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 .
Status of Claims
The claim set received 09 August 2022 has been entered into the application.
Claims 1-14 are pending
Election/Restrictions
Claims 1-7 are withdrawn from further consideration pursuant to 37 CFR 1.142(b), as being drawn to a nonelected invention, there being no allowable generic or linking claim. Applicant timely traversed the restriction (election) requirement in the reply filed on 03 March 2026.
Therefore, claims 7-14 are pending examination.
The Applicant states the search for both sets of claims substantially overlaps. Further, the issues regarding patentability are the same for both sets of claims.
The argument is note persuasive because as noted in the Office Action mailed 03 March 2026, the inventions of Groups I-II are drawn to distinct inventions (i.e., Group I - drug screening process, Group II – EEG/EMG system/machine) although they both encompass using an EEG and/or EMG.
Therefore, the restriction requirement is not withdrawn.
Claims 7-14 are pending.
Priority
This Application claims benefit to U.S. Provisional Patent Application 63/243,749 filed 14 September 2021.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 09 August 2026 is being considered by the examiner.
Drawings
The drawings were received on 09 August 2026. These drawings are 09 August 2026.
Claim Rejections - 35 USC § 112
35 USC § 112(a)
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.
Claim 7-14 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.
Rejection under 112(a) in view of considerations under 112(f)
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Such claim limitation(s) is/are:
Here, under Prong I (A) of the 112(f) three-prong analysis, claim 7 recites the nuance term/generic placeholder “unit” configured for”. For example, claim 7 recites “a data acquisition ‘unit’ configure for”, “a feature extraction ‘unit’ configured for”, and “a classification ‘unit’ configured for”.
Next, under Prong II (B) of the 112(f) analysis, the generic means place holders recites functional language such as: claim 7 recites “a feature extraction ‘unit’ configured for…”, and “a classification ‘unit’ configured for…” which provides functional language/description of the nuance term/generic placeholder.
However, and furthermore, and under Prong III (C) of the 112(f) analysis, the means/generic placeholders of claim 7 are not supported by sufficient definite structure, material, or acts for achieving the specified function. Therefore, under Prong III(C), the claimed limitations are interpreted under 112(f).
Thus, in review of the specification, it does not disclose an algorithm (i.e., software) or structure (i.e., computer processor) that can accomplish the claimed function of acquiring data, extracting features, and classifying data. Thus the recitation of the “unit” invokes claimed language to be examined under 112f.
MPEP 2181(II)(B) explains that:
For a computer implemented 112(f) claim limitation that performs a specific computer function, the specification must disclose an algorithm for performing the claimed specific computer function. An algorithm is defined as a finite sequence of steps for solving a logical or mathematical problem for performing a task. Applicant may express that algorithm in any understandable terms including as a mathematical formula, in prose, or as a flow chart, or in any other manner that provides sufficient structure.
Claim 7 is drawn to a machine learning system for screening a potential drug candidate based on EEG or EMG. Here, a review of the specification shows that aspects of the invention may be implemented using software and computer devices (page 10 para 0051, 0053, and 0054). The specification discloses a “data acquisition unit [page 2 para 009]”, “extraction and classification unit [page 3 para 0010], and “a data acquisition unit [page 5 para 0027]”. The specification discloses “the EEG data is pre-processed…filtered [page 5 para 0028]“, but the specification does not provide a “pre-processor (i.e., computer component/equipment)” for performing the data acquisition. For example, the term ‘unit” is a structureless nuance term for a “means” for performing the recited functions. Here, the specification does not provide as to what the "means” (i.e., software or computer processor) for: a data acquisition “unit” configured for…comprises a pre-processor. a feature extraction “unit” configured for, and a classification “unit” configured for”. Additionally, the specification does not provide in any embodiments or examples exemplifying software, algorithms, and/or computer code or computer processer which act as “units” that structurally perform the functions claimed. . Therefore, one of ordinary skill in the art would not know what “structure(s)” are performing the claimed functions and/or how to utilize these structures to perform the claimed function because a written descriptions of these structures has not been provided.
MPEP 2161.01(l) explains that the specification should describe how the claimed computerized function is achieved. Furthermore, it is not enough that one skilled in the art could theoretically write a program to achieve the claimed function, rather the specification itself must explain how the claimed function is achieved. Here, it is recommended to amend the claim to clarify what the “unit” is referring. For example, are the units constructed of software/algorithms or constructed of physical computer processing units or other computer hardware or components. It is further recommended to amend the claim to be drawn to a system comprising a processor with instructions for, performing the recited process steps.
Claims 8-14 are rejected because they fail to provide algorithm/structure to overcome the deficiencies of the base claim(s).
35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 7-14 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Rejection under 112(b) in view of considerations under 112(f)
Claim 7:
Here, it is not clear what the structure or series of steps that correspond to nuance term/generic placeholder “unit” of the claimed “a data acquisition unit configured for…comprises a pre-processor”, “a feature extraction unit configured for”, and “a classification unit configured for” are. It is not clear if software modules, algorithm, or physical computer processor or other computer components are acting as and/or performing as “units” for data acquisition, feature extraction, and classifying images.
Claim 7 recites “means plus function” for “a data acquisition unit configured for…comprises a pre-processor”, “a feature extraction unit configured for”, and “a classification unit configured for”.
MPEP 2181(II)(B) explains that:
For a computer implemented 112(f) claim limitation that performs a specific computer function, the specification must disclose an algorithm for performing the claimed specific computer function. An algorithm is defined as a finite sequence of steps for solving a logical or mathematical problem for performing a task. Applicant may express that algorithm in any understandable terms including as a mathematical formula, in prose, or as a flow chart, or in any other manner that provides sufficient structure.
The claim should be amended to clarify the structure of the “unit”. For example, are the units constructed of software modules/algorithms or constructed of physical computer processing units or other computer hardware or components. It is further recommended to amend the claim to be drawn to a system comprising a processor with instructions for, performing the recited process steps and/or replace “unit” with “instructions” for performing the claimed process/function.
Claim 7 is drawn to a machine learning system for screening a potential drug candidate based on EEG or EMG. Here, a review of the specification shows that aspects of the invention may be implemented using software and computer devices (page 10 para 0051, 0053, and 0054). The specification discloses a “data acquisition unit [page 2 para 009]”, “extraction and classification unit [page 3 para 0010], and “a data acquisition unit [page 5 para 0027]”. Moreover, the specification does not provide as to what the "means (i.e., unit) for: a data acquisition unit configured for…comprises a pre-processor. a feature extraction unit configured for, and a classification unit configured for”. Additionally, the specification does not provide in any embodiments or examples exemplifying software, algorithms, series of steps, computer hardware, and/or computer code that act as units which structurally perform the function the claimed limitations.
Therefore, under consideration set forth under 112(f), it is thus unclear what structure corresponds to the claimed “a data acquisition unit configured for…comprises a pre-processor”, “a feature extraction unit configured for”, and “a classification unit configured for”. As such, one of ordinary skill in the art would not know what is needed to be a means for carrying out the claimed function.
Claims 8-14 are rejected because they fail to provide algorithm/structure to overcome the deficiencies of the base claim(s).
Claim 8 recites “outliers”. The metes and bounds of the term “outlier” render the claim indefinite because it is not clear what data is considered as outliers. The specification does not provide a definition for the term. It is noted the term can encompasses various types of information that can be considered an outlier.
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 7-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
Step I - Process, Machine, Manufacture or Composition
Claims 7-14 are drawn to a system for screening protentional drug candidates, so a machine.
Step 2A Prong I - Identification of an Abstract Idea
extracting seizure related signals from the EEG or EMG signals output by the data acquisition unit
This step can be performed in the human mind by observing and evaluating data for extracting/selecting EEG and/or EMG signals related to seizures and is therefore an abstract idea.
converting the extracted signals into two-dimensional images for classification and annotation
This step can be performed in the human mind by organizing information (i.e., seizure related signals from the EEG or EMG signals output) into two-dimensional images for classification and annotation and is therefore an abstract idea..
classifying the two-dimensional images into seizure and normal events and annotating thereof according to the classification result
This step can be performed in the human mind by observing and evaluating information (i.e., classification results) to classify two-dimensional images into seizure and normal events and is therefore an abstract ideas. This step encompasses classifying data into categories which encompasses using mathematical concepts (i.e., equalities and inequalities) for separating and classifying data based on quantitative ranges/thresholds which reads on abstract ideas. See MPEP 2106.04(a)(2)(III)(C)(1-3).
This step encompasses classifying data which read on mathematically organizing data into categories/classifications (i.e., using equalities and inequalities) which reads abstract ideas
an autoencoder based on a convolutional neural network (CNN) for encoding the classified and annotated images output by the classification unit into a plurality of feature maps in different dimensions according to a sequence of convolutional layers followed by generating a plurality of feature vectors from the plurality of feature maps by a plurality of fully connected layers arranged subsequent to the plurality of convolutional layers.
This step encompasses using an autoencoder based on a convolutional neural network (CNN) which encompasses utilizing vector and matrix mathematics which reads on abstract ideas. Here, the autoencoder/convolutional network is generically recited and reads on abstract ideas. Additionally, the step encompasses taking information (i.e., classified and annotated images output) and manipulating the data via mathematical correlation (i.e., autoencoder/CNN) for organizing the data into a different form (i.e., generating a plurality of feature vectors from the plurality of feature maps) which reads on abstract ideas. See MPEP 2106.04(a)(2)(III)(A)(iv) and 2106.04(a)(2)(III)(C)(1-3).
Step 2A Prong II - Consideration of Practical Application
Here, in the instant case, claim 7 merely sets forth a method of data analysis using a system for screening potential drug candidates by gathering EEG and EMG signal data for generating feature vectors from feature vector maps. As such, practicing the claims merely results in generating feature maps for subsequent input into convolutional layers. Such a result only produces information and does not provide for a practical application in the physical-realm of physical things and acts, i.e., the claims do not utilize the data generated by the judicial exception to affect any type of change. See MPEP 2106.04(a)(2)(A)(iv).
Claim 7 autoencoder step recites “autoencoder based on a convolutional neural network (CNN) for encoding the classified and annotated images output by the classification unit into a plurality of feature maps in different dimensions according to a sequence of convolutional layers followed by generating a plurality of feature vectors from the plurality of feature maps by a plurality of fully connected layers arranged subsequent to the plurality of convolutional layers”. Here, even though the claimed steps utilize a “machine learning model/convolution neural network (CNN) (MLCNN)”, the MLCNN is broadly and generically recited and reads on mere instructions to implement an abstract idea on a generic computer and reads on mathematical/statistical computations. See 2024 Subject Matter Eligibility Update (AI) [Example 47 Claim 2] and MPEP 2106.04(a)(2)(III)(C)(1-3) and 2106.05(f).
Furthermore, and for sake of compact prosecution, even if the MLCNN of claims 7 and 14 is also considered an additional element, the MLCNN is used to generally apply the abstract idea without limiting how the trained MLCNN functions. The MLCNN is described at a high level such that it amounts to using a computer with a generic MLCNN to apply the abstract idea. These limitations only recite the outcomes for “an autoencoder based on a convolutional neural network (CNN) for encoding the classified and annotated images output by the classification unit into a plurality of feature maps” without any details about how convolutional neural network (CNN) is used for encoding the classified and annotated images output of the classification unit into a plurality of feature maps which does not integrate the judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words "apply it". See 2024 Subject Matter Eligibility Update (AI) [Example 47 Claim 2] and MPEP 2106.05(f).
This judicial exception is not integrated into a practical application because the claims do not meet any of the following criteria:
An additional element reflects an improvement in the functioning of a computer, or an improvement to other technology or technical field;
an additional element that applies or uses a judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition;
an additional element implements a judicial exception with, or uses a judicial exception in conjunction with, a particular machine or manufacture that is integral to the claim;
an additional element effects a transformation or reduction of a particular article to a different state or thing; and
an additional element applies or uses the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception.
Step 2B: Consideration of Additional Elements and Significantly More
The claimed method also recites "additional elements" that are not limitations drawn to an abstract idea.
The recited additional elements of using electrodes from an EEG or EMG of claim 7 does not add significantly more than the recited judicial exception because using electrodes to gather brain wave data is deemed routine and conventional. To provide evidence of conventionality of using electrodes and an EEG device, Zikov discloses using an EEG with electrodes for detecting seizures [Zikov claim 1] (US Patent: 9,554,721, Patent Date: 31 January 2017).
The recited additional elements of data gathering by data acquisition of claim 7 a data acquisition unit does not add significantly more than the recited judicial exception because gathering data from EEG and EMG is deemed routine and conventional. See MPEP 2106.05(g).
The recited additional elements using computer process (i.e., classifying unit, extraction unit, preprocessor), components (low- and high- pass filters) and equipment of claims 7 (i.e., data acquisition unit) and 9 (low- and high- pass) does not add significantly more than the recited judicial exception because using computers to processes, store, and evaluate abstract ideas is merely tangential to the claimed method and is deemed routine and conventional. See MPEP 2105.06(d)(II) and 2106.05(g). To provide evidence of conventionality of using low- and high- band filters (i.e., preprocessor), Saminu teaches filtering techniques applied to raw EEG data to remove or reduce artifact and noise (i.e., pre-processing). Saminu teach using wavelet transform using low- and high-pass filters [page 9 in discrete wavelet form para] (Brain sciences, 2021-05, Vol.11 (5), p.668)
In conclusion, and when viewed as a whole, these additional claim element(s) do not provide meaningful limitation(s) to transform the abstract idea recited in the instantly presented claims into a patent eligible application of the abstract idea such that the claim(s) amounts to significantly more than the abstract idea itself. Therefore, the claim(s) are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 7 and 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over Saminu et al. (Brain sciences, 2021-05, Vol.11 (5), p.668) in view of Mahammad et al. (IEEE access, 2018-01, Vol.6, p.45372-45383) in view of Sors et al. (Deep Learning for Continuous EEG Analysis. Diss. Université Grenoble Alpes, 2018).
Claim 7 recites a plurality of electrodes configured for recording EEG or EMG signals.
Claim 7 recites a data acquisition unit configured for receiving the EEG or EMG signals, wherein the data acquisition unit comprises a pre-processor.
Claim 7 recites a feature extraction unit configured for extracting seizure related signals from the EEG or EMG signals output by the data acquisition unit and converting the extracted signals into two-dimensional images for classification and annotation;
Claim 7 recites a classification unit configured for classifying the two-dimensional images from the feature extraction unit into seizure and normal events and annotating thereof according to the classification result.
Claim 7 recites an autoencoder based on a convolutional neural network (CNN) for encoding the classified and annotated images output by the classification unit into a plurality of feature maps in different dimensions according to a sequence of convolutional layers followed by generating a plurality of feature vectors from the plurality of feature maps by a plurality of fully connected layers arranged subsequent to the plurality of convolutional layers.
Saminu et al. (Saminu) teaches an epileptic seizure detection system that consists of data acquisition, preprocessing, feature extraction, classification, and performance analysis [Saminu page 3 section 2]. Saminu teaches acquisition step that uses EEG electrode for EEG recording [page 3 section 2.1], as in claim 7 a plurality of electrodes configured for recording EEG or EMG signals.
Saminu teaches filtering techniques applied to raw EEG data to remove or reduce artifact and noise (i.e., pre-processing). Saminu teach using wavelet transform using low- and high-pass filters [page 9 in discrete wavelet form para], as in claim 7 a data acquisition unit configured for receiving the EEG or EMG signals, wherein the data acquisition unit comprises a pre-processor.
Saminu et al. teaches features extraction in an epileptic seizure detection system [page 3 figure 1]. Saminu teaches different feature extraction techniques [page 6 section 3]. Saminu teaches discrete wavelength decomposition images (i.e., periodograms) showing sample points [page 10 figure 4]. Saminu teaches the classification algorithm is largely dependent on the feature extracted and fed to the classifier [Saminu page 11 section 4], as in claim 7 a feature extraction unit configured for extracting seizure related signals from the EEG or EMG signals output by the data acquisition unit and converting the extracted signals into two-dimensional images for classification and annotation.
Saminu teaches the classification algorithm is largely dependent on the feature extracted and fed to the classifier [Saminu page 11 section 4]. Saminu teaches the features are extracted and can be characterized and/or classified between normal and different seizure categories when classifying [page 11 section 4]. Saminu teaches the wavelet as classified as seizure [page 10 fig 4], as in instant claim 7 a classification unit configured for classifying the two-dimensional images from the feature extraction unit into seizure and normal events and annotating thereof according to the classification result.
Dependent claim(s): 11
Saminu teaches seizure signals related to amplitude [Saminu page 6 section 3.1]. Saminu teaches using frequency domain [Saminu page 7 section 3.2]. Saminu teaches interictal signal are seen as sharp, spikey and temporary waveforms [Saminu page 2], as in instant claim 11.
Saminu does not teach claim 7 an autoencoder based on a convolutional neural network (CNN) for encoding the classified and annotated images output by the classification unit into a plurality of feature maps in different dimensions according to a sequence of convolutional layers followed by generating a plurality of feature vectors from the plurality of feature maps by a plurality of fully connected layers arranged subsequent to the plurality of convolutional layers. Saminu does not teach claim 12.
Muhammad
Muhammad et al. (Muhammad) teaches a seizure detection system using an autoencoder and CNN combination [Muhammad page 45377 figure 2]. Muhammed teaches using an autoencoders for reducing data dimensions [Muhammed page 453778]. Muhammad teaches used autoencoders to produce a dimension of 1280 [Muhammad page 45379], as in instant claim 7 an autoencoder based on CNN.
Sors
Sors et al. (Sors) teaches using feature maps [page 43 first para]. Sors teaches showing the number of feature maps [Sors page 69 fig 4.13]. Sors teaches feature maps [Sors page 25 figs 2.7-2.8]. Sors teaches feature extraction of EEG signals and processing the signals using feature vectors and classifying the EEG signals [Sors page 37 fig 2.16]. Sors teaches different dimensions in CNN [Sors page 43 fig 3.1-3.2], as in claim 7 autoencoder step. Sors teaches EEG sequence is transformed into a time series of feature vectors and teaches the classifier predicts outcome from the series of feature vectors [Sors page 37 top para].
Sors teaches using both spectrogram and periodograms [Sors page 14 fig 1.4 (b-c)], as in instant claim 12.
Obvious claimed step:
With respect to claim 7, the claim recites an autoencoder based on a convolutional neural network (CNN) for encoding the classified and annotated images output by the classification unit into a plurality of feature maps in different dimensions according to a sequence of convolutional layers followed by generating a plurality of feature vectors from the plurality of feature maps by a plurality of fully connected layers arranged subsequent to the plurality of convolutional layers,
Muhammad et al. (Muhammad) teaches a seizure detection system using an autoencoder and CNN combination [Muhammad page 45377 figure 2]. Muhammed teaches using an autoencoders for reducing data dimensions [Muhammed page 453778]. Muhammad teaches used autoencoders to produce a dimension of 1280 [Muhammad page 45379].
Sors et al. (Sors) teaches using feature maps [page 43 first para]. Sors teaches showing the number of feature maps [Sors page 69 fig 4.13]. Sors teaches feature maps [Sors page 25 figs 2.7-2.8]. Sors teaches feature extraction of EEG signals and processing the signals using feature vectors and classifying the EEG signals [Sors page 37 fig 2.16]. Sors teaches different dimensions in CNN [Sors page 43 fig 3.1-3.2]. Sors teach using weight vectors that work best with CNN [Sors page 33].
Here, although Muhammed and Sors do not explicitly teach generating feature vectors from feature maps, it is obvious that feature vectors from feature maps are generated because feature vectors are created directly from feature maps in a Convolutional Neural Network (CNN). Therefore, the autoencoder step of claim 7 is rendered obvious.
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention to modify Saminu in view of Muhammad because Muhammad teaches using a combination of CNN and autoencoders for processing EEG signal data. One of ordinary skill in the art would recognize that Saminu and Muhammed teach methods for analyzing EEG signals using machine learning elements. One of ordinary skill in the art would be motivated to combine Saminu with Muhammed because while Samin reviews various methods/techniques for a seizure detection system using combinations of different machine learning elements Muhammad teaches using a CNN-autoencoder combinations that can be substituted into the seizure detection system pipeline (i.e., block diagram [Saminu, page 3]) of Saminu to provide a method using a CNN of varying dimensions and CNN-autoencoder combination. Here, combining the methods of Saminu with Mahammad would create a method that can analyze convert 1-D EEG signals into 2-D EEG signal output with a greater than 99% accuracy because Mahammad teaches a seizure detection system that produced accuracies of 99% with respect to patients having or not having seizures signals [Muhammad, pages 45380-45381]. Thus, one of ordinary skill in the art would have a reasonable expectation of success combining the seizure detection system/pipeline of Saminu in view of the CNN-autoencoder Muhammed because the CNN-autoencoder system of Muhammad also teaches the system processes one dimensional (1D) EEG signal data by combining the signals into 23 channels to obtain 2-D representations of EEG signals for subsequent classification [Muhammad page 45377, figure 2]. Therefore, combining the detection system process of Saminu in view of Mahammad would yield a predictable CNN-autoencoding system of different dimensions that can achieve greater than 99% accuracies when analyzing EEG signal data.
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention to modify Saminu in view of Muhammad in view of Sors because Sors teaches utilizing feature maps and feature vectors using CNN classifier [Sors page 42-43]. One of ordinary skill in the art would recognize that Saminu, Mahammad, and Sors are related to similar fields of endeavor such as using machine learning elements for processing and evaluating EEG signaling. One of ordinary skill in the art would be motivated to combine Saminu in view of Mahammad in view of Sors because the methods of Sors are used to improve automated analysis for continuous EEG (cEEG) of advance systems by teaching methods that understand and characterize EEG signal data [Sors, page 4 Thesis organization] using feature maps and feature vectors for processing unprocessed EEG signals [Sors page 43]. Thus, one of ordinary skill in the art would have a reasonable expectation of success combining Saminu in view of Muhammad in view of Sors because Sors expands on using feature maps and feature vectors when using CNN/autoencoder combination for processing one dimensional EEG signal data. Therefore, combining seizure detection system workflow of Saminu in view of CNN-autoencoder and CNN dimensions of Muhammad in view of Sors would yield an improved machine learning (ML) based system that can understand and characterize EEG signal data for screening a potential drug candidate based on electroencephalogram (EEG) or electromyogram (EMG) data.
Claim(s) 8-10 are rejected under 35 U.S.C. 103 as being unpatentable over Saminu in view of Mahammad in view of Sors, as applied into claim 7 and 11-12 above, and in view further view of Wagner (EEG Preprocessing in EEGLAB Virtual EEGLAB workshop 2021 University of California San Diego Johanna Wagner).
Saminu in view of Mahammad in view of Sors teach claims 7 and 11-12.
Saminu in view of Mahammad in view of Sors teach a method using machine learning system for screening a potential drug candidates-based EEG or EMG data.
Saminu in view of Mahammad in view of Sors do not teach claims 8-11.
With respect to claim 8, Wagner teaches removing possibly high amplitude data using high-pass filter software using MATLAB [Wagner, page 33].
Sors recognizes that data should be data excluded if it contains outliers (i.e., epoch) should be excluded because of outliers [page 43 section 3.3.2]. Muhammed teaches using sliding window [page 453776 left col section III A]. Saminu teach EEG data are segmented into overlapping segments and each segment is windowed and estimated from its periodogram [page 8 top of page]. Here, it even though Saminu, Sors, Muhammad, and Wagner do not explicitly teach recombining the segmented signals with overlapping window characteristics it would be obvious the windows are recombined so as to construct an EEG representation of the overlapping segmented signals such as for rejecting abnormal and normal data [Wagner page 59] for preprocessing EEG data.
Saminu teach using wavelet transform using low- and high-pass filters [page 9 in discrete wavelet form para], as in instant claim 9.
Muhammed teaches using a sliding window of 2 second window [page 45376 section III A], as in instant claim 10.
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention to modify Saminu in view of Muhammad in view of Sors, and in further view of Wagner because Wagner teaches methods for removing high amplitude EEG signal data using preprocessing methods in MATLAB. Here, one of ordinary skill in the art would recognize that Wagner teaches additional preprocessing methods that can be substituted into the workflow of Saminu. One of ordinary skill in the art would have a reasonable expectation of success combining preprocessing processes of Wagner’s MATLAB high amplitude removal epoch analysis into the workflow of Saminu with the sliding window of Muhammed and the feature maps and vectors of Sors because the data analysis method (i.e., data removal) of Wagner can be incorporated into the workflow of Samini and/or substituted for the preprocessing methods of Sors or Muhammad to construct a method step that utilizes the exclusion or removal of high amplitude EEG data. Therefore, combining the preprocessing processes of Wagners MATLAB high amplitude removal epoch analysis into the workflow of Saminu in view of Muhammed in view of Sors would yield a predictable method step that can filter amplitude signals and outlier values from EEG or EMG signal data when screening for potential drug candidates.
Claim(s) 13 are rejected under 35 U.S.C. 103 as being unpatentable over Saminu in view of Mahammad in view of Sors, as applied into claim 7 and 11-12 above, and in view further view of He et al. (Journal of Neuroscience Methods, 2011-02, Vol.195 (2), p.261-269).
Saminu in view of Mahammad in view of Sors teach claims 7 and 11-12.
Saminu in view of Mahammad in view of Sors teach a method using machine learning system for screening a potential drug candidates based EEG or EMG data.
Saminu in view of Mahammad in view of Sors do not teach claim 13.
He et al. (He) teaches using MATLAB-based tool-box, eConnectome, for mapping and imaging functional connectivity connectivity at both the scalp and cortical levels from the electroencephalogram (EEG), as well as from the electrocorticogram (ECoG) [abstract]. He teaches the “ECOM” was designed to store EEG/ECoG data including acquisition information (e.g. sampling rate), electrodes locations, time series, event information (e.g. onset time), and intermediate data such as preprocessed EEG/ECoG data, estimated cortical sources and connectivity measures can be exported for later analysis and review [He page 262 right col]. He teaches EEG recordings [He page 265 fig 3], as in instant claim 13.
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention to modify Saminu in view of Muhammad in view of Sors, and in further view of He because He teaches utilizing MATLAB for processing, evaluating, displaying, and storing EEG and ECoG data. Here, one ordinary skill in the art would be motivated to combine Saminu in view of Muhammad in view of Sors, and in further view of He because He specifically teaches utilizing MATLAB software, eConnectome, for mapping and imaging functional connectivity at both the scalp and cortical levels from the electroencephalogram (EEG) and ECoG, and He also teaches the MATLAB eConnectome software/modules functions and interfaces are customizable [He page 262 right col]. Here, one of ordinary skill in the art would recognize the method of storing data in MATLAB of He can be incorporated into the seizure detection workflow of Saminu such that classified and analysis results of Saminu can be stored in MATLAB as per He. Thus, one of ordinary skill in the art would be motivated to combine seizure detection analysis method of Saminu with the CNN-autoencoder of Mahammad with the feature maps and feature vectors of Sors with the MATLAB storage methods and customizable modules and interfaces of He because although He does not teach using CNNs, CNN-autoencoders, feature maps and vectors, CNN dimensions, He does teach MATLAB can be utilized to run modules in command line or write customized modules with available functions and interfaces [He page 262 right col]. As such, the customizability of eConnectome of He provides a software platform that can significantly facilitate research of functional brain connectivity because the software can be tailored to specific researcher/research needs such as modifying the MATLAB modules and incorporating them into known/novel systems and/or data analysis pipelines (i.e., pipelines of Saminu, Muhammad, Sor) for screening potential drug candidates. Thus, one of ordinary skill would have a reasonable expectation of success in writing and creating customized modules as per He into the seizure detection system of Saminu such that the results of Saminu, Mahammad, and Sors can be stored in MATLAB for subsequent utilization. Therefore, combining the seizure detection workflow/pipeline of Saminu with the CNN-autoencoder of Mahammad, and feature map and vectors of Sors with the ability to write customize workflow modules for storing and processing EEG data in MATLAB of He would yield a predictable customizable classification unit that can classify EEG results and subsequently store EEG results and annotated EEG images in MATLAB.
Conclusion
Claims 7-14 are rejected.
No claims are allowed.
Finality
This Office action is a Non-Final action. A shortened statutory period for reply to this action is set to expire THREE MONTHS from the mailing date of this action.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSEPH C PULLIAM whose telephone number is (571)272-8696. The examiner can normally be reached 0730-1700 M-F.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Karlheinz Skowronek can be reached at (571) 272-9047. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/J.C.P./Examiner, Art Unit 1687
/Anna Skibinsky/
Primary Examiner, AU 1635
Prosecution Insights