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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in the instant Application No. 18/248,272, filed on 10/11/2021.
Claim Status
Claims 1-26, and 28 are pending.
Claim 27 is cancelled.
Claims 1-26, and 28 are rejected.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 5/16/2023, 6/26/2023, and 7/10/2026 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Specification
The disclosure is objected to because it contains an embedded hyperlink and/or other form of browser-executable code. Applicant is required to delete the embedded hyperlink and/or other form of browser-executable code; references to websites should be limited to the top-level domain name without any prefix such as http:// or other browser-executable code. See MPEP § 608.01.
The use of the term Bluetooth, Bluetooth Low Energy, Sigfox, LoRa, which is a trade name or a mark used in commerce, has been noted in this application. The term should be accompanied by the generic terminology; furthermore the term should be capitalized wherever it appears or, where appropriate, include a proper symbol indicating use in commerce such as ™, SM , or ® following the term.
Although the use of trade names and marks used in commerce (i.e., trademarks, service marks, certification marks, and collective marks) are permissible in patent applications, the proprietary nature of the marks should be respected and every effort made to prevent their use in any manner which might adversely affect their validity as commercial marks.
Claim Objections
Claim 15 is objected to because of the following informalities: there are two misplaced commas, one in between “MEG” and “signal”, one between “EGG” and “signal”, and one between “EIT” and “signal”. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 9 is rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Specifically claim 9 imposes the following, “FFTs have the same oversampling factors” or “oversampling factors of the FFTs…are different”. As this is a binary choice, where both outcomes are claimed, there is no further limitation placed on the invention, as if the previous operation in claims 1, and 7-8 is performed both outcomes are claimed, there is no difference in what has been claimed. Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 1-26, and 28 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract ideas without significantly more. The claims recite a method for detecting biosignals and life-threatening conditions using a computer model. The judicial exception is not integrated into a practical application because while claims 1-26, and 28 attempt to integrate the exception into a practical application, said application is either generically recited computer elements that do not add a meaningful limitation to the abstract idea or it is insignificant extra solution activity and merely implementing the abstract idea on a computer. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the computer elements only store and retrieve information in memory as well as perform basic calculations that are known to be well-understood, routine and conventional computer functions as recognized by the decisions listed in MPEP § 2106.05(d).
Framework with which to Analyze Subject Matter Eligibility:
Step 1: Are the claims directed to a category of stator subject matter (a process, machine, manufacture, or composition of matter)? [See MPEP § 2106.03]
Claims are directed to statutory subject matter, specifically methods (Claims 1-24), and devices (Claims 25-26, and 28).
Step 2A Prong One: Do the claims recite a judicially recognized exception, i.e., an abstract idea, a law of nature, or a natural phenomenon? [See MPEP § 2106.04(a)]
The claims herein recite abstract ideas, specifically mental processes and mathematical concepts.
With respect to the Step 2A Prong One evaluation, the instant claims are found herein to recite abstract ideas that fall into the grouping of mental processes and mathematical concepts.
Claim 1: Determining information indicating timing of conditions, windowing two-dimensional power spectral densities, and labeling the generated two-dimensional power spectral densities are processes of identifying, selecting, isolating, comparing/contrasting, and calculating information that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 2 Scaling the two-dimensional power spectral densities to a pre-defined range is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process. Scaling the two-dimensional power spectral densities to a pre-defined range is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 3: Interpolating or decimating the two-dimensional power spectral densities to a constant height and width is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 4: The data comprising those specified is merely further limiting the data itself which is an abstract idea, specifically a mental process.
Claim 5: Applying log-transformations and/or absolute value transformations to the two-dimensional power spectral densities is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process. Applying log-transformations and/or absolute value transformations to the two-dimensional power spectral densities is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 6: Monitoring quality of the biosignals is a process of examining, and comparing/contrasting information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 7: Generating the two-dimensional power spectral densities on the basis of Fast Fourier Transform using an oversampling factor greater than or equal to 1 is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process. Generating the two-dimensional power spectral densities on the basis of Fast Fourier Transform using an oversampling factor greater than or equal to 1 is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 8: Generating the two-dimensional power spectral densities on the basis of two Fast Fourier Transforms is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process. Generating the two-dimensional power spectral densities on the basis of two Fast Fourier Transforms is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 9: The Fast Fourier Transforms having the specified oversampling factors is merely further limiting the data itself which is an abstract idea, specifically a mental process.
Claim 10: Applying a modification to a portion of the generating two-dimensional power spectral densities is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 11: Flipping a temporal axis of the generated two-dimensional power spectral densities is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 12: Windowing the sequences on the basis of a predefined window length, generating two-dimensional power spectral densities of the windowed sequences, and controlling a data communications interface to indicate an increased risk are processes of comparing/contrasting, selecting, and calculating information that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 13: The modeling being one of those specified is merely further limiting the data itself which is an abstract idea, specifically a mental process.
Claim 14: The modeling being one of those specified is merely further limiting the data itself which is an abstract idea, specifically a mental process. Forming input sequences of the generating two-dimensional power spectral densities is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 15: The signal data comprising those specified is merely further limiting the data itself which is an abstract idea, specifically a mental process.
Claim 16: The condition comprising those specified is merely further limiting the data itself which is an abstract idea, specifically a mental process.
Claim 17: Windowing the received sequences, and generating two-dimensional power spectral densities are processes of comparing/contrasting, selecting, and calculating information that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 19: Determining the increased risk on the basis of the output exceeding a threshold is a process of comparing/contrasting information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 20: Determining contributions of the generated two-dimensional power spectral densities to increased risk, and determining a contribution history of the two-dimensional power spectral densities to increased risk are processes of calculating information that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 21: Filtering the information indicating the condition is a process of comparing/contrasting and selecting information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 22: Applying log-transformations and/or absolute value transformations to the two-dimensional power spectral densities is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process. Applying log-transformations and/or absolute value transformations to the two-dimensional power spectral densities is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 23: Monitoring quality of the biosignals is a process of examining, and comparing/contrasting information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 24: The model being one of those specified is merely further limiting the data itself which is an abstract idea, specifically a mental process. Forming input sequences of the generated two-dimensional power spectral densities is a process of calculating information that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 25: Windowing the received sequences, and generating two-dimensional power spectral densities are processes of comparing/contrasting, selecting, and calculating information that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 26: The detection device comprising one of those specified is merely further limiting the data itself which is an abstract idea, specifically a mental process.
Claim 28: Determining information indicating timing of one or more conditions, windowing the received sequences, generating two-dimensional power spectral densities, and labeling the generated two-dimensional power spectral densities are processes of comparing/contrasting, selecting, and calculating information that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Step 2A Prong Two: If the claims recite a judicial exception under prong one, then is the judicial exception integrated into a practical application? [See MPEP § 2106.04(d) and MPEP § 2106.05(a)-(c) & (e)-(h)]
Because the claims do recite judicial exceptions, direction under Step 2A Prong Two provides that the claims must be examined further to determine whether they integrate the abstract ideas into a practical application.
The following claims recite the following additional elements in the form of non-abstract elements:
Claim 1: Receiving time-domain sample sequences, and training a computerized model for detection are insignificant extra solution activities, specifically mere data gathering (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 5: Training the model based on the transformations of the two-dimensional power spectral densities is an insignificant extra solution activity, specifically mere data gathering (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 10: Training the computerized model via the generated two-dimensional power spectral densities is an insignificant extra solution activity, specifically mere data gathering (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 11: Training the computerized model via the flipped generated two-dimensional power spectral densities is an insignificant extra solution activity, specifically mere data gathering (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 12: Receiving time-domain sequences, receiving the generated two-dimensional power spectral densities, and outputting information are insignificant extra solution activities, specifically mere data gathering and necessary data outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 14: Training the computerized model via the formed sequences is an insignificant extra solution activity, specifically mere data gathering (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 17: A detection device is a generic and nonspecific element of a computer that does not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)]. Receiving time-domain sequences, receiving the generated two-dimensional power spectral densities, controlling a data communications interface to indicate an increased risk, and outputting information are insignificant extra solution activities, specifically mere data gathering and necessary data outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 18: Controlling a data communications interface to display a risk for a condition is an insignificant extra solution activity, specifically necessary data outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 20: Displaying the current contributions and history in a UI is an insignificant extra solution activity, specifically necessary data outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 22: Feeding the transformations to the model is an insignificant extra solution activity, specifically mere data gathering (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 24: Feeding sequences into the model is an insignificant extra solution activity, specifically mere data gathering (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 25: A detection device, processor, memory, and instructions are generic and nonspecific elements of a computer that do not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)]. Receiving time-domain sequences, receiving the generated two-dimensional power spectral densities, controlling a data communications interface to indicate an increased risk, and outputting information are insignificant extra solution activities, specifically mere data gathering and necessary data outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 28: A training device, memory, instructions, and processor are generic and nonspecific elements of a computer that do not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)]. Receiving time-domain sequences, and training a model for detection of a condition are insignificant extra solution activities, specifically mere data gathering and necessary data outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Step 2B: If the claims do not integrate the judicial exception, do the claims provide an inventive concept? [See MPEP § 2106.05]
Because the additional claim elements do not integrate the abstract idea into a practical application, the claims are further examined under Step 2B, which evaluates whether the additional elements, individually and in combination, amount to significantly more than the judicial exception itself by providing an inventive concept.
The claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite additional elements that are generic, conventional or nonspecific. These additional elements include:
The additional elements of receiving time-domain sample sequences (Conventional: Specification Page 10, Line 10-11 – EEG and PPG biosignals are conventional within the art), receiving the generated two-dimensional power spectral densities, outputting information, controlling a data communications interface to indicate an increased risk, displaying the current contributions and history in a UI, feeding the transformations to the model, feeding the sequences to the model, and training a computerized model for detection (Conventional: Basheer et al. Page 12, Columns 1-2, Paragraphs 1, 3, and 1(2nd column)) are insignificant extra solution activities, specifically mere data gathering and necessary data outputting, that are recognized as well understood, routine and conventional by the courts (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989), Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis), Analyzing DNA to provide sequence information or detect allelic variants, Genetic Techs. Ltd., 818 F.3d at 1377; 118 USPQ2d at 1546, and Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information)) [See MPEP § 2106.05(g)]. Therefore, taken both individually and as whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
The additional elements of a detection device, a training device, memory, instructions, and processor are generic and nonspecific elements of a computer that are well-understood, routine and conventional within the art and therefore do not improve the functioning of any computer or technology described therein (Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information), Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values), and Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015)) [See § MPEP 2106.05(d)(II)]. Therefore, taken both individually and as a whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
Therefore, claims 1-26, and 28, when the limitations are considered individually and as a whole, are rejected under 35 USC § 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 are rejected under 35 U.S.C. 102(a)(I) as being anticipated by Icer et al. (Expert Systems with Applications (2006) 406–413).
Claim 1 is directed to a method for training a device with a computerized model for detection of a specified condition using two-dimensional spectral densities.
Claim 17 is directed to a method for training a device with a computerized model for detection of a specified condition using two-dimensional spectral densities.
Claim 25 is directed to a method for training a device with a computerized model for detection of a specified condition using two-dimensional spectral densities.
Claim 28 is directed to a training a device with a computerized model for detection of a specified condition using two-dimensional spectral densities.
Icer et al. teaches in the abstract “we developed an expert diagnostic system for the interpretation of the portal vein Doppler signals belong the patients with cirrhosis and healthy subjects using signal processing and Artificial Neural Network (ANN) methods. Power spectral densities (PSD) of these signals were obtained to input of ANN using Short Time Fourier Transform (STFT) method. The four layered Multilayer Perceptron (MLP) training algorithms that we have built had given very promising results in classifying the healthy and cirrhosis”. Icer et al. teaches on page 407, column 2, paragraph 2 “portal vein flow waveforms were recorded for patients and healthy subjects using Doppler ultrasound”, reading on receiving, by the one or more training devices, time-domain sample sequences of two or more biosignals from subjects. Icer et al. teaches on page 407, column 1, paragraph 4 “The study included 73 patients with liver disease; (43 men and 30 women with an age range of 30–65, mean: 51 years). Grading of the severity of chronic liver disease was assessed according to the Child classification modified by Pugh, Murray-Lyon, Dawson, Pietroni, & Williams”, reading on determining, by the one or more training devices, on the basis of computer-readable data from a subject database, information indicating timing of one or more life-threatening conditions of subjects. Icer et al. teaches on page 407, column 2, paragraph 4 - 408, column 1, paragraph 1 “Time frequency representation of the nonstationary Doppler signal is performed using the STFT (Short time Forier Transform). The STFT of x(n) is a set of such discrete time Fourier Transform corresponding to different time section of x(n). The time section for time t is obtained by multiplying x(t) with a shifting sequence w(tKt). The expression for the discrete time STFT at time t is therefore given by where w is referred to as the analysis window or sometimes as the analysis filter. Since a short time section of x(n) is the product x(t)w(tKt), it is clear that changing the analysis window will generally change all the short time sections and therefore the STFT (Jae & Oppenheim, 1988). In STFT, the signal is divided into small enough segments, where these segments (portions) of the signal can be assumed to be stationary. The width of this analysis window must be equal to the segment of the signal where its stationarity is valid. In this study, the STFT was performed using a 256 point Hamming window with an overlap of %50 and no zero padding was used”, and it should be noted that a short time Fourier transform inherently maps a one dimensional signal to a two dimensional matrix of time and frequency, thus creating a two-dimensional spectral density, thus reading on windowing, by the one or more training devices, the received time-domain sample sequences on the basis of a predefined window length, and generating, by the one or more training devices, two-dimensional power spectral densities, 2D PSDs, of the windowed time-domain sample sequences. Icer et al. teaches on page 410, column 1, paragraph 1 “During supervised learning, the ANN was trained on input vectors and the target output vectors with which it is required to associate the input vectors. The outputs are represented by unit basis vectors: [0 1] Cirrhosis [1 0] Healthy”, reading on labeling, by the one or more training devices, the generated 2D PSDs to indicate a relationship to a life-threatening condition on the basis of the determined information indicating timing of one or more life-threatening conditions of the subjects and training, by the one or more training devices, a computerized model for detection of a life-threatening condition on the basis of the labeled 2D PSDs. Icer et al. teaches on page 407, column 2, paragraph 3 “The audio output of ultrasound unit was sampled at 44, 100 Hz and then sent to a PC via an input–output card. Thus, the system hardware was composed of digital Doppler ultrasound unit that can works in the pulsed mode, a linear ultrasound probe, an input–output card and a personal computer (PC), which was used for storage, displaying and spectral analysis of the acquired data”, reading on controlling, by the one or more detection devices, the data communications interface to indicate an increased risk for a life-threatening condition on the basis of the output from the trained computerized model.
Claim 4 is directed to the method of claim 1 but further specifies that the data comprises time instants of conditions or elements whose association to conditions can be inferred.
Icer et al. teaches on page 407, column 2, paragraph 2 “portal vein flow waveforms were recorded for patients and healthy subjects using Doppler ultrasound”, on page 407, column 1, paragraph 4 “The study included 73 patients with liver disease; (43 men and 30 women with an age range of 30–65, mean: 51 years). Grading of the severity of chronic liver disease was assessed according to the Child classification modified by Pugh, Murray-Lyon, Dawson, Pietroni, & Williams”, and on page 410, column 1, paragraph 1 “During supervised learning, the ANN was trained on input vectors and the target output vectors with which it is required to associate the input vectors. The outputs are represented by unit basis vectors: [0 1] Cirrhosis [1 0] Healthy”, reading on wherein the computer-readable data from a subject database comprises time instants of life-threatening conditions and/or elements whose association to one or more life- threatening conditions can be inferred, such as, diagnoses, treatments, procedures, SNOMED Clinical Terms and/or ICD-codes associated with timestamps.
Claim 5 is directed to the method of claim 1 but further specifies the application of a log or absolute value transform to the spectral densities and training on those transforms.
Claim 22 is directed to the method of claim 17 but further specifies the application of a log or absolute value transform to the spectral densities and training on those transforms.
Icer et al. teaches in Table 1 “An example of a training set consists of random selected subjects”, which includes the “Network Inputs” as “the logarithm of PSD”, reading on applying log transformations to the generated 2D PSDs and/or absolute value transformations to the generated 2D PSDs and training the computerized model based on the log-transformations of the generated 2D PSDs and/or the absolute value transformations of the generated 2D PSDs.
Claim 10 is directed to the method of claim 1 but further specifies the application of a modification to at least a portion of the spectral density and then training on the modified density.
Icer et al. teaches in Table 1 “An example of a training set consists of random selected subjects”, which includes the “Network Inputs” as “the logarithm of PSD”, reading on applying, by the one or more training devices, a modification to a portion of at least one of the generated 2D PSDs, and training, by the one or more training devices, the computerized model on the basis of the generated 2D PSDs comprising at least one 2D PSD comprising the modification.
Claim 12 is directed to the method of claim 1 but further specifies performing the method following training.
Icer et al. teaches on age 410, column 1, paragraph 3 “The test performance of the network classifier was evaluated by computing of the statistical parameters the percentages of correct classification, false negative-normal, false positive cirrhosis, sensitivity and specificity”, reading on wherein after training of the computerized model has been completed, wherein the method comprises. Icer et al. teaches in the abstract “we developed an expert diagnostic system for the interpretation of the portal vein Doppler signals belong the patients with cirrhosis and healthy subjects using signal processing and Artificial Neural Network (ANN) methods. Power spectral densities (PSD) of these signals were obtained to input of ANN using Short Time Fourier Transform (STFT) method. The four layered Multilayer Perceptron (MLP) training algorithms that we have built had given very promising results in classifying the healthy and cirrhosis”. Icer et al. teaches on page 407, column 2, paragraph 2 “portal vein flow waveforms were recorded for patients and healthy subjects using Doppler ultrasound”, reading on receiving, by the one or more training devices, time-domain sample sequences of two or more biosignals from subjects. Icer et al. teaches on page 407, column 1, paragraph 4 “The study included 73 patients with liver disease; (43 men and 30 women with an age range of 30–65, mean: 51 years). Grading of the severity of chronic liver disease was assessed according to the Child classification modified by Pugh, Murray-Lyon, Dawson, Pietroni, & Williams”, reading on determining, by the one or more training devices, on the basis of computer-readable data from a subject database, information indicating timing of one or more life-threatening conditions of subjects. Icer et al. teaches on page 407, column 2, paragraph 4 - 408, column 1, paragraph 1 “Time frequency representation of the nonstationary Doppler signal is performed using the STFT (Short time Forier Transform). The STFT of x(n) is a set of such discrete time Fourier Transform corresponding to different time section of x(n). The time section for time t is obtained by multiplying x(t) with a shifting sequence w(tKt). The expression for the discrete time STFT at time t is therefore given by where w is referred to as the analysis window or sometimes as the analysis filter. Since a short time section of x(n) is the product x(t)w(tKt), it is clear that changing the analysis window will generally change all the short time sections and therefore the STFT (Jae & Oppenheim, 1988). In STFT, the signal is divided into small enough segments, where these segments (portions) of the signal can be assumed to be stationary. The width of this analysis window must be equal to the segment of the signal where its stationarity is valid. In this study, the STFT was performed using a 256 point Hamming window with an overlap of %50 and no zero padding was used”, and it should be noted that a short time Fourier transform inherently maps a one dimensional signal to a two dimensional matrix of time and frequency, thus creating a two-dimensional spectral density, thus reading on windowing, by the one or more training devices, the received time-domain sample sequences on the basis of a predefined window length, and generating, by the one or more training devices, two-dimensional power spectral densities, 2D PSDs, of the windowed time-domain sample sequences. Icer et al. teaches on page 410, column 1, paragraph 1 “During supervised learning, the ANN was trained on input vectors and the target output vectors with which it is required to associate the input vectors. The outputs are represented by unit basis vectors: [0 1] Cirrhosis [1 0] Healthy”, reading on labeling, by the one or more training devices, the generated 2D PSDs to indicate a relationship to a life-threatening condition on the basis of the determined information indicating timing of one or more life-threatening conditions of the subjects and training, by the one or more training devices, a computerized model for detection of a life-threatening condition on the basis of the labeled 2D PSDs. Icer et al. teaches on page 407, column 2, paragraph 3 “The audio output of ultrasound unit was sampled at 44, 100 Hz and then sent to a PC via an input–output card. Thus, the system hardware was composed of digital Doppler ultrasound unit that can works in the pulsed mode, a linear ultrasound probe, an input–output card and a personal computer (PC), which was used for storage, displaying and spectral analysis of the acquired data”, reading on controlling, by the one or more detection devices, the data communications interface to indicate an increased risk for a life-threatening condition on the basis of the output from the trained computerized model.
Claim 18 is directed to the method of claim 17 but further specifies controlling a user interface to display the increased risk for the condition.
Icer et al. teaches on page 407, column 2, paragraph 3 “The audio output of ultrasound unit was sampled at 44, 100 Hz and then sent to a PC via an input–output card. Thus, the system hardware was composed of digital Doppler ultrasound unit that can works in the pulsed mode, a linear ultrasound probe, an input–output card and a personal computer (PC), which was used for storage, displaying and spectral analysis of the acquired data”, reading on controlling, by the one or more detection devices, a user interface operatively connected to the one or more detection devices, to display the increased risk for a life-threatening condition.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 2-3, 7-9 are rejected under 35 U.S.C. 103 as being unpatentable over Icer et al. (Expert Systems with Applications (2006) 406–413) as applied to claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 above, and further in view of Bisina et al. (International Conference on Intelligent Computing and Control Systems (ICICCS) (2017) 871-875).
Claim 2 is directed to the method of claim 1 but further specifies that the sequences or power spectral densities be scaled to a predefined range.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 as described above.
Icer et al. does not teach that the sequences or power spectral densities be scaled to a predefined range.
Bisina et al. teaches on page 873, column 1, paragraph 5 “In order to avoid these problems, only a small subset of the total data is analyzed through a process called windowing. Figure 3 shows the window filter for a 3-tap symmetric FIR filter. Window w[n] can be any smaller value less than one to scale down the input”, reading on scaling, by the one or more training devices, the 2D PSDs or the time-domain sample sequences to predefined range of values common to the 2D PSDs or the time-domain sample sequences.
It would have been obvious at the time of first filing to have modified the teachings of Icer et al. for the method of claim 1, with the teachings of Bisina et al. for the use of a window size less than one to scale the input, as the latter teaches in the abstract “Power Spectral density analysis plays an important role in different applications. So an efficient method is needed for the computation. Fast fourier transform can be implemented using CORDIC algorithm which uses shifters and adders for the computation. Replacing the normal FFT by CORDIC FFT in PSD computation will reduce the memory requirement, delay, power and the number of lookup tables”. One would have had a reasonable expectation of success given that the latter is merely specifying an alternative method for calculating the two-dimensional power spectral densities which would be merely a substitution of known methods with expected outcomes, and the latter method is computationally more efficient. Therefore, it would have been obvious at the time of filing to have modified the teachings of each and to be successful.
Claim 3 is directed to the method of claim 1 but further specifies the interpolating or decimating of the two-dimensional power spectral densities to a constant height and width.
Bisina et al. teaches on page 873, column 1, paragraph 3 “decimation is the process of decreasing the sampling rate of the signal whereas interpolation is the process of increasing the sampling rate. Decimation factor M is usually an integer value which keeps only the Mth sample of the input given to the decimator. Therefore, the number of samples is reduced by using a decimator to avoid the computation burden”, which when using the two-dimensional power spectral densities as an input to the network, would require the two-dimensional power spectral densities to be of identical dimensions, K x K, such that the convolutional network could process them, making this step obvious and inherent to the method and reading on interpolating or decimating the 2D PSDs to a constant height and width.
Claim 7 is directed to the method of claim 1 but further specifies the two-dimensional power spectral densities to be derived from a fast Fourier transform with oversampling greater than 1.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 as described above.
Icer et al. does not teach that the two-dimensional power spectral densities to be derived from a fast Fourier transform with oversampling greater than 1.
Bisina et al. teaches on page 871, column 2, paragraph 3 “Fast Fourier Transform (FFT) algorithm is used to compute the Discrete Fourier Transform (DFT) in an efficient way (number of computations are lesser for FFT) and are used in computation of spectral densities. DFT is a mathematical operation which transforms a signal from its original domain to frequency domain and vice-versa.The introduction of fast algorithms to calculate the DFT, known as Fast Fourier Transforms (FFTs), reduces the complexity and the processing time, particularly for large signal segments”, on page 872, column 2, paragraph 3 “When a particular frequency response is needed, there are different filter design methods. They are: (a) Window design, (b) Frequency sampling, (c) Weighted least squares and (d) Parks- McClellan (also known as Equiripple, Optimal or Minimax method)”, and on page 873, column 1, paragraph 3 “In Digital Signal Processing (DSP), decimation is the process of decreasing the sampling rate of the signal whereas interpolation is the process of increasing the sampling rate. Decimation factor M is usually an integer value which keeps only the Mth sample of the input given to the decimator”, therefore the selection of an oversampling factor greater than 1 is merely obvious to optimize as a parameter within the model, which reads on generating, by the one or more training devices, the 2D PSDs on the basis of Fast Fourier Transform, FFT, using an oversampling factor > 1.
Claim 8 is directed to the method of claim 7 and thus claim 1, but further specifies that there be two fast Fourier transforms.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 as described above.
Icer et al. does not teach that there be two fast Fourier transforms.
Bisina et al. teaches on oage 871, column 2, paragraph 3 “Fast Fourier Transform (FFT) algorithm is used to compute the Discrete Fourier Transform (DFT) in an efficient way (number of computations are lesser for FFT) and are used in computation of spectral densities. DFT is a mathematical operation which transforms a signal from its original domain to frequency domain and vice-versa.The introduction of fast algorithms to calculate the DFT, known as Fast Fourier Transforms (FFTs), reduces the complexity and the processing time, particularly for large signal segments”, claim 1 requires the generating of two-dimensional power spectral densities, furthermore, claim 8 requires the use of the Fast Fourier Transform, but in order to get a two-dimensional power spectral density using a Fast Fourier Transform, it would be necessary to compute the Fast Faourier Transform twice as only doing it once would result in a one dimensional power spectral density, and therefore it is inherent to the method and reads on generating, by the one or more training devices, one or more combined 2D PSDs on the basis of at least two Fast Fourier Transforms, FFTs.
Claim 9 is directed to the method of claim 8 and thus claim 1, but further specifies the oversampling factors to either be the same or different.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 as described above.
Icer et al. does not teach that the oversampling factors to either be the same or different.
Bisina et al. teaches on oage 871, column 2, paragraph 3 “Fast Fourier Transform (FFT) algorithm is used to compute the Discrete Fourier Transform (DFT) in an efficient way (number of computations are lesser for FFT) and are used in computation of spectral densities. DFT is a mathematical operation which transforms a signal from its original domain to frequency domain and vice-versa.The introduction of fast algorithms to calculate the DFT, known as Fast Fourier Transforms (FFTs), reduces the complexity and the processing time, particularly for large signal segments”, on page 872, column 2, paragraph 3 “When a particular frequency response is needed, there are different filter design methods. They are: (a) Window design, (b) Frequency sampling, (c) Weighted least squares and (d) Parks- McClellan (also known as Equiripple, Optimal or Minimax method)”, and on page 873, column 1, paragraph 3 “In Digital Signal Processing (DSP), decimation is the process of decreasing the sampling rate of the signal whereas interpolation is the process of increasing the sampling rate. Decimation factor M is usually an integer value which keeps only the Mth sample of the input given to the decimator”, as there are only two choices, the factors are the same or different, and the claim limitation claims both, it would be obvious and inherent to method that the use of the FFT and oversampling that the limitations of the claim be met, and so reads on wherein the FFTs have the same oversampling factors or oversampling factors of the FFTs of the single 2D PSDs are different.
Claims 6 and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Icer et al. (Expert Systems with Applications (2006) 406–413) as applied to claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 above, and further in view of Hu et al. (IEEE transactions on nanobioscience (2015) 553-561).
Claim 6 is directed to the method of claim 1 but further specifies that biosignals be monitored for quality by a computerized model.
Claim 23 is directed to the method of claim 17 but further specifies that biosignals be monitored for quality by a computerized model.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 as described above.
Icer et al. does not teach that the biosignals be monitored for quality by a computerized model.
Hu et al. teaches in the abstract “In order to improve the performance and reliability of EEG sensors in real-life settings, we propose a method to evaluate the quality of EEG signals, based on which users can easily adjust the connection between electrodes and their skin. Our method helps to filter invalid EEG data from personal trials in both domestic and office settings. We then apply an algorithm based on Discrete Wavelet Transformation (DWT) and Adaptive Noise Cancellation (ANC) which has been designed to remove ocular artifacts (OA) from the EEG signal. DWT is applied to obtain a reconstructed OA signal as a reference while ANC, based on recursive least squares, is used to remove the OA from the original EEG data”, reading on monitoring quality of one or more of the biosignals based on one or more biosignal-specific computerized models.
It would have been obvious at the time of first filing to have modified the teachings of Icer et al. for the method of claim 1 with the teachings of Hu et al. for a quality monitoring model for signal data as the latter teaches in the abstract “Evaluation results demonstrate that our EEG sensor and data processing algorithms have successfully addressed the requirements and challenges of a portable system for patient monitoring”, and on page 560, column 1, paragraph 3 “EEG signals collected from subject's forehead are very easily contaminated by noise. This is especially true for OA. The paper addresses this issue by proposing a new model combining DWT and ANC to remove OA in the low frequency band even when OA's frequency band is overlapping with that of the EEG signal”. One would have had a reasonable expectation of success given that the latter is merely performing a quality control step prior to implementation of the model within the prior claims and would only function to remove poor quality signal data. Furthermore, within the paper the method is implemented as an intermediate step in the process of diagnostics for EEG data, similar to its proposed implementation within the instant application. Therefore, it would have been obvious at the time of filing to have modified the teachings of each and to be successful.
Claims 11 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Icer et al. (Expert Systems with Applications (2006) 406–413) as applied to claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 above, and further in view of Chambon et al. (IEEE Transactions on Neural Systems and Rehabilitation Engineering 26.4 (2018): 758-769).
Claim 11 is directed to the method of claim 1 but further specifies the flipping of the temporal axis of the two-dimensional power spectral densities and then training the model.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 as described above.
Icer et al. does not teach the flipping of the temporal axis of the two-dimensional power spectral densities and then training the model.
Chambon et al. teaches on page 760, column 2, paragraph 2 “Following this linear operation, the dimensions are permuted, see layer 4 in Tab. I. Then two blocks of temporal convolution followed by non-linearity and max pooling are consecutively applied. The parameters have been set for signals sampled at 128Hz. In this case the number of time steps is T = 128 × 30 = 3840. Each block first convolves its input signal with 8 estimated kernels of length 64 with stride 1 (∼ 0.5 s of record) before applying a rectified linear unit, a.k.a. ReLU non-linearity x → max(x, 0) [31]. The outputs are then reduced along the time axis with a max pooling layer (size of 16 without overlap). The output of the two convolution blocks is finally passed through a dropout layer [32] which randomly prevents updates of 25% of its output neurons at each gradient step”, and in Table 1 provides a description for each of the layers including layer 4 which is the permutation of the temporal axis as described in the cited portion above, thereby reading on flipping, by the one or more training devices, a temporal axis of at least one of the generated 2D PSDs, and training, by the one or more training devices, the computerized model on the basis of the generated 2D PSDs comprising the at least one 2D PSD comprising the flipped temporal axis.
It would have been obvious at the time of first filing to have modified the teachings of Icer et al. for the method of claim 1 with the teachings of Chambon et al. for the permuting/flipping of the temporal axis as the latter teaches within the abstract “Results obtained on 61 publicly available PSG records with up to 20 EEG channels demonstrate that our network architecture yields the state-of-the-art performance”. One would have had a reasonable expectation of success given that both are using similar signal data, neural networks, and producing a classification, with the latter merely adding in the step of permuting the temporal axis which resulted in an increase to model performance. Therefore, it would have been obvious at the time of filing to have modified the teachings of each and to be successful.
Claim 20 is directed to the method of claim 17 but further specifies the determination of the contributions of the power spectral densities to the condition and their history of contribution.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 as described above.
Icer et al. does not teach the determination of the contributions of the power spectral densities to the condition and their history of contribution.
Chambon et al. teaches on page 762, column 2, paragraph 7 “we perform a general benchmark of our feature extractor against hand-crafted features classified with Gradient Boosting, and the two network architectures just described. The purpose of this experiment is to benchmark different feature representations on a similar spatial context, Fz-Cz, without using the temporal context, and to emphasize the benefits of processing multivariate time series”, reading on determining, by the one or more detection devices, current contributions of the generated 2D PSDs to the increased risk for life-threatening condition, determining, by the one or more detection devices, a contribution history of the generated 2D PSDs to the increased risk for a life-threatening condition, and displaying, by the one or more detection devices, the current contributions and the contribution history on a user interface.
Claim 21 is directed to the method of claim 17 but further specifies the filtering of the data by condition.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 as described above.
Icer et al. does not teach the filtering of the data by condition.
Chambon et al. teaches on page 761, column 2, paragraph 4 “Data used in our experiments is the publicly available MASS dataset - session 3 [17]. It corresponds to 62 night records, each one coming from a different subject. Because of preprocessing issues we removed the record 01-03-0034”, it would be obvious to a person skilled in the art to remove or filter data that do not correspond to the condition being examined, or to filter for the specified condition being examined, thereby reading on filtering, by the one or more detection devices, the information indicating a life-threatening condition.
Claims 13, 15-16, and 26 are rejected under 35 U.S.C. 103 as being unpatentable over Icer et al. (Expert Systems with Applications (2006) 406–413) as applied to claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 above, and further in view of Acharya et al. (Computers in biology and medicine (2018) 270-278).
Claim 13 is directed to the method of claim 1 but further specifies that the model be one of those specified.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 as described above.
Icer et al. does not teach that the model be one of those specified.
Acharya et al. teaches on page 272, column 1, paragraph 2 “a deep learning method is employed to automatically identify the three classes of EEG signals. To the best the authors' knowledge, this is the first EEG study to employ deep learning algorithm for the automated classification of three EEG classes. A 13-layer deep convolutional neural network (CNN) is developed to categorize the normal, preictal, and seizure class”, and on the same page, column 2, paragraph 3 “An improved and recently-developed neural network, known as Convolutional Neural Network (CNN) is employed in this research”, reading on wherein the computerized model is a convolutional neural network, a Bayesian convolutional neural network, an ensemble of convolutional neural networks, an ensemble of Bayesian convolutional neural networks, a transformer network, an ensemble of transformer networks, Bayesian transformer network or an ensemble of Bayesian transformer networks.
It would have been obvious at the time of first filing to have modified the teachings of Icer et al. for the method of claim 1 with the teachings of Acharya et al. for the use of a CNN, as the latter is using EEG signal data to create spectral densities to predict using the CNN, a diseased status, similar Icer et al. using doppler to predict a diseased status. Furthermore, Acharya et al. teaches in the abstract that “The proposed technique achieved an accuracy, specificity, and sensitivity of 88.67%, 90.00% and 95.00%, respectively”. One would have had a reasonable expectation of success given that it is merely the substitution of one known method using similar data with another known method, and in fact the substituted method is merely a subcategory of the original method. Therefore, it would have been obvious at the time of filing to have modified the teachings of each and to be successful.
Claim 15 is directed to the method of claim 1 but further specifies that the sequences comprise one of those specified.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17, 22, 25, and 28 as described above.
Icer et al. does not teach that the sequences comprise one of those specified.
Acharya et al. teaches on page 272, column 1, paragraph 2 “a deep learning method is employed to automatically identify the three classes of EEG signals. To the best the authors' knowledge, this is the first EEG study to employ deep learning algorithm for the automated classification of three EEG classes. A 13-layer deep convolutional neural network (CNN) is developed to categorize the normal, preictal, and seizure class”, reading on wherein the time-domain sample sequences comprise at least one of electrocardiogram, ECG, signal, a thermocouple signal, electroencephalogram, EEG, signal, infrared signal, pressure signal, accelerometer signal, radar signal, ballistocardiographic signal, capnography signal, photoplethysmography signal, electrodermal activity signal, near- infrared spectroscopy signal, mid-infrared spectroscopy signal, transcutaneous bilirubin signal, impedance pneumography signal, electromyography, EMG, signal Filed Herewith magnetoencephalography, MEG, signal, electrogastrogram, EGG, signal, electrical impedance tomography, EIT, signal and an invasive blood pressure signal.
Claim 16 is directed to the method of claim 1 but further specifies that the condition comprise one of those specified.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17, 22, 25, and 28 as described above.
Icer et al. does not teach that the condition comprises one of those specified.
Acharya et al. teaches on page 272, column 1, paragraph 2 “a deep learning method is employed to automatically identify the three classes of EEG signals. To the best the authors' knowledge, this is the first EEG study to employ deep learning algorithm for the automated classification of three EEG classes. A 13-layer deep convolutional neural network (CNN) is developed to categorize the normal, preictal, and seizure class”, reading on wherein the life-threatening condition comprises at least one of respiratory failure, sepsis, cardiac arrest, cardiac failure, congestive heart failure, renal failure, overhydration, pulmonary edema, hyper metabolic state, overexertion, brain injury, ischemic stroke, hemorrhagic stroke, multiorgan failure, anastomotic leak, internal bleeding, cardiac injury, intestinal obstruction, intestinal rupture, pulmonary embolus, opioid induced respiratory depression, seizure, over sedation, anaphylaxis, hypoxic brain damage, pneumonia, deep vein thrombosis, meningitis, malignant arrhythmia, hypovolemic shock, cardiogenic shock, obstructive shock, distributive shock, toxic shock, septic shock, myocardial infarction, wound infection, diabetic coma, endocarditis, myocarditis, pericarditis, intracranial hypertension, intestinal injury, liver failure, liver injury, pancreatitis, cardiovascular collapse, peritonitis, poisoning, drug reaction, aortic dissection and acute respiratory distress syndrome.
Claim 26 is directed to the method of claim 1 but further specifies that the condition comprise one of those specified.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17, 22, 25, and 28 as described above.
Icer et al. does not teach that the condition comprises one of those specified.
Acharya et al. teaches on page 272, column 1, paragraph 2 “a deep learning method is employed to automatically identify the three classes of EEG signals. To the best the authors' knowledge, this is the first EEG study to employ deep learning algorithm for the automated classification of three EEG classes. A 13-layer deep convolutional neural network (CNN) is developed to categorize the normal, preictal, and seizure class”, reading on wherein the detection device for measuring biosignals comprises at least one of electrocardiogram, ECG, signal measurement device, a thermocouple signal measurement device, electroencephalogram, EEG, signal measurement device, infrared signal measurement device, pressure signal measurement device, accelerometer signal measurement device, radar signal measurement device, ballistocardiographic signal measurement device, capnography signal measurement device, photoplethysmography signal measurement device, electrodermal activity signal measurement device, near-infrared spectroscopy signal measurement device, mid-infrared spectroscopy signal measurement device, transcutaneous bilirubin signal measurement device and impedance pneumography signal measurement device, electromyography, EMG, signal measurement device, invasive blood pressure measurement device, magnetoencephalography, MEG, signal measurement device, electrogastrogram, EGG, signal measurement device, electrical impedance tomography, EIT, signal measurement device an interface configured to connect to an electrocardiogram, ECG, signal measurement device, an interface configured to connect to a thermocouple signal measurement device, an interface Filed Herewith configured to connect to electroencephalogram, EEG, signal measurement device, an interface configured to connect to a infrared signal measurement device, an interface configured to connect to a pressure signal measurement device, an interface configured to connect to a accelerometer signal measurement device, an interface configured to connect to a radar signal measurement device, an interface configured to connect to a ballistocardiographic signal measurement device, an interface configured to connect to a capnography signal measurement device, an interface configured to connect to a photoplethysmography signal measurement device, an interface configured to connect to a electrodermal activity signal measurement device, an interface configured to connect to a near-infrared spectroscopy signal measurement device, an interface configured to connect to a mid-infrared spectroscopy signal measurement device, an interface configured to connect to a transcutaneous bilirubin signal measurement device, an interface configured to connect to an impedance pneumography signal measurement device, an interface configured to connect to a electromyography, EMG, signal measurement device, an interface configured to connect to magnetoencephalography, MEG, signal measurement device, an interface configured to connect to electrogastrogram, EGG, signal measurement device, an interface configured to connect to electrical impedance tomography, EIT, signal measurement device and an interface configured to connect to a invasive blood pressure measurement device.
Claims 14 and 24 are rejected under 35 U.S.C. 103 as being unpatentable over Icer et al. (Expert Systems with Applications (2006) 406–413) and Acharya et al. (Computers in biology and medicine (2018) 270-278) as applied to claims 1, 4-5, 10, 12-13, 15-18, 22, 25-26, and 28 above, and further in view of Wu et al. (Advances in neural information processing systems (2020) 17105-17115).
Claim 14 is directed to the method of claim 13 and thus claim 1, but further specifies that the model comprise one of the specified models and using that model for the method.
Claim 24 is directed to the method of claim 17 but further specifies that the model comprise one of the specified models and using that model for the method.
Icer et al. and Acharya et al. teach the method of claims 1, 4-5, 10, 12-13, 15-18, 22, 25-26, and 28 as described above.
Icer et al. and Acharya et al. do not teach that the model comprises one of the specified models and using that model for the method.
Wu et al. teaches in the abstract “we propose a new time series forecasting model – Adversarial Sparse Transformer (AST), based on Generative Adversarial Networks (GANs). Specifically, AST adopts a Sparse Transformer as the generator to learn a sparse attention map for time series forecasting, and uses a discriminator to improve the prediction performance at a sequence level”, reading on wherein the computerized model is a transformer network, an ensemble of transformer networks, Bayesian transformer network or an ensemble of Bayesian transformer networks, and the method comprises: forming input sequences of the generated 2D PSDs, and training the computerized model by feeding the computerized model the formed sequences.
It would have been obvious at the time of first filing to have modified the teachings of Icer et al. and Acharya et al. for the method of claims 1, 13, and 17 with the teachings of Wu et al. for the use of a transformer network, specifically their adversarial sparse transformer, as the latter teaches on page 9, paragraph 1 “we improve the contiguous and fidelity at the sequence level… Extensive experiments on a series of real-world time series datasets have demonstrated the effectiveness of AST for both short-term and long-term time series forecasting. According to the experimental results, we argue that (1) adversarial training can improve the time series forecasting from a global perspective, and (2) the dependencies among steps of time series have some tend of sparsity”. One would have had a reasonable expectation of success given that the all papers are working with time series data and neural networks, merely different subcategories of networks, which would merely be a substitution of known methods. Therefore, it would have been obvious at the time of filing to have modified the teachings of each and to be successful.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Icer et al. (Expert Systems with Applications (2006) 406–413) as applied to claims 1, 4-5, 10, 12, 17-18, 22, 25, and 28 above, and further in view of Mirowski et al. (IEEE workshop on machine learning for signal processing (2008) 244-249).
Claim 19 is directed to the method of claim 17 but further specifies determining an increased risk based on the output exceeding a predefined threshold.
Icer et al. teaches the method of claims 1, 4-5, 10, 12, 17, 22, 25, and 28 as described above.
Icer et al. does not teach determining an increased risk based on the output exceeding a predefined threshold.
Mirowski et al. teaches in the abstract “In this study, we use modern machine learning techniques to predict seizures from a number of features proposed in the literature. We concentrate on aggregated features that encode the relationship between pairs of EEG channels, such as cross-correlation, nonlinear interdependence, difference of Lyapunov exponents and wavelet analysis-based synchrony such as phase locking. We compare L1-regularized logistic regression, convolutional networks, and support vector machines”, and on page 245, column 1, paragraph 3 “the common approach is to average EEG-derived features (over time and/or over several EEG channels) and to ultimately perform binary classification of a single variable [6]. Binary classification consists in an a posteriori and in-sample tuning of a threshold”, reading on determining, by the one or more detection devices, the increased risk for a life-threatening condition on the basis of the output from the trained computerized model exceeding a predefined threshold.
It would have been obvious at the time of first filing to have modified the teachings of Icer et al. for the method of claim 1 with the teachings of Mirowski et al. for the use of a threshold in calculating the risk of a condition, as the latter is presenting current methods in a review of how to associate signals, specifically EEG signals, to predict a condition, seizures. Furthermore, Mirowski et al. specifically points to binary classification as the common approach, which is what the neural network in Icer et al. is doing, predicting a binary. One would have had a reasonable expectation of success given that it is merely the substitution of one known method using similar data with another known method, and the primary reference is performing binary classification. Therefore, it would have been obvious at the time of filing to have modified the teachings of each and to be successful.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEENAN NEIL ANDERSON-FEARS whose telephone number is (571)272-0108. The examiner can normally be reached M-Th, alternate F, 8-5.
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, Karlheinz Skowronek can be reached at 571-272-9047. 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.
/K.N.A./Examiner, Art Unit 1687
/LARRY D RIGGS II/Supervisory Patent Examiner, Art Unit 1686
Prosecution Insights