DETAILED ACTION
Applicant's response, filed 1/29/2026, has been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
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 .
Claim Status
Claims 1-4, 7, 9-17 and 20 are pending.
Claims 5, 6, 8, 11, 18, and 19 are cancelled.
Claims 1-4, 7, 9-17 and 20 are rejected.
Claim Rejections - 35 USC § 112
Response to Amendment
In view of applicant’s amendments to the claims, specifically the cancellation of claims 5 and 11, previous rejections under 35 U.S.C. 112 of claims 5 and 11 are withdrawn.
Claim Rejections - 35 USC § 101
Response to Amendment
In view of applicant’s amendments to the claims, previous rejections under 35 U.S.C. 101 have been withdrawn.
Response to Arguments
Applicant's arguments filed 1/29/2026 have been fully considered and are persuasive. Applicant asserts on page 7 of the Remarks filed 1/29/2026 that independent claims 1, 13, and 17 have incorporated the structure of claim 19 which was not rejected under 35 U.S.C. 101 for reciting sufficient structure as to be no longer directed to the judicial exception. Examiner agrees and has withdrawn the rejection.
Claim Rejections - 35 USC § 102
Response to Amendment
In view of applicant’s amendments to the claims, previous rejections under 35 U.S.C. 102 have been withdrawn.
Claim Rejections - 35 USC § 103
Response to Amendment
In response to applicant’s amendments a new prior art search was performed and subsequent review under 35 U.S.C 103 is provided below.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-3, 7, 9-10, and 12-17 are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (Multimedia Tools and Applications (2020) 10655-10675; previously cited) and Delorme et al. (Journal of neuroscience methods (2004) 9-21; newly cited).
Claim 1 is directed to a method for identifying a human subject using EEG data, where a plurality of feature points are extracted from said data and subsequently analyzed to identify the human subject.
Claim 13 is directed to a device comprising an EEG sensor, memory and processor which performs the method of claim 1, receiving EEG data, extracting feature points and predicting identity.
Claim 17 is directed to a system containing memory and a processor which is configured to perform the method of claim 1.
Chen et al. teaches in the abstract “Although more interest arising in biometric identification with electroencephalogram (EEG) signals, there is still a lack of simple and robust models that can be applied in real applications. This work proposes a new convolutional neural network with global spatial and local temporal filter called (GSLT-CNN), which works directly with raw EEG data…” and on page 10660, paragraph 7 “To obtain baseline performance for existing shallow classifiers, two types of features commonly used in the existing EEG-based biometric identification methods were extracted including auto-regression (AR) coefficients and power spectrum density (PSD)”, reading on a method for identifying a human subject, the method comprising: obtaining, at a computer system, electroencephalogram (EEG) data of human brainwaves of a human subject, extracting a plurality of feature points of spectral features corresponding to different frequency bands in the human brainwaves from the EEG data, and implementing a neural network with the computer system to: analyze the extracted plurality of feature points with the neural network and classify an individual based on the analyzed extracted plurality of feature points with the neural network to identify the human subject. Additionally, the use of a BCI (Brain computer interaction) and computer vision reads on a processor configured to perform the method of claim 1 and a memory configured to store EEG data from the EEG sensor. Figure 1 displaying the channel maps of the EEG device reads on an electroencephalogram (EEG) sensor. Chen et al. teaches on page 1063, paragraph 2 “Thus, the unpooling operation uses these switches to place the reconstructions from the layer above into appropriate locations, preserving the structure of the stimulus”, reading on electroencephalogram (EEG) data of human brainwaves of a human subject responding to a stimulus. Furthermore, Chen et al. teaches in Figure 2(B) 3 fully connected layers, equation 1 depicts a ReLU transformation, and on page 10662, paragraph 4 “ReLU modules were also applied on top of each fully connected layer”, reading on wherein the neural network comprises three fully connected layers and two ReLU layers. Finally, Chen et al. teaches on page 10659, paragraph 4 “Preprocessing was performed on all the four experiment datasets using a standardized, automated EEG preprocessing pipeline called PREP. The PREP pipeline preprocessing included band-pass filtering from 0.1 to 55 Hz, robust signal referencing, and identifying and interpolating the bad channels (channels with a low recording SNR), and baseline removal using EEGLAB”.
Delorme et al. teaches in the abstract “We have developed a toolbox and graphic user interface, EEGLAB, running under the crossplatform MATLAB environment (The Mathworks, Inc.) for processing collections of single-trial and/or averaged EEG data of any number of channels. Available functions include EEG data, channel and event information importing, data visualization (scrolling, scalp map and dipole model plotting, plus multi-trial ERP-image plots), preprocessing (including artifact rejection, filtering, epoch selection, and averaging), independent component analysis (ICA) and time/frequency decompositions including channel and component cross-coherence supported by bootstrap statistical methods based on data resampling. EEGLAB functions are organized into three layers”, and on page 20, column 1, paragraph 2 “In this case, ICA may dedicate a single component to the electrode noise, thus unnecessarily reducing the number of components available to separate other neural and artifact sources. Therefore, we find it best to train ICA on carefully pruned ‘clean’ data epochs, which can, however, retain spatially stereotyped artifact activity such as eye blinks and eye movements, repeated muscle activity, etc”, which in view of Chen et al. reads on wherein pre-processing the EEG data further comprises using independent component analysis (ICA) to remove the motor control artifacts.
It would have been obvious at the time of first filing to have modified the teachings of Chen et al. for the method, device and system of claims 1, 13, and 17 with the teachings of Delorme et al. for the removal of artifacts as the latter is the paper for the same EEGLAB pre-processing that was used by Chen et al. One would have had a reasonable expectation of success because it was used previously for those exact purposes. Therefore, it would have been obvious at the time of first filing to have modified the teachings of each and to be successful.
Claim 2 is directed to the method of claim 1 but further specifies that the stimulus is one or more of a visual stimulus, an audio stimulus, or a sensory stimulus.
Chen et al. teaches on page 10658, paragraph 1 “GSLT-CNN model was tested the on a large collection of EEG datasets including 157 subjects collected from four BCI tasks measuring both natural brain states (driving fatigue and emotion) and time-locked artificially elicited brain response such as rapid serial visual response (RSVP)”, reading on wherein the stimulus is one or more of a visual stimulus, an audio stimulus, or a sensory stimulus.
Claim 3 is directed to the method of claim 1 but further specifies that the EEG data comprise motor control data of the human subject responsive to a stimulus.
Chen et al. teaches on page 10658, paragraph 1 “GSLT-CNN model was tested the on a large collection of EEG datasets including 157 subjects collected from four BCI tasks measuring both natural brain states (driving fatigue and emotion) and time-locked artificially elicited brain response such as rapid serial visual response (RSVP)”, reading on wherein the EEG data comprises motor control data of the human subject responsive to the stimulus.
Claim 7 is directed to the method of claim 6 which is directed to the method claims 5 and thus 1, but further specifies that the stimulus comprise a visual stimulus and the pre-processing comprises pre-processing to remove ocular artifacts.
Chen et al. teaches on page 10659, paragraph 4 “Preprocessing was performed on all the four experiment datasets using a standardized, automated EEG preprocessing pipeline called PREP. The PREP pipeline preprocessing included band-pass filtering from 0.1 to 55 Hz, robust signal referencing, and identifying and interpolating the bad channels (channels with a low recording SNR), and baseline removal using EEGLAB”, reading on wherein the stimulus comprises a visual stimulus and pre-processing the EEG data comprises pre-processing the EEG data to remove ocular artifacts prior to extracting the plurality of spectral feature points.
Claim 9 is directed to the method of claim 8 and thus claims 7, 6, 5 and 1, but further specifies that the pre-processing includes bandpass filtering and normalization.
Chen et al. teaches on page 10659, paragraph 4 “Preprocessing was performed on all the four experiment datasets using a standardized, automated EEG preprocessing pipeline called PREP. The PREP pipeline preprocessing included band-pass filtering from 0.1 to 55 Hz, robust signal referencing, and identifying and interpolating the bad channels (channels with a low recording SNR), and baseline removal using EEGLAB”, reading on wherein pre-processing the EEG data further comprises: bandpass filtering the EEG data within a range of human brain waves; and normalizing the EEG data across each channel of the EEG data.
Claim 10 is directed to the method of claim 8 and thus claims 7, 6, 5 and 1, but further specifies the EEG data be down sampled.
Chen et al. teaches on page 10659, paragraph 4 “All datasets were down-sampled…”, reading on wherein pre-processing the EEG data further comprises down sampling the EEG data for the ICA.
Claim 12 is directed to the method of claim 1 but further specifies that the EEG data comprise multi-channel EEG data.
Chen et al. teaches on page 10660, paragraph 2 “This dataset includes 1 s epochs each with 64 channels”, reading on wherein the EEG data comprises multi-channel EEG data.
Claim 14 is directed to the device of claim 13 but further specifies that the EEG sensor be a multi-channel EEG sensor.
Chen et al. teaches on page 10660, paragraph 2 “This dataset includes 1 s epochs each with 64 channels”, reading on wherein the EEG sensor is a multi-channel EEG sensor.
Claim 15 is directed to the device of claim 13 but further specifies that the stimulus is displayed via a visual output device.
Chen et al. teaches on page 10660, paragraph 2 “For CT2WS RSVP, the stimuli are short grayscale video clips presented at 2 Hz”, reading on further comprising a visual output device; wherein the processor is further configured to cause the stimulus to be displayed via the visual output device.
Claim 16 is directed to the device of claim 15 and thus claim 13, but further specifies that there be an input device configured to receive an input response.
Chen et al. teaches on page 10660, paragraph 2 “For CT2WS RSVP, the stimuli are short grayscale video clips presented at 2 Hz”, reading on further comprising an input device configured to receive an input response to the stimulus.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (Multimedia Tools and Applications (2020) 10655-10675; previously cited) and Delorme et al. (Journal of neuroscience methods (2004) 9-21; newly cited) as applied claims 1 and 3, and further in view of Abiri et al. (Journal of Neural Engineering (2019) 1-21; previously cited).
Claim 4 is directed to the method of claim 3 and thus claim 1, but further specifies providing the stimulus as a prompt to interact with a user interface.
Abiri et al. teaches on page 11, column 1, paragraph 2 “In recent BCI studies, combining various mentioned paradigms or combining a BCI paradigm with another interface has shown to enhanced BCI performance. For example, Luth et al paired P300 and SSVEP in controlling an assistive robotic arm. In a 2D cursor task, Li et al used Mu and Beta rhythms for controlling horizontal movement and P300 for vertical movement. Bi et al also used a combination of SSVEP and P300. The SSVEP paradigm was used to extract directional information (clockwise/counterclockwise), and the P300 was used to decode the speed of the cursor”, reading on further comprising providing the stimulus as a prompt to interact with a user interface.
It would have been obvious at the time of invention to modify the teachings of Chen et al. for the method of claims 1-3 with the teachings of Abiri et al. for the use of stimulation in EEG data using a user interface as the latter teaches on page 7, column 2, paragraph 3 “the SSVEP frequencies can be more reliably classified than event-related potentials”, which is that in experiments that use stimuli there is a higher reliability of classification, due to increased peak distinctiveness and an enhanced control over the subjects mental state. One would have had a reasonable expectation of success given that the latter is a review paper on the use of EEG data in brain-computer interface paradigms and the former is teaching the entirety of the rest of the method. Therefore, it would have been obvious at the time of first filing to have modified the teachings of each and to be successful.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (Multimedia Tools and Applications (2020) 10655-10675; previously cited) and Delorme et al. (Journal of neuroscience methods (2004) 9-21; newly cited) as applied to claim 17 above, and further in view of Palaniappan et al. (EEE transactions on pattern analysis and machine intelligence (2007) 738-42; previously cited).
Claim 20 is directed to the system of claim 18 and thus claim 17, but further specifies the use of one-hot encoding for the neural network.
Palaniappan et al. teaches on page 740, column 2, paragraph 3 “The number of output layer units was 102 so that the ENN could classify into one of the 102 categories representing the subject. One-hot encoding was used for the target values (either 0 or 1). The number of hidden layer units was varied between 50 and 300 in steps of 50”, reading on wherein the neural network further comprises one-hot encoding at an output.
It would have been obvious at the time of first filing to modify the teachings of Chen et al. for the method of claims 17-19 with the teachings of Palaniappan et al. for the use of one-hot encoding as the latter is extracting features from EEG data for use in neural network which ensures no false ordinal relationship between categories. One would have had a reasonable expectation of success given that Palaniappan et al. is extracting features from brain activity data (EEGs) during visual stimulus for the identification of individuals. Therefore, it would have been obvious at the time of first filing to modify the teachings of each and to be successful.
Response to Arguments
Applicant's arguments filed 1/29/2026 have been fully considered but they are not persuasive. Applicant asserts on page 9 of the remarks that not all claim limitations are taught by the cited references in view of the amendments. Examiner has done an updated search and applied new art, cited above, which reads on the newly recited claim limitations.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEENAN NEIL ANDERSON-FEARS whose telephone number is (571)272-0108. The examiner can normally be reached M-Th, alternate F, 8-5.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Karlheinz Skowronek can be reached at 571-272-9047. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/K.N.A./Examiner, Art Unit 1687
/OLIVIA M. WISE/Supervisory Patent Examiner, Art Unit 1685
Prosecution Insights