DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Applicant’s arguments, see pages 11-14, filed 10/20/2025, with respect to the rejection(s) of Claims 1-16, 18, and 20 under 35 U.S.C. § 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Minici, Cheng, Zhang, Asada, Walsh, and Mazumder.
Applicant's arguments filed 10/20/2025 have been fully considered but they are not persuasive.
Regarding the rejection of the Claims 1-16, 18 and 20 under 35 U.S.C. § 101, the applicant has argued the training of a convolutional neural network (CNN) and utilizing the trained CNN to classify the data matrices is not a mental process practically performed in the human mind. Specifically, "In the specification, the terms, claim 1, before the amendments in this Response, recited, inter alia, "training, by the one or more processors, with training data, a convolutional neural network process comprising a machine learning algorithm to classify segments into a finite number of groups, wherein each group represents a distinct physical activity of the physical activities; and utilizing, by the one or more processors, the previously trained convolutional neural network process, to classify the one or more data matrices into the one or more pre-defined stability categories." There is no reasonable interpretation that does not limit this claim to a convolutional neural network, which is not in anyone's mind and is not a mathematical computation. Hence, it is inextricably tied to computing…The Office Action states does not even explain how [the claim limitation] can be accomplished in the human mind or by as a mathematical computation. There is no support for Examiner's implication that this aspect is a mental process or mathematical computation but furthermore, one cannot eliminate the context of the claim in determining "the broadest reasonable interpretation." However, the Applicant has failed to clearly distinguish even their broadest reasonable interpretation of this claim from the similar limitations of steps (c)-(e) in Example 47 in the “July 2024 Subject Matter Eligibility Examples” discussed in the 2024 Guidance Update on Patent Subject Matter Eligibility, Including on Artificial Intelligence published by the USPTO (“2024 Guidance”), wherein training and utilizing a machine learning algorithm to classify information has already been considered a judicial exception. For reference, a comparison is made below:
Claim 2, Example 47. Anomaly Detection
Claim 1, 17/504939
(c) training, by the computer, the ANN based on the input data and a selected training algorithm to generate a trained ANN, wherein the selected training algorithm includes a backpropagation algorithm and a gradient descent algorithm;
wherein training the machine learning algorithm comprises: training ... with training data, a
convolutional neural network process comprising a machine learning algorithm to classify
segments into a finite number of groups, wherein each group represents a distinct physical
activity of the physical activities; and utilizing ... the previously trained convolutional neural network process, to classify the one or
more data matrices into the one or more pre-defined stability categories
(d) detecting one or more anomalies in a data set using the trained ANN;
classifying, by the one or more processors, based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories, wherein the pre-defined stability categories comprise a first category and a second category…
(e) analyzing the one or more detected anomalies using the trained ANN to generate anomaly data; and
wherein the first category indicates stability and the second category indicates instability, wherein the first category and the second category indicate postural performance and gait performance;
(f) outputting the anomaly data from the trained ANN.
generating ... a stability score representing stability of the wearer when performing the
common physical activity for each group of the at least one group, based on analyzing the one
or more data matrices and weighting the classifications into the one or more pre-defined
stability categories
The 2024 Guidance states “Step (c) recites training an ANN using a selected algorithm. The training algorithm is a backpropagation algorithm and a gradient descent algorithm. When given their broadest reasonable interpretation in light of the background, the backpropagation algorithm and gradient descent algorithm are mathematical calculations. The plain meaning of these terms are optimization algorithms, which compute neural network parameters using a series of mathematical calculations”. The applicant’s own specification recites “the CNN can be MobileNet or MobileNet2 and available in libraries such as Keras, TensorFlow, and other libraries known by a person of ordinary skill in the art” ([0065]). This is also an algorithm that, at its base level, computes neural network parameters using a series of mathematical calculations. Therefore, it follows that if Claim 2 of Example 47 of the 2024 Guidance is considered a judicial exception, then the pending claims must also be considered a judicial exception.
The Applicant further argues “Updates to the MPEP, the 2019 Revised Patent Subject Matter Eligibility Guidance ("Guidance"), the examples published with the Guidance, which were integrated into the MPEP, the updated October 17, 2019 Guidance (the "October Guidance"), the Federal Circuit's decision in Berkheimer, and the April 19, 2018 Memorandum entitled Changes in Examination Procedure Pertaining to Subject Matter Eligibility, Recent Subject Matter Eligibility Decision (Berkheimer v. HP. Inc.) ("Memorandum") would not support a finding of claims 1, 13, and 20 being directed to a mental process and support a contrary finding.” However, notably absent from this list is the “July 2024 Subject Matter Eligibility Examples” discussed in the 2024 Guidance Update on Patent Subject Matter Eligibility, Including on Artificial Intelligence published by the USPTO. It was in this guidance that training and utilizing a machine learning algorithm to classify information was unequivocally considered a judicial exception.
The applicant has further argued “Although scrutinizing whether the claims are directed to a practical application is unnecessary because the claims are inextricably tied to computing, the claims are expressly directed to a practical application (in the technical field of computing)… The generation of this score in the independent claims, claims 1 and 20, is described in the aspects of the claims and is not "abstract" in any way. Additionally, this is practical. As stated in the specification, "[T]he program code continually improves the risk assessment methodology applied based on machine learning. Utilizing machine learning to improve predictions for subject stability is a practical application that is inextricably tied to computing and is achieved in the pending claims.” However, the generation of this score in the independent claims is disclosed to be a numerical score in the Applicant’s specification (“The second classification process 500 can comprise classifying the sample segments 17 of a user activity related data group 41 according to stability classes or values that can be categorical or numerical”, [0034]; “In some examples, the weighting process 700 can comprise a classification process to classify the sample segments 17 in a data group into certain categorical or numerical levels or values of stability”, [0035]). This is the very definition of a mathematical operation, which is an abstract idea, and abstract ideas cannot provide a practical application or significantly more (e.g., an improvement). Both Step 2A, Prong Two and Step 2B require an additional element, not an abstract idea, to provide a practical application or significantly more (e.g., an improvement). See Genetic Technologies Limited v. Merial LLC (Fed Cir 2016).
For these reasons, the rejection of the Claims 1-16, 18, and 20 under 35 U.S.C. § 101 is maintained.
Specification
The disclosure is objected to because of the following informalities:
In [0017], “Aspects of the examples assess therapeutic responses to show an temporal changes, including improvements and/or impairments, of the postural and gait performance of the individual, when the individual is engaged in daily activities” should read “Aspects of the examples assess therapeutic responses to show [[an]] temporal changes, including improvements and/or impairments, of the postural and gait performance of the individual, when the individual is engaged in daily activities”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-16, 18, and 20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claims 1 and 20 recite “classifying, by the one or more processors, based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories, wherein the pre-defined stability categories comprise a first category and a second category, wherein the first category indicates stability and the second category indicates instability, wherein the first category and the second category indicate postural performance and gait performance”. However, the only mention of postural performance in the originally filed specification comes from [0017] in the written description, which recites “Aspects of the examples assess therapeutic responses to show an temporal changes, including improvements and/or impairments, of the postural and gait performance of the individual, when the individual is engaged in daily activities.”. There are no further words, descriptions, figures, diagrams, disclosure of an actual reduction to practice, or algorithmic flowcharts that show the Applicant had possession of a first and second category that indicate postural performance, specifically.
Claims 1-16, 18 are rejected by virtue of dependence on Claim 1, respectively.
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.
Claims 1-16, 18, and 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) as a whole, considering all claim elements both individually and in combination, do not amount to significantly more than an abstract idea. A streamlined analysis of claim 1 follows.
Regarding Claim 1, the claim recites a computer-implemented method for determining a user stability score. Thus, the claim is directed to a process, which is one of the statutory categories of invention (Step 1).
The claim is then analyzed to determine whether it is directed to any judicial exception (Step 2A, Prong One). The following limitations set forth a judicial exception:
obtaining…a data sample from an inertial sensor device, …wherein the data sample is comprised of data signals and a time vector, wherein the data sample is obtained by the inertial sensor device based on the inertial sensor device monitoring physical activities of a wearer during a time period represented by the time vector
segmenting…the data sample into segments, wherein each segment comprises data from a time slice of the time period represented by the time vector
determining…a physical activity of the physical activities of the wearer performed during each time slice
grouping…into at least one group, times slices in which the wearer performed a common physical activity of the physical activities
applying…a change of basis transformation on data signals comprising each group of the at least one group, to generate one or more data matrices
classifying… based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories, wherein the pre-defined stability categories comprise a first category and a second category, wherein the first category indicates stability and the second category indicates instability, wherein the first category and the second category indicate postural performance and gait performance
wherein training the machine learning algorithm comprises: training…with training data, a convolutional neural network process comprising a machine learning algorithm to classify segments into a finite number of groups, wherein each group represents a distinct physical activity of the physical activities
utilizing… the previously trained convolutional neural network process, to classify the one or more data matrices into the one or more pre-defined stability categories
generating…a stability score representing stability of the wearer when performing the common physical activity for each group of the at least one group, based on analyzing the one or more data matrices and weighting the classifications into the one or more pre-defined stability categories
These limitations describe a mathematical calculation and/or a mental process as the skilled artisan is capable of performing the recited limitations and making a mental assessment thereafter. Examiner also notes that nothing from the claims suggest that the limitations cannot be practically performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time. Examiner also notes that nothing from the claims suggests an undue level of complexity that the mathematical calculations and/or the mental process steps cannot be practically performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps.
For example:
A human is capable of manually/mentally obtaining, by one or more processors, a data sample from an inertial sensor device.
Segmenting the data sample into segments, wherein each segment comprises data from a time slice of the time period represented by the time vector is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Determining a physical activity of the physical activities of the wearer performed during each time slice is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Grouping into at least one group, times slices in which the wearer performed a common physical activity of the physical activities is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Applying a change of basis transformation on data signals comprising each group of the at least one group, to generate one or more data matrices is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Classifying based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories, wherein the pre-defined stability categories comprise a first category and a second category, wherein the first category indicates stability and the second category indicates instability, and wherein the first category and the second category indicate postural performance and gait performance is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Training, by the one or more processors, with training data, a convolutional neural network process comprising a machine learning algorithm to classify segments into a finite number of groups, wherein each group represents a distinct physical activity of the physical activities is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Utilizing the previously trained convolutional neural network process, to classify the one or more data matrices into the one or more pre-defined stability categories is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Generating a stability score representing stability of the wearer when performing the common physical activity for each group of the at least one group, based on analyzing the one or more data matrices and weighting the classifications into the one or more pre-defined stability categories is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Next, the claim as a whole is analyzed to determine whether any element, or combination of elements, integrates the identified judicial exception into a practical application (Step 2A, Prong Two).
The following limitations amount to insignificant extra-solution activity to the judicial exception, e.g. mere data gathering. See MPEP 2106.05(g).
wherein a wearable device comprises the inertial sensor device
wherein the data sample is obtained by the inertial sensor device based on the inertial sensor device monitoring physical activities of a wearer during a time period represented by the time vector
The following limitations amount to a recitation of the words "apply it" (or an equivalent)and/or nothing more than mere instructions to implement the abstract idea on a generic computer. See MPEP 2106.05(f).
obtaining, by one or more processors…
determining, by the one or more processors…
determining, by the one or more processors…
grouping, by the one or more processors…
applying, by the one or more processors…
classifying, by the one or more processors…
training, by the one or more processors…
utilizing, by the one or more processors…
generating, by the one or more processors…
Therefore, these additional limitations do not integrate the judicial exception into a practical application.
Next, the claim as a whole is analyzed to determine whether any element, or combination of elements, amounts to significantly more than the identified judicial exception (Step 2B):
The following limitations do not amount to significantly more than the abstract idea for substantially similar reasons applied in Step 2A, Prong Two.
wherein a wearable device comprises the inertial sensor device
wherein the data sample is obtained by the inertial sensor device based on the inertial sensor device monitoring physical activities of a wearer during a time period represented by the time vector
obtaining, by one or more processors…
determining, by the one or more processors…
determining, by the one or more processors…
grouping, by the one or more processors…
applying, by the one or more processors…
classifying, by the one or more processors…
training, by the one or more processors…
utilizing, by the one or more processors…
generating, by the one or more processors…
The following limitations is/are considered to be well-understood, routine, and conventional (WURC).
The inertial sensor device is considered to be well-understood, routine, and conventional based on statement from the applicant' s specification filed 10/19/2021 (“The inertial sensor device 200 can be a hardware element that comprises one or more sensor elements configured to obtain data, including one or more data signals 10, from the user 32. In some examples, the sensor is an accelerometer, gyroscope, magnetometer, equivalent technologies that are known by a person of ordinary skill in the art, or combinations thereof”, [0069]).
Regarding Claim 20, the claim recites a computer program product. Thus, the claim is directed to an apparatus, which is one of the statutory categories of invention (Step 1).
The claim is then analyzed to determine whether it is directed to any judicial exception (Step 2A, Prong One). The following limitations set forth a judicial exception:
obtaining…a data sample from an inertial sensor device, …wherein the data sample is comprised of data signals and a time vector, wherein the data sample is obtained by the inertial sensor device based on the inertial sensor device monitoring physical activities of a wearer during a time period represented by the time vector
segmenting…the data sample into segments, wherein each segment comprises data from a time slice of the time period represented by the time vector
determining…a physical activity of the physical activities of the wearer performed during each time slice
grouping…into at least one group, times slices in which the wearer performed a common physical activity of the physical activities
applying…a change of basis transformation on data signals comprising each group of the at least one group, to generate one or more data matrices
classifying… based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories, wherein the pre-defined stability categories comprise a first category and a second category, wherein the first category indicates stability and the second category indicates instability, wherein the first category and the second category indicate postural performance and gait performance
wherein training the machine learning algorithm comprises: training…with training data, a convolutional neural network process comprising a machine learning algorithm to classify segments into a finite number of groups, wherein each group represents a distinct physical activity of the physical activities
utilizing… the previously trained convolutional neural network process, to classify the one or more data matrices into the one or more pre-defined stability categories
generating…a stability score representing stability of the wearer when performing the common physical activity for each group of the at least one group, based on analyzing the one or more data matrices and weighting the classifications into the one or more pre-defined stability categories
These limitations describe a mathematical calculation and/or a mental process as the skilled artisan is capable of performing the recited limitations and making a mental assessment thereafter. Examiner also notes that nothing from the claims suggest that the limitations cannot be practically performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time. Examiner also notes that nothing from the claims suggests an undue level of complexity that the mathematical calculations and/or the mental process steps cannot be practically performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps.
For example:
A human is capable of manually/mentally obtaining, by one or more processors, a data sample from an inertial sensor device.
Segmenting the data sample into segments, wherein each segment comprises data from a time slice of the time period represented by the time vector is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Determining a physical activity of the physical activities of the wearer performed during each time slice is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Grouping into at least one group, times slices in which the wearer performed a common physical activity of the physical activities is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Applying a change of basis transformation on data signals comprising each group of the at least one group, to generate one or more data matrices is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Classifying based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories, wherein the pre-defined stability categories comprise a first category and a second category, wherein the first category indicates stability and the second category indicates instability, and wherein the first category and the second category indicate postural performance and gait performance is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Training, by the one or more processors, with training data, a convolutional neural network process comprising a machine learning algorithm to classify segments into a finite number of groups, wherein each group represents a distinct physical activity of the physical activities is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Utilizing the previously trained convolutional neural network process, to classify the one or more data matrices into the one or more pre-defined stability categories is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Generating a stability score representing stability of the wearer when performing the common physical activity for each group of the at least one group, based on analyzing the one or more data matrices and weighting the classifications into the one or more pre-defined stability categories is a mathematical calculation that can be performed by a human with the aid of a pen and paper, or using a generic computer as a tool to perform mathematical calculations and/or mental process steps in real time.
Next, the claim as a whole is analyzed to determine whether any element, or combination of elements, integrates the identified judicial exception into a practical application (Step 2A, Prong Two).
The following limitations amount to insignificant extra-solution activity to the judicial exception, e.g. mere data gathering. See MPEP 2106.05(g).
wherein a wearable device comprises the inertial sensor device
wherein the data sample is obtained by the inertial sensor device based on the inertial sensor device monitoring physical activities of a wearer during a time period represented by the time vector
The following limitations amount to a recitation of the words "apply it" (or an equivalent)and/or nothing more than mere instructions to implement the abstract idea on a generic computer. See MPEP 2106.05(f).
a computer readable storage medium readable by one or more processors of a computing system and storing instructions for execution by the one or more processors for performing a method comprising…
obtaining, by one or more processors…
determining, by the one or more processors…
determining, by the one or more processors…
grouping, by the one or more processors…
applying, by the one or more processors…
classifying, by the one or more processors…
training, by the one or more processors…
utilizing, by the one or more processors…
generating, by the one or more processors…
Therefore, these additional limitations do not integrate the judicial exception into a practical application.
Next, the claim as a whole is analyzed to determine whether any element, or combination of elements, amounts to significantly more than the identified judicial exception (Step 2B):
The following limitations do not amount to significantly more than the abstract idea for substantially similar reasons applied in Step 2A, Prong Two.
wherein a wearable device comprises the inertial sensor device
wherein the data sample is obtained by the inertial sensor device based on the inertial sensor device monitoring physical activities of a wearer during a time period represented by the time vector
a computer readable storage medium readable by one or more processors of a computing system and storing instructions for execution by the one or more processors for performing a method comprising…
obtaining, by one or more processors…
determining, by the one or more processors…
determining, by the one or more processors…
grouping, by the one or more processors…
applying, by the one or more processors…
classifying, by the one or more processors…
training, by the one or more processors…
utilizing, by the one or more processors…
generating, by the one or more processors…
The following limitations is/are considered to be well-understood, routine, and conventional (WURC).
The inertial sensor device is considered to be well-understood, routine, and conventional based on statement from the applicant' s specification filed 10/19/2021 (“The inertial sensor device 200 can be a hardware element that comprises one or more sensor elements configured to obtain data, including one or more data signals 10, from the user 32. In some examples, the sensor is an accelerometer, gyroscope, magnetometer, equivalent technologies that are known by a person of ordinary skill in the art, or combinations thereof”, [0069]).
Dependent Claims 2-7, 9-16 and 18 also fail to add subject matter qualifying as significantly more to the abstract independent claims as they merely further limit the abstract idea.
Dependent Claims 8-11, and 15 also fail to add subject qualifying as significantly more to the abstract independent claims as they recite limitations that do not integrate the claims into a practical application for substantially similar reasons as set forth above.
Dependent Claims 8-11, and 15 also fail to add subject matter integrating the judicial exception or qualifying as significantly more to the abstract independent claims as they do not recite significantly more than the identified abstract idea for substantially similar reasons as set forth above.
Therefore, Claims 1-16, 18, and 20 are not patent eligible under 35 U.S.C. § 101.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-4, 6-8, 12-13, 16 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over the Non-Patent Literature (NPL) to Minici et al (“Wavelet-based analysis of gait for automated frailty assessment with a wrist-worn device”, hereinafter Minici) in view of Cheng et al (US 20200218974 Al, hereinafter Cheng) and Mazumder et al (US 20190008417 A1, hereinafter Mazumder).
Regarding Claim 1, Minici discloses a computer-implemented method for determining a user stability score (“Wavelet-based analysis of gait for automated frailty assessment with a wrist-worn device”, Title), the method comprising:
obtaining, by one or more processors, a data sample from an inertial sensor device, wherein a wearable device comprises the inertial sensor device (“Shimmer 3 is a wearable device embedding a tri-axial accelerometer (STMicroLSM303DLHC) [15], which was used to collect acceleration samples at 102:4 Hz”, Section III.A; “Filtered acceleration components are then provided to the gait segment detection module”, Section II.A), wherein the data sample is comprised of data signals and a time vector (“Acceleration is sampled at 102:4 Hz”, Section II.A; this means acceleration data signals are sampled with a certain number of samples per unit time, i.e. a time vector accompanies the data), wherein the data sample is obtained by the inertial sensor device based on the inertial sensor device monitoring physical activities of a wearer during a time period represented by the time vector (“participants were asked to walk 60 meters at their preferred pace”, Section III.A);
segmenting, by the one or more processors, the data sample into segments (“a gait segment detection technique identifies gait segments on the whole signal trace”, Section II), wherein each segment comprises data from a time slice of the time period represented by the time vector (“A gait cycle is the sequence of events that occur during the walking process between two consecutive heel strikes of the same foot. Henceforth, we will use the term gait segment to indicate four consecutive gait cycles”, Section II.B; each gait cycle would be accompanied by the time vector data corresponding to it);
determining, by the one or more processors, a physical activity of the physical activities of the wearer performed during each time slice (“a gait segment detection technique identifies gait segments on the whole signal trace”, Section II);
grouping, by the one or more processors, into at least one group, times slices in which the wearer performed a common physical activity of the physical activities (“Henceforth, we will use the term gait segment to indicate four consecutive gait cycles”, Section II.B; “Wavelet analysis is applied to gait segments detected in the previous step”, Section II.C);
applying, by the one or more processors, a change of basis transformation on data signals comprising each group of the at least one group (“we use the Continuous Wavelet Transform (CWT) on the acceleration magnitude signal to obtain a representation of the gait segment into the time-frequency domain,”, Section II.C), to generate one or more data matrices (“The phase discussed above produces as output a matrix MCWT of coefficients cij for each gait segment, where i denotes the frequency value, obtained from the scale factor, and j denotes the instant in time ”, Section II.D);
classifying, by the one or more processors, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories, wherein the pre-defined stability categories comprise a first category and a second category, wherein the first category indicates stability and the second category indicates instability (“Finally, band-based feature extraction is responsible for gathering information from the CWT output, which is used to determine which Frequency Bands (FBs) contain the most valuable information for frailty status assessment”, Section II; “the subject was classified according to a majority voting scheme: if more than 40% of the band-based gait instances were classified as non-robust, the subject was classified as non-robust”, Section III.B), wherein the first category and the second category indicate gait performance (“if more than 40% of the band-based gait instances were classified as non-robust, the subject was classified as non-robust”, Section III.B; therefore, a <40% or >40% non-robust classification are a first and second category that indicate stability and instability, respectively, and also indicate gait performance), and
generating, by the one or more processors, a stability score representing stability of the wearer when performing the common physical activity for each group of the at least one group, based on analyzing the one or more data matrices and weighting the classifications into the one or more pre- defined stability categories (“the subject was classified according to a majority voting scheme: if more than 40% of the band-based gait instances were classified as non-robust, the subject was classified as non-robust”, Section III.B; therefore, a <40% or >40% non-robust classification is a stability score representing stability of the wearer).
Minici discloses the claimed invention except for expressly disclosing classifying, by the one or more processors, based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories, wherein the first category and the second category indicate postural performance, and wherein training the machine learning algorithm comprises:
training, by the one or more processors, with training data, a convolutional neural network process comprising a machine learning algorithm to classify segments into a finite number of groups, wherein each group represents a distinct physical activity of the physical activities; and
utilizing, by the one or more processors, the previously trained convolutional neural network process, to classify the one or more data matrices into the one or more pre-defined stability categories.
However, Cheng teaches classifying, by the one or more processors, based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined activity categories (See Fig. 4), wherein training the machine learning algorithm comprises:
training, by the one or more processors, with training data (“The input data 20 may also be applied to training the CNN 30”, [0158]), a convolutional neural network process (“The NN may be a convolutional neural network (“CNN”)”, [0009]) comprising a machine learning algorithm to classify segments (“The processor 18 applies a deep learning neural network that is a convolutional neural network 30 (“CNN”) to the input data 20 for classifying the subject's activity and resulting in classified activity data 38 that may be expressed in any suitable form”, [0157]) into a finite number of groups, wherein each group represents a distinct physical activity of the physical activities (“the activity includes standing, sitting, lying, crouching, walking, running, shuffling, skipping, dancing, ascending or descending stairs”, [0063]); and
utilizing, by the one or more processors, the previously trained convolutional neural network process, to classify the one or more data matrices (See Fig. 4; after the recursive “TRAINING: YES” step, the trained CNN can be used to classify activity data in the “TRAINING: NO” step) into the one or more pre-defined activity categories (See Fig. 4; after the recursive “TRAINING: YES” step, the trained CNN can be used to classify activity data in the “TRAINING: NO” step).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the computer-implemented method of Minici with the classifying input data using a convolutional neural network (i.e. classifying data matrices into the pre-defined stability categories already taught by Minici), because using a convolutional neural network to classify data matrices improves classification by distinguishing between potentially small measurable differences, as taught by Cheng ([0005]).
Mazumder, which also discloses a computer-implemented method for determining a user stability score (“By processing the SLS duration, the body joint vibration, and the body sway area together, a postural stability index score for the user is determined, and based on this score, postural stability assessment for the user is performed”, Abstract) teaches pre-defined stability categories, wherein the first category and the second category indicate postural performance (“A stability index generation module of the postural stability assessment system then determines the SLS duration, the body joint vibration, and the body sway area, of the user as falling under at least one respective category, and further generates a postural stability index score for the user, based on the determined at least one category of the SLS duration, the body joint vibration, and the body sway area. A stability assessment module of the postural stability assessment system then assesses postural stability of the user, based on the postural stability index score”, [0007]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include postural performance in the first and second categories of Minici, because postural instability is one of the prominent symptoms associated with geriatric population (Mazumder, [0003]), and accounting for posture makes the computer-implemented method of Minici more accurate in its assessment of frailty.
Regarding Claim 2, modified Minici discloses the computer-implemented method of claim 1, wherein the change of basis transformation comprises a wavelet transformation (“we use the Continuous Wavelet Transform (CWT) on the acceleration magnitude signal to obtain a representation of the gait segment into the time-frequency domain,”, Section II.C).
Regarding Claim 3, modified Minici computer-implemented of claim 1, wherein each time slice comprises: a pre-defined length of time or a quantifiable number of acts completed in a given physical activity of the physical activities during the time slice (“A gait cycle is the sequence of events that occur during the walking process between two consecutive heel strikes of the same foot. Henceforth, we will use the term gait segment to indicate four consecutive gait cycles”, Section II.B; each gait cycle would be accompanied by the time vector data corresponding to it).
Regarding Claim 4, modified Minici discloses the computer-implemented method of claim 1, wherein determining the physical activity is based on one or more of: a portion of the data sample from the inertial sensor device (“a gait segment detection technique identifies gait segments on the whole signal trace”, Section II), or data entry by the wearer through an interface of the inertial sensor device.
Regarding Claim 6, modified Minici discloses the computer-implemented method of claim 1, wherein a given group of the at least one group comprises a gait group (“Henceforth, we will use the term gait segment to indicate four consecutive gait cycles”, Section II.B).
Regarding Claim 7, modified Minici discloses the computer-implemented method of claim 1, wherein the pre-defined stability categories comprise a first category and a second category, wherein the first category indicates stability and the second category indicates instability (“Specifically, we implemented seven Random Forest binary classifiers by means of the Python module Scikit-learn … in order to distinguish robust subjects from non-robust ones (i.e., pre-frail or frail)”, Section III.B).
Regarding Claim 8, modified Minici discloses the computer-implemented method of claim 1, wherein the inertial sensor device comprises one inertial measurement unit sensor (“Shimmer 3 is a wearable device embedding a tri-axial accelerometer (STMicroLSM303DLHC) [15], which was used to collect acceleration samples at 102:4 Hz”, Section III.A).
Regarding Claim 12, modified Minici discloses the computer-implemented method of claim 1, wherein the one or more data matrices comprise scalograms (“The phase discussed above produces as output a matrix MCWT of coefficients cij for each gait segment, where i denotes the frequency value, obtained from the scale factor, and j denotes the instant in time. Usually, this matrix of coefficients is plotted through the wavelet power spectrum (or scalogram).”, Section II.D).
Regarding Claim 13, Minici discloses the computer-implemented method of claim 1, wherein the data signals are selected from the group consisting of: three-axis-low noise acceleration (“Shimmer 3 is a wearable device embedding a tri-axial accelerometer (STMicroLSM303DLHC) [15], which was used to collect acceleration samples at 102:4 Hz”, Section III.A; “After a preprocessing step aimed at reducing noise…”, Section II), three-axis- wide range acceleration, and three-axis-gyroscopic angular rate.
Regarding Claim 16, modified Minici discloses the computer-implemented method of claim 1, wherein the physical activity of the physical activities of the wearer performed during each time slice comprises:
identifying, by the one or more processors, the physical activity, based on at least one parameter of data comprising each segment selected from the group consisting of: mean, variance, standard deviation, energy, leading frequencies, maximum values (“In this phase, gait segments are automatically identified by means of the walking detection algorithm described in [13], which is based on the analysis of the acceleration magnitude signal.”, Section II.B), minimum values, and correlation values.
Regarding Claim 18, modified Minici discloses the computer-implemented method of claim 1. Modified Minici discloses the claimed invention except for expressly disclosing wherein each group of the finite number of groups represents a distinct physical activity selected from the group consisting of: walking group, walking on stairs, and standing. However, Cheng teaches wherein each group of the finite number of groups represents a distinct physical activity selected from the group consisting of: walking group, walking on stairs, and standing (“the activity includes standing, sitting, lying, crouching, walking, running, shuffling, skipping, dancing, ascending or descending stairs”, [0063]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify the computer-implemented method of Minci with the physical activity group of Cheng, because all of the claimed physical activities were known in the prior art before the effective filing date of the claimed invention, and one with ordinary skill in the art could have combined all the claimed physical activity groups of the references by known methods, and the result would have been obvious to one of ordinary skill in the art.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Minici in view of Cheng and Mazumder, and further in view of Zhang (US 20150269824 A1, hereinafter Zhang).
Regarding Claim 5, modified Minici discloses the computer-implemented method of claim 1. Modified Minici discloses the claimed invention except for expressly disclosing the computer-implemented method further comprising:
automatically alerting, by the one or more processors, at least one pre-configured contact, of the stability score, via a communications network.
However, Zhang, which is also directed towards monitoring a patient’s movement (“the wellness index may be calculated using a dynamically growing number of parameters passively monitored by the monitoring device, including at least one of the following: a body temperature value, a temperature trend, one or more non-purposeful movements, one or more purposeful activities patterns, a movement intensity, a movement quality…”, [0044]), teaches automatically alerting, by the one or more processors (“the memory 1340, in at least one embodiment, includes an operating system 1344 and one or more application programs, modules, or services for implementing the features disclosed herein. For example, the contents of the memory 1340 can include a wellness monitoring engine 1348 and an emergency alert engine 1350”, [0180]; “Merely by way of example, one or more processes described with respect to the method(s) discussed above might be implemented as code and/or instructions executable by the wrist-worn device 108 (and/or processing unit(s) 1303 within a wrist-worn device 108)”, [0181]), at least one pre-configured contact (“The emergency detection engine 1620 can cause the emergency notification engine 1624 to generate and transmit an alert notification. … the notification engine 1624 may cause a notification to be sent to the indicated physician/emergency contact/emergency personnel.”, [0211]), of the stability score (“The minimum wellness value can indicate a wellness index that is indicative of the lowest wellness index a patient may have without triggering an emergency notification. In said example, the emergency detection engine 1620 can determine that the current wellness index of 4 is less than the minimum wellness of 5. The emergency notification engine 1624 can transmit a request to the notification engine 1624 to generate and transmit an alert notification.”, [0218]; “the wellness index may be calculated using a dynamically growing number of parameters passively monitored by the monitoring device, including at least one of the following: …one or more non-purposeful movements, one or more purposeful activities patterns, a movement intensity, a movement quality…”, [0044]), via a communications network (“Based on the wellness index of 4 and the strength of the cellular/Wi-Fi signals, the emergency notification engine 1624 can determine that the alert notification should be sent as a text message on the cellular network to increase the chances the alert notification is successfully transmitted. The notification engine can generate the alert notification and instruct the wireless communication interface 1304 to transmit the alert notification via the cellular network”, [0219]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to add the automatic alerting of Zhang to the computer-implemented method of modified Minici, because this assists medical crews in locating and attending to the wearer, as taught by Zhang (“The alert notification may include information about the wearer's location and elevation, as well as any other information relevant to assisting medical crews in locating and attending to the wearer”, [0050]).
Claims 9-10, 14, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Minici in view of Cheng and Mazumder, and further in view of Asada et al (US 20190254569 A1, hereinafter Asada).
Regarding Claim 9, modified Minici discloses the computer-implemented method of claim 1, further comprising:
prior to the segmenting, validating, by the one or more processors, the data sample (“After a preprocessing step aimed at reducing noise”, Section II).
Modified Minici discloses the claimed invention except for expressly disclosing wherein the validating comprises:
determining, by the one or more processors, if the data signals comprising the data sample indicate that the wearer was in motion during the time period; and
based on determining, by the one or more processors, that the wearer was in motion during the time period, commencing the segmenting.
However, Asada, which is also directed towards monitoring a patient’s movement and gait (Figs. 1-5), teaches determining, by the one or more processors (Element 42, Fig. 2), if the data signals comprising the data sample indicate that the wearer was in motion during the time period (Step S04, Fig. 6; “At step S04, signal processing circuit 24 determines whether subject M starts moving, based on an output signal from sensor unit 10”, [0130]); and
based on determining, by the one or more processors, that the wearer was in motion during the time period (See Fig. 6; Steps S06-S08 are based on “YES” in S04), commencing the segmenting (Step S18, Fig. 6, which is further explained in Fig. 7; mid-stance, heel contact and stepping motion times are segmented).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to add the validating process of Asada to the computer-implemented method of modified Minici, because this is a way to discard faulty data from the gait analysis process.
Regarding Claim 10, modified Minici discloses the computer-implemented method of claim 1, further comprising:
prior to the segmenting, validating, by the one or more processors, the data sample (“After a preprocessing step aimed at reducing noise…”, Section II).
Minici discloses the claimed invention except for expressly disclosing wherein the validating comprises:
determining, by the one or more processors, if the data signals comprising the data sample indicate that the wearer was in motion during the time period; and
based on determining, by the one or more processors, that the wearer was not in motion during the time period, obtaining, from the inertial sensor device, additional data over a new period of time, wherein based on the determining, the new period of time comprises the time period and the additional data comprises the data sample.
However, Asada teaches wherein the validating comprises:
determining, by the one or more processors (Element 42, Fig. 2), if the data signals comprising the data sample indicate that the wearer was in motion during the time period; and
based on determining, by the one or more processors, that the wearer was not in motion during the time period (Steps S02-S04, Fig. 6; “at step S02, signal processing circuit 24 determines whether subject M is standing still, based on an output signal of sensor unit 10”, [0128]; S04 “NO”, Fig. 6), obtaining, from the inertial sensor device (Element 1, Fig. 4), additional data over a new period of time (See the flowchart from S01-S07, Fig. 6, which happens after a recursive “NO” in Step S04”), wherein based on the determining, the new period of time comprises the time period and the additional data comprises the data sample (See the flowchart from S01-S07, Fig. 6, which happens after a recursive “NO” in Step S04”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to add the validating process of Asada to the computer-implemented method of modified Minici, because this is a way to discard faulty data from the gait analysis process.
Regarding Claim 14, modified Minici discloses the computer-implemented method of claim 8, wherein the data signals comprise acceleration data (“Shimmer 3 is a wearable device embedding a tri-axial accelerometer (STMicroLSM303DLHC) [15], which was used to collect acceleration samples at 102:4 Hz”, Section III.A). Modified Minici discloses the claimed invention except for expressly disclosing wherein determining if the data signals comprising the data sample indicate that the wearer was in motion during the time period comprises determining that the acceleration data is within a predetermined acceleration range. However, Asada teaches wherein determining if the data signals comprising the data sample indicate that the wearer was in motion during the time period comprises determining that the acceleration data is within a predetermined acceleration range (“At step S04, signal processing circuit 24 determines whether subject M starts moving, based on an output signal from sensor unit 10. If a change is observed in at least one of front-back acceleration, right-left acceleration, and up-down acceleration (for example, if the variation range of at least one acceleration is greater than a threshold), signal processing circuit 24 determines that subject M starts moving”, [0130]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to add the predetermined acceleration range of Asada to the computer-implemented method of modified Minici, because this is a way to discard faulty data from the gait analysis process.
Regarding Claim 20, Minici discloses obtaining, by one or more processors, a data sample from an inertial sensor device, wherein a wearable device comprises the inertial sensor device (“Shimmer 3 is a wearable device embedding a tri-axial accelerometer (STMicroLSM303DLHC) [15], which was used to collect acceleration samples at 102:4 Hz”, Section III.A; “Filtered acceleration components are then provided to the gait segment detection module”, Section II.A), wherein the data sample is comprised of data signals and a time vector (“Acceleration is sampled at 102:4 Hz”, Section II.A; this means acceleration data signals are sampled with a certain number of samples per unit time, i.e. a time vector accompanies the data), wherein the data sample is obtained by the inertial sensor device based on the inertial sensor device monitoring physical activities of a wearer during a time period represented by the time vector (“participants were asked to walk 60 meters at their preferred pace”, Section III.A);
segmenting, by the one or more processors, the data sample into segments (“a gait segment detection technique identifies gait segments on the whole signal trace”, Section II), wherein each segment comprises data from a time slice of the time period represented by the time vector (“A gait cycle is the sequence of events that occur during the walking process between two consecutive heel strikes of the same foot. Henceforth, we will use the term gait segment to indicate four consecutive gait cycles”, Section II.B; each gait cycle would be accompanied by the time vector data corresponding to it);
determining, by the one or more processors, a physical activity of the physical activities of the wearer performed during each time slice (“a gait segment detection technique identifies gait segments on the whole signal trace”, Section II);
grouping, by the one or more processors, into at least one group, times slices in which the wearer performed a common physical activity of the physical activities (“Henceforth, we will use the term gait segment to indicate four consecutive gait cycles”, Section II.B; “Wavelet analysis is applied to gait segments detected in the previous step”, Section II.C);
applying, by the one or more processors, a change of basis transformation on data signals comprising each group of the at least one group (“we use the Continuous Wavelet Transform (CWT) on the acceleration magnitude signal to obtain a representation of the gait segment into the time-frequency domain,”, Section II.C), to generate one or more data matrices (“The phase discussed above produces as output a matrix MCWT of coefficients cij for each gait segment, where i denotes the frequency value, obtained from the scale factor, and j denotes the instant in time ”, Section II.D);
classifying, by the one or more processors, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories, wherein the pre-defined stability categories comprise a first category and a second category, wherein the first category indicates stability and the second category indicates instability (“Finally, band-based feature extraction is responsible for gathering information from the CWT output, which is used to determine which Frequency Bands (FBs) contain the most valuable information for frailty status assessment”, Section II; “the subject was classified according to a majority voting scheme: if more than 40% of the band-based gait instances were classified as non-robust, the subject was classified as non-robust”, Section III.B), wherein the first category and the second category indicate gait performance (“if more than 40% of the band-based gait instances were classified as non-robust, the subject was classified as non-robust”, Section III.B; therefore, a <40% or >40% non-robust classification are a first and second category that indicate stability and instability, respectively, and also indicate gait performance), and
generating, by the one or more processors, a stability score representing stability of the wearer when performing the common physical activity for each group of the at least one group, based on analyzing the one or more data matrices and weighting the classifications into the one or more pre- defined stability categories (“the subject was classified according to a majority voting scheme: if more than 40% of the band-based gait instances were classified as non-robust, the subject was classified as non-robust”, Section III.B; therefore, a <40% or >40% non-robust classification is a stability score representing stability of the wearer).
Minici discloses the claimed invention except for expressly disclosing a computer readable storage medium readable by one or more processors of a computing system and storing instructions for execution by the one or more processors for performing a method comprising: the aforementioned method steps of Claim 20;
classifying, by the one or more processors, based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined stability categories,
wherein training the machine learning algorithm comprises:
training, by the one or more processors, with training data, a convolutional neural network process comprising a machine learning algorithm to classify segments into a finite number of groups, wherein each group represents a distinct physical activity of the physical activities; and
utilizing, by the one or more processors, the previously trained convolutional neural network process, to classify the one or more data matrices into the one or more pre-defined stability categories.
However, Asada teaches a computer program product (Element 2, Fig. 2) comprising:
a computer readable storage medium readable by one or more processors of a computing system (“The movement ability evaluating program causes the computer to execute the steps of…”, [0072]) and storing instructions for execution by the one or more processors for performing a method (“A computer-readable storage medium such as USB (Universal Serial Bus) memory, flexible disc, CD (Compact Disc), DVD. Blu-ray Disc (registered trademark). MO (Magneto-Optical disc), SD card, memory stick (registered trademark), magnetic disc, optical disc, magneto-optical disc, semiconductor memory, and magnetic tape can be used as a storage medium to store the movement ability evaluating program”, [0074]) comprising:
a computer-method for determining a user stability score (“When the subject is moving in a correct posture, the value of integral Sr is equal to the value of integral Sl and therefore the ratio Sr/Sl is a value close to 1. On the other hand, if the body center of gravity is inclined to the left, the body center of gravity shifts in the left direction when the right heel touches the ground, and the value of integral Sr is greater, so that the ratio Sr/Sl is a value greater than 1. When the body center of gravity is inclined to the right, the body center of gravity shifts in the right direction when the left heel touches the ground, and the value of integral Sl is greater, so that the ratio Sr/Sl is a value smaller than 1. Control unit 64 gives a score to the calculated ratio Sr/Sl, where the ratio Sr/Sl=1 is an ideal value”, [0188]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to add the computer program product comprising the computer readable storage medium storing instructions for execution by one or more processors for performing the computer-implemented method of Minici, as suggested by Asada, because all of the claimed elements were known in the prior art before the effective filing date of the claimed invention, and one with ordinary skill in the art could have combined all the claimed elements by known methods, and the result would have been obvious to one of ordinary skill in the art.
Cheng teaches classifying, by the one or more processors, based on utilizing a trained machine learning algorithm, the one or more data matrices generated from each group of the at least one group into one or more pre-defined activity categories (See Fig. 4), wherein the first category and the second category indicate postural performance, and wherein training the machine learning algorithm comprises:
training, by the one or more processors, with training data (“The input data 20 may also be applied to training the CNN 30”, [0158]), a convolutional neural network process (“The NN may be a convolutional neural network (“CNN”)”, [0009]) comprising a machine learning algorithm to classify segments (“The processor 18 applies a deep learning neural network that is a convolutional neural network 30 (“CNN”) to the input data 20 for classifying the subject's activity and resulting in classified activity data 38 that may be expressed in any suitable form”, [0157]) into a finite number of groups, wherein each group represents a distinct physical activity of the physical activities (“the activity includes standing, sitting, lying, crouching, walking, running, shuffling, skipping, dancing, ascending or descending stairs”, [0063]); and
utilizing, by the one or more processors, the previously trained convolutional neural network process, to classify the one or more data matrices (See Fig. 4; after the recursive “TRAINING: YES” step, the trained CNN can be used to classify activity data in the “TRAINING: NO” step) into the one or more pre-defined activity categories (See Fig. 4; after the recursive “TRAINING: YES” step, the trained CNN can be used to classify activity data in the “TRAINING: NO” step).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify the method of Minici with the classifying input data using a convolutional neural network (i.e. classifying data matrices into the pre-defined stability categories already taught by Minici), because using a convolutional neural network to classify data matrices improves classification by distinguishing between potentially small measurable differences, as taught by Cheng ([0005]).
Mazumder, which also discloses a method for determining a user stability score (“By processing the SLS duration, the body joint vibration, and the body sway area together, a postural stability index score for the user is determined, and based on this score, postural stability assessment for the user is performed”, Abstract) teaches pre-defined stability categories, wherein the first category and the second category indicate postural performance (“A stability index generation module of the postural stability assessment system then determines the SLS duration, the body joint vibration, and the body sway area, of the user as falling under at least one respective category, and further generates a postural stability index score for the user, based on the determined at least one category of the SLS duration, the body joint vibration, and the body sway area. A stability assessment module of the postural stability assessment system then assesses postural stability of the user, based on the postural stability index score”, [0007]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include postural performance in the first and second categories of Minici, because postural instability is one of the prominent symptoms associated with geriatric population (Mazumder, [0003]), and accounting for posture makes the method of Minici more accurate in its assessment of frailty.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Minici in view of Cheng, Asada and Mazumder, and further in view of Walsh et al (US 20160107309 A1, hereinafter Walsh).
Regarding Claim 11, modified Minici discloses the computer-implemented method of claim 10. Modified Minici discloses the claimed invention except for expressly disclosing the computer-implement method further comprising:
based on determining that the wearer was in not motion during the time period, alerting, by the one or more processors, the wearer that the inertial sensor device will collect additional data.
However, Walsh teaches based on determining that the wearer was in not motion during the time period (“Thus, the soft exosuit control system continuously monitors, or monitors at a high frequency, a status of the wearer's movements (or corresponding absence of movements)”, [0260]), alerting, by the one or more processors, the wearer that the inertial sensor device will collect additional data (“Hyper-alert mode”, element 1055, Fig. 25; “Thus, the soft exosuit control system continuously monitors, or monitors at a high frequency, a status of the wearer's movements (or corresponding absence of movements)”, [0260]; the exosuit being in hyper-alert mode means the wearer is also alerted that the inertial sensor device will collect additional data). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to add the method steps of Walsh to the computer-implemented method of modified Minici, because this enables the device to be modulated for the activity or activities in which the wearer is engaged, as taught by Walsh ([0260]).
Examiner’s Note
The Examiner notes that Claim 15 is not currently rejected under prior art.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
See Nicolas et al (US 20210052196 A1), which discloses wherein analysis of gait with a wrist-worn device (similar to Minici) includes postural performance ([0036]).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONATHAN EPHRAIM COOPER whose telephone number is (571)272-2860. The examiner can normally be reached Monday-Friday 7:30AM-5:30PM EST.
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, Jacqueline Cheng can be reached at (571) 272-5596. 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.
/JONATHAN E. COOPER/Examiner, Art Unit 3791
/JACQUELINE CHENG/Supervisory Patent Examiner, Art Unit 3791