DETAILED ACTIONS
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 .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 01/10/2025. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Claim Rejections- 35 USC §101
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 1-20 are rejected under 35 U.S.C.§101 because the claimed invention is directed to judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Regarding claim 1,
A computer-implemented method in an analytical instrument support apparatus, the method comprising:
receiving, by one or more processors, preliminary sample data collected from a short scan of a sample;
determining, by the one or more processors, a bright-max intensity level based on, at least, the preliminary sample data;
determining, by the one or more processors, a performance class based on, at least, the bright-max intensity level;
determining, by the one or more processors, an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class;
determining, by the one or more processors, a first prediction representing a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model, or
a second prediction representing a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model; and
storing, on one or more computer-readable memory devices, the first maximum intensity level or the first parameter exposure time.
The claim limitations underlined above is abstract idea, and the remaining limitations are “additional elements”.
Step 1 (Statutory Category): Yes. we determine whether the claims are to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: Process, machine, manufacture, or composition of matter. The above claim is considered to be in a statutory category (a mathematical manipulation). Therefore, it is directed to a statutory category, i.e., a mathematical manipulation.
Step 2 A, Prong-1 (the claim is evaluated to determine whether it is directed to a judicial-exception/abstract-idea): Yes.
In the above claim, the underlined portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitations that fall into/recite an abstract idea exception. Specifically, under the 2019 Revised Patent Subject Matter Eligibility Guidance, it falls into the grouping of subject matter when recited as such in a claim limitation that covers mental processes – concepts performed in the human mind including an observation, evaluation, judgement, and/or opinion and mathematical concepts (mathematical relationships, mathematical formulas or equations, mathematical calculations, a mathematical manipulation).
For example, steps of “determining, by the one or more processors, a bright-max intensity level based on, at least, the preliminary sample data”, “determining, by the one or more processors, a performance class based on, at least, the bright-max intensity level”, Step of “determining, by the one or more processors, an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class”, represents the mathematical concepts. Steps of determining maximum intensity level and classifying the performance classification based on intensity level of the acquired Raman Spectrum, and determining intensity-to-time model etc. are mathematical manipulations executed by a processor/computer and one or more software and/or hardware components in various combinations and configurations see (Specification [0101]-[0107],[0112]-[0113] are abstract idea. These steps represent a process (a mathematical manipulation and use of software and/or hardware) that, under its broadest reasonable interpretation, it encompasses mathematical manipulation of the collected spectrum data. In addition, the step of “determining, by the one or more processors, a first prediction representing a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model”, or “a second prediction representing a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model” is directed to an abstract idea /mathematical concept because the determination is made based on mathematical manipulations.
Step 2A, Prong-2 (the claim is evaluated to determine whether the judicial exception/abstract-idea is integrated into a Practical Application): No.
Claim 1 recites additional elements “receiving, by one or more processors, preliminary sample data collected from a short scan of a sample”, is a data gathering steps for the particular technological environment or field of use and mere data gathering steps and only add an insignificant extra-solution activity to the judicial exception. The additional element “storing, on one or more computer-readable memory devices, the first maximum intensity level or the first parameter exposure time” represent a post solution activity of storing the output data such as intensity level data and time exposure data. The additional element considered individually and in combination with the other claim elements do not reflect an improvement to other technology or technical field, and, therefore, do not integrate the judicial exception into a practical application. The claim do not recite any practical application of the determination outcome except storing the data. Therefore, the claims are directed to a judicial exception and require further analysis under the Step 2B.
Step 2B (the claim is evaluated to determine whether recites additional elements that amount to an inventive concept, or also, the additional elements are significantly more than the recited the judicial-exception/abstract-idea): No. the additional element(s) are just insignificant extra-solution activity which are simply routine and conventional steps previously known to the pertinent industry that includes acquiring data from external factors such as pipe environmental and dimensional data. Therefore, the claim does not include additional element(s) significantly more, and/or, does not amount to more than the judicial-exception/abstract-idea itself and the claim is not patent eligible.
claims 2-17 are rejected under 35 U.S.C. 101 because claims depend on
claim 1, therefore, has the abstract idea of claim 1 and also has the routine and conventional structure above of claim 1. In addition, claims 2-17 further recite the elements which are simply more standard computational, mathematical-calculation to data gathering /generate data and/ or a model, and. Furthermore, claims 2-17 do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 18,
An analytical instrument support system comprising: one or more processors, one or more non-transitory computer-readable storage media; and program instructions stored on at least one of the one or more non-transitory computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
program instructions to receive, preliminary sample data collected from a short scan of a sample;
program instructions to determine a bright-max intensity level based on, at least, the preliminary sample data;
program instructions to determine a performance class based on, at least, the bright-max intensity level;
program instructions to determine an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class;
program instructions to determine, a first prediction representing a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model,
or
a second prediction representing a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model; and
program instructions to store, on one or more computer-readable memory devices, the first maximum intensity level or the first parameter exposure time.
The claim limitations underlined above is abstract idea, and the remaining limitations are “additional elements”.
Step 1 (Statutory Category): Yes. we determine whether the claims are to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: Process, machine, manufacture, or composition of matter. The above claim is considered to be in a statutory category (a mathematical manipulation). Therefore, it is directed to a statutory category, i.e., a mathematical manipulation.
Step 2 A, Prong-1 (the claim is evaluated to determine whether it is directed to a judicial-exception/abstract-idea): Yes.
In the above claim, the underlined portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitations that fall into/recite an abstract idea exception. Specifically, under the 2019 Revised Patent Subject Matter Eligibility Guidance, it falls into the grouping of subject matter when recited as such in a claim limitation that covers mental processes – concepts performed in the human mind including an observation, evaluation, judgement, and/or opinion and mathematical concepts (mathematical relationships, mathematical formulas or equations, mathematical calculations, a mathematical manipulation).
For example, steps of “one or more processors, one or more non-transitory computer-readable storage media; and program instructions stored on at least one of the one or more non-transitory computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising”, “program instructions to determine a bright-max intensity level based on, at least, the preliminary sample data”,” “program instructions to determine a performance class based on, at least, the bright-max intensity level”, represents the mathematical concepts. Steps of determining maximum intensity level and classifying the performance classification based on intensity level of the acquired Raman Spectrum, and determining intensity-to-time model etc. are mathematical manipulations executed by a processor/computer and one or more software and/or hardware components in various combinations and configurations see (Specification [0101]-[0107],[0112]-[0113] and [0127]) are abstract idea. These steps represent a process (a mathematical manipulation and use of software and/or hardware) that, under its broadest reasonable interpretation, it encompasses mathematical manipulation of the collected spectrum data. In addition, the step of ““program instructions to determine an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class”, “program instructions to determine, a first prediction representing a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model”, or“ a second prediction representing a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model” is directed to an abstract idea /mathematical concept because the determination is made based on mathematical manipulations.
Step 2A, Prong-2 (the claim is evaluated to determine whether the judicial exception/abstract-idea is integrated into a Practical Application): No.
Claim 18 recites additional elements “program instructions to receive, preliminary sample data collected from a short scan of a sample”, is a data gathering steps for the particular technological environment or field of use and mere data gathering steps and only add an insignificant extra-solution activity to the judicial exception. The additional element “program instructions to store, on one or more computer-readable memory devices, the first maximum intensity level or the first parameter exposure time” represent a post solution activity of storing the output data such as intensity level data and time exposure data. The additional element considered individually and in combination with the other claim elements do not reflect an improvement to other technology or technical field, and, therefore, do not integrate the judicial exception into a practical application. The claim does not recite any practical application of the determination outcome except storing the data. Therefore, the claims are directed to a judicial exception and require further analysis under the Step 2B.
Step 2B (the claim is evaluated to determine whether recites additional elements that amount to an inventive concept, or also, the additional elements are significantly more than the recited the judicial-exception/abstract-idea): No. the additional element(s) are just insignificant extra-solution activity which are simply routine and conventional steps previously known to the pertinent industry that includes acquiring data from external factors such as pipe environmental and dimensional data. Therefore, the claim does not include additional element(s) significantly more, and/or, does not amount to more than the judicial-exception/abstract-idea itself and the claim is not patent eligible.
claim 19 is rejected under 35 U.S.C. 101 because claims depend on
claim 18, therefore, has the abstract idea of claim 18 and also has the routine and conventional structure above of claim 18. In addition, claim 19 further recite the elements which are simply more standard computational, mathematical-calculation to data gathering /generate data and/ or a model, and. Furthermore, claims 19 do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 20,
An analytical instrument comprising:
a light source configured to direct light onto a surface of a sample;
a spectrograph to acquire a Raman spectrum from the surface of the sample in response to the light source directing light onto the surface of the sample;
one or more processors;
one or more non-transitory computer-readable storage media; and program instructions stored on at least one of the one or more non-transitory computer-readable storage media for execution by at least one of the one or more processors,
wherein upon execution of the program instructions by at least one of the one or more processors, cause the analytical instrument to implement a set of acts comprising:
analyzing Raman spectrum data from the acquired Raman spectrum associated with the surface of the sample,
determining a bright-max intensity level based on, at least, the acquired Raman spectrum,
determining a performance class based on the bright-max intensity level associated with the acquired Raman spectrum,
determining an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class;
determining a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model, or, a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model, and
storing on at least one of the one or more non-transitory computer-readable storage media the first maximum intensity level or the first parameter exposure time
The claim limitations underlined above is abstract idea, and the remaining limitations are “additional elements”.
Step 1 (Statutory Category): Yes. we determine whether the claims are to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: Process, machine, manufacture, or composition of matter. The above claim is considered to be in a statutory category (a mathematical manipulation). Therefore, it is directed to a statutory category, i.e., a mathematical manipulation.
Step 2 A, Prong-1 (the claim is evaluated to determine whether it is directed to a judicial-exception/abstract-idea): Yes.
In the above claim, the underlined portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitations that fall into/recite an abstract idea exception. Specifically, under the 2019 Revised Patent Subject Matter Eligibility Guidance, it falls into the grouping of subject matter when recited as such in a claim limitation that covers mental processes – concepts performed in the human mind including an observation, evaluation, judgement, and/or opinion and mathematical concepts (mathematical relationships, mathematical formulas or equations, mathematical calculations, a mathematical manipulation).
For example, steps of “one or more non-transitory computer-readable storage media; and program instructions stored on at least one of the one or more non-transitory computer-readable storage media for execution by at least one of the one or more processors, wherein upon execution of the program instructions by at least one of the one or more processors,” “cause the analytical instrument to implement a set of acts comprising: analyzing Raman spectrum data from the acquired Raman spectrum associated with the surface of the sample,”
“determining a bright-max intensity level based on, at least, the acquired Raman spectrum, determining a performance class based on the bright-max intensity level associated with the acquired Raman spectrum”, “determining an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class”, “determining a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model, or, a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model,”, represents the mathematical concepts. Steps of determining maximum intensity level and classifying the performance classification based on intensity level of the acquired Raman Spectrum, and determining intensity-to-time model etc. are mathematical manipulations executed by a processor/computer and one or more software and/or hardware components in various combinations and configurations see (Specification [0101]-[0107],[0112]-[0113] and [0127]) are abstract idea. These steps represent a process (a mathematical manipulation and use of software and/or hardware) that, under its broadest reasonable interpretation, it encompasses mathematical manipulation of the collected spectrum data. These steps are directed to an abstract idea /mathematical concept because the determination is made based on mathematical manipulations.
Step 2A, Prong-2 (the claim is evaluated to determine whether the judicial exception/abstract-idea is integrated into a Practical Application): No.
Claim 20 recites additional elements “a light source configured to direct light onto a surface of a sample; a spectrograph to acquire a Raman spectrum from the surface of the sample in response to the light source directing light onto the surface of the sample” is a data gathering steps for the particular technological environment or field of use and only add an insignificant extra-solution activity to the judicial exception. The additional element “storing on at least one of the one or more non-transitory computer-readable storage media the first maximum intensity level or the first parameter exposure time” represent a post solution activity of storing the output data such as intensity level data and time exposure data. The additional element considered individually and in combination with the other claim elements do not reflect an improvement to other technology or technical field, and, therefore, do not integrate the judicial exception into a practical application. The claim does not recite any practical application of the determination outcome except storing the data. Therefore, the claims are directed to a judicial exception and require further analysis under the Step 2B.
Step 2B (the claim is evaluated to determine whether recites additional elements that amount to an inventive concept, or also, the additional elements are significantly more than the recited the judicial-exception/abstract-idea): No. the additional element(s) are just insignificant extra-solution activity which are simply routine and conventional steps previously known to the pertinent industry that includes acquiring data from external factors such as pipe environmental and dimensional data. Therefore, the claim does not include additional element(s) significantly more, and/or, does not amount to more than the judicial-exception/abstract-idea itself and the claim is not patent eligible.
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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Yadav et al. (US 2023/0240538 A1, hereinafter Yadav) and in view of Xue et al. (hereinafter, Xue) "Model Parameter Self-Correcting Fuzzy Proportional–Integral–Derivative Adaptive Control of the Integration Time of Raman Spectrometers," in IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-10, Publication Date: 2023-01-01, Print Publication Date: 2022-12-24, Electronic Publication Date: 2022-12-26.
Regarding claim 1, Yadav teaches
A computer-implemented method in an analytical instrument support apparatus (Yadav, Figure 1 [0007] FIG. 1 shows an inventive Raman spectroscopy system), the method comprising:
receiving, by one or more processors, preliminary sample data collected from a short scan of a sample (Yadav, Figures2- 3, Data acquisition Raman spectra);
determining, by the one or more processors, a bright-max intensity level based on, at least, the preliminary sample data (Yadav, [0009] FIG. 3 is a block diagram showing use of a data acquisition algorithm to optimize laser excitation power. [0028], Figure 3c, “For each measurement determine the maximum measured intensity as maxRS 1 and maxRS2. By using these two measurement pairs it is possible to extrapolate and determine the optimal excitation laser power P opt, such that the maximum measured intensity is 90% of allowable spectrometer/CCD dynamic range”);
determining, by the one or more processors, a performance class based on, at least, the bright-max intensity level (Yadav, Figure 2, Raman spectra extraction, feature extraction and classify. [0026] “In the Raman Spectra Extraction or the Preprocessing block, signal processing algorithms are applied to extract the Raman Spectra from the acquired Raman data. [0054] In the simplest implementation, Raman intensity at each of the identified spectral location is used as a feature vector of K-elements for classification. In one implementation,
we selected K=300 spectral bands with J=50 bootstrapped iterations. FIG. 7 depicts the outcome of this feature extraction from one of the training datasets.);
storing, on one or more computer-readable memory devices, the first maximum intensity level or the first parameter exposure time. (Yadav, Figure 1, Raman spectrum system with a computer and memory).
Yadav is silent on
determining, by the one or more processors, an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class;
determining, by the one or more processors, a first prediction representing a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model, or
a second prediction representing a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model; and
However, Xue teaches determining, by the one or more processors, an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class (Xue, Figure 2, Page 3000110, right col. After calculating the maximum peak height [hmax(0)] of the strongest effective peak or SNR [SNR(0)] by analyzing the detected Raman spectrum data, the initial parameters required by the fuzzy PID controller are roughly estimated by the initial parameter prediction model and then transmitted to the fuzzy PID controller for automatic
integration time control. The fuzzy PID controller compares the collected [hmax(n)] or [SNR(n)] with the set value (h_) or (SNR_), automatically corrects the model parameters, and calculates the optimal integration time, automatically controlling the Raman spectrometer for spectrum acquisition. Since the initial parameter prediction model is established according to a specific Raman spectrometer, it has strong parameter sensitivity, while the performance of different spectrometers varies greatly; thus, the parameters of the prediction model”) ;
determining, by the one or more processors, a first prediction representing a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model, (Xue, Figure 2, Page 3000110, Right col. the preacquisition spectrum stage mainly provides rough initial parameters of PID control model for fuzzy PID controller to reduce iteration time and the fuzzy PID controller will further autocorrect the initial parameters according to the fuzzy rule database. After calculating the maximum peak height [hmax(0)] of the strongest effective peak or SNR [SNR(0)] by analyzing the detected Raman spectrum data, the
initial parameters required by the fuzzy PID controller are roughly estimated by the initial parameter prediction model then, the parameters of the PID
controller are fuzzily adjusted by the fuzzy expert database,
ensuring the rapid convergence control of different samples”) or
a second prediction representing a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model.
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Yadav’s method for predicting Raman spectral quality to incorporate a machine learning based intensity to time model as taught by Xue incorporating time and intensity parameters to calculate the optimal integration time fast to shorten the total spectrum acquisition time, improves the efficiency of spectrum acquisition and enhances the control performance (Xue, Abstract). It would have been obvious to a person of ordinary skill to include the well-known Machine learning model in order to yield the predicted results of to calculate spectrum quality and at efficient speed, yet with higher accuracy (KSR).
Regarding claim 2, combination of Yadav and Xue teaches the computer-implemented method of claim 1,
Yadav further teaches wherein determining the first prediction includes receiving, by the one or more processors, first sample data collected from a first sample scan of the sample wherein the sample is scanned for the first corresponding exposure time. (Yadav, Figure 3a-3b, Data acquisition Acquire N Raman Spectra, Figure 3b, Determine Optimal Excitation Exposure Time)
Regarding claim 3, combination of Yadav and Xue teaches the computer-implemented method of claim 1,
Yadav further teaches wherein determining the second prediction includes receiving, by the one or more processors, second sample data collected from a second sample scan of the sample, wherein the sample is scanned to the first corresponding intensity level. (Yadav, Figures 2 and figure 3c, [0028] FIG. 3(c) shows one possible scheme for optimizing the excitation laser power. Main concept here is to make Raman measurements at two relatively low excitation laser power, P 1 and P 2 . For each measurement determine the maximum measured intensity as maxRS 1 and maxRS2. By using these two measurement pairs it is possible to extrapolate and determine the optimal excitation laser power P opt, such that the maximum measured intensity is 90% of allowable Spectrometer/CCD”)
Regarding claim 4, combination of Yadav and Xue teaches the computer-implemented method of claim 1,
Yadav further teaches wherein the analytical instrument support apparatus is a Raman spectrometer. (Yadav, Figure 1, [0007] FIG. 1 shows an inventive Raman spectroscopy system adapted for use with the inventive methods”).
Regarding claim 5, combination of Yadav and Xue teaches the computer-implemented method of claim 1
Yadav further teaches the method further comprising: generating, by the one or more processors, the intensity linear model, based on, at least, the bright-max intensity level associated with the preliminary sample data (Yadav, figures 3,7, and 15 [0026] “In the Raman Spectra Extraction or the Preprocessing block, signal processing algorithms are applied to extract the Raman Spectra from the acquired Raman data. [0054] In the simplest implementation, Raman intensity at each of the identified spectral location is used as a feature vector of K-elements for classification. In one implementation, we selected K=300 spectral bands with J=50 bootstrapped iterations. FIG. 7 depicts the outcome of this feature extraction from one of the training datasets”)
Yadav is silent on converting, by the one or more processors, a domain of the generated intensity linear model from exposure time to intensity; applying, by the one or more processors, the one or more deviations to the intensity linear model; and converting, by the one or more processors, a domain of the intensity linear model from intensity to exposure time, to form the intensity-to-time model.
However, Xue teaches converting, by the one or more processors, a domain of the generated intensity linear model from exposure time to intensity; applying, by the one or more processors, the one or more deviations to the intensity linear model; and converting, by the one or more processors, a domain of the intensity linear model from intensity to exposure time, to form the intensity-to-time model (Xue, Figure 2, Page 3000110, right col. After calculating the maximum peak height [hmax(0)] of the strongest effective peak or SNR [SNR(0)] by analyzing the detected Raman spectrum data, the initial parameters required by the fuzzy PID controller are roughly estimated by the initial parameter prediction model and then transmitted to the fuzzy PID controller for automatic integration time control. The fuzzy PID controller compares the collected [hmax(n)] or [SNR(n)] with the set value (h_) or (SNR_), automatically corrects the model parameters, and calculates the optimal integration time, automatically controlling the Raman spectrometer for spectrum acquisition. Since the initial parameter prediction model is established according to a specific Raman spectrometer, it has strong parameter sensitivity, while the performance of different spectrometers varies greatly; thus, the parameters of the prediction model”)
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Yadav’s method for predicting Raman spectral quality to incorporate a machine learning based intensity to time model as taught by Xue incorporating time and intensity parameters to calculate the optimal integration time fast to shorten the total spectrum acquisition time, improves the efficiency of spectrum acquisition and enhances the control performance (Xue, Abstract). It would have been obvious to a person of ordinary skill to include the well-known Machine learning model in order to yield the predicted results of to calculate spectrum quality and at efficient speed, yet with higher accuracy (KSR).
Regarding claim 6, combination of Yadav and Xue teaches the computer-implemented method of claim 5,
Yadav is silent on, wherein the one or more deviations from the intensity linear model includes an exponential deviation.
However, Xue teaches wherein the one or more deviations from the intensity linear model includes an exponential deviation. (Xue, Page3000110, right col, “Although increasing the number of accumulations in a small range can increase the signal-to-noise ratio (SNR) of Raman spectrum, the effect is increasingly weaker as the number increases; in addition, the total acquisition time
will increase exponentially as well “)
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Yadav’s method for predicting Raman spectral quality to incorporate a machine learning based intensity to time model as taught by Xue incorporating time and intensity parameters to calculate the optimal integration time fast to shorten the total spectrum acquisition time, improves the efficiency of spectrum acquisition and enhances the control performance (Xue, Abstract). It would have been obvious to a person of ordinary skill to include the well-known Machine learning model in order to yield the predicted results of to calculate spectrum quality and at efficient speed, yet with higher accuracy (KSR).
Regarding claim 7, combination of Yadav and Xue teaches the computer-implemented method of claim 1
Yadav is silent on wherein determining the intensity-to-time model includes: iterating the plurality of intensity levels until the first corresponding exposure time is reached on the intensity-to-time model, wherein an intensity level corresponding with the first corresponding exposure time is the first maximum intensity level, or
iterating the plurality of exposure times until the first corresponding intensity level is reached on the intensity-to-time model, wherein an exposure time corresponding with the first corresponding intensity level is the first parameter exposure time.
However, Xue teaches wherein determining the intensity-to-time model includes: iterating the plurality of intensity levels until the first corresponding exposure time is reached on the intensity-to-time model, wherein an intensity level corresponding with the first corresponding exposure time is the first maximum intensity level, Xue, Page 3, left col. Bottom paragraph, In the acquisition process of Raman spectrum, the spectrum quality is mainly adjusted by setting integration time, and normally, laser power and the number of accumulations are generally set fixed. To obtain a Raman spectrum of good quality, it is often necessary to change the integration time for repeated iterative acquisition, and the number of iterations directly affects the acquisition efficiency. Therefore, it is very critical to calculate the optimal integration time fast to shorten the total spectrum acquisition time.
or
iterating the plurality of exposure times until the first corresponding intensity level is reached on the intensity-to-time model, wherein an exposure time corresponding with the first corresponding intensity level is the first parameter exposure time.
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Yadav’s method for predicting Raman spectral quality to incorporate a machine learning based intensity to time model as taught by Xue incorporating time and intensity parameters to calculate the optimal integration time fast to shorten the total spectrum acquisition time, improves the efficiency of spectrum acquisition and enhances the control performance (Xue, Abstract). It would have been obvious to a person of ordinary skill to include the well-known Machine learning model in order to yield the predicted results of to calculate spectrum quality and at efficient speed, yet with higher accuracy (KSR).
Regarding claim 8, combination of Yadav and Xue teaches the computer-implemented method of claim 5,
Yadav further teaches, the method further comprising: retrieving, by the one or more processors, one or more device characteristics of the analytical instrument support apparatus (Yadav, Figure 1, Raman spectroscopic system), wherein the device characteristics of the analytical instrument include a bias, a gain, and a sigma read; and determining, by the one or more processors, a base level intensity based on, at least, one of the one or more analytical instrument characteristics. (Yadav, [0044] 1°i is the j'h spectral band of the normalized ambient light signal's contribution on the measurement. It is obtained by performing a tissue sample measurement without the excitation (dark measurement), so that the light collected at the surface of the sample is solely the ambient light signal. This measurement is then normalized by the exposure time, the laser power, the normalized system response and the detector gain”).
Regarding claim 9, combination of Yadav and Xue teaches the computer-implemented method of claim 8,
Yadav further teaches the method further comprising generating, by the one or more processors, the intensity linear model based on, at least, (i) the base level intensity and (ii) the bright-max intensity level at an exposure time (Yadav,[0028] FIG. 3(c) shows one possible scheme for optimizing the excitation laser power. Main concept here is to make Raman measurements at two relatively low excitation laser power, P 1 and P 2 . For each measurement determine the maximum measured intensity as maxRS 1 and maxRS2 . By using these two measurement pairs it is possible to extrapolate and determine the optimal excitation laser power P opt, such that the maximum measured intensity is 90% of allowable Spectrometer/CCD dynamic range. In a similar way it is possible to optimize the excitation laser exposure time.”), wherein the exposure time is between 1 millisecond and 20 seconds. (Yadav, [0041] t is the acquisition time for an individual spectrum, in milliseconds. [0023] The representative inventive embodiment of FIG. 1 is capable of acquiring and processing Raman data, classifying sampled tissue and presenting a classification answer ( e.g., cancer/no cancer) to a clinician in real-time during surgery. In this context, real-time means a practically instantaneous classification that does not interfere with surgeon workflow, most ideally l00's of ms to perhaps just over 1 second”).
Regarding claim 10, combination of Yadav and Xue teaches the computer-implemented method of claim 8,
Yadav further teaches wherein the determining of the performance class of the short scan of the sample is based on a selection from a plurality of performance classes, (Yadav, Figure 2, Raman spectra extraction, feature extraction and classify. [0026] “In the Raman Spectra Extraction or the Preprocessing block, signal processing algorithms are applied to extract the Raman Spectra from the acquired Raman data. [0054] In the simplest implementation, Raman intensity at each of the identified spectral location is used as a feature vector of K-elements for classification and wherein the plurality of performance classes is based on, at least, the bright-max intensity level of the short scan of the sample at 1 millisecond to 20 seconds exposure time (Yadav, [0041] t is the acquisition time for an individual spectrum, in milliseconds. [0023],” real-time means a practically instantaneous classification that does not interfere with surgeon workflow, most ideally l00's of ms to perhaps just over 1 second”).and an intensity count ranging between 0 and a saturation value of a detector of the analytical instrument support apparatus (Yadav, Figure 9, Intensity count).
Regarding claim 11, combination of Yadav and Xue teaches the computer-implemented method of claim 1,
Yadav further teaches the method further comprising: determining, by the one or more processors, an SNR-to-intensity model, the SNR-to-intensity model including a plurality of SNR values and a plurality of intensities based on, at least, one or more deviations from a SNR linear model, the one or more deviations associated with the determined performance class; (Yadav, Figure 2,compute SNR/SBR ,[0026] In the Raman Spectra Extraction or the preprocessing block, signal processing algorithms are applied to extract the Raman Spectra from the acquired Raman data. The extracted Raman Spectrum is further processed to evaluate Signal-to-Noise Ratio (SNR) and other metrics to determine the applicability of the Raman Spectra for classification of tissue type. Evaluation of the SNR is performed with the application of a novel SNR definition that can be applied on a single realization of Raman Spectra. One of the key components of the inventive system is the extraction of appropriate features from the Raman Spectra to allow data dimensionality reduction and classification for tissue classification”)
determining, by the one or more processors, a third prediction representing an intensity level-based SNR value based on, at least, a second corresponding intensity level, or a fourth prediction representing a second maximum intensity level based on, at least, a first corresponding SNR value (Yadav [0038] “Present invention provides a novel scheme for assessing Raman Signal SNR”. [0040] n is the number of individual spectra that are being averaged to form the final spectrum”. [0054] The process is repeated for J bootstrap partitions. At each iteration, the identified spectral bands are concatenated with those of previous iteration to yield a matrix F of size Jx(K-L). Following the final iteration, voting is used to select the K most occurring spectral bands for feature calculation. In the simplest implementation, Raman intensity at each of the identified spectral location is used as a feature vector of K-elements for classification. In one implementation, we selected K=300 spectral bands with J=50 bootstrapped iterations. FIG. 7 depicts the outcome of this feature extraction from one of the training datasets NOTE: number of measurements is repeated and any measurement step could be first and second and so on in order of steps) and
storing, on the one or more computer-readable memory devices, the intensity level-based SNR value or the second maximum intensity level. (Yadav, Figure 1, 2, Raman spectrum system with a computer and memory)
Regarding claim 12, combination of Yadav and Xue teaches the computer-implemented method of claim 11,
Yadav further teaches wherein determining the third prediction includes receiving, by the one or more processors, third sample data collected from a third sample scan of the sample, wherein the sample is scanned to the second corresponding intensity level. (Yadav, Figure 2, [0038] The Raman biomarker assessment allows us to evaluate the quality of Raman measurements, particularly from biological tissues. Generally, the Raman signal-tonoise
ratio (SNR) is defined as the ratio of the Raman peak height to the standard deviation of the peak height where j corresponds to the spectral index and μ(i)=mean and cr(i)=standard deviation of the Raman Spectra at the j'h
spectral location”).
Regarding claim 13, combination of Yadav and Xue teaches the computer-implemented method of claim 11,
Yadav further teaches wherein determining the fourth prediction includes receiving, by the one or more processors, fourth sample data collected from a fourth sample scan of the sample, wherein the sample is scanned to the first corresponding SNR value. . (Yadav, Figure 2, [0038] the Raman signal-to-noise ratio (SNR) is defined as the ratio of the Raman peak height to the standard deviation of the peak height where j corresponds to the spectral index and μ(i)=mean and cr(i)=standard deviation of the Raman Spectra at the j'h spectral location”.[0040] n is the number of individual spectra that are being averaged to form the final spectrum”).
Regarding claim 14, combination of Yadav and Xue teaches the computer-implemented method of claim 1,
Yadav further teaches the method further comprising:
determining, by the one or more processors, a SNR-to-intensity model, the SNR-to-intensity model including a plurality of SNR values and a plurality of intensities based on, at least (Yadav, Figure 2, compute SNR/SBR) , one or more logarithmic deviations from a SNR linear model, the one or more logarithmic deviations associated with the determined performance class (Yadav,[0038] [0038] The Raman biomarker assessment allows us to evaluate the quality of Raman measurements, particularly from biological tissues. Generally, the Raman signal-tonoise
ratio (SNR) is defined as the ratio of the Raman peak height to the standard deviation of the peak height.
PNG
media_image1.png
36
97
media_image1.png
Greyscale
where j corresponds to the spectral index and μ(i)=mean and cr(i)=standard deviation of the Raman Spectra at the j'h spectral location”) ;
storing, on the one or more computer-readable memory devices, the exposure time-based SNR value or the second parameter exposure time. Yadav, Figure 1, 2, Raman spectrum system with a computer and memory)
Yadav is silent on determining, by the one or more processors, a fifth prediction representing an exposure time-based SNR value based on, at least, a second corresponding exposure time, the SNR-to-intensity model, and the intensity-to-time model,
or a sixth prediction representing a second parameter exposure time based on, at least, a second corresponding SNR value, the SNR-to-intensity model, and the intensity-to-time model; and
However, Xue teaches determining, by the one or more processors, a fifth prediction representing an exposure time-based SNR value based on, at least, a second corresponding exposure time, the SNR-to-intensity model, and the intensity-to-time model, (Xue, Figure 2, Page 3, Right col, Evaluation methods of spectrum quality include intensity, SNR, and so on, which are generally in positive correlation [3].. Raman signals detected by very short time generally have poor SNR and are coupled with strong noise interference signals. However, the preacquisition spectrum stage mainly provides rough initial parameters of PID control model for fuzzy PID controller to reduce iteration time and the fuzzy PID controller will further autocorrect the initial parameters according to the fuzzy rule database. After calculating the maximum peak height [hmax(0)] of the strongest effective peak or SNR [SNR(0)] by analyzing the detected Raman spectrum data, the initial parameters required by the fuzzy PID controller are roughly estimated by the initial parameter prediction model and then transmitted to the fuzzy PID controller for automatic integration time control. The fuzzy PID controller compare s the collected [hmax(n)] or [SNR(n)] with the set value (h_) or (SNR_), automatically corrects the model parameters, and calculates the optimal integration time, automatically controlling the Raman spectrometer for spectrum acquisition”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Yadav’s method for predicting Raman spectral quality to incorporate a machine learning based intensity to time model as taught by Xue incorporating time and intensity parameters to calculate the optimal integration time fast to shorten the total spectrum acquisition time, improves the efficiency of spectrum acquisition and enhances the control performance (Xue, Abstract). It would have been obvious to a person of ordinary skill to include the well-known Machine learning model in order to yield the predicted results of to calculate spectrum quality and at efficient speed, yet with higher accuracy (KSR).
Regarding claim 15, combination of Yadav and Xue teaches the computer-implemented method of claim 14,
Yadav is silent on wherein determining the fifth prediction includes receiving, by the one or more processors, fifth sample data collected from a fifth sample scan of the sample, wherein the sample is scanned for the second corresponding exposure time.
However, Xue teaches wherein determining the fifth prediction includes receiving, by the one or more processors, fifth sample data collected from a fifth sample scan of the sample, wherein the sample is scanned for the second corresponding exposure time (Xue, Figure 2, Page 4, right col. Bottom paragraph, and page 5, left col, top paragraph, As shown in Fig. 3, the error [e(n)] between the set peak height (h_) or the SNR (SNR_) and the feedback peak height [hmax(n)] or SNR [SNR(n)] and the error change rate [ec(n)] are taken as the input variables of the fuzzy control module to calculate the corrected values of the optimal proportional coefficient [Kp(n)] and the integration coefficient [KI (n)] for the PID controller in real time, thus to ensure the accuracy of the PID controller model parameters. The input error [e(n)] and the error change rate [ec(n)] are transformed into fuzzy variables EC and E by fuz ification with Gaussian function as the membership function. According to the analysis of a large number of sample data of Raman spectrum in the early stage, the complexity of fuzzy rule base is reduced as far as possible on the premise of meeting the basic requirements of control accuracy, so as to improve the calculation speed in practical applications. In this article, expert rule bases of fuzzy reasoning are constructed for proportional coefficient [Kp(n)] and the integration coefficient [KI (n)], respectively” )
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Yadav’s method for predicting Raman spectral quality to incorporate a machine learning based intensity to time model as taught by Xue incorporating time and intensity parameters to calculate the optimal integration time fast to shorten the total spectrum acquisition time, improves the efficiency of spectrum acquisition and enhances the control performance (Xue, Abstract). It would have been obvious to a person of ordinary skill to include the well-known Machine learning model in order to yield the predicted results of to calculate spectrum quality and at efficient speed, yet with higher accuracy (KSR).
Regarding claim 16, combination of Yadav and Xue teaches the computer-implemented method of claim 14,
Yadav is silent on wherein determining the sixth prediction includes receiving, by the one or more processors, sixth sample data collected from a sixth sample scan of the sample, wherein the sample is scanned at the second corresponding SNR value. (Xue, Figure 2, Page 4, right col. Bottom paragraph, and page 5, left col, top paragraph, As shown in Fig. 3, the error [e(n)] between the set peak height (h_) or the SNR (SNR_) and the feedback peak height [hmax(n)] or SNR [SNR(n)] and the error change rate [ec(n)] are taken as the input variables of the fuzzy control module to calculate the corrected values of the optimal proportional coefficient [Kp(n)] and the integration coefficient [KI (n)] for the PID controller in real time, thus to ensure the accuracy of the PID controller model parameters. The input error [e(n)] and the error change rate [ec(n)] are transformed into fuzzy variables EC and E by fuz ification with Gaussian function as the membership function. According to the analysis of a large number of sample data of Raman spectrum in the early stage, the complexity of fuzzy rule base is reduced as far as possible on the premise of meeting the basic requirements of control accuracy, so as to improve the calculation speed in practical applications. In this article, expert rule bases of fuzzy reasoning are constructed for proportional coefficient [Kp(n)] and the integration coefficient [KI (n)], respectively” the measurement is repeated any number of measurement step could be 5th sixth.).
Regarding claim 17, combination of Yadav and Xue teaches the computer-implemented method of claim 14,
Yadav further teaches, the method further comprising:
determining, by the one or more processors, a threshold signal-to-noise ratio (SNR) intensity value based on the preliminary sample data, wherein the preliminary sample data includes a dark Raman spectra data; generating, by the one or more processors, the SNR linear model based on, at least, the threshold SNR intensity value (Yadav, [0049]” In accordance with FIG. 2, the SNR and SBR metric are compared to a threshold. Based on our extensive data analysis and the ground truth of what constitutes a good or bad spectrum, we have experimentally defined thresholds for these two metrics. Only spectra that meet the set cut-off thresholds are considered high quality Raman Spectra and used in the subsequent feature extraction and classification schemes”).;
Yadav is silent on converting, by the one or more processors, a domain of the generated SNR linear model from intensity level to SNR; applying the one or more deviations to the SNR linear model; and converting, by the one or more processors, a domain of the SNR linear model from SNR to intensity level, to form the SNR-to-intensity model.
However, Xue teaches converting, by the one or more processors, a domain of the generated SNR linear model from intensity level to SNR; applying the one or more deviations to the SNR linear model; and converting, by the one or more processors, a domain of the SNR linear model from SNR to intensity level, to form the SNR-to-intensity model. (Xue, Figure 2, Page 3, Right col, Evaluation methods of spectrum quality include intensity, SNR, and so on, which are generally in positive correlation [3].. Raman signals detected by very short time generally have poor SNR and are coupled with strong noise interference signals. However, the preacquisition spectrum stage mainly provides rough initial parameters of PID control model for fuzzy PID controller to reduce iteration time and the fuzzy PID controller will further autocorrect the initial parameters according to the fuzzy rule database. After calculating the maximum peak height [hmax(0)] of the strongest effective peak or SNR [SNR(0)] by analyzing the detected Raman spectrum data, the initial parameters required by the fuzzy PID controller are roughly estimated by the initial parameter prediction model and then transmitted to the fuzzy PID controller for automatic integration time control. The fuzzy PID controller compare s the collected [hmax(n)] or [SNR(n)] with the set value (h_) or (SNR_), automatically corrects the model parameters, and calculates the optimal integration time, automatically controlling the Raman spectrometer for spectrum acquisition”).
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Yadav’s method for predicting Raman spectral quality to incorporate a machine learning based intensity to time model as taught by Xue incorporating time and intensity parameters to calculate the optimal integration time fast to shorten the total spectrum acquisition time, improves the efficiency of spectrum acquisition and enhances the control performance (Xue, Abstract). It would have been obvious to a person of ordinary skill to include the well-known Machine learning model in order to yield the predicted results of to calculate spectrum quality and at efficient speed, yet with higher accuracy (KSR).
Regarding claim 18, Yadav teaches
An analytical instrument support system comprising:
one or more processors, one or more non-transitory computer-readable storage media; and program instructions stored on at least one of the one or more non-transitory computer-readable storage media for execution by at least one of the one or more processors (Yadav, Figure 1), the program instructions comprising:
program instructions to receive, preliminary sample data collected from a short scan of a sample; program instructions to determine a bright-max intensity level based on, at least, the preliminary sample data; (Yadav, [0009] FIG. 3 is a block diagram showing use of a data acquisition algorithm to optimize laser excitation power. [0028], Figure 3c, “For each measurement determine the maximum measured intensity as maxRS 1 and maxRS2. By using these two measurement pairs it is possible to extrapolate and determine the optimal excitation laser power P opt, such that the maximum measured intensity is 90% of allowable spectrometer/CCD dynamic range”);
program instructions to determine a performance class based on, at least, the bright-max intensity level (Yadav, Figure 2, Raman spectra extraction, feature extraction and classify. [0026] “In the Raman Spectra Extraction or the Preprocessing block, signal processing algorithms are applied to extract the Raman Spectra from the acquired Raman data. [0054] In the simplest implementation, Raman intensity at each of the identified spectral location is used as a feature vector of K-elements for classification. In one implementation,
we selected K=300 spectral bands with J=50 bootstrapped iterations. FIG. 7 depicts the outcome of this feature extraction from one of the training datasets.);
program instructions to store, on one or more computer-readable memory devices, the first maximum intensity level or the first parameter exposure time. Yadav, Figure 1, Raman spectrum system with a computer and memory)
Yadav is silent on program instructions to determine an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class;
program instructions to determine, a first prediction representing a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model, or a second prediction representing a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model;
However, Xue teaches program instructions to determine an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class (Xue, Figure 2, Page 3000110, right col. After calculating the maximum peak height [hmax(0)] of the strongest effective peak or SNR [SNR(0)] by analyzing the detected Raman spectrum data, the initial parameters required by the fuzzy PID controller are roughly estimated by the initial parameter prediction model and then transmitted to the fuzzy PID controller for automatic integration time control. The fuzzy PID controller compares the collected [hmax(n)] or [SNR(n)] with the set value (h_) or (SNR_), automatically corrects the model parameters, and calculates the optimal integration time, automatically controlling the Raman spectrometer for spectrum acquisition. Since the initial parameter prediction model is established according to a specific Raman spectrometer, it has strong parameter sensitivity, while the performance of different spectrometers varies greatly; thus, the parameters of the prediction model”);
; program instructions to determine, a first prediction representing a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model, Xue, Figure 2, Page 3000110, Right col. the preacquisition spectrum stage mainly provides rough initial parameters of PID control model for fuzzy PID controller to reduce iteration time and the fuzzy PID controller will further autocorrect the initial parameters according to the fuzzy rule database. After calculating the maximum peak height [hmax(0)] of the strongest effective peak or SNR [SNR(0)] by analyzing the detected Raman spectrum data, the
initial parameters required by the fuzzy PID controller are roughly estimated by the initial parameter prediction model then, the parameters of the PID
controller are fuzzily adjusted by the fuzzy expert database,ensuring the rapid convergence control of different samples”)
or
a second prediction representing a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model; and
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Yadav’s method for predicting Raman spectral quality to incorporate a machine learning based intensity to time model as taught by Xue incorporating time and intensity parameters to calculate the optimal integration time fast to shorten the total spectrum acquisition time, improves the efficiency of spectrum acquisition and enhances the control performance (Xue, Abstract). It would have been obvious to a person of ordinary skill to include the well-known Machine learning model in order to yield the predicted results of to calculate spectrum quality and at efficient speed, yet with higher accuracy (KSR).
Regarding claim 19, combination of Yadav and Xue teaches the analytical instrument support system of claim 18,
Yadav further teaches wherein the program instructions are executed on a common computing device including at least one of the one or more processors. (Yadav, Figure 1).
Regarding claim 20, Yadav teaches
An analytical instrument (Yadav Figure 1) comprising:
a light source configured to direct light onto a surface of a sample (Yadav, Figure 1, [0023], Laser light source);
a spectrograph to acquire a Raman spectrum from the surface of the sample in response to the light source directing light onto the surface of the sample (Yadav Figure 1, [0023] representative embodiment is shown in FIG. 1. The representative inventive embodiment of FIG. 1 is capable of acquiring and processing Raman data,); one or more processors; one or more non-transitory computer-readable storage media; and program instructions stored on at least one of the one or more non-transitory computer-readable storage media for execution by at least one of the one or more processors, wherein upon execution of the program instructions by at least one of the one or more processors, cause the analytical instrument to implement a set of acts comprising: (Yadav, Figure 1, [0023] “a data processing module consisting of laptop or a PC. The data processing module is responsible for controlling the light source, CCD and processing the acquired Raman data”), analyzing Raman spectrum data from the acquired Raman spectrum associated with the surface of the sample, (Yadav, [0007] FIG. 1 shows an inventive Raman spectroscopy. [0023] FIG. 1. The representative inventive embodiment of FIG. 1 is capable of acquiring and processing Raman data,);
determining a bright-max intensity level based on, at least, the acquired Raman spectrum, (Yadav, [0009] FIG. 3 is a block diagram showing use of a data acquisition algorithm to optimize laser excitation power. [0028], Figure 3c, “For each measurement determine the maximum measured intensity as maxRS 1 and maxRS2. By using these two measurement pairs it is possible to extrapolate and determine the optimal excitation laser power P opt, such that the maximum measured intensity is 90% of allowable spectrometer/CCD dynamic range”); determining a performance class based on the bright-max intensity level associated with the acquired Raman spectrum, (Yadav, Figure 2, Raman spectra extraction, feature extraction and classify. [0026] “In the Raman Spectra Extraction or the Preprocessing block, signal processing algorithms are applied to extract the Raman Spectra from the acquired Raman data. [0054] In the simplest implementation, Raman intensity at each of the identified spectral location is used as a feature vector of K-elements for classification. In one implementation,
we selected K=300 spectral bands with J=50 bootstrapped iterations. FIG. 7 depicts the outcome of this feature extraction from one of the training datasets.);
storing on at least one of the one or more non-transitory computer-readable storage media the first maximum intensity level or the first parameter exposure time. (Yadav, Figure 1, Raman spectrum system with a computer and memory, [0023] “a data processing module consisting of laptop or a PC. The data processing module is responsible for controlling the light source, CCD and processing the acquired Raman data).
Yadav is silent on determining an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class; determining a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model, or, a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model, and
However, Xue teaches determining an intensity-to-time model, the intensity-to-time model including a plurality of intensity levels and a plurality of exposure times based on, at least, one or more deviations from an intensity linear model, the one or more deviations associated with the determined performance class (Xue, Figure 2, Page 3000110, right col. After calculating the maximum peak height [hmax(0)] of the strongest effective peak or SNR [SNR(0)] by analyzing the detected Raman spectrum data, the initial parameters required by the fuzzy PID controller are roughly estimated by the initial parameter prediction model and then transmitted to the fuzzy PID controller for automatic
integration time control. The fuzzy PID controller compares the collected [hmax(n)] or [SNR(n)] with the set value (h_) or (SNR_), automatically corrects the model parameters, and calculates the optimal integration time, automatically controlling the Raman spectrometer for spectrum acquisition. Since the initial parameter prediction model is established according to a specific Raman spectrometer, it has strong parameter sensitivity, while the performance of different spectrometers varies greatly; thus, the parameters of the prediction model”) ;
determining, by the one or more processors, a first prediction representing a first maximum intensity level based on, at least, a first corresponding exposure time and the intensity-to-time model, (Xue, Figure 2, Page 3000110, Right col. the preacquisition spectrum stage mainly provides rough initial parameters of PID control model for fuzzy PID controller to reduce iteration time and the fuzzy PID controller will further autocorrect the initial parameters according to the fuzzy rule database. After calculating the maximum peak height [hmax(0)] of the strongest effective peak or SNR [SNR(0)] by analyzing the detected Raman spectrum data, the
initial parameters required by the fuzzy PID controller are roughly estimated by the initial parameter prediction model then, the parameters of the PID
controller are fuzzily adjusted by the fuzzy expert database,
ensuring the rapid convergence control of different samples”) or
a second prediction representing a first parameter exposure time based on, at least, a first corresponding intensity level and the intensity-to-time model.
It would have been obvious to a person having ordinary skill in the art before the effective filing date to modify Yadav’s method for predicting Raman spectral quality to incorporate a machine learning based intensity to time model as taught by Xue incorporating time and intensity parameters to calculate the optimal integration time fast to shorten the total spectrum acquisition time, improves the efficiency of spectrum acquisition and enhances the control performance (Xue, Abstract). It would have been obvious to a person of ordinary skill to include the well-known Machine learning model in order to yield the predicted results of to calculate spectrum quality and at efficient speed, yet with higher accuracy (KSR).
Conclusion
Citation of Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
HE et al (CN 109993155 A) recites Characteristic peak extracting method disclosed by the invention for low signal-to-noise ratio uv raman spectroscopy, belongs to spectrographic detection and spectral processing techniques and field of signal processing. The present invention acquires ultraviolet Raman signal in real time, counts to acquisition Raman signal data, predicts Raman signal effective peak. Each frame Raman spectrum of acquisition is handled, for each frame Raman spectrum, by each frame Raman spectrum cutting is each piece of region by effective low ebb of acquisition, judges each piece of area attribute of cutting respectively. For each noise region, wherein each point is allowed to be equal to the minimum value in the region, then, by Raman signal region and treated that noise region carries out split. Later, treated N+1 frame spectrum along time shaft is spliced into 2D image, by the bilateral filtering method of iteration, which is filtered, N+1 spectrum is overlapped and is normalized along time shaft after filtering, obtains clean Raman characteristic peak spectrum picture” (Abstract)
Barton et al “Convolution Network with Custom Loss Function for the Denoising of Low SNR Raman Spectra”, Sensors. 2021; 21(14):4623
Abstract
Raman spectroscopy is a powerful diagnostic tool in biomedical science, whereby different disease groups can be classified based on subtle differences in the cell or tissue spectra. A key component in the classification of Raman spectra is the application of multi-variate statistical models. However, Raman scattering is a weak process, resulting in a trade-off between acquisition times and signal-to-noise ratios, which has limited its more widespread adoption as a clinical tool. Typically denoising is applied to the Raman spectrum from a biological sample to improve the signal-to-noise ratio before application of statistical modeling. A popular method for performing this is Savitsky–Golay filtering. Such an algorithm is difficult to tailor so that it can strike a balance between denoising and excessive smoothing of spectral peaks, the characteristics of which are critically important for classification purposes. In this paper, we demonstrate how Convolutional Neural Networks may be enhanced with a non-standard loss function in order to improve the overall signal-to-noise ratio of spectra while limiting corruption of the spectral peaks. Simulated Raman spectra and experimental data are used to train and evaluate the performance of the algorithm in terms of the signal to noise ratio and peak fidelity. The proposed method is demonstrated to effectively smooth noise while preserving spectral features in low intensity spectra which is advantageous when compared with Savitzky–Golay filtering. For low intensity spectra the proposed algorithm was shown to improve the signal to noise ratios by up to 100% in terms of both local and overall signal to noise ratios, indicating that this method would be most suitable for low light or high throughput applications.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DILARA SULTANA whose telephone number is (571)272-3861. The examiner can normally be reached Mon-Fri, 9 AM-5:30 PM.
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, EMAN ALKAFAWI can be reached on (571) 272-4448. 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.
/DILARA SULTANA/Examiner, Art Unit 2858 08/22/2026
/EMAN A ALKAFAWI/Supervisory Patent Examiner, Art Unit 2858 9/2/2026
Prosecution Insights