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 Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-2, 5-8, 10, 12, 14-20 are rejected under 35 U.S.C. 102 (a)(1) as being anticipated by US 2022/0039882 Botzer et al., hereinafter “Botzer”.
Regarding claim 1, Botzer discloses a method (Para 12 and Figure 5) comprising: obtaining an input data signal (Figure 5, elements 512, 514, and 520) for a given individual (Para 119; biometric data of an individual); generating a noisy version of the input data signal (Para 123 discloses that the input data is a signal noise); processing the noisy version of the input data signal in a denoising encoder-decoder neural network (Para 123 discloses a signal with noise is represented by inputs 512 and 514 shown in Figure 5, these inputs are processed by a denoising encoder-decoder neural network system 500 to output a clean/denoised ECG output 552) to generate a classification for the input data signal (Para 118; “the neural network 600 can be an autoencoder of the mapping engine 101 that extracts intracardiac based features for classification”); and executing at least one automated action based at least in part on the generated classification (Para 123 and Figure 5, element 580; “the cleaned biometric data include enabling more accurate monitor, diagnosis, and treatment any number of various diseases”, see also Para 119 that identifies the mapping engine 101 includes the neural network that results in output 580 that allows a physician (Figure 6, element 115) to make a diagnosis or follow with treatment based on the cleaned biometric); wherein the method is performed by at least one processing device comprising a processor coupled to a memory (Figure 2, element 222 coupled to memory 224).
Regarding claim 2, Botzer discloses the input data signal comprises at least one electrocardiogram (ECG) data signal (Para 122-123) obtained from one or more ECG sensors (Figure 1, element 111 and Para 65).
Regarding claim 5, Botzer discloses the denoising encoder-decoder neural network comprises a deep artificial denoising auto-encoder-decoder (DADAED) neural network (Para 121 and 122, see also Para 110).
Regarding claim 6, Botzer discloses the input data signal (Figure 5, element 510 and Para 119) comprises at least a first data signal of a first type (Figure 5, element 512 and Para 119) and a second data signal of a second type different than the first type (Figure 5, element 512 and Para 119, the first type can be BS ECG data biometric data, the second could be IC ECG data), and further wherein noisy versions of the respective first and second data signals are generated (Para 123 discloses that the input data is a signal noise) and applied to respective first and second encoder-decoder pairs of the denoising encoder-decoder neural network (Figure 5, element 520 to 525, See Para 115 that discloses a number of connections (e.g., encoder/decoder connections) that implies multiple encoder/decoder structures) for generation of respective first and second latent representations therefrom (Para 120), the first and second latent representations being processed to generate the classification for the input data signal (Para 120; “The latent representation includes one or more intermediary data representations derived from the plurality of inputs”).
Regarding claim 7, Botzer discloses the denoising encoder-decoder neural network (Figure 5, element 500) comprises: at least one encoder-decoder pair comprising an encoder and a decoder (Figure 5, elements 525 and 545, See Para 115 that discloses a number of connections (e.g., encoder/decoder connections)), the encoder having an input adapted to receive the noisy version of the input data signal (See annotated Figure 5 below) and an output (See annotated Figure 5 below) coupled to an input of the decoder (See annotated Figure 5 below); an attention layer (See annotated Figure 5 below and Para 130) configured to process a latent representation generated by the encoder to generate a corresponding weighted representation (Para 130 and 120); and a classifier configured to receive the weighted representation from the attention layer and to generate therefrom the classification for the input data signal (Para 120 “a representation for a set of data”).
PNG
media_image1.png
713
665
media_image1.png
Greyscale
Annotated Figure 5
Regarding claim 8, Botzer discloses the encoder-decoder pair (Figure 5, element 500) is implemented using at least one artificial neural network (ANN) (Para 111, 119, and 120).
Regarding claim 10, Botzer discloses the attention layer comprises: a non-linear activation function configured to normalize received input (Para 52 and 113); and a softmax layer configured to process the normalized input to generate the weighted representation from the latent representation (Para 123 and 172).
Regarding claim 12, Botzer discloses the input data signal comprises a first data signal of a first type (Figure 5, element 512 and Para 119) and a second data signal of a second type different than the first type (Figure 5, element 512 and Para 119, the first type can be BS ECG data biometric data, the second could be IC ECG data), and the denoising encoder-decoder neural network (Figure 5, element 500) comprises: a first encoder-decoder pair (Figure 5, element 500) comprising a first encoder (Figure 5, element 510 and 525) and a first decoder (Figure 5, element 510 and 525), the first encoder having an input adapted to receive a noisy version of the first data signal (See annotated Figure 5 above) and an output (See annotated Figure 5 above) coupled to an input of the first decoder (See annotated Figure 5 above), the first encoder generating a first latent representation from the noisy version of the first data signal (Para 130 and 120); a second encoder-decoder pair comprising a second encoder and a second decoder (Figure 5, elements 525 and 545, See Para 115 that discloses a number of connections (e.g., encoder/decoder connections)), the second encoder having an input adapted to receive a noisy version of the second data signal (See annotated Figure 5 above) and an output (See annotated Figure 5 above) coupled to an input of the second decoder (See annotated Figure 5 above), the second encoder generating a second latent representation from the noisy version of the second data signal (Para 130 and 120); an attention layer configured to process the first and second latent representations generated by the respective first and second encoders to generate at least one corresponding weighted representation (See annotated Figure 5 below and Para 130); and a classifier configured to receive the at least one weighted representation from the attention layer and to generate therefrom the classification for the input data signal (Para 120 “a representation for a set of data”).
Regarding claim 14, Botzer discloses executing at least one automated action based at least in part on the generated classification (Para 123 and Figure 5, element 580; “the cleaned biometric data include enabling more accurate monitor, diagnosis, and treatment any number of various diseases”, see also Para 119 that identifies the mapping engine 101 includes the neural network that results in output 580 that allows a physician (Figure 6, element 115) to make a diagnosis or follow with treatment based on the cleaned biometric) comprises generating at least one output signal in a telemedicine application (Figure 6, element 600), wherein said at least one output signal in a telemedicine application comprises at least one of: classification information for presentation on a user terminal or other display device (Figure 6, element 165); classification information transmitted over a network to a medical professional (Figure 6, transported to device 653 operated by physician 115); and classification information transmitted over a network to a prescription-filling entity.
Regarding claim 15, Botzer discloses a system (Figure 2, element 200 and Figure 5, element 500) comprising: at least one processing device comprising a processor (Figure 2, element 222) coupled to a memory (Figure 2, element 224); the at least one processing device being configured: to obtain an input data signal (Figure 5, elements 512, 514, and 520) for a given individual (Para 119; biometric data of an individual); to generate a noisy version of the input data signal (Para 123 discloses that the input data is a signal noise); to process the noisy version of the input data signal in a denoising encoder-decoder neural network (Para 123 discloses a signal with noise is represented by inputs 512 and 514 shown in Figure 5, these inputs are processed by a denoising encoder-decoder neural network system 500 to output a clean/denoised ECG output 552) to generate a classification for the input data signal (Para 118; “the neural network 600 can be an autoencoder of the mapping engine 101 that extracts intracardiac based features for classification”); and to execute at least one automated action based at least in part on the generated classification (Para 123 and Figure 5, element 580; “the cleaned biometric data include enabling more accurate monitor, diagnosis, and treatment any number of various diseases”, see also Para 119 that identifies the mapping engine 101 includes the neural network that results in output 580 that allows a physician (Figure 6, element 115) to make a diagnosis or follow with treatment based on the cleaned biometric).
Regarding claim 16, Botzer discloses the input data signal (Figure 5, element 510 and Para 119) comprises at least a first data signal of a first type (Figure 5, element 512 and Para 119) and a second data signal of a second type different than the first type (Figure 5, element 512 and Para 119, the first type can be BS ECG data biometric data, the second could be IC ECG data), and further wherein noisy versions of the respective first and second data signals are generated (Para 123 discloses that the input data is a signal noise) and applied to respective first and second encoder-decoder pairs of the denoising encoder-decoder neural network (Figure 5, element 520 to 525, See Para 115 that discloses a number of connections (e.g., encoder/decoder connections) that implies multiple encoder/decoder structures) for generation of respective first and second latent representations therefrom (Para 120), the first and second latent representations being processed to generate the classification for the input data signal (Para 120; “The latent representation includes one or more intermediary data representations derived from the plurality of inputs”).
Regarding claim 17, Botzer discloses the denoising encoder-decoder neural network (Figure 5, element 500) comprises: at least one encoder-decoder pair comprising an encoder and a decoder (Figure 5, elements 525 and 545, See Para 115 that discloses a number of connections (e.g., encoder/decoder connections)), the encoder having an input adapted to receive the noisy version of the input data signal (See annotated Figure 5 above) and an output (See annotated Figure 5 above) coupled to an input of the decoder (See annotated Figure 5 above); an attention layer (See annotated Figure 5 above and Para 130) configured to process a latent representation generated by the encoder to generate a corresponding weighted representation (Para 130 and 120); and a classifier configured to receive the weighted representation from the attention layer and to generate therefrom the classification for the input data signal (Para 120 “a representation for a set of data”).
Regarding claim 18, Botzer discloses a computer program product (abstract) comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs (Para 57 and 59), wherein the program code, when executed by at least one processing device comprising a processor coupled to a memory, causes the at least one processing device (Abstract): to obtain an input data signal (Figure 5, elements 512, 514, and 520) for a given individual (Para 119; biometric data of an individual); to generate a noisy version of the input data signal (Para 123 discloses that the input data is a signal noise); to process the noisy version of the input data signal in a denoising encoder-decoder neural network (Para 123 discloses a signal with noise is represented by inputs 512 and 514 shown in Figure 5, these inputs are processed by a denoising encoder-decoder neural network system 500 to output a clean/denoised ECG output 552) to generate a classification for the input data signal (Para 118; “the neural network 600 can be an autoencoder of the mapping engine 101 that extracts intracardiac based features for classification”); and to execute at least one automated action based at least in part on the generated classification (Para 123 and Figure 5, element 580; “the cleaned biometric data include enabling more accurate monitor, diagnosis, and treatment any number of various diseases”, see also Para 119 that identifies the mapping engine 101 includes the neural network that results in output 580 that allows a physician (Figure 6, element 115) to make a diagnosis or follow with treatment based on the cleaned biometric).
Regarding claim 19, Botzer discloses the input data signal (Figure 5, element 510 and Para 119) comprises at least a first data signal of a first type (Figure 5, element 512 and Para 119) and a second data signal of a second type different than the first type (Figure 5, element 512 and Para 119, the first type can be BS ECG data biometric data, the second could be IC ECG data), and further wherein noisy versions of the respective first and second data signals are generated (Para 123 discloses that the input data is a signal noise) and applied to respective first and second encoder-decoder pairs of the denoising encoder-decoder neural network (Figure 5, element 520 to 525, See Para 115 that discloses a number of connections (e.g., encoder/decoder connections) that implies multiple encoder/decoder structures) for generation of respective first and second latent representations therefrom (Para 120), the first and second latent representations being processed to generate the classification for the input data signal (Para 120; “The latent representation includes one or more intermediary data representations derived from the plurality of inputs”).
Regarding claim 20, Botzer discloses the denoising encoder-decoder neural network (Figure 5, element 500) comprises: at least one encoder-decoder pair comprising an encoder and a decoder (Figure 5, elements 525 and 545, See Para 115 that discloses a number of connections (e.g., encoder/decoder connections)), the encoder having an input adapted to receive the noisy version of the input data signal (See annotated Figure 5 above) and an output (See annotated Figure 5 above) coupled to an input of the decoder (See annotated Figure 5 above); an attention layer (See annotated Figure 5 above and Para 130) configured to process a latent representation generated by the encoder to generate a corresponding weighted representation (Para 130 and 120); and a classifier configured to receive the weighted representation from the attention layer and to generate therefrom the classification for the input data signal (Para 120 “a representation for a set of data”).
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) 3 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over US 2022/0039882 Botzer et al., hereinafter “Botzer”, in view of US 2023/0196567 Aykut et al., hereinafter “Aykut”.
Regarding claim 3, Botzer discloses the input data signal (Figure 5, elements 512, 514, and 520) .
Botzer does not disclose at least one photoplethysmography (PPG) data signal obtained from one or more PPG sensors.
However, Aykut discloses denoising encoder-decoder (Para 83 and Figure 10C) and teaches at least one photoplethysmography (PPG) data signal (Para 85) obtained from one or more PPG sensors (Para 68).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed a PPG signal as taught by Aykut, in the invention of Botzer, in order to measure a change of blood volume characteristic (Aykut; Para 68).
Regarding claim 13, Botzer discloses the first data signal of the first type comprises at least one ECG data signal (Para 122, Figure 5, element 512) and the second data signal (Figure 5, element 514).
Botzer does not disclose the second type comprises at least one PPG data signal.
However, Aykut teaches the second type comprises at least one PPG data signal (Para 85).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed a PPG signal as taught by Aykut, in the invention of Botzer, in order to measure a change of blood volume characteristic (Aykut; Para 68).
Claim(s) 4 is rejected under 35 U.S.C. 103 as being unpatentable over US 2022/0039882 Botzer et al., hereinafter “Botzer”, in view of US 2020/0268313 Burton, hereinafter “Burton”.
Regarding claim 4, Botzer discloses the classification for the input data signal (Para 118; “the neural network 600 can be an autoencoder of the mapping engine 101 that extracts intracardiac based features for classification”).
Botzer does not disclose a pain recognition classification providing a pain biomarker for the input data signal.
However, Burton discloses a neural processes of encoding (Para 220) and teaches a pain recognition classification providing a pain biomarker for the input data signal (Para 53, 87, 132, and 163).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed pain recognition as taught by Burton, in the invention of Botzer, in order to monitor pain of a subject (Burton; Para 53).
Claim(s) 9 is rejected under 35 U.S.C. 103 as being unpatentable over US 2022/0039882 Botzer et al., hereinafter “Botzer”, in view of WO 2022/073947 Lee et al., hereinafter “Lee”.
Regarding claim 9, Botzer discloses all the limitations of claim 7.
Botzer does not disclose one or more parameters of the encoder and the decoder are selected to minimize error between the input data signal and a reconstructed version thereof generated by the decoder.
However, Lee discloses a denoising autoencoder (Abstract) and teaches one or more parameters of the encoder and the decoder (Figure 1A, element 100 with inputs y) are selected to minimize error between the input data signal and a reconstructed version thereof generated by the decoder (Para 3).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed minimizing error as taught by Lee, in the invention of Botzer, in order to maximize the quality of denoising the received signal (Lee; Para 3 and 56).
Claim(s) 11 is rejected under 35 U.S.C. 103 as being unpatentable over US 2022/0039882 Botzer et al., hereinafter “Botzer”, in view of CN 115797830 Li et al., hereinafter “Li”.
Regarding claim 11, Botzer discloses all the limitations of claim 7.
Botzer does not disclose the classifier comprises a multi-layer perceptron (MLP) classifier trained using a cross-entropy loss function.
However, Li discloses an autoencoder (Para 5) and teaches the classifier comprises a multi-layer perceptron (MLP) classifier (Para 21) trained using a cross-entropy loss function (Para 50 and 119).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed MLP as taught by Li, in the invention of Botzer, in order to output the final target characteristic (Li; Para 21-22).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AYA ZIAD BAKKAR whose telephone number is (313)446-6659. The examiner can normally be reached on 7:30 am - 5:00 pm M-Th.
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, Carl Layno can be reached on (571) 272-4949. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AYA ZIAD BAKKAR/
Examiner, Art Unit 3796
/CARL H LAYNO/Supervisory Patent Examiner, Art Unit 3796
Prosecution Insights