DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
The amendments filed on 08/31/2026 has been entered. Claims 1, 7, 10, 11, 13, 15, 18 were amended and claim 6 was cancelled. Claims 1-5, 7-18 remain pending in the application. The specification, drawings, and claims objection have been withdrawn due to the amendments.
Response to Arguments
Applicant’s remarks (filed 08/31/2026) indicate there is an “Allowable Subject Matter” section in the Office Action filed 06/02/2026, but there is none. There is, however, a typo in the PTO-326 form in (e.g. item 6) that states that claim 6 is allowable, but the Office Action filed 06/02/2026 does not reflect that. A second Non-Final Office Action will be issued to allow Applicant time to address the rejection.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-5, 7, 9, 10, 11, 14, 15, 17, 18 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Paliwal (“Real Time Heart Rate Detection and Heart Rate Variability Calculation”, 2016), in view of Chen (“RealSense= real heart rate: Illumination invariant heart rate estimation from videos”, 2016), further in view of Mao (“Motion Artifact Reduction In Photoplethysmography For Reliable Signal Selection”, 2019).
Regarding claims 1 and 18, Paliwal teaches A method for camera-based heart rate variability monitoring (Paliwal, pg 2, column 1, Section III, reproduced below:
PNG
media_image1.png
680
604
media_image1.png
Greyscale
. “video mode of the camera” and “heart rate variability”), the method comprising:
determining colored skin pixels (Paliwal, see image above, “flash of light enters the skin” and “fluctuating red color video”, which is being interpreted to involve colored skin pixels) in color image frames taken by a camera (Paliwal, see image above, “recorded video signals” is being interpreted as involving “color image frames taken by a camera”), and
extracting mean RGB signal from the skin pixels (Paliwal, see image above: “The average values of the red components of every frame were calculated”. Which is being interpreted to involve RGB signal);
obtaining rPPG (remote photoplethysmography) signal from the mean RGB signal (Paliwal, see image above: “After this step Photoplethysmography signals were obtained.” Which is being interpreted to involve remote Photoplethysmography);
enhancing quality of the rPPG signal (Paliwal, see nearest image below, “peaks were smoothed” and “divided into intervals” is being interpreted to involve “enhancing quality of the rPPG signal”) to obtain reconstructed rPPG signal by a windowing method (Paliwal, pg 2, column 2, paragraphs 3-5, reproduced below:
PNG
media_image2.png
476
600
media_image2.png
Greyscale
. “Divided into intervals” is being interpreted as involving “a windowing method”);
detecting peaks of the reconstructed rPPG signal to obtain HRV (Heart Rate Variability) values (Paliwal, see nearest image above, “The peaks were detected on the PPG signal plot”); and
analyzing peak to peak distances statistically to improve the HRV values (Paliwal, see nearest image above, “NN Intervals”, as one with ordinary skill would know, involve peak to peak distances, and is used as one of many statistics for HRV values).
wherein in step of enhancing quality of the rPPG signal (Paliwal, see nearest image below, “peaks were smoothed” and “divided into intervals” is being interpreted to involve “enhancing quality of the rPPG signal”) to obtain reconstructed rPPG signal by a windowing method (Paliwal, see nearest image above. “Divided into intervals” is being interpreted as involving “a windowing method”), the windowing method comprises:
However, Paliwal does not appear to explicitly teach wide band pass filtering. Although, Paliwal does teach filtering.
Pertaining to the same field of endeavor, Chen teaches
applying wide band pass filtering with a heart rate band (Chen, pg 2, Section II A, ¶1, reproduced below:
PNG
media_image3.png
534
490
media_image3.png
Greyscale
. “Band pass filter” for “the normal interval of heart rate of a human” is being interpreted as heart rate band with wide band pass filtering);
removing edge effects by applying a Gaussian style function (Chen, see nearest image above, the “band pass filter” is being interpreted as removing edge effects that uses Gaussian style function);
finding heart rate from FFT of the rPPG signal (Chen, see nearest image above, “FFT” that then is later used for “obtaining average HR” of the rPPG signal);
However, Paliwal and Chen does not appear to explicitly teach applying narrow band pass filtering with a band of the hate rate (interpreted as heart rate).
Paliwal and Chen are considered to be analogous art because they are directed to photoplethysmography. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for photoplethysmography with temporal concatenation and averaging (as taught by Paliwal) to include wide band pass filtering (as taught by Chen) because the combination provides an improvement to heart rate estimation (Chen, Abstract).
Pertaining to the same field of endeavor, Mao teaches
applying narrow band pass filtering with a band of the hate rate (Mao, pg 3-4, Section IIB, ¶2: “Based on the instantaneous heart rate derived from the ECG signal, a lowpass and a high-pass digital filter are designed and cascaded for narrow passband filtering. The filters process the input PPG signal in both forward and reverse directions to preserve time-domain alignment”); and
retaining pulsatile part of the rPPG signal (Mao, pg 3, Subsection D, lines 1-3: “In order to evaluate the cardio-respiratory features embedded in the pseudo clean PPG signal, we derive the average heart rate and respiration rate of the PPG segment”. Deriving HR data shows the pulsatile part has been retained).
Paliwal, Chen, and Mao are considered to be analogous art because they are directed to photoplethysmography. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for photoplethysmography with wide band pass filtering (as taught by Paliwal and Chen) to include narrow band pass filtering (as taught by Mao) because the combination provides an improvement to PPG analysis (Mao, Abstract).
Regarding claim 2, Paliwal teaches The method as in claim 1, wherein step of determining colored skin pixels in color image frames taken by a camera, and extracting mean RGB signal from the skin pixels, comprises:
However, Paliwal does not appear to explicitly teach face detection. Although, Paliwal does teach temporal concatenation (otherwise no HRV data could be collected) and averaging of data.
Pertaining to the same field of endeavor, Chen teaches
locating position of the face inside of the color image frame using a machine learning network (Chen, pg 2, column 2, Section II A, reproduced below:
PNG
media_image4.png
824
582
media_image4.png
Greyscale
. “Face detection” is being interpreted to involve color image and machine learning network);
creating an image patch containing a face image in the image frame (Chen, see nearest image above, “isolate and segment the cheek region” is being interpreted as part of the image patch containing a face image in the image frame);
distinguishing skin pixels and non-skin pixels of the face image (Chen, see nearest image above, the isolation of the cheek region is being interpreted as distinguishing skin pixels and non-skin pixels, otherwise all parts of the image would be considered the cheek); and
taking and concatenating temporally spatial mean of the skin pixels to obtain the mean RGB signal (Chen, see nearest image above, “average NIR intensity of the selected region” is being interpreted as spatial mean. “temporal moving-average filter” shows the RGB signal is temporally concatenated; otherwise, no data such as heart rate would be calculated).
Paliwal and Chen are considered to be analogous art because they are directed to photoplethysmography. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for photoplethysmography with temporal concatenation and averaging (as taught by Paliwal) to include face detection (as taught by Chen) because the combination provides an improvement to heart rate estimation (Chen, Abstract).
Regarding claim 3, Paliwal teaches The method as in claim 2, wherein in step of taking and concatenating temporally spatial mean of the skin pixels to obtain the mean RGB signal (Chen, see nearest image below, “average NIR intensity of the selected region” is being interpreted as spatial mean. “temporal moving-average filter” shows the RGB signal is temporally concatenated; otherwise, no data such as heart rate would be calculated),
a region of interest algorithm (Chen, see nearest image below, “face detection” shows region of interest algorithm was used to detect faces) is applied to select some parts of the skin pixels (Chen, see nearest image below: “cheek region” is being interpreted as some parts of the skin pixels) for obtaining the mean RGB signal (Chen, pg 2, column 2, Section II A, reproduced below:
PNG
media_image4.png
824
582
media_image4.png
Greyscale
.).
Regarding claim 4, Paliwal teaches The method as in claim 1, wherein in step of obtaining rPPG signal from the mean RGB signal (Chen, pg 2, column 2, Section II A, paragraph 1, reproduced below:
PNG
media_image5.png
586
592
media_image5.png
Greyscale
. “Temporal moving-average” is being interpreted to involve the mean RGB signal),
a machine learning algorithm (Chen, see nearest image above, the framework is being interpreted as involving a machine learning algorithm to obtain an rPPG signal) is applied to the mean RGB signal to obtain the rPPG signal (Chen, see nearest image above: “we perform an FFT to transform the signal” shows the rPPG signal is involved, otherwise no HR value could be found).
Paliwal and Chen are considered to be analogous art because they are directed to photoplethysmography. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for photoplethysmography with temporal concatenation and averaging (as taught by Paliwal) to include a machine learning algorithm (as taught by Chen) because the combination provides an improvement to heart rate estimation (Chen, Abstract).
Regarding claim 5, Paliwal teaches The method as in claim 1, wherein step of enhancing quality of the rPPG signal to obtain reconstructed rPPG signal by a windowing method, comprising:
interpolating the rPPG signal with interpolation to obtain an interpolated rPPG signal (Reali, pg 2-3, paragraph before Section 2, reproduced below:
PNG
media_image6.png
582
921
media_image6.png
Greyscale
, “We assessed the efficacy of three interpolation techniques”, which is being interpreted to be done on PPG signals);
applying the windowing method to the interpolated rPPG signal and obtain windowed rPPG signals (Reali, see nearest image above, “IBI estimates” are being interpreted as involving a windowing method to retrieve the intervals. The Reali reference does both non-interpolated and interpolated PPG IBIs);
combining the windowed rPPG signals to reconstruct a reconstructed rPPG signal (Reali, pg 11, ¶1: “IBIs derived from the interpolated PPGs”. IBIs, or interbeat intervals, are being interpreted as windowed rPPG signals that are then reconstructed to allow for HRV calculations); and
resolving edge issues by magnifying edges of the reconstructed rPPG signal (Reali, pg 6, Section 2.1.3, ¶2: “the PPG signal is filtered with a fourth order Butterworth bandpass filter with cut-off frequencies of 0.13 and 0.48 Hz”, which is being interpreted to involve sharpening, or magnifying edges, within the frequency range).
Regarding claim 7, Paliwal, Chen, and Mao teaches The method as in claim 1, wherein the heart rate band is 0.8-2.5 Hz (Mao, pg 2, column 2, Subsection B, ¶1: “The passband of bandpass filter is selected based on the range of instantaneous heart rate so that all heartbeat activity could be preserved”. Which is being interpreted as involving the heart rate band of 0.8-2.5 Hz).
Regarding claim 9, Paliwal, Chen, and Mao teaches The method as in claim 1, wherein step of detecting peaks of the reconstructed rPPG signal to obtain HRV values (Paliwal, pg 2, column 2, paragraphs 3-5, reproduced below:
PNG
media_image2.png
476
600
media_image2.png
Greyscale
. “The PPG signal plot” is being interpreted to involve detecting peaks of the reconstructed rPPG signal), comprising:
applying a peak detection algorithm (Paliwal, see nearest image above, “the peaks were detected” are being interpreted to use a peak detection algorithm) on the reconstructed rPPG signal to detect pulse peaks (Paliwal, see nearest image above, “the peaks were detected” are being interpreted to involve pulse peaks); and
calculating instantaneous peak-to-peak intervals according to the pulse peaks (Paliwal, see nearest image above, “NN intervals (Normal Sinus to Normal Sinus Interval” are being interpreted as involving instantaneous peak-to-peak intervals).
Regarding claim 10, Paliwal teaches The method as in claim 9, wherein the peak-to-peak intervals include IBIs (Inter-Beat Intervals) (Paliwal, pg 2, column 2, paragraphs 4-6, reproduced below:
PNG
media_image7.png
478
598
media_image7.png
Greyscale
. SDNN is the standard deviation of the IBI series, as one with ordinary skill in the art would know. Which shows IBIs are involved), RR intervals (Paliwal, pg 2, column 2, last paragraph: “R-R interval”) and NN (Normal-to-Normal) intervals (Paliwal, see nearest image above, “NN Intervals”).
Regarding claim 11, Paliwal teaches The method as in claim 1, wherein step of analyzing peak to peak distances statistically to improve the HRV values, comprising:
applying IBI (Inter-Beat Interval) analysis method to get refined IBIs (Paliwal, pg 2, column 2, lines 1-3: “Hanning window is applied on all the sets of the interval. It is used in order to minimize the leakage before computing Fast Fourier Transformation.” “Hanning window” is being interpreted as “IBI analysis method” that results in refined IBIs).
Regarding claim 14, Paliwal teaches The method as in claim 11, wherein step of analyzing peak to peak distances statistically to improve the HRV values, further comprising:
applying HRV formulas (Paliwal, see nearest image below, “Five Heart Rate Variability parameters were calculated” which is being interpreted to involve HRV formulas to do the calculations) to the refined IBIs for obtaining HRV time-domain metrics (Paliwal, pg 2, column 2, paragraph 5, reproduced below:
PNG
media_image8.png
228
588
media_image8.png
Greyscale
. “Heart Rate Variability” is being interpreted to involve HRV time-domain metrics) and frequency domain metrics (Paliwal, pg 2, column 2, paragraphs 2-3, reproduced below:
PNG
media_image9.png
218
594
media_image9.png
Greyscale
. “Magnitude value” that leads to “heartbeat” is being interpreted as involving frequency domain metrics).
Regarding claim 15, Paliwal teaches The method as in claim 14, The method as in claim 14, wherein the HRV time-domain metrics includes SDNN (standard deviation of normal to normal interval) and RMSSD (root mean square of successive heartbeat interval differences) (Paliwal, pg 2, column 2, paragraph 5, reproduced below:
PNG
media_image8.png
228
588
media_image8.png
Greyscale
. Which shows SDNN and RMSSD);
the frequency domain metrics includes LF/HF (low-frequency/high-frequency) (Paliwal, pg 2, column 2, paragraphs 2-3, reproduced below:
PNG
media_image9.png
218
594
media_image9.png
Greyscale
. “Fast Fourier Transform” is being interpreted to have Low Frequency (LF) and High Frequency (HF) values in it, as one with ordinary skill in the art would know).
Regarding claim 17, Paliwal teaches The method as in claim 1, wherein in step of determining colored skin pixels in color image frames taken by a camera (Paliwal, pg 2, column 1, paragraph before Section III: “smart phone cameras”. Which is interpreted to take colored skin pixels in color image frames), and
extracting mean RGB signal from the skin pixels (Paliwal, pg 2, column 1, Section III, paragraph 4: “The average values of the red components of every frame were calculated.”),
the camera is an independent camera or a built-in camera of a smart phone (Paliwal, pg 2, column 1, paragraph before Section III: “This paper presents a non-invasive, relatively inexpensive and easily available technique for utilizing PPG to monitor heart health. It is based on utilizing smart phone cameras with flash that are becoming ubiquitous in today’s world.”), tablet or laptop.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paliwal, as modified by Chen and Mao, in view of Park (“Photoplethysmogram Analysis and Applications: An Integrative Review”, 2022).
Regarding claim 8, Paliwal teaches The method as in claim 1, wherein in step of enhancing quality of the rPPG signal to obtain reconstructed rPPG signal by a windowing method, the windowing method comprises:
applying wide bandpass filtering (Chen, pg 2, column 2, Subsection A, ¶1: “After that, we use a band pass filter to cut outside of [0.7, 4] range in the frequency domain, which is the normal interval of heart rate of a human”. “band pass filter” is being interpreted to involve “wide bandpass filtering”) to interpolated rPPG (Chen, pg 5, column 1, full ¶2: “The sampling rate is 250HZ”. The sampling rate is being interpreted to involve interpolation) in order to obtain cleaned rPPG by removing high frequency noise and retaining pulse region (Chen, pg 2, column 2, Subsection A, ¶1: “After that, we use a band pass filter to cut outside of [0.7, 4] range in the frequency domain, which is the normal interval of heart rate of a human”. “band pass filter” is being interpreted as involving “removing high frequency noise” and retaining the pulse region, otherwise, no heart data could be extracted);
constructing K-Means clustering (Chen, pg 4, column 1, subsection C, ¶4-5, reproduced below:
PNG
media_image10.png
462
490
media_image10.png
Greyscale
. “K clusters” is being interpreted as involving K-Means clustering) with frequency and energy (Chen, pg 2, column 2, Section II A, ¶1: “We use the frequency with the maximal power response as the HR frequency”. “Power” is being interpreted to involve “energy”) as an input to find adaptive band (Chen, pg 2, Section II A, ¶1: “After that, we use a band pass filter to cut outside of [0.7, 4] range in the frequency domain, which is the normal interval of heart rate of a human”. The range is being interpreted as involving adaptive band.);
However, Paliwal and Chen does not appear to explicitly teach calculating energy around first harmonic frequency for each window and first order Wavelet Scattering Transform or Scattering Transform.
Pertaining to the same field of endeavor, Park teaches
calculating energy around first harmonic frequency for each window (Park, pg 4, column 2, last paragraph: “Min reported that most of the energy of the waveform is contained up to the 3rd harmonics”. Which is being interpreted to involve “calculating energy around first harmonic frequency for each window”);
applying first order Wavelet Scattering Transform or Scattering Transform to the cleaned rPPG (Park, pg 10, column 1, last 4 lines: “Similarly, in a study using a wavelet transform, noise is removed by obtaining a sub-band signal through wavelet decomposition and combining specific sub-bands”. “Wavelet transform” is being interpreted to involve “Wavelet Scattering Transform or Scattering Transform”);
Paliwal, Chen, and Park are considered to be analogous art because they are directed to photoplethysmography. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for photoplethysmography with temporal concatenation and averaging (as taught by Paliwal and Chen) to include calculating energy around first harmonic frequency for each window and first order Wavelet Scattering Transform or Scattering Transform (as taught by Park) because the combination provides an improvement to PPG analysis (Park, Abstract).
However, Paliwal, Chen, and Park does not appear to explicitly teach applying narrow band pass filtering.
Pertaining to the same field of endeavor, Mao teaches
applying narrow band pass filtering (Mao, pg 3, column 1, line 1: “narrow passband filtering”) with the adaptive band (Mao, pg 2, column 2, subsection B, ¶1: “The passband of bandpass filter is selected based on the range of instantaneous heart rate so that all heartbeat activity could be preserved”. Which is being interpreted as adaptive);
retaining pulsatile part of windowed rPPG signal (Mao, pg 3, column 1, lines 1-3: “The filters process the input PPG signal in both forward and reverse directions to preserve time-domain alignment”. This is being interpreted as retaining pulsatile part of the windowed rPPG signal, otherwise no heart rate related data could be gathered.).
Paliwal, Chen, Park and Mao are considered to be analogous art because they are directed to photoplethysmography. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for photoplethysmography with energy analysis for harmonics and wavelet scattering transform (as taught by Paliwal, Chen and Park) to include narrow bandpass filtering (as taught by Mao) because the combination provides an improvement to PPG analysis (Mao, Abstract).
Claim(s) 12, 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paliwal, as modified by Chen and Mao, in view of Vila (“Real-Time Quality Index to Control Data Loss in Real-Life Cardiac Monitoring Applications”, 2019).
Regarding claim 12, Paliwal teaches The method as in claim 11, wherein the IBI analysis method comprises:
However, Paliwal does not appear to explicitly rejecting physiologically impossible IBI regions. Although, Paliwal does teach temporal concatenation (otherwise no HRV data could be collected), averaging of data, and noise removal.
Pertaining to the same field of endeavor, Vila teaches
rejecting physiologically impossible IBI regions (Vila, pg 6-7, Section 2.2.1, ¶1, reproduced below:
PNG
media_image11.png
473
911
media_image11.png
Greyscale
. Outlier rejection is being interpreted to involve removing physiological impossible IBI regions.);
calculating mean IBI and rejecting all IBIs that are off more than X% from the mean IBI, the X% a value is between 20%-45% (Vila, see nearest image above, 30% is a value between 20% and 45%);
applying an IBI windowing method (Vila, see nearest image above, “A 5 s moving average was computed at first by focusing on each sample of the IBI signal, successively”. Which is being interpreted to involve windows); and
concatenating IBIs from each window to get the refined IBIs (Vila, see nearest image above, “bpm” is being interpreted as involving concatenating IBIs of the refined IBIs in order to calculated bpm, or beats per minute).
Paliwal and Vila are considered to be analogous art because they are directed to photoplethysmography. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for photoplethysmography with temporal concatenation and averaging (as taught by Paliwal) to include IBI outlier management (as taught by Vila) because the combination provides an improvement to photoplethysmography analysis (Vila, abstract).
Regarding claim 13, Paliwal, Chen, Mao, and Vila teaches The method as in claim 12, wherein the IBI windowing method comprises:
calculating mean IBI window (Vila, pg 6-7, Section 2.2.1, ¶1, reproduced below:
PNG
media_image11.png
473
911
media_image11.png
Greyscale
. “Moving average” is being interpreted to involve a mean IBI window); and
rejecting IBIs that are off more than Y% from the mean IBI window, the Y% is a value between 10%-25% (Vila, see nearest image above: “rejecting every sample that expressed an instantaneous heart rate outside the range [30; 250] bpm”. Which is being interpreted to involve a value between 10%-25%).
Claim(s) 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paliwal, as modified by Chen and Mao, in view of Yu (“Remote photoplethysmograph signal measurement from facial videos using spatio-temporal networks”, 2019).
Regarding claim 16, Paliwal teaches The method as in claim 1, wherein the method further comprising:
However, Paliwal does not appear to explicitly teach hyperparameters.
Pertaining to the same field of endeavor, Yu teaches
looping (Yu, see Section 3.2 image below, one with ordinary skill in the art would know that machine learning algorithm loop through as part of the learning process) through step of enhancing quality of the rPPG signal to obtain reconstructed rPPG signal (Yu, pg 2, full paragraphs 2-3, reproduced below:
PNG
media_image12.png
544
1132
media_image12.png
Greyscale
. “rPPG signal measurement from raw facial videos” is being interpreted as reconstructing rPPG signal. One with ordinary skill in the art would know that the goal of the machine learning algorithm would be to enhance the quality of the rPPG signal, as shown by the loss function section cited below) by a windowing method (Yu, see Section 3.2 image below, “predicted rPPG signal” is being interpreted as involving windowing method for a selection) to step of analyzing peak to peak distances statistically (Yu, see Section 3.2 image below, the difference between predicted and ground truth PPG signals is being interpreted as analyzing peak to peak distance statistically) to improve the HRV values (Yu, see nearest image above, rPPG signals allow for “HRV analysis”, which shows PPG signal has HRV values that are being improved as the machine learning algorithm operates) to optimize hyperparameters (Yu, pg 5, Section 3.2, reproduced below:
PNG
media_image13.png
488
854
media_image13.png
Greyscale
. One with ordinary skill in the art would know that loss functions help optimize hyperparameters; otherwise, no training would occur); and
redoing (Yu, see Section 3.2 image below, one with ordinary skill in the art would know that machine learning algorithm loop through as part of the learning process. This is an iterative process, so the next step of the iteration is part of the “redoing”) step of enhancing quality of the rPPG signal to obtain reconstructed rPPG signal (Yu, see pg 2 image above, “rPPG signal measurement from raw facial videos” is being interpreted as reconstructing rPPG signal. One with ordinary skill in the art would know that the goal of the machine learning algorithm would be to enhance the quality of the rPPG signal, as shown by the loss function section above) by a windowing method (Yu, see Section 3.2 image above, “predicted rPPG signal” is being interpreted as involving windowing method for a selection) to step of analyzing peak to peak distances statistically (Yu, see Section 3.2 image above, the difference between predicted and ground truth PPG signals is being interpreted as analyzing peak to peak distance statistically) to improve the HRV values with optimized hyperparameters (Yu, see pg 2 image above, rPPG signals allow for “HRV analysis”, which shows PPG signal has HRV values that are being improved as the machine learning algorithm operates).
Paliwal and Yu are considered to be analogous art because they are directed to photoplethysmography. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method and system for photoplethysmography with temporal concatenation and averaging (as taught by Paliwal) to include hyperparameters (as taught by Yu) because the combination provides an improvement to HRV analysis (Yu, Abstract).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Lee et al (US 2021/0361179 A1) discloses wide and narrow band pass filters for photoplethysmography.
Addison et al (US 2010/0298676 A1) discloses wavelet analysis (that includes photoplethysmography signals) using techniques such as band pass filtering and managing edge effects with a Gaussian style function
Watson et al (US 2011/0306858 A1) discloses wavelet analysis that includes managing edge effects with a Gaussian style function.
Coleman et al (US 2019/0113973 A1) discloses wavelet analysis (including photoplethysmography signals) wide band pass filtering, interpolation, and wavelet scattering transform.
Mejia-Mejia et al (“Outlier Management for Pulse Rate Variability Analysis from Photoplethysmographic Signals”, July 2022) discloses outlier management that are a certain standard deviation away from the mean.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHNNY B DUONG whose telephone number is (571)272-1358. The examiner can normally be reached Monday - Thursday 10a-9p (ET).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Matthew Bella can be reached at (571)272-7778. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/J.B.D./Examiner, Art Unit 2667
/MATTHEW C BELLA/Supervisory Patent Examiner, Art Unit 2667