range probability map and / or multiple range bins.

[0075] In 412, the tracking algorithm 104 can extract phase data that may correspond to the center of mass (e.g., from a probability map). The phase data may represent a wrapped phase signal that may correspond to the center of mass.

[0076] In 414, the tracking algorithm 104 may perform a signal phase unwrapping process on the phase data and / or wrapped phase signals to obtain a continuous phase signal that can correspond to the center of mass.

[0077] In 416, the tracking algorithm 104 may apply a filter to the continuous phase signal to acquire and output an entity respiration amplitude signal 418. The filter may be operable to remove data that may indicate defined entity movements that may be associated with the entity's respiration (e.g., subtle movements the entity makes during inhalation and / or exhalation).

[0078] In additional and / or alternative embodiments, the entity breathing amplitude signal 418 may be input to an alignment algorithm 106 that compares the entity breathing amplitude signal 418 with the proposed breathing signal and / or determines the degree to which the entity breathing amplitude signal 418 is aligned with the proposed breathing signal. That is, for example, the entity breathing amplitude signal 418 may be input (e.g., by a user computing device 710 and / or a server component system 740) to determine the alignment score 310 as described above with reference to Figure 3.

[0079] Figures 5A and 5B show exemplary non-limiting signal evaluation processes 500a and 500b according to one or more exemplary embodiments of the present disclosure, respectively. Computing systems described herein may implement signal evaluation processes 500a and / or 500b to facilitate a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time, according to exemplary embodiments of the present disclosure. For example, a user computing device 710 and / or a server component system 740, described later and shown in Figure 7, may implement (e.g., run, operate, etc.) the tracking algorithm 104 and / or alignment algorithm 106 to perform signal evaluation processes 500a and / or 500b according to exemplary embodiments of the present disclosure to facilitate a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time.

[0080] As described above with reference to Figures 1, 2, 3, and 4, the user computing device 710 and / or the server component system 740 may perform the tracking algorithm 104 (e.g., run, operate, etc.) to generate the entity breathing signal 214. In this embodiment, the user computing device 710 and / or the server component system 740 may generate a proposed breathing signal 502 corresponding to a proposed breathing (e.g., data indicating a proposed breathing), which may be defined and / or recommended by the user computing device 710 and / or the server component system 740 as described above. In this embodiment, the user computing device 710 and / or the server component system 740 may perform the alignment algorithm 106 (e.g., run, operate, etc.) to calculate a spectral vector 504 that may correspond to the entity breathing data and / or the entity breathing signal 214 (e.g., the entity breathing amplitude signal), and a spectral vector 506 that may correspond to the proposed breathing (e.g., data indicating a proposed breathing) and / or the proposed breathing signal 502. In this embodiment, the user computing device 710 and / or the server component system 740 may perform the alignment algorithm 106 (e.g., execute, operate, etc.) to compute spectral vectors 504 and 506 in the inner product space 508, as shown in Figures 5A and 5B.

[0081] In the exemplary embodiments shown in Figures 5A and 5B, the inner product space 508 may include and / or constitute an L2 normalized vector space. In these embodiments, spectral vectors 504 and 506 may each describe and / or correspond to a normalized vector (e.g., an L2 normalized vector). In embodiments where spectral vectors 504 and 506 are close to each other (e.g., as shown by the depiction of spectral vectors 504 and 506 in the inner product space 508 shown in Figure 5A), it means that the dot product is maximized. In embodiments where spectral vectors 504 and 506 are not close to each other, for example, where they are far apart (e.g., as shown by the depiction of spectral vectors 504 and 506 in the inner product space 508 shown in Figure 5B), it means that the dot product is small. In the embodiments described above, this is because, mathematically, the dot product of L2 normalized vectors is used to measure the "angle" between L2 normalized vectors in the inner product space. For example, in the exemplary embodiments shown in Figures 5A and 5B, the user computing device 710 and / or the server component system 740 may perform an alignment algorithm 106 to obtain the dot product of spectral vectors 504 and 506 as described herein, and determine the angle between spectral vectors 504 and 506 in the inner product space 508. In these exemplary embodiments or other exemplary embodiments, the user computing device 710 and / or the server component system 740 may thereby determine the extent to which the respiration of an entity (represented, for example, by the entity respiration signal 214 in Figures 5A and 5B) is aligned with the proposed respiration (represented, for example, by the proposed respiration signal 502 in Figures 5A and 5B).

[0082] In one embodiment, based on performing a signal evaluation process 500a, the user computing device 710 and / or server component system 740 may determine that the entity breathing signal 214 has a relatively good alignment with the proposed breathing signal 502. Accordingly, the user computing device 710 and / or server component system 740 may further calculate and / or output an alignment score (e.g., an alignment score 310) (e.g., via the alignment algorithm 106) having a value (e.g., a value of about 1) that reflects such a relatively good alignment of the entity breathing signal 214 with the proposed breathing signal 502.

[0083] In another embodiment, based on performing the signal evaluation process 500b, the user computing device 710 and / or the server component system 740 may determine that the entity breathing signal 214 has a relatively poor alignment with the proposed breathing signal 502. Therefore, the user computing device 710 and / or the server component system 740 may further calculate and / or output an alignment score (e.g., an alignment score 310) (e.g., via the alignment algorithm 106) having a value (e.g., a value of about zero (0)) that reflects such a relatively poor alignment of the entity breathing signal 214 with the proposed breathing signal 502.

[0084] Figure 6 shows an exemplary non-limiting alignment feedback data 600 according to one or more exemplary embodiments of the present disclosure. The alignment feedback data 600 may include and / or constitute exemplary non-limiting embodiments of the alignment feedback data 108 described above with reference to Figure 1. For example, the alignment feedback data 600 may include and / or constitute exemplary non-limiting embodiments of the alignment visualization described above, which may include and / or constitute visualization of entity breathing signals (e.g., entity breathing amplitude signals) and / or proposed breathing signals. In one embodiment, the alignment feedback data 600 may include and / or constitute images (e.g., still images) of entity breathing signals (e.g., entity breathing amplitude signals) and / or proposed breathing signals. In another embodiment, the alignment feedback data 600 may include and / or constitute video (e.g., live video, real-time video) of entity breathing signals (e.g., entity breathing amplitude signals) and / or proposed breathing signals.

[0085] A computing system according to an exemplary embodiment of the present disclosure may generate alignment feedback data 600 by performing one or more of the processes, algorithms, and / or methods (e.g., computer implementations) described herein. For example, to generate alignment feedback data 600, a user computing device 710 and / or a server component system 740, described later and shown in Figure 7, may perform a data flow process 100, a tracking algorithm 104, an alignment algorithm 106, a data flow process 200, a data flow process 300, a data flow process 400, a signal evaluation process 500a and / or 500b, and / or computer implementations 800 and / or 900, described later and shown in Figures 8 and 9, respectively.

[0086] As shown in the exemplary embodiment in Figure 6, the alignment feedback data 600 may include an entity respiration signal plot 602 of the entity respiration curve 606 and / or an alignment score plot 604 of the alignment score curve 608. In this embodiment, the entity respiration signal plot 602 illustrates the respiration amplitude values ​​of the entity respiration curve 606 over time, and the alignment score plot 604 illustrates the alignment score values ​​of the alignment score curve 608 over time.

[0087] In one embodiment, the entity respiration curve 606 corresponds to and / or represents the entity respiration signal 214. In another embodiment, the entity respiration curve 606 corresponds to and / or represents the entity respiration amplitude signal 418. In any of the above embodiments, the alignment score curve 608 corresponds to and / or represents the alignment score 310. In the exemplary embodiment shown in Figure 6, the entity respiration signal plot 602 and the alignment score plot 604 show that the entity respiration signal corresponding to the entity respiration curve 606 (e.g., entity respiration signal 214 or entity respiration amplitude signal 418) has relatively good alignment with the proposed respiration signal (not shown).

[0088] Figure 7 shows a block diagram of an exemplary, non-limiting computing system 700 according to one or more exemplary embodiments of the present disclosure. The computing system 700 may include a user computing device 710 and / or a server computing system 740 that can be communicatively coupled via a network 730. The computing system 700, the user computing device 710, and / or the server component system 740 may be used to facilitate a closed-loop non-contact breathing guidance process that provides quantified alignment feedback data in real time by performing one or more of the processes, algorithms, and / or methods (e.g., computer implementation methods) described herein.

[0089] The user computing device 710 may be any type of computing device, such as a personal computing device (e.g., a laptop or desktop), a mobile computing device (e.g., a smartphone or tablet), a game console or controller, a wearable computing device, an embedded computing device, or any other type of computing device.

[0090] The user computing device 710 includes one or more processors 712 and memory 714. The one or more processors 712 may be any suitable processing device (e.g., a processor core, microprocessor, ASIC, FPGA, controller, microcontroller, etc.) and may be one processor or multiple operably connected processors. The memory 714 may include one or more non-temporary computer-readable storage media such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memory 714 may store data 716 and instructions 718 executed by the processors 712 to cause the user computing device 710 to perform an operation such as one of the operations described herein. In at least one embodiment, the data 716 and / or instructions 718 may include and / or constitute, for example, a tracking algorithm 104 and / or an alignment algorithm 106.

[0091] The user computing device 710 may also include one or more user input components 720 that receive, acquire, capture, and / or collect input data (e.g., user input, input data 102, and the respiratory data described above). For example, a user input component 720 may be a touch-sensitive component (e.g., a touch-sensitive display screen or touchpad) that senses the touch of a user input object (e.g., a finger or stylus). The touch-sensitive component may serve to implement a virtual keyboard. Other exemplary user input components include a microphone, a conventional keyboard, or other means by which a user may provide user input. In at least one embodiment, the user input component 720 may include and / or configure the aforementioned non-contact sources and / or devices that can capture, collect, and / or otherwise acquire input data (e.g., input data 102) and / or respiratory data of an entity without physically engaging with the entity (e.g., without touching the entity). For example, the user input component 720 may include and / or configure radar devices (e.g., high-frequency radar, real-time motion tracking radar, FMCW radar, etc.), sonar devices, camera devices, audio devices (e.g., microphones, etc.), and / or other non-contact sources and / or devices that can capture, collect, and / or otherwise acquire such input data and / or respiratory data without physically engaging with the entity. The user computing device 710 may also include a user output component 722. The user output component 722 can provide information and may include, for example, a display screen, an audio output device, a haptic device, or other suitable devices.

[0092] The server computing system 740 includes one or more processors 742 and memory 744. The one or more processors 742 may be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.), and may be a single processor or multiple operably connected processors. The memory 744 may include one or more non-temporary computer-readable storage media such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memory 744 may store data 746 and instructions 748 executed by the processors 742 to cause the server computing system 740 to perform an operation such as any of the operations described herein.

[0093] In some embodiments, the server computing system 740 includes one or more server computing devices, or is implemented by one or more server computing devices. If the server computing system 740 includes multiple server computing devices, such server computing devices may operate according to a sequential computing architecture, a parallel computing architecture, or any combination thereof.

[0094] Network 730 may be any type of communication network, such as a local area network (e.g., an intranet), a wide area network (e.g., the Internet), or any combination thereof, and may include any number of wired or wireless links. Generally, communication over Network 7300 may be conducted over any type of wired and / or wireless connection using a wide variety of communication protocols (e.g., TCP / IP, HTTP, SMTP, FTP), encoding or formatting (e.g., HTML, XML), and / or protection schemes (e.g., VPN, Secure HTTP, SSL).

[0095] Figure 8 shows a flowchart of an exemplary, non-limiting computer implementation 800 according to one or more exemplary embodiments of the present disclosure. The computer implementation 800 may be implemented, for example, using the computing system 700, user computing device 710, and / or server component system 740 described above with reference to Figure 7. The exemplary embodiments shown in Figure 8 illustrate operations performed in a specific order for illustrative and explanatory purposes. Those skilled in the art will understand, using the disclosures provided herein, that various operations or steps of the computer implementation 800 or any other methods disclosed herein may be adapted, modified, rearranged, performed concurrently, including operations not shown, and / or modified in various ways without departing from the scope of the present disclosure.

[0096] In 802, the computer implementation method 800 may include receiving input data (e.g., input data 102, continuous chirp rider signal 402, etc.) including respiration data indicating the respiration of an entity, by a computing system (e.g., computing system 700, user computing device 710, and / or server component system 740) operably coupled to one or more processors (e.g., one or more processors 712).

[0097] In 804, the computer implementation method 800 may include converting respiration data into entity respiration signals (e.g., entity respiration signal 214, entity respiration amplitude signal 418, etc.) by a computing system (e.g., via tracking algorithm 104, dataflow process 200, dataflow process 400, etc.) so that the entity respiration signals track (e.g., mimic, simulate, replicate, etc.) the entity's respiration in real time (e.g., live, in parallel, and / or simultaneously with the entity's respiration).

[0098] In 806, the computer implementation method 800 may include comparing the entity breathing signal with a proposed breathing signal indicating the proposed breathing (e.g., a proposed breathing signal 502, or another proposed breathing signal that may be generated by the user computing device 710 and / or server component system 740 as described above with reference to Figures 1, 2, 3, 4, 5A and 5B) by a computing system (e.g., via the alignment algorithm 106, the data flow process 300, the signal evaluation process 500a and / or 500b, etc.).

[0099] In 808, the computer implementation method 800 may include providing the entity with alignment feedback data (e.g., alignment feedback data 108, alignment score 310, alignment feedback data 600, and alignment feedback data 1000a and / or 1000b, described later with reference to Figures 10A and 10B, respectively) in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) at least in part on the entity's breathing. The alignment feedback data indicates the alignment between the entity's breathing signal and the proposed breathing signal.

[0100] Figure 9 shows a flowchart of an exemplary, non-limiting computerized implementation 900 according to one or more exemplary embodiments of the present disclosure. The computerized implementation 900 may be implemented, for example, using the computing system 700, user computing device 710, and / or server component system 740 described above with reference to Figure 7. The exemplary embodiments shown in Figure 9 illustrate operations performed in a specific order for illustrative and explanatory purposes. Those skilled in the art will understand, using the disclosures provided herein, that various operations or steps of the computerized implementation 900 or any other methods disclosed herein may be adapted, modified, rearranged, performed concurrently, and / or modified in various ways, without departing from the scope of the present disclosure, including operations not shown.

[0101] In 902, the computer implementation method 900 may include receiving a continuous chirp-radar signal (e.g., a continuous chirp-radar signal 402) containing respiration data indicating the respiration of an entity, by a computing system (e.g., a user computing device 710 and / or a server component system 740) operably coupled to one or more processors (e.g., one or more processors 712). The continuous chirp-radar signal includes a plurality of chirps.

[0102] In 904, the computer implementation method 900 may include converting a continuous chirp player signal into an entity breathing amplitude signal (e.g., entity breathing amplitude signal 418, etc.) by a computing system (e.g., via a tracking algorithm 104, a data flow process 400, etc.) so that the entity breathing amplitude signal tracks (e.g., mimic, simulate, replicate, etc.) the entity's breathing in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing). The signal amplitude of the entity breathing amplitude signal is generated when each of the multiple chirps is received.

[0103] In 906, the computer implementation method 900 may include comparing the entity respiration amplitude signal with a proposed respiration signal (e.g., a proposed respiration signal 502, or another proposed respiration signal that may be generated by the user computing device 710 and / or server component system 740 as described above with reference to Figures 1, 2, 3, 4, 5A and 5B) by a computing system (e.g., via an alignment algorithm 106, a data flow process 300, a signal evaluation process 500a and / or 500b, etc.).

[0104] In 908, the computer implementation method 900 may include providing the entity with alignment feedback data (e.g., alignment feedback data 108, alignment score 310, alignment feedback data 600, and / or alignment feedback data 1000a and / or 1000b, described later with reference to Figures 10A and 10B, respectively) in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing) at least in part on the entity's breathing. The alignment feedback data indicates the alignment between the entity's breathing amplitude signal and the proposed breathing signal.

[0105] Figures 10A and 10B show exemplary non-limiting alignment feedback data 1000a and 1000b according to one or more exemplary embodiments of the present disclosure, respectively. Alignment feedback data 1000a and / or 1000b may include and / or constitute exemplary non-limiting embodiments of alignment feedback data 108 described above with reference to Figure 1. Additionally, or alternatively, alignment feedback data 1000a and / or 1000b may include and / or constitute exemplary non-limiting alternative embodiments of alignment feedback data 600 described above with reference to Figure 6. For example, alignment feedback data 1000a and / or 1000b may include and / or constitute exemplary non-limiting embodiments of the alignment visualization described above, which may include and / or constitute visualization of entity breathing signals (e.g., entity breathing amplitude signals) overlaid on and / or adjacent to the proposed breathing signal. In one embodiment, the alignment feedback data 1000a and / or 1000b may include and / or consist of an image (e.g., a still image) of an entity breathing signal (e.g., an entity breathing amplitude signal) overlaid on and / or adjacent to the proposed breathing signal (e.g., superimposed on and / or adjacent to the proposed breathing signal). In another embodiment, the alignment feedback data 1000a and / or 1000b may include and / or consist of a video (e.g., live video, real-time video) of an entity breathing signal (e.g., an entity breathing amplitude signal) overlaid on and / or adjacent to the proposed breathing signal (e.g., superimposed on and / or adjacent to the proposed breathing signal).

[0106] A computing system according to an exemplary embodiment of the present disclosure may generate alignment feedback data 1000a and / or 1000b by performing one or more of the processes, algorithms, and / or methods (e.g., computer implementations) described herein. For example, to generate alignment feedback data 1000a and / or 1000b, a user computing device 710 and / or a server component system 740 may perform a data flow process 100, a tracking algorithm 104, an alignment algorithm 106, a data flow process 200, a data flow process 300, a data flow process 400, a signal evaluation process 500a and / or 500b, and / or computer implementations 800 and / or 900. In one exemplary embodiment, the user computing device 710 and / or the server component system 740 may perform the data flow process 100, the tracking algorithm 104, and / or the alignment algorithm 106 to perform the above-described comparison between an entity breathing signal (e.g., entity breathing signal 214 or entity breathing amplitude signal 418) and a proposed breathing signal (e.g., proposed breathing signal 502), and / or determine the extent to which such an entity breathing signal is aligned (or not aligned) with such a proposed breathing signal, as described above with reference to Figures 1 to 4. In this embodiment, the user computing device 710 and / or the server component system 740 may generate alignment feedback data 1000a and / or 1000b based at least in part on such comparison and determination of the extent of alignment between such entity breathing signal and such proposed breathing signal.It should be understood that the user computing device 710 and / or server component system 740 may generate and / or provide alignment feedback data 1000a and / or 1000b to an entity implementing one or more embodiments described herein, thereby providing the entity with user-friendly alignment feedback data that enables the entity to easily, readily, and / or quickly interpret data for understanding how well or poorly it is mimicking (e.g., simulating) the proposed respiratory signal.

[0107] As shown in the exemplary embodiments in Figures 10A and 10B, the alignment feedback data 1000a and 1000b may each include an entity breathing signal representation 1002 and / or a proposed breathing signal representation 1004. In this embodiment, the entity breathing signal representation 1002 may be overlaid on and / or adjacent to the proposed breathing signal representation 1004 (for example, superimposed on and / or adjacent to the proposed breathing signal representation 1004).

[0108] Entity breathing signal representation 1002 may correspond to and / or represent an entity breathing signal, such as entity breathing signal 214 or entity breathing amplitude signal 418. Entity breathing signal representation 1002 may track (e.g., mimic, simulate, replicate, etc.) such entity breathing signals in real time (e.g., live, in parallel, and / or simultaneously with the entity's breathing). Proposed breathing signal representation 1004 may correspond to and / or represent a proposed breathing signal, such as proposed breathing signal 502. Proposed breathing signal representation 1004 may track (e.g., mimic, simulate, replicate, etc.) such proposed breathing signals in real time (e.g., live, in parallel, and / or simultaneously with the proposed breathing signal).

[0109] In the exemplary embodiment shown in Figure 10A, alignment feedback data 1000a indicates that the entity breathing signal corresponding to entity breathing signal representation 1002 (e.g., entity breathing signal 214 or entity breathing amplitude signal 418) has relatively poor alignment with the proposed breathing signal corresponding to proposed breathing signal representation 1004 (e.g., proposed breathing signal 502), as indicated by the relatively poor alignment between entity breathing signal representation 1002 and proposed breathing signal representation 1004. In the exemplary embodiment shown in Figure 10B, alignment feedback data 1000b indicates that the entity breathing signal corresponding to entity breathing signal representation 1002 (e.g., entity breathing signal 214 or entity breathing amplitude signal 418) has relatively good alignment with the proposed breathing signal corresponding to proposed breathing signal representation 1004 (e.g., proposed breathing signal 502), as indicated by the relatively good alignment between entity breathing signal representation 1002 and proposed breathing signal representation 1004.

[0110] While the subject matter has been described in detail in various specific and exemplary embodiments, each embodiment is provided for illustrative purposes only and does not limit the disclosure. Those skilled in the art, understanding the foregoing, will readily be able to create variations, modifications, and equivalents of such embodiments. Therefore, the disclosure does not exclude the inclusion of such modifications, modifications, and / or additions to the subject matter, as will be readily apparent to those skilled in the art. For example, features illustrated or described as part of one embodiment can be used in another embodiment to create yet another embodiment. Thus, the disclosure is intended to cover such variations, modifications, and equivalents.

Claims

1. A computing system, One or more processors, The system comprises one or more non-temporary computer-readable storage media that store instructions for causing the computing system to perform an operation when executed by the one or more processors, and the operation is Receiving input data that includes breathing data indicating the entity's respiration, Convert the respiration data into an entity respiration amplitude signal so that the entity respiration amplitude signal tracks the entity's respiration in real time. The first spectral vector corresponding to the entity respiration amplitude signal is compared with the second spectral vector corresponding to the proposed respiration signal that represents the proposed respiration, and A computing system comprising providing alignment feedback data to the entity in real time, at least in part, based on the respiration of the entity, wherein the alignment feedback data shows the alignment of the first spectral vector corresponding to the entity's respiration amplitude signal and the second spectral vector corresponding to the proposed respiration signal.

2. The aforementioned operation is, The computing system according to claim 1, further comprising determining an alignment score indicating the degree of alignment between the entity respiration amplitude signal and the proposed respiration signal.

3. The computing system according to claim 1, wherein the alignment feedback data includes an alignment score indicating the degree of alignment between the entity breathing amplitude signal and the proposed breathing signal.

4. The computing system according to any one of claims 1 to 3, wherein the alignment feedback data includes alignment visualization, which includes at least one of the entity respiratory amplitude signal or the proposed respiratory signal.

5. The computing system according to any one of claims 1 to 4, wherein at least one of the input data or the respiration data includes at least one of the following: radar data indicating the respiration of the entity, high-frequency radar data indicating the respiration of the entity, sonar data indicating the respiration of the entity, acoustic data indicating the respiration of the entity, video data indicating the respiration of the entity, or time-series data indicating the respiration of the entity.

6. A computer implementation method, A computing system operably coupled to one or more processors receives input data including respiration data indicating the respiration of an entity, The computing system converts the respiration data into an entity respiration amplitude signal so that the entity respiration amplitude signal tracks the entity's respiration in real time. The computing system compares a first spectral vector corresponding to the entity respiration amplitude signal with a second spectral vector corresponding to the proposed respiration signal representing the proposed respiration, A computer-aided method comprising providing the entity with alignment feedback data in real time, at least in part, based on the entity's respiration, wherein the computing system provides the entity with alignment feedback data indicating the alignment of the first spectral vector corresponding to the entity's respiration amplitude signal and the second spectral vector corresponding to the proposed respiration signal.

7. The computerized method according to claim 6, further comprising determining an alignment score indicating the degree of alignment between the entity respiratory amplitude signal and the proposed respiratory signal using the computing system.

8. The computing system provides the entity with the alignment feedback data in real time, at least partially based on the entity's breathing. The computer implementation method according to claim 6, comprising providing an alignment score indicating the degree of alignment between the entity respiration amplitude signal and the proposed respiration signal using the computing system.

9. The computing system provides the entity with the alignment feedback data in real time, at least partially based on the entity's breathing. The computer-aided method according to any one of claims 6 to 8, comprising providing an alignment visualization including at least one of the entity respiratory amplitude signal or the proposed respiratory signal by the computing system.

10. The computer implementation method according to any one of claims 6 to 9, wherein at least one of the input data or the respiration data includes at least one of the following: radar data indicating the respiration of the entity, high-frequency radar data indicating the respiration of the entity, sonar data indicating the respiration of the entity, acoustic data indicating the respiration of the entity, video data indicating the respiration of the entity, or time-series data indicating the respiration of the entity.

11. A computing system, One or more processors, The system comprises one or more non-temporary computer-readable storage media that store instructions for causing the computing system to perform an operation when executed by the one or more processors, and the operation is The operation includes receiving a continuous chirp-radar signal containing respiration data indicating the respiration of an entity, wherein the continuous chirp-radar signal contains a plurality of chirps, and the operation is The process includes converting the continuous chirp-radar signal to the entity breathing amplitude signal so that the entity breathing amplitude signal tracks the breathing of the entity in real time, wherein the signal amplitude of the entity breathing amplitude signal is generated when each of the plurality of chirps is received, and converting the continuous chirp-radar signal is performed. The process of transforming the continuous chirpedar signal includes removing noise data from the continuous chirpedar signal, wherein the noise data includes data indicating at least one movement corresponding to one or more second entities, and the process of transforming the continuous chirpedar signal is as follows: The process further includes mapping a range associated with the continuous chirpedor signal, wherein the range includes at least a portion of the respiratory data, and transforming the continuous chirpedor signal. Further comprising normalizing the range into a range probability map including multiple range bins, each of which includes at least a portion of the respiratory data, and transforming the continuous chirpedor signal, Applying one or more inertia functions to at least one of the range probability map or the plurality of range bins to determine the center of mass corresponding to at least one of the range probability map or the plurality of range bins, The further includes extracting phase data corresponding to the center of mass, wherein the phase data represents a wrapped phase signal corresponding to the center of mass, and converting the continuous char plater signal, The operation further includes performing a signal phase unwrapping process on at least one of the phase data or the wrapped phase signal to obtain a continuous phase signal corresponding to the center of mass, wherein the operation is The entity respiratory amplitude signal is compared with the proposed respiratory signal indicating the proposed respiration, and A computing system comprising providing alignment feedback data to the entity in real time, at least in part, based on the respiration of the entity, wherein the alignment feedback data indicates the alignment between the entity's respiration amplitude signal and the proposed respiration signal.

12. The aforementioned operation is, The computing system according to claim 11, further comprising determining an alignment score indicating the degree of alignment between the entity respiration amplitude signal and the proposed respiration signal.

13. The computing system according to claim 11, wherein the alignment feedback data includes at least one of the following: an alignment score indicating the degree of alignment between the entity respiratory amplitude signal and the proposed respiratory signal, or an alignment visualization including at least one of the entity respiratory amplitude signal or the proposed respiratory signal.

14. The aforementioned operation is, The computing system according to claim 11, comprising applying a filter to the continuous phase signal to obtain the entity respiration amplitude signal, wherein the filter is operable to remove data indicating defined entity movement associated with the respiration of the entity.

15. A program comprising executable instructions for causing the computing system according to any one of claims 1 to 5 and 11 to 14 to perform the operation.

Images