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 .
Claim Objections
Claim 17 is objected to because of the following informalities:
Claim 17 and claim 6 are essentially duplicate claims. For the purpose of examination, it is construed that claim 17 is meant to be dependent on claim 14 (instead of claim 1).
Appropriate correction is required.
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) 1-3, 8-9, 11, 14, 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over LEARMAN (US 2020/0187793) in view of Goh, Choon-Hian, et al. "Robust PPG motion artifact detection using a 1-D convolution neural network", hereafter Goh.
Regarding claim 1, LEARMAN teaches a method of detecting a level of an analyte, comprising:
transmitting a transmit signal into a subject using a transmit antenna of a non-invasive sensor ([0063], [0133] “transmitting radio waves below the skin surface of a person and across a range of stepped frequencies”);
obtaining a response signal from the subject using a receive antenna of the non-invasive sensor ([0087], [0133]) and
processing the response signal using a machine learning algorithm to determine a level of an analyte in the subject ([0142], [0147]), wherein the machine learning algorithm is trained by:
transmitting a frequency sweep into a test subject using a transmit antenna of a test non-invasive sensor ([0106]-[0107], [0151], [0155]);
obtaining a test response to the frequency sweep from the test subject using a receive antenna of the test non-invasive sensor ([0075], [0133]-[0134], [0140], [0154]);
obtaining a test analyte level in the test subject using a reference sensor ([0130], [0146], [0154]);
associating the test response with the test analyte level ([0151], [0154], [0168]);
processing features of the test response to generate training data ([0140], [0142]-[0143], [0151], [0154]); and
inputting the training data into the machine learning algorithm ([0140], [0146], [0151]).
LEARMAN teaches determining glucose level of a subject, which is construed to be analogous to the analyte and "stepped frequency", which is construed to be analogous to frequency sweep.
However, to fully show and obviate a determining of an analyte in a living subject, Goh discloses – determine a level of an analyte in the [living] subject and a test analyte level in the [living] test subject (Goh p.3 C1 ¶2.2).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of LEARMAN to determine an analyte in a living subject as disclosed by Goh. Doing so would provide a useful information and a more reliable biometric identification (Goh p.2 C2L1-5).
Regarding claim 14, LEARMAN teaches a method of training a machine learning algorithm to detect a level of an analyte in a subject, comprising:
transmitting a frequency sweep into a test subject using a transmit antenna of a test non-invasive sensor; obtaining a test response to the frequency sweep from the test subject using a receive antenna of the test non-invasive sensor; obtaining a test analyte level in the test subject using a reference sensor; associating the test response with the test analyte level; processing features of the test response to generate training data; and inputting the training data into the machine learning algorithm.
Claim 14 recites substantially the same limitations as claim 1 and is rejected for substantially the same reasons.
Regarding claim 2, LEARMAN as modified teaches the method of claim 1, wherein the machine learning algorithm is a neural network (Goh p.2 C2 last par., p.7 C2 ¶4).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of LEARMAN to include a neural network as disclosed by Goh. Doing so would help automatically learn patterns from inputs and store them as the parameters of network connections, thus re-quiring minimal manual engineering (p.7 C2 ¶4).
Regarding claim 3, LEARMAN as modified teaches the method of claim 2, wherein the neural network includes two blocks each with a one dimensional convolution layer (Goh p.2 C2 last par, the two blocks followed by a pooling layer, a dropout layer (Goh p.2 C2, p.5 ¶2.4 C2), and a neuron trained to predict the level of the analyte based on the response signal (Goh F3, p.5 ¶2.4).
Regarding claims 8 and 19, LEARMAN as modified teaches the method of claims 1 and 14, wherein the frequency sweep is at 1 MHz intervals within a range of frequencies (LEARMAN [0066], [0076], [0134], [0138], Goh p.3 ¶2.3, F2).
Regarding claim 9, LEARMAN as modified teaches the method of claim 1, wherein following training of the machine learning algorithm, the machine learning algorithm is tested by:
obtaining a validation signal using a validation non-invasive sensor; obtaining a corresponding validation analyte level (LEARMAN [0146]-[0147]); determining an output analyte level based on the validation signal, using the machine learning algorithm, and comparing the output analyte level with the validation analyte level (LEARMAN [0147]-[0148], Goh F1, p.5 ¶2.4).
Regarding claims 11 and 20, LEARMAN as modified teaches the method of claims 1 and 14, wherein processing features of the test response includes averaging features over at least one of a frequency domain or a time domain (LEARMAN [0136], [0147]).
Claim(s) 4-5, 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over LEARMAN as modified in view of Ten Grotenhuis et al. (US 20140238136).
Regarding claims 4 and 15, LEARMAN as modified teaches the method of claims 1 and 14, wherein the processing of the features includes smoothing of the features using a Kalman filter (LEARMAN [0089]).
LEARMAN does not explicitly teach, however Ten Grotenhuis discloses Savitzky-Golay filter ([0263], ).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of LEARMAN to include Savitzky-Golay filter as disclosed by Ten Grotenhuis. Doing so reduces quantization noise by approximating the input coordinates by an unweighted linear least-squares fit using a polynomial of a given degree and provides superior performance in smoothing out a noisy signal whose frequency range is large, by eliminating high frequency content while preserving data features of interest (Ten Grotenhuis [0263], [0265], [0272]).
Regarding claims 5 and 16, LEARMAN as modified teaches the method of claims 1 and 14, wherein the parameters of the Savitzky-Golay filter include a window length of 2000 ([0272] “Larger window sizes may be used for the Savitzky-Golay filter”), a polynomial order of 4 (Ten Grotenhuis [0267]), Table A6, a derivative order of 1, and using the extension mode nearest.
While the prior art does not explicitly disclose a derivative order of 1, and using the extension mode nearest, such particular extensions are well known in art and would be based on the particular design choices based on the goals and tradeoffs in order to achieve a predictable results. The particular numerical values are results-effective experimentation and the claimed “nearest” extension mode is merely a known boundary handling option. Applying conventional parameters values to improve signal quality would have been an obvious modification requiring no inventive skill, as the particular parameters are merely optimized values. See MPEP 2143.
Claim(s) 6-7, 17-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over LEARMAN as modified in view of Mensink et al. (US 20120054130).
Regarding claims 6 and 17, LEARMAN as modified does not explicitly teach, however Mensink discloses the method of claim 1, wherein the processing of the features includes reducing a feature space using Gaussian random projection and/or a Gaussian mixture model ([0025]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of LEARMAN as modified to include Gaussian mixture model as disclosed by Mensink. Doing so would improve detection of visual similarity metrics (Mensink [0025]).
NOTE in analogous art (US 20070139251) likewise discloses claims 6 and 17 in [0027] and further obviates the teachings of LEARMAN as modified.
Regarding claims 7 and 18, LEARMAN as modified teaches the method of claims 1 and 14, wherein the feature space is reduced to between 2 and 1024 features (Mensink [0025]).
Further note any particular values would be an obvious to try combination of elements in order to achieve a predictable results. See MPEP 2143.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over LEARMAN as modified in view of Connor et al. (US 20170164878) or Bosua et al. (US 11284819).
Regarding claim 10, LEARMAN as modified teaches the method of claim 1, wherein at least a portion of the response signal is received from
LEARMAN does not explicitly teach, however Connor discloses interstitial fluid ([0348]- [0349]). Bosua discloses the same in C6L41-45.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of LEARMAN to include interstitial fluid as disclosed by Connor or Bosua. Doing so helps predict changes in body glucose levels (Connor [0348).
Claim(s) 12-13 is/are rejected under 35 U.S.C. 103 as being unpatentable over LEARMAN as modified in view of Zhao et al. “Building Cooling load prediction based on LightGBM”.
Regarding claim 12, LEARMAN as modified does not explicitly teach, however Zhao discloses the method of claim 1, wherein the machine learning algorithm is a light gradient boosting machine model (p.117 ¶4 , p.118 ¶5).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of LEARMAN as modified to include a light gradient boosting machine model as disclosed by Zhao. Doing so provides performance improvement on test and validation sets with high accuracy (Zhao p.118 ¶5).
NOTE in analogous art (US 20210287759) likewise discloses claim 12 in [0151]-[0152], [0326] and further obviates the teachings of LEARMAN as modified.
Regarding claim 13, LEARMAN as modified teaches the method of claim 12, wherein a loss function of the light gradient boosting machine model is based on a mean average relative difference relative to the test analyte level (Zhao p.117 ¶4.2).
Claim(s) 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over LEARMAN (US 2020/0187793) in view of Diab et al. (US 20210113121).
Regarding claim 21, LEARMAN teaches a non-invasive analyte sensing system, comprising:
a transmit antenna configured to transmit a transmit signal into a subject ([0053]);
a receive antenna configured to obtain a response signal from the subject ([0077]); and
a controller configured to process the response signal using a machine learning algorithm to determine a level of an analyte in the subject,
LEARMAN teaches determining glucose level of a subject, which is construed to be analogous to the analyte and "stepped frequency", which construed to be analogous to frequency sweep.
However, to fully show and obviate determine an analyte in a living subject, Diab discloses – determine a level of an analyte in the [living] subject and a test analyte level in the [living] test subject ([0081], [0104]-[0105]).
LEARMAN does not explicitly teach, however Diab discloses wherein the machine learning algorithm is a neural network.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of LEARMAN to include a neural network and determine an analyte in a living subject as disclosed by Diab. Doing so would calibrate or improve an accuracy of one or more other sensors (Diab [0087]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure is indicated on PTO-892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to POLINA G PEACH whose telephone number is (571)270-7646. The examiner can normally be reached Monday-Friday, 9:30 - 5:30.
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, Aleksandr Kerzhner can be reached at 571-270-1760. 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.
/POLINA G PEACH/Primary Examiner, Art Unit 2165 August 2, 2026
Prosecution Insights