DETAILED ACTION
This action is pursuant to claims filed on 01/23/2026. Claims 1-3 and 5-11 are pending. An action on the merits of claims 1-3 and 5-11 is as follows.
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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 01/23/2026 has been entered.
Claim Objections
Claims 1-2 and 10 are objected to because of the following informalities:
In claim 1, line 21, “time domain feature information” should read “the time domain feature information”
In claim 2, line 28, “a chest portion” should read “the chest portion”
In claim 2, line 28, “a wrist” should read “the wrist”
In claim 2, lines 28-29, “an ankle” should read “the ankle”
In claim 10, lines 20-21, “time domain feature information” should read “the time domain feature information”
Appropriate correction is required.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: “a processing unit” in claim 10. This limitation invokes 112(f) based on the three-prong analysis:
(A) “a processing unit for” is a generic placeholder for “means”
(B) The functional language that modifies “ a processing unit for” is the step of “processing the ECG signal based on a deep learning network”
(C) “a processing unit for” is not modified by a sufficient structure for performing the claimed inventions, therefore 35 U.S.C. 112(f) is invoked.
The corresponding structure for “a processing unit” in claim 10 configured to process signals using a deep learning network requires disclosure of an algorithm for performing the claimed specific computer function. In other words, for a special purpose computer-implemented means-plus-function limitation, the structure required is more than simply a general-purposes computer or processor and the specification must disclose an algorithm for performing the claimed function. Paragraphs [0074]-[0081] disclose the algorithm used to create the network, and therefore will be interpreted as the requisite structure of the processing unit.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 2-3 and 11 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 2, the claim recites the limitation “a first clothing” in line 22. It is unclear if this limitation is meant to refer to the clothing from claim 1, line 6, or different clothing. If it is meant to refer to the clothing from claim 1, it needs to refer back to it. If it is meant to refer to a different clothing, it needs to be distinguished from the clothing from claim 1. For purposes of examination, it is being interpreted as referring to the clothing from claim 1. Claim 3 is also rejected due to its dependence on claim 2.
Further regarding claim 2, the claim recites the limitation “a second clothing” in line 26. It is unclear if this limitation is meant to refer to the clothing from claim 1, line 6, or different clothing. If it is meant to refer to the clothing from claim 1, it needs to refer back to it. If it is meant to refer to a different clothing, it needs to be distinguished from the clothing from claim 1. For purposes of examination, it is being interpreted as referring to the clothing from claim 1. Claim 3 is also rejected due to its dependence on claim 2.
Further regarding claim 2, the claim recites the limitation “a third clothing” in line 31. It is unclear if this limitation is meant to refer to the clothing from claim 1, line 6, or different clothing. If it is meant to refer to the clothing from claim 1, it needs to refer back to it. If it is meant to refer to a different clothing, it needs to be distinguished from the clothing from claim 1. For purposes of examination, it is being interpreted as referring to the clothing from claim 1. Claim 3 is also rejected due to its dependence on claim 2.
Further regarding claim 2, the claim recites the limitation “an ECG electrode” in line 32. It is unclear if this limitation is meant to refer to the ECG electrode from lines 2-3, or a different ECG electrode. If it is meant to refer to the ECG electrode from lines 2-3, it needs to refer back to it. If it is meant to refer to a different ECG electrode, it needs to be distinguished from the ECG electrode from lines 2-3. For purposes of examination, it is being interpreted as referring to the ECG electrode from lines 2-3. Claim 3 is also rejected due to its dependence on claim 2.
Further regarding claim 2, the claim recites the limitation “the ECG electrode of the clothing is in contact with the left hand and the left side of a neck” in lines 17-19. It is unclear how a single electrode can be in contact with both the left hand and the left side of a neck. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, it is being interpreted as only requiring the electrode to be in contact with either the left hand or the left side of a neck. Claim 3 is also rejected due to its dependence on claim 2.
Further regarding claim 2, the claim recites the limitation “the ECG electrode separately arranged at a chest portion, a wrist and an ankle” in lines 23-24. It is unclear how a single electrode can be arranged at a chest portion, a wrist and an ankle. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, it is being interpreted as only requiring the electrode to be in contact with either the chest portion, a wrist, or an ankle. Claim 3 is also rejected due to its dependence on claim 2.
Further regarding claim 2, the claim recites the limitation “the ECG electrode separately arranged on a chest portion, a back, a wrist and an ankle” in lines 27-29. It is unclear how a single electrode can be arranged at a chest portion, a back, a wrist and an ankle. The broad and indefinite scope of the limitation fails to inform a person of ordinary skill in the art with reasonable certainty of the metes and bounds of the claimed invention, therefore the claim is rendered indefinite. For purposes of examination, it is being interpreted as only requiring the electrode to be in contact with either the chest portion, a back, a wrist, or an ankle. Claim 3 is also rejected due to its dependence on claim 2.
Regarding claim 11, the claim recites the limitation “at least one lead ECG signal” in lines 6-7. It is unclear if this limitation is meant to refer to the at least one lead ECG signal from claim 1, line 5, or a different at least one lead ECG signal. If it is meant to refer to the at least one lead ECG signal from claim 1, it needs to refer back to it. If it is meant to refer to a different at least one ECG signal, it needs to be distinguished from the at least one ECG signal from claim 1. For purposes of examination, it is being interpreted as referring to the at least one lead ECG signal from claim 1.
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 1 and 8-11 are rejected under 35 U.S.C. 103 as being unpatentable over Khare (US 20240252051) in view of Yang (US 20140343392), Wariar (US 20230337988), and George (US 20200121544).
Regarding independent claim 1, Khare teaches a deep learning-based wearable electro-arteriography (ETAG) processing method for the automatic detection of cardiac diseases, comprising:
acquiring at least one electrocardiogram (ECG) signal collected from a clothing worn by a subject of detection ([0067]: “Animal data can be derived from (e.g., collected from) a targeted individual or multiple targeted individuals (e.g., including a targeted group of multiple targeted individuals, multiple targeted groups of multiple targeted individuals). In the case of sensors, the animal data can be obtained from a single sensor 18 gathering information from each targeted individual”; [0071]: “FIG. 2 illustrates an exemplary output of the ECG measurements from which heart rate variability can be derived.”; [0069]: “Examples include, but are not limited to, … a sensor integrated or embedded into clothing (e.g., shirt, jersey, shorts, wristband, socks, compression gear)” The one sensor embedded into clothing is used to measure ECG signals of the subject.);
acquiring a low-frequency signal related to blood pressure from the collected at least one lead ECG signal ([0070]: “HRV can be measured using a variety of methods and techniques including time-domain (e.g. AVNN, SDNN, pNN50, RMSSD), frequency domain (e.g., ultra-low-frequency (ULF), very-low-frequency (VLF), low-frequency (LF), and high-frequency (HF) bands)”. The ultra-low frequency, very-low-frequency, and low-frequency bands are the low-frequency signals.), wherein the low frequency signal is obtained by passing the collected at least one lead ECG signal through a filter ([0149]: “sensors enters the system is in one of the following structures: raw (no manipulation of the data) or processed (manipulated). The system may house one or more algorithms or other logic that deploy data noise filtering/cleaning techniques”).
However, Khare does not teach the filter specifically being a low-pass filter.
Yang discloses a method and system for detecting heartbeat through ECG electrodes. Specifically, Yang teaches passing the collected at least one lead ECG signal through a low-pass filter ([0277]: “The low-pass filter is connected on the front end of the instrument amplifier, the low-frequency ECG signal (lower than 40 Hz) can be transmitted to the instrument amplifier”). Khare and Yang are analogous arts as they are both related to methods that measure ECG signals and detect the condition of a user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the low-pass filter from Yang into the method from Khare as Khare is silent on the type of filter used, and Yang discloses a suitable filter in an analogous device.
The Khare/Yang combination teaches processing both the collected at least one lead ECG signal and the acquired low-frequency signal as inputs by a deep learning network; wherein the deep learning network comprises a frequency domain-based deep neural network and a time-domain- based neural network (Khare, [0071]: “FIG. 2 illustrates an exemplary output of the ECG measurements from which heart rate variability can be derived.”; [0183]: “one or more Artificial Intelligence techniques can be utilized as part of the one or more methods or systems to create, modify, or enhance one or more reference insights, primary insights, or predictive indicators, as well as to execute any one of the steps required in the one or more methods to collection, transform, and distribute data (e.g., derive R-R intervals, calculate one or more heart rate variability values, calculating one or more heart rate variability baselines, and the like). For definition purposes, Artificial Intelligence includes, but is not limited to, Machine Learning, Deep Learning, Statistical Learning, and the like”; [0070]: “Heart rate variability (HRV) is the variation between each heartbeat and can be computed based upon (e.g., from) the Interbeat Intervals (IBI). HRV can be measured using a variety of methods and techniques including time-domain (e.g. AVNN, SDNN, pNN50, RMSSD), frequency domain (e.g., ultra-low-frequency (ULF), very-low-frequency (VLF), low-frequency (LF), and high-frequency (HF) bands)”. The ECG measurements are used to determine IBIs and the heart rate variability, as shown in Fig. 2, which includes the low frequency signals, and determines the time-domain feature information and frequency-domain feature information. Additionally, deep learning networks are utilized as part of the methods, which can include the determination of heart rate variability.).
However, the Khare/Yang combination does not teach wherein each of which is adapted to perform parallel processing of the inputs to determine a frequency domain feature information and a time domain feature information, respectively.
Wariar discloses an AI-based detection method of physiological events using electrograms. Specifically, Wariar teaches wherein each of which is adapted to perform parallel processing of the inputs to determine a frequency domain feature information and a time domain feature information, respectively ([0050]: “One or more of the external device 106 or the remote device 108 can estimate physiological parameters, detect a physiological event, or detect an operating status of the IMD 102 or the wearable medical device 103 using information collected from the IMD 102 or the wearable medical device 103, such as ambulatory EGMs or ambulatory ECGs collected from the patient 101. In various examples, artificial intelligence (AI) or machine learning (ML) can be used to assist in estimating physiological parameters, or detecting physiological events or device operating status. For example, one or more of the external device 106 or the remote device 108 can include an ML engine that uses a trained ML model to assess and identify different physiological events or physiological parameters. In some examples, one or more of the external device 106 or the remote device 108 can include a computing platform utilizing a parallel processing with interconnected processing nodes and queues that form a workflow for estimating multiple physiological parameters or detecting multiple physiological events substantially concurrently.”). Khare, Yang, and Wariar are analogous arts as they are all related to inventions that analyze heart signals to determine health parameters of a user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the parallel processing from Wariar into the Khare/Yang combination as the combination is silent on the order of the processing steps, and including parallel processing allows for speedier, more efficient processing of the physiological parameters.
The Khare/Yang/Wariar combination teaches based on the determined frequency domain feature information and time domain feature information, determining and outputting a signal processing result (Khare, [0066]: “a schematic of a method and system for generating dynamic real-time predictions using heart rate variability is provided”; A system can be one or more sets of one or more interrelated or interacting components which work together towards achieving one or more common goals or producing one or more desired outputs. The one or more components of a system can include one or more applications, frameworks, platforms or other subsystems, which can be integral to the system or separate from the system but part of a network or multiple networks linked with the system and operable to achieve the one or more common goals or produce the one or more desired outputs”).
The Khare/Yang/Wariar combination teaches outputting a HRV value, however the combination does not teach the signal processing result being related to a tonoarteriogram information comprising a blood pressure variation information, and/or related to a cardiac disease information comprising a myocardial infarction test result.
George teaches systems and methods to treat neurological disorders. Specifically, George teaches the signal processing result being related to a tonoarteriogram information comprising a blood pressure variation information, and/or related to a cardiac disease information comprising a myocardial infarction test result ([0324]: “Decreased heart rate variability can signify decreased parasympathetic response and/or increased sympathetic response, which can be evidence of … myocardial infarction”. The heart rate variability from the Khare/Yang/Wariar combination is the signal processing result, which is related to a cardiac disease information comprising a myocardial infarction test result, as a decrease in heart rate variability can be evidence of myocardial infarction, which can be used as a test to determine possible myocardial infarction.). Khare, Yang, Wariar, and George are analogous arts as they are all related to inventions that analyze heart signals to determine health parameters of a user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the signal processing result being related to a myocardial infarction result as it allows the method to determine more health parameters with the measured values, which can provide the user with more information about their health.
Regarding claim 8, the Khare/Yang/Wariar/George combination teaches the method according to claim 1, wherein the signal processing result related to the tonoarteriogram information further comprises at least one of a tonoarteriogram signal, a systolic blood pressure information, a diastolic blood pressure information and a high blood pressure information (Khare, [0190]: “one or more biological parameters (e.g., heart rate, HRV, diastolic blood pressure, systolic blood pressure, perspiration rate, distance run, etc.) for a specified targeted individual can be, as a function of time while engaged in an activity, functionally modeled (e.g., fit to polynomials)”); the signal processing result related to the cardiac information further comprises at least one of an electrocardiogram and an arrhythmia test result (Khare, [0071]: “FIG. 2 illustrates an exemplary output of the ECG measurements from which heart rate variability can be derived.”).
Regarding claim 9, the Khare/Yang/Wariar/George combination teaches the method according to claim 1, further comprising at least one of the following: transmitting the signal processing result to a user apparatus to display the signal processing result to a user; the user apparatus comprises at least one of a mobile phone, a watch and glasses (Khare, [0177]: “Computing device 42 can also include systems located on the one or more targeted individuals (e.g., another wearable with a display such as a smartwatch, smart glasses, or virtual reality/augmented reality headset) or other individuals interested in accessing the targeted individual's data”; [0182]: “the display can be operating as part of, or displaying receiving animal data or animal data-related information”); uploading the signal processing result to a cloud database and/or a medical platform (Khare, [0043]: “any reference to the collection or gathering of animal data from one or more source sensors from a subject includes gathering the animal data from one or more computing devices associated with the one or more source sensors (e.g., a cloud server or other computing device associated with the one or more source sensors where the data is stored or accessible)”; [0134]: “the on-body transceiver can be operable to communicate with one or more computing devices (e.g., computing subsystem 22, cloud 40)”).
Regarding independent claim 10, Khare teaches a deep learning-based wearable electro-arteriography (ETAG) apparatus for the automatic detection of cardiac diseases, comprising:
an acquiring unit for acquiring at least one electrocardiogram (ECG) signal collected from a clothing worn by a subject of detection ([0067]: “Animal data can be derived from (e.g., collected from) a targeted individual or multiple targeted individuals (e.g., including a targeted group of multiple targeted individuals, multiple targeted groups of multiple targeted individuals). In the case of sensors, the animal data can be obtained from a single sensor 18 gathering information from each targeted individual”; [0071]: “FIG. 2 illustrates an exemplary output of the ECG measurements from which heart rate variability can be derived.”; [0069]: “Examples include, but are not limited to, … a sensor integrated or embedded into clothing (e.g., shirt, jersey, shorts, wristband, socks, compression gear)” The one sensor embedded into clothing is used to measure ECG signals of the subject and is the acquiring unit.);
acquiring a low-frequency signal related to blood pressure from the collected at least one lead ECG signal ([0070]: “HRV can be measured using a variety of methods and techniques including time-domain (e.g. AVNN, SDNN, pNN50, RMSSD), frequency domain (e.g., ultra-low-frequency (ULF), very-low-frequency (VLF), low-frequency (LF), and high-frequency (HF) bands)”. The ultra-low frequency, very-low-frequency, and low-frequency bands are the low-frequency signals.), wherein the low frequency signal is obtained by passing the collected at least one lead ECG signal through a filter ([0149]: “sensors enters the system is in one of the following structures: raw (no manipulation of the data) or processed (manipulated). The system may house one or more algorithms or other logic that deploy data noise filtering/cleaning techniques”).
However, Khare does not teach the filter specifically being a low-pass filter.
Yang discloses a method and system for detecting heartbeat through ECG electrodes. Specifically, Yang teaches passing the collected at least one lead ECG signal through a low-pass filter ([0277]: “The low-pass filter is connected on the front end of the instrument amplifier, the low-frequency ECG signal (lower than 40 Hz) can be transmitted to the instrument amplifier”). Khare and Yang are analogous arts as they are both related to methods that measure ECG signals and detect the condition of a user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the low-pass filter from Yang into the method from Khare as Khare is silent on the type of filter used, and Yang discloses a suitable filter in an analogous device.
The Khare/Yang combination teaches a processing unit for processing both the collected at least one lead ECG signal and the acquired low-frequency signal as inputs by a deep learning network; wherein the deep learning network comprises a frequency domain-based deep neural network and a time-domain- based neural network (Khare, [0071]: “FIG. 2 illustrates an exemplary output of the ECG measurements from which heart rate variability can be derived.”; [0183]: “one or more Artificial Intelligence techniques can be utilized as part of the one or more methods or systems to create, modify, or enhance one or more reference insights, primary insights, or predictive indicators, as well as to execute any one of the steps required in the one or more methods to collection, transform, and distribute data (e.g., derive R-R intervals, calculate one or more heart rate variability values, calculating one or more heart rate variability baselines, and the like). For definition purposes, Artificial Intelligence includes, but is not limited to, Machine Learning, Deep Learning, Statistical Learning, and the like”; [0070]: “Heart rate variability (HRV) is the variation between each heartbeat and can be computed based upon (e.g., from) the Interbeat Intervals (IBI). HRV can be measured using a variety of methods and techniques including time-domain (e.g. AVNN, SDNN, pNN50, RMSSD), frequency domain (e.g., ultra-low-frequency (ULF), very-low-frequency (VLF), low-frequency (LF), and high-frequency (HF) bands)”. The artificial intelligence techniques are the processing unit. The ECG measurements are used to determine IBIs and the heart rate variability, as shown in Fig. 2, which includes the low frequency signals, and determines the time-domain feature information and frequency-domain feature information. Additionally, deep learning networks are utilized as part of the methods, which can include the determination of heart rate variability.).
However, the Khare/Yang combination does not teach wherein each of which is adapted to perform parallel processing of the inputs to determine a frequency domain feature information and a time domain feature information, respectively.
Wariar discloses an AI-based detection method of physiological events using electrograms. Specifically, Wariar teaches wherein each of which is adapted to perform parallel processing of the inputs to determine a frequency domain feature information and a time domain feature information, respectively ([0050]: “One or more of the external device 106 or the remote device 108 can estimate physiological parameters, detect a physiological event, or detect an operating status of the IMD 102 or the wearable medical device 103 using information collected from the IMD 102 or the wearable medical device 103, such as ambulatory EGMs or ambulatory ECGs collected from the patient 101. In various examples, artificial intelligence (AI) or machine learning (ML) can be used to assist in estimating physiological parameters, or detecting physiological events or device operating status. For example, one or more of the external device 106 or the remote device 108 can include an ML engine that uses a trained ML model to assess and identify different physiological events or physiological parameters. In some examples, one or more of the external device 106 or the remote device 108 can include a computing platform utilizing a parallel processing with interconnected processing nodes and queues that form a workflow for estimating multiple physiological parameters or detecting multiple physiological events substantially concurrently.”). Khare, Yang, and Wariar are analogous arts as they are all related to inventions that analyze heart signals to determine health parameters of a user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the parallel processing from Wariar into the Khare/Yang combination as the combination is silent on the order of the processing steps, and including parallel processing allows for speedier, more efficient processing of the physiological parameters.
The Khare/Yang/Wariar combination teaches based on the determined frequency domain feature information and time domain feature information, determining a signal processing result (Khare, [0066]: “a schematic of a method and system for generating dynamic real-time predictions using heart rate variability is provided”; A system can be one or more sets of one or more interrelated or interacting components which work together towards achieving one or more common goals or producing one or more desired outputs. The one or more components of a system can include one or more applications, frameworks, platforms or other subsystems, which can be integral to the system or separate from the system but part of a network or multiple networks linked with the system and operable to achieve the one or more common goals or produce the one or more desired outputs”).
The Khare/Yang/Wariar combination teaches outputting a HRV value, however the combination does not teach the signal processing result being related to a tonoarteriogram information comprising a blood pressure variation information, and/or related to a cardiac disease information comprising a myocardial infarction test result.
George teaches systems and methods to treat neurological disorders. Specifically, George teaches the signal processing result being related to a tonoarteriogram information comprising a blood pressure variation information, and/or related to a cardiac disease information comprising a myocardial infarction test result ([0324]: “Decreased heart rate variability can signify decreased parasympathetic response and/or increased sympathetic response, which can be evidence of … myocardial infarction”. The heart rate variability from the Khare/Yang/Wariar combination is the signal processing result, which is related to a cardiac disease information comprising a myocardial infarction test result, as a decrease in heart rate variability can be evidence of myocardial infarction, which can be used as a test to determine possible myocardial infarction.). Khare, Yang, Wariar, and George are analogous arts as they are all related to inventions that analyze heart signals to determine health parameters of a user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the signal processing result being related to a myocardial infarction result as it allows the method to determine more health parameters with the measured values, which can provide the user with more information about their health.
Regarding claim 11, the Khare/Yang/Wariar/George combination teaches a system for a deep learning-based electro-tonoarteriography for the automatic detection of cardiac diseases, comprising an electronic apparatus and the clothing for the subject of detection (Khare, [0134]: “the on-body transceiver is affixed to, integrated with, or in contact with, a subject's body, skin, hair, vital organ, muscle, skeletal system, eyeball, clothing, object, or other apparatus on a subject”); the clothing collects at least one lead ECG signal of the subject for detection (Khare, [0067]: “Animal data can be derived from (e.g., collected from) a targeted individual or multiple targeted individuals (e.g., including a targeted group of multiple targeted individuals, multiple targeted groups of multiple targeted individuals). In the case of sensors, the animal data can be obtained from a single sensor 18 gathering information from each targeted individual”; [0071]: “FIG. 2 illustrates an exemplary output of the ECG measurements from which heart rate variability can be derived.”; [0069]: “Examples include, but are not limited to, … a sensor integrated or embedded into clothing (e.g., shirt, jersey, shorts, wristband, socks, compression gear)” The one sensor embedded into clothing is used to measure ECG signals of the subject.); and transmits the collected ECG signal to the electronic apparatus via a wireless unit (Khare, [0131]: “computing subsystem 22 can gather animal data 14 from source 12 via one or more communication links either wirelessly, via one or more wired connections, or a combination thereof”; [0132]: “the transmission subsystem enables the one or more sensors 18 to transmit data wirelessly for real-time or near real-time communication”); the electronic apparatus implements the steps of claim 1 (see rejection of claim 1 above).
Claims 2-3 are rejected under 35 U.S.C. 103 as being unpatentable over the Khare/Yang/Wariar/George combination as applied to claim 1 above, and further in view of Saleh (US 20210236039).
Regarding claim 2, the Khare/Yang/Wariar/George combination teaches the method according to claim 1.
However, the Khare/Yang/Wariar/George combination does not teach wherein the clothing is integrated with an ECG electrode; the step of acquiring the at least one lead ECG signal collected from the clothing worn by the subject of detection comprises at least one of the following: acquiring a lead ECG signal I of a limb collected when the clothing is worn at a right hand and the ECG electrode of the clothing is in contact with a left hand of the subject of detection; acquiring a lead ECG signal II of the limb collected when the clothing is worn at the right hand and the clothing is in contact with a left side of a neck or a region above the left side of the neck of the subject of detection; acquiring a lead ECG signal I, II, or III collected when the clothing worn at the right hand and the ECG electrode of the clothing is in contact with the left hand and the left side of a neck, or the region above the left side of the neck of the subject of detection; acquiring at least one lead from twelve-lead ECG signals collected from a first clothing worn by the subject of detection; the first clothing comprises the ECG electrode separately arranged at a chest portion, a wrist and an ankle; acquiring at least one lead from a fifteen-lead ECG signals collected from a second clothing worn by the subject of detection; the second clothing comprises the ECG electrode separately arranged on a chest portion, a back, a wrist and an ankle; acquiring a lead ECG signal VI of the chest portion collected from a third clothing worn by the subject of detection; the third clothing comprises an ECG electrode arranged at the chest portion.
Yang discloses wherein the clothing is integrated with an ECG electrode (Abstract: “The heartbeat is detected by arranging multiple textile electrodes on the textile, using ECG equipotential line diagram”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the ECG electrode from Yang into the Khare/Yang/Wariar/George combination as the combination is silent to the specific structure of the ECG sensor, and Yang discloses a suitable structure in an analogous device.
However, the Khare/Yang/Wariar/George combination is silent on the location of the electrode and the clothing relative to the user’s body.
Saleh discloses an ECG monitoring device. Specifically, Saleh teaches the step of acquiring the at least one lead ECG signal collected from the device worn by the subject of detection comprises at least one of the following: acquiring a lead ECG signal I of a limb collected when the device is worn at a right hand and the ECG electrode of the clothing is in contact with a left hand of the subject of detection ([0046]: “The controller may comprise a set of electrodes including electrodes to contact the user's hands and perform a single lead ECG”); acquiring a lead ECG signal II of the limb collected when the clothing is worn at the right hand and the clothing is in contact with a left side of a neck or a region above the left side of the neck of the subject of detection; acquiring a lead ECG signal I, II, or III collected when the clothing worn at the right hand and the ECG electrode of the clothing is in contact with the left hand and the left side of a neck, or the region above the left side of the neck of the subject of detection; acquiring at least one lead from twelve-lead ECG signals collected from a first clothing worn by the subject of detection; the first clothing comprises the ECG electrode separately arranged at a chest portion, a wrist and an ankle; acquiring at least one lead from a fifteen-lead ECG signals collected from a second clothing worn by the subject of detection; the second clothing comprises the ECG electrode separately arranged on a chest portion, a back, a wrist and an ankle; acquiring a lead ECG signal VI of the chest portion collected from a third clothing worn by the subject of detection; the third clothing comprises an ECG electrode arranged at the chest portion. Khare, Yang, Wariar, and Saleh are analogous arts as they are all related to devices that measure and ECG signal of a user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the position of the ECG sensor from Saleh into the Khare/Yang/Wariar/George combination as the combination is silent on the location of the ECG sensor, and Saleh discloses a suitable location in an analogous device.
Regarding claim 3, the Khare/Yang/Wariar/George/Saleh combination teaches the method according to claim 2.
However, the Khare/Yang/Wariar/George/Saleh combination does not teach wherein the ECG electrode comprises at least one of a dry electrode, a wet electrode, a flexible electrode, a hydrogel ion electrode, an electronic fabric electrode and contactless electronics.
Yang teaches wherein the ECG electrode comprises at least one of a dry electrode, a wet electrode, a flexible electrode, a hydrogel ion electrode, an electronic fabric electrode and contactless electronics ([0016]: “The other purpose of the invention is to provide an object, a method and a system for detecting heartbeat or whether an electrode is in good contact; the technical solution to be solved is that ECG signals can be picked up by dry electrode”).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the specific type of ECG electrode from Yang into the Khare/Yang/Wariar/George/Saleh combination as the combination is silent on the specific type of electrode used, and Yang discloses a suitable electrode in an analogous device.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over the Khare/Yang/Wariar/George combination as applied to claim 1 above, and further in view of Liu (US 20240203599).
Regarding claim 5, the Khare/Yang/Wariar/George combination teaches the method according to claim 1, wherein the step of processing the ECG signal and the low-frequency signal by the deep learning network, determining the signal processing result related to the tonoarteriogram information and/or related to the cardiac disease information comprises: performing a feature extraction on the ECG signal and the low-frequency signal by the frequency-domain based deep neural network of the deep learning network to obtain the frequency domain feature information (Khare, [0149]: “The system may house one or more algorithms or other logic that deploy … extraction or prediction techniques to extract the relevant “good” sensor data from all the sensor data”; [0324]: “To execute the prediction system, the computing subsystem can be configured to operate in a multi-dimensional space (e.g., spatial and temporal dimensions) with one or more inputs from gathered data that include animal data, its associated contextual data, event data (i.e., which includes event outcome data), or a combination thereof. Characteristically, at least a portion of the one or more inputs is orthogonal data (e.g., environmental data). The dimensionality of the gathered data can be reduced using one or more Artificial Intelligence or Statistical techniques like CNNs (Convolutional Neural Networks), PCA (Principal Component Analysis), or other linear and non-linear dimensionality reduction techniques or processes (or a combination thereof) to identify and extract the most important factors (e.g., derived features or representative features of the data set derived from the one or more inputs) contributing towards a prediction”. The artificial intelligence (which includes the deep learning network) extracts important features, which includes the frequency domain feature information.), and performing a feature extraction on the ECG signal and the low-frequency signal by the time-domain based deep neural network of the deep learning network to obtain the time domain feature information (Khare, [0149]: “The system may house one or more algorithms or other logic that deploy … extraction or prediction techniques to extract the relevant “good” sensor data from all the sensor data”; [0324]: “To execute the prediction system, the computing subsystem can be configured to operate in a multi-dimensional space (e.g., spatial and temporal dimensions) with one or more inputs from gathered data that include animal data, its associated contextual data, event data (i.e., which includes event outcome data), or a combination thereof. Characteristically, at least a portion of the one or more inputs is orthogonal data (e.g., environmental data). The dimensionality of the gathered data can be reduced using one or more Artificial Intelligence or Statistical techniques like CNNs (Convolutional Neural Networks), PCA (Principal Component Analysis), or other linear and non-linear dimensionality reduction techniques or processes (or a combination thereof) to identify and extract the most important factors (e.g., derived features or representative features of the data set derived from the one or more inputs) contributing towards a prediction”. The artificial intelligence (which includes the deep learning network) extracts important features, which includes the time domain feature information.).
However, the Khare/Yang/Wariar/George combination is silent on the processing steps included in the determination steps.
Liu discloses a method and system for predicting disease risk. Specifically, Liu teaches performing a pooling operation on the feature information to obtain a pooled feature information ([0088]: “For the feature fusion module, as shown in FIG. 3, a connection layer connects the structured data features and the unstructured data features in parallel along the specified dimension, adopts the SMOTE to reduce the imbalance rate by analyzing the minority class sample data and newly generating the sample of the class, and extracts the important information of the data with different structures respectively according to the different data types by adding the piecewise pooling operation.”); performing a feature fusion classification processing against the pooled feature information by a fully connected network ([0049]-[0050]: “a feature fusion module, being used to fuse the unstructured data features and the structured data features to extract and obtain fusion features; and a classification module, being used to obtain a disease risk prediction result using the fusion features as an input”). Khare, Yang, Wariar, and Liu are analogous arts as they are all related to methods that measure physiological parameters such as ECG signals and determining a health condition of the user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the processing steps from Liu into the Khare/Yang/Wariar/George combination as the combination is silent on the processing steps and Liu discloses suitable steps in an analogous device.
The Khare/Yang/Wariar/George/Liu combination teaches determining the signal processing result related to the tonoarteriogram information and/or related to the cardiac disease information (Khare, [0066]: “a schematic of a method and system for generating dynamic real-time predictions using heart rate variability is provided”; A system can be one or more sets of one or more interrelated or interacting components which work together towards achieving one or more common goals or producing one or more desired outputs. The one or more components of a system can include one or more applications, frameworks, platforms or other subsystems, which can be integral to the system or separate from the system but part of a network or multiple networks linked with the system and operable to achieve the one or more common goals or produce the one or more desired outputs”; George, [0324]: “Decreased heart rate variability can signify decreased parasympathetic response and/or increased sympathetic response, which can be evidence of … myocardial infarction”).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over the Khare/Yang/Wariar/George/Liu combination as applied to claim 5 above, and further in view of Hao (US 20240312638).
Regarding claim 6, the Khare/Yang/Wariar/George/Liu combination teaches the method according to claim 5, wherein the time-domain based deep neural network comprises a sequentially connected convolutional neural network (Khare, [0234]: “The dimensionality of the gathered data can be reduced using one or more Artificial Intelligence or Statistical techniques like CNNs (Convolutional Neural Networks)”).
However, the Khare/Yang/Wariar/George/Liu combination does not teach wherein the time-domain based deep neural network comprises a sequentially connected convolutional neural network and at least one layer of long short-term memory neural network.
Hao discloses a system that gathers data such as ECG data to determine a condition of a user. Specifically, Hao teaches wherein the deep neural network comprises a sequentially connected convolutional neural network ([0088]: “Taking the trained LSTM model as an example, the estimation model may include a plurality of sequentially connected trained neural networks each of which includes an input layer, a hidden layer, and an output layer”) and at least one layer of long short-term memory neural network ([0087]: “The trained sequence model may include a trained recurrent neural network (RNN) (e.g., a trained Long Short-Term Memory (LSTM) model)”). Khare, Yang, Wariar, Liu, and Hao are analogous arts as they are all related to methods that measure physiological parameters such as ECG signals and determining a health condition of the user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the structure of the neural network from Hao into the Khare/Yang/Wariar/George/Liu combination as the combination is silent on the specific structure of the neural network and Hao discloses a suitable structure in an analogous device.
The Khare/Yang/Wariar/George/Liu/Hao combination teaches the step of performing the feature extraction on the ECG signal and the low-frequency signal by the time-domain based deep neural network to obtain the time domain feature information comprises: performing the feature extraction on the ECG signal and the low-frequency signal by the convolutional neural network to obtain a convolutional feature information (Khare, [0149]: “The system may house one or more algorithms or other logic that deploy … extraction or prediction techniques to extract the relevant “good” sensor data from all the sensor data”; [0324]: “To execute the prediction system, the computing subsystem can be configured to operate in a multi-dimensional space (e.g., spatial and temporal dimensions) with one or more inputs from gathered data that include animal data, its associated contextual data, event data (i.e., which includes event outcome data), or a combination thereof. Characteristically, at least a portion of the one or more inputs is orthogonal data (e.g., environmental data). The dimensionality of the gathered data can be reduced using one or more Artificial Intelligence or Statistical techniques like CNNs (Convolutional Neural Networks), PCA (Principal Component Analysis), or other linear and non-linear dimensionality reduction techniques or processes (or a combination thereof) to identify and extract the most important factors (e.g., derived features or representative features of the data set derived from the one or more inputs) contributing towards a prediction”. The convolutional neural network extracts important features, which includes the convolutional feature information.); processing the convolutional feature information by the long short-term memory neural network to obtain the time domain feature information (Khare, [0071]: “FIG. 2 illustrates an exemplary output of the ECG measurements from which heart rate variability can be derived.”; [0183]: “one or more Artificial Intelligence techniques can be utilized as part of the one or more methods or systems to create, modify, or enhance one or more reference insights, primary insights, or predictive indicators, as well as to execute any one of the steps required in the one or more methods to collection, transform, and distribute data (e.g., derive R-R intervals, calculate one or more heart rate variability values, calculating one or more heart rate variability baselines, and the like). For definition purposes, Artificial Intelligence includes, but is not limited to, Machine Learning, Deep Learning, Statistical Learning, and the like”; [0070]: “Heart rate variability (HRV) is the variation between each heartbeat and can be computed based upon (e.g., from) the Interbeat Intervals (IBI). HRV can be measured using a variety of methods and techniques including time-domain (e.g. AVNN, SDNN, pNN50, RMSSD), frequency domain (e.g., ultra-low-frequency (ULF), very-low-frequency (VLF), low-frequency (LF), and high-frequency (HF) bands)”. The ECG measurements are used to determine IBIs and the heart rate variability, as shown in Fig. 2, which includes the low frequency signals, and determines the time-domain feature information.); the time domain feature information comprises dependent information of blood pressure dynamic to time (Khare, [0190]: “one or more biological parameters (e.g., heart rate, HRV, diastolic blood pressure, systolic blood pressure, perspiration rate, distance run, etc.) for a specified targeted individual can be, as a function of time while engaged in an activity, functionally modeled (e.g., fit to polynomials)”. The diastolic blood pressure and systolic blood pressure being a function of time is the blood pressure dynamic over time that can be the time-domain feature information.).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over the Khare/Yang/Wariar/George/Liu combination as applied to claim 5 above, and further in view of Hao and Gao (CN 110575141). Citations to CN 110575141 will refer to the English Machine Translation that accompanies this Office Action.
Regarding claim 7, the Khare/Yang/Wariar/George/Liu combination teaches the method according to claim 5.
However, the Khare/Yang/Wariar/George/Liu combination does not teach wherein the time-domain based deep neural network is a time-domain based interpretable deep learning network; steps of constructing the network comprises: re-structuring the input ECG signal and the low-frequency signal by an input layer; extracting a re-structured feature information of the ECG signal and the low-frequency signal by a convolutional layer; performing a pooling process on the feature information obtained from convolution by a pool layer; processing, sequentially, the feature information obtained from pooling by a previous pooling layer by adding any number of the convolutional layer and the pooling layer; performing, by a fully connected layer, a classification on the feature information obtained from the pooling by a last pooling layer, the fully connected layer is provided with a regularization parameter; calculating a deviation of a result of the classification and evaluating accuracy of a current network.
Hao teaches wherein the time-domain based deep neural network is a time-domain based interpretable deep learning network; steps of constructing the network comprises: re-structuring the input ECG signal and the low-frequency signal by an input layer ([0088]: “the estimation model may include a plurality of sequentially connected trained neural networks each of which includes an input layer”; [0123]: “The heart rate curve may be input to an input layer of the updated first machine learning model 700. For example, the heart rate curve may include a plurality of heart rates over a sequence including different time points. The plurality of heart rates may be input to input layers of the plurality of neural networks of the updated first machine learning model 700 sequentially according to the sequence”. The plurality of heart rates include the ECG signal and the low-frequency signal, and inputting the plurality of heart rates into the machine learning model sequentially according to the sequence is the restructuring of the data.); extracting a re-structured feature information of the ECG signal and the low-frequency signal by a convolutional layer ([0134]: “exemplary model parameters of the first machine learning model 700 may include the number (count) of the plurality of sequentially connected neural networks”; [0134]: “The multiple hidden layers 920 may include one or more convolutional layers, one or more Rectified Linear Units layers (ReLU layers), one or more pooling layers, one or more fully connected layers, or the like, or a combination thereof. For example, the multiple hidden layers 920 may include a layer 1, a layer 2, . . . , a layer L. L is an integer greater than 1. Different layers of the second machine learning model 900 may perform different kinds of processing on their respective input. A successive layer may use an output from a previous layer of the successive hidden layer as an input. In some embodiments, each layer of the second machine learning model 900 may include one or more nodes (e.g., neural units). In some embodiments, each node may be connected to one or more nodes in a previous layer and/or a next layer. The number (or count) of nodes in each layer may be the same or different. In some embodiments, each node may correspond to an activation function”; Khare, [0149]: “The system may house one or more algorithms or other logic that deploy … extraction or prediction techniques to extract the relevant “good” sensor data from all the sensor data”; [0324]: “To execute the prediction system, the computing subsystem can be configured to operate in a multi-dimensional space (e.g., spatial and temporal dimensions) with one or more inputs from gathered data that include animal data, its associated contextual data, event data (i.e., which includes event outcome data), or a combination thereof. Characteristically, at least a portion of the one or more inputs is orthogonal data (e.g., environmental data). The dimensionality of the gathered data can be reduced using one or more Artificial Intelligence or Statistical techniques like CNNs (Convolutional Neural Networks), PCA (Principal Component Analysis), or other linear and non-linear dimensionality reduction techniques or processes (or a combination thereof) to identify and extract the most important factors (e.g., derived features or representative features of the data set derived from the one or more inputs) contributing towards a prediction”. The artificial intelligence (which includes the convolutional layer) extracts important features, which includes the feature information.).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the processing steps from Hao into the Khare/Yang/Wariar/George/Liu combination as the combination is silent on the processing steps and Hao discloses suitable steps in an analogous device.
The Khare/Yang/Wariar/George/Liu/Hao combination teaches performing a pooling process on the feature information obtained from convolution by a pool layer (Hao, Khare/Yang/Wariar/George/Liu combination; Liu, [0088]: “For the feature fusion module, as shown in FIG. 3, a connection layer connects the structured data features and the unstructured data features in parallel along the specified dimension, adopts the SMOTE to reduce the imbalance rate by analyzing the minority class sample data and newly generating the sample of the class, and extracts the important information of the data with different structures respectively according to the different data types by adding the piecewise pooling operation.”).
However, the Khare/Yang/Wariar/George/Liu/Hao combination does not teach processing, sequentially, the feature information obtained from pooling by a previous pooling layer by adding any number of the convolutional layer and the pooling layer.
Gao discloses a network-based seizure detection method. Specifically, Gao teaches processing, sequentially, the feature information obtained from pooling by a previous pooling layer by adding any number of the convolutional layer and the pooling layer (Claim 1: “pooling layer (pooling layer): merging operation reduces the size of the output neuron from a convolution layer, reduce the computational intensity and prevent over-fitting, using the Max-Pooling operation in the present invention”. The pooling layer merges the convolution layer through the merging operation, which includes adding and merging the layers.). Khare, Yang, Wariar, and Gao are analogous arts as they are all devices that use neural networks to detect health conditions of a user.
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the processing steps from Gao into the Khare/Yang/Wariar/George/Liu/Hao combination as the combination is silent on the processing steps of the pooling operation, and Gao discloses suitable processing steps in an analogous device.
The Khare/Yang/Wariar/George/Liu/Hao/Gao combination teaches performing, by a fully connected layer, a classification on the feature information obtained from the pooling by a last pooling layer (Hao, [0134]: “The multiple hidden layers 920 may include … one or more fully connected layers”; [0102]: “The trained CNN model may be configured to determine the at least one scan parameter as a classification problem”; [0134]: “the multiple hidden layers 920 may include a layer 1, a layer 2, . . . , a layer L. L is an integer greater than 1. Different layers of the second machine learning model 900 may perform different kinds of processing on their respective input. A successive layer may use an output from a previous layer of the successive hidden layer as an input. In some embodiments, each layer of the second machine learning model 900 may include one or more nodes (e.g., neural units). In some embodiments, each node may be connected to one or more nodes in a previous layer and/or a next layer”. The layers gather information from the previous layers, therefore the fully connected layer uses information obtained from the pooling by the last pooling layer.).
However, the Khare/Yang/Wariar/George/Liu/Hao/Gao combination does not teach the fully connected layer is provided with a regularization parameter; calculating a deviation of a result of the classification and evaluating accuracy of a current network.
Gao teaches the fully connected layer is provided with a regularization parameter (Claim 1: “the final output decision of CNN model depends on the previous weight and deviation of the layer in the network structure, we use the following formula (7), formula (8) to set the weights and bias: wherein, W, B, l, λ, x, n, m, t, and C respectively represents weight, the deviation, the number of layers, the regularization parameter”); calculating a deviation of a result of the classification and evaluating accuracy of a current network ([0037]: “input the test set into the network for testing and calculate the detection accuracy”. The accuracy of detection shows the deviation of the current network.).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include the regularization parameter and evaluating accuracy of the network from Gao into the Khare/Yang/Wariar/George/Liu/Hao/Gao combination as the combination is silent on the processing steps in the fully connected layer, and Gao provides suitable processing steps in an analogous device. Additionally, including an evaluation of accuracy of a current network can provide the user with a result that informs them how accurate the results of the analysis are, which can further inform them of their health condition and how likely the provided analysis is.
Response to Arguments
Applicant’s arguments with respect to claims 1-3 and 5-11 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ERIN K MCCORMACK whose telephone number is (703)756-1886. The examiner can normally be reached Mon-Fri 7:30-5.
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, Jason Sims can be reached at 5712727540. 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.
/E.K.M./Examiner, Art Unit 3791
/MATTHEW KREMER/Primary Examiner, Art Unit 3791
Prosecution Insights