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 .
DETAILED ACTION
Priority
Acknowledgment is made of applicant's claim for domestic benefit based on a provisional application 63/424,235 filed on November 10, 2022.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 4, 6, 11, 14, 16, and 20 are rejected under 35 U.S.C. 102(a)(1) or 102(a)(2) as being anticipated by Pilly et al. (US PG Pub. No. 20210240265), herein “Pilly,”
Regarding claim 1,
Pilly teaches a method of training a brain machine interface system comprising: (Par. 0034: “The brain state encoder 102 may be any suitable type or kind of brain state encoder. FIG. 5 depicts a brain-state (BS) self-organizing feature map (SOFM). The encoding system is personalized based on brain state representations derived from fused sensor signals acquired during testing and training sessions.” Par. 0035. See also task interface module(s), item 104 that are coupled to the brain state encoder and decoder that are trained and directly interface to the brain.)
conducting an initial session of sensing brain state data of a brain of a subject during performance of a task at a first time; (Par. 0035, lines 1 – 25: “A Self-Organizing Feature Map (SOFM) is a type of artificial neural network that is trained using unsupervised learning to produce a low-dimensional (e.g., two-dimensional), discretized representation of the input space of the training samples, called a map, and is therefore a method to do dimensionality reduction, and clustering. The task is to read the brain activity data, cluster it into the most similar cognitive state, and then to provide transcranial stimulation to change that cognitive state into one which causes the user to perceive the sensory feedback. The lower layer of the BS-SOFM represents what is called the Action Principles Layer in FIG. 5. This is a self-organized feature map of percept-action-percept triads that links action principles (stimulation parameters) to brain states for seamless activation of specific percepts in the user's brain that are robust to context (the user's initial brain state), and are sensitive to the sequential aspects of both perceptual and action representations. The method includes iteratively applying stimulus patterns so as to drive or steer the brain's cognitive state into the desired state. A pre-training phase is used to capture information to train the SOFM concerning the application control space as well as consideration of the input signal type and environmental noise that will be present during use (see FIG. 6). During pre-training, finite element models are derived from structural imaging data (FIG. 6, step 1).”)
recording the brain state data correlated with the performance of the task; (Par. 0035, lines 25 – 36: “The user will perform a series of tasks in the context of interest with varying cognitive loads. In particular, while the user explores the degrees of freedom for various tasks, multi-modal high-resolution brain activity data is acquired (FIG. 6, step 2) to learn the initial predictive relationships between the fused brain data and the control signals in the brain state decoder module (FIG. 6, step 3). Brain activity data is also acquired while the subject is perceiving or visualizing each of the categories of sensory feedback from the device sensors about the task environment, to be stored as potential goal states in the SOFM lookup table.”)
assembling a pre-training set of the brain state data correlated with the performance of the task by the subject; (Par. 0043: “Accordingly, in one or more embodiments, the brain state encoder 102 is a method of producing cognitive states in a user that cause the user to experience a certain sensory perception, without involving the 5 senses. In one or more embodiments, the method includes a task of (a) a pre-training phase trains a Brain State Self-Organizing Feature Map (SOFM) to identify the brain regions whose activity correlates with the task and context of interest, and clusters their activity.”)
pre-training a decoder module of the brain machine interface system with the pre-training set of the recorded brain state data to decode intentions of the subject correlated with brain state; (Par. 0032: “As an example, the user might be trained to visualize a movement vector as an egocentric arrow. The brain decoder can be trained to recognize such a brain state, and encode a command message for the task. Additionally, in one or more embodiments, the systems and methods of the present disclosure are configured to enable continuous, asynchronous cognitive control of the one or more tasks for a sustained duration, such as, for example, 1 minute, or 5 minutes, or 30 minutes, or 2 hours, or so on, limited only by the user's need to rest or sleep and the brain encode/decode system's ability to continue to interface with the brain. Continuous control is implemented by a stream of discrete commands to a task, and discrete feedback from the task.” Par. 0035: “A pre-training phase is used to capture information to train the SOFM concerning the application control space as well as consideration of the input signal type and environmental noise that will be present during use (see FIG. 6). During pre-training, finite element models are derived from structural imaging data (FIG. 6, step 1).” See full paragraphs 0032 – 0035.)
and conducting a current session at a second time subsequent to the first time, wherein the current session includes the pre-trained decoder module accepting a brain state data input of the brain of the subject, decoding a brain state output from the brain state data input, and generating a control signal to perform the task based on the determined brain state output. (Par. 0010 – 0012: “The task interface module may further include a command multiplexer configured to transmit the control signals to the one or more tasks. [0011] The task interface module may further include a status multiplexer configured to transmit the status information of the one of the at least one task to the brain state encoder. [0012] The one or more tasks may be performed on a same semi-autonomous device or on two or more separate semi-autonomous devices. For example, in one or more embodiments, a flying platform might have a task related to steering and navigation, and a different task related to controlling a video or audio sensor and analyzing the data in search of particular objects of interest.” Par. 0032: “The systems and methods of the present disclosure may be utilized to enable asynchronous, low-latency cognitive control of any semi-autonomous device capable of accepting discrete commands, such as, for instance, air vehicles (e.g., UAVs), ground vehicles, water vehicles, humanoid robots (e.g., a robot arm), or interfaces of computers. As used herein, the term “discrete commands” refers to a command that is individually separate and distinct (i.e., not continuous). As an example, the user might be trained to visualize a movement vector as an egocentric arrow. The brain decoder can be trained to recognize such a brain state, and encode a command message for the task. Additionally, in one or more embodiments, the systems and methods of the present disclosure are configured to enable continuous, asynchronous cognitive control of the one or more tasks for a sustained duration, such as, for example, 1 minute, or 5 minutes, or 30 minutes, or 2 hours, or so on, limited only by the user's need to rest or sleep and the brain encode/decode system's ability to continue to interface with the brain. Continuous control is implemented by a stream of discrete commands to a task, and discrete feedback from the task.” See paragraphs: 0019, 0033 – 0035; 0043 and 0044 – (once trained then output commands for the task); 0055, 0059, 0061. Examiner’s Note – Pilly implicitly and/or explicitly teaches using a brain decoder to recognize a brain state at a subsequent time to enable continuous and/or asynchronous control of a task, on point of the instant application of controlling a task at a second time. See also Contrevas-Vidal, cited in the conclusion section. Contrevas-Vidal teaches most elements of claim 1 including using the system during daily activity.)
Regarding claim 4,
The previously cited reference(s) teach the limitations of claim 1 which claim 4 depends. Pilly also teaches sensing brain state data of the brain of the subject during performance of the task during the current session; recording the brain state data correlated with the performance of the task; and adding the brain state data correlated with the performance of the task by the subject to the pre-training set of recorded brain state data. (Par. 0036: “A cap/helmet equipped for recording brain signals is fitted to the user in order to begin training the system algorithms governing the learning of neural patterns for feedback. This allows for learning a personalizable policy of neurostimulation mapped to subjective experience. Depending on the brain stimulation technology, structural models are also developed based on vascular patterns and brain topology for the purpose of generating finite-elements modeling (FEM) predictions of current spread throughout the brain and refining beam-steering properties of electrical stimulation. HD-tCS includes these structural models for the most accurate stimulation. See also Par. 0035 – pre-training and 0043 - recording.)
Regarding claim 6,
The previously cited reference(s) teach the limitations of claim 1 which claim 6 depends. Pilly also teaches that the brain state data are taken from an imaging plane of the brain, and wherein the pre-training includes aligning the brain state data of the pre-training data set to produce a pre-registration alignment image. (Par. 0035: “During pre-training, finite element models are derived from structural imaging data (FIG. 6, step 1). The user will perform a series of tasks in the context of interest with varying cognitive loads. In particular, while the user explores the degrees of freedom for various tasks, multi-modal high-resolution brain activity data is acquired (FIG. 6, step 2) to learn the initial predictive relationships between the fused brain data and the control signals in the brain state decoder module (FIG. 6, step 3). Brain activity data is also acquired while the subject is perceiving or visualizing each of the categories of sensory feedback from the device sensors about the task environment, to be stored as potential goal states in the SOFM lookup table.” Par. 0038: “FEM models are generated and potential montages and protocols are computed using structural imagery of the user's brain. A dictionary of possible stimulation combinations and beam-steering properties are encoded and stored. The dictionary of neurostimulation intervention definitions are mapped to the neurophysiological/subjective sensory information to enable conversion from sensor percept to subjective sensory experience.” Par. 0042: “the system or device includes a PhotoAcoustic Tomography (PAT) device or technique and an electroencephalogram (EEG) device or technique. In the illustrated embodiment, PAT and EEG may be combined utilizing a tensor decomposition technique to fuse the multi-dimensional data in a way that employs the advantages of both technique (e.g., the brain state encoder 102 may utilize a method for sensor data fusion employing independent component analysis of tensors). PAT is a very high resolution sensing technique that can penetrate the human skull to provide a high-resolution image with only one-way distoration of ultrasound (compared to round-trip distorations of functional ultrasound), and it is complementary to EEG because of its low speed. PAT directly detecs both oxy- and deoxy-hemodynamic changes related to neural activities, and when fused with EEG will preserve high frequency features within high spatiotemporal brain imaging at less than or equal to approximately (about) 1 mm.sup.3 spatial resolution and less than or equal to approximately (about) 10 millisecond (ms) temporal resolution.”
Regarding claims 11, 14, and 16, they are directed to a system or apparatuses to implement the method of steps set forth in claims 1, 4, and 16, respectively. Pilly teaches the claimed method of steps in claims 1, 4, and 16. Pilly also teaches a scanner (sensor and sensor signals – Par. 0034, 0038, 0042, etc.) Therefore, Pilly teaches the system or apparatuses to implement the claimed method of steps in claims 11, 14, and 16. (Examiner’s Note – See also O’Brien, cited below for claim 2, that teaches a scanner that senses blood flow of a brain.)
Regarding claim 20, they are directed to a non-transitory computer-readable medium having machine-readable instructions to implement the method of steps set forth in claim 1. Pilly teaches the claimed method of steps in claim 1. Therefore, Pilly teaches the non-transitory computer-readable medium having machine-readable instructions implement the claimed method of steps in claims 11, 14, and 16. See also Pilly Par. 0062: “The computer program instructions are stored in a memory which may be implemented in a computing device using a standard memory device, such as, for example, a random access memory (RAM). The computer program instructions may also be stored in other non-transitory computer readable media such as, for example, a CD-ROM, flash drive, or the like.”
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 2 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Pilly in view of O’Brien (PG Pub. No. 20200178925), herein “O’Brien.”
Regarding claim 2,
The previously cited reference(s) teach the limitations of claim 1 which claim 2 depends. The reference(s) do not teach a scanning device that is part or coupled to a scanner. However, O’Brien teaches that the brain state data input of the brain of the subject is obtained via a functional ultrasound transducer coupled to a scanner. (Par. 0007: “One example embodiment of the present disclosure includes a transcranial scanning system for identifying a neurologic-injury-mechanism, comprising a sensing wand comprising a transducer that produces and receives sound waves and a sound amplification component, the transducer generates a sound wave that is amplified by the sound amplification component to comprise an amplified sound wave when the sensing wand is passed over a head of a patent with cerebral malaria, the amplified sound wave reflects off of blood cells in blood vessels in the head of the patient and causes a change in pitch of the amplified sound wave creating an output sound wave responsive to a blood flow of the patient, the output sound wave is received by the transducer, a processor in communication with said sensing wand, and an output screen coupled to the sensing wand and the processor, the output screen displays in real time an output waveform corresponding to the output sound wave, wherein the processor identifies, based on characteristics of a repeating pattern displayed on the output waveform, a neurologic-injury-mechanism occurring within the patient.” See also Par. 0026, 0027 and claim 1.)
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have combined the method of training a brain interface and/or brain state encoder/decoder to conduct a task based on the brain state as in Pilly with determining a brain state of a brain using a scanner and transducer as in O’Brien in order to determine blood flow (which is indicative of a brain state) and determine the functioning or dysfunction portion of the brain using waveforms. (O’Brien Par. 0046 – 0048)
Regarding claim 12, it is directed to a system or apparatuses to implement the method of steps set forth in claim 2. Pilly and O’Brien teach the claimed method of steps in claim 2. Therefore, Pilly and O’Brien teach the system or apparatuses, to implement the claimed method of steps, in claim 12.
Claims 3 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Pilly in view of O’Brien in further view of Fainstain (PG Pub. No. 20200356172), herein “Fainstain.”
Regarding claim 3,
The previously cited reference(s) teach the limitations of claim 2 which claim 3 depends. The reference(s) do not teach a scanner or transducer that scans PPC of the brain. However, Fainstain teaches that the functional ultrasound transducer is positioned for the posterior parietal cortex (PPC) of the brain. (Par. 0081: “FIG. 12 is a method diagram showing an exemplary process for enhanced neural rehabilitation. Initially, the full-head embodiment of the device is placed on a patient's head 1201. The patient is then presented with a rehabilitative task, usually a physical task such as moving a part of the body (e.g., asking the patient to touch an object with his or her right hand) 1202. While the patient is performing the task, simultaneously stimulate the head using electrical transducers at a location above the area of the brain responsible for handling that task (e.g. for right hand movement, the posterior parietal cortex region) 1203.” Par. 0078: “This full-head embodiment may be particularly useful in neural rehabilitation by stimulating particular regions of the brain. For individuals with brain impairments (e.g., stroke patients suffering from varying degrees of brain damage), the conventional treatment approach consists of mainly “isolated” neural rehabilitation routines, such as specific bodily movements, speech therapy, and stationary video gameplays. This embodiment of the device improves on existing neural rehabilitation routines by providing synchronized haptic and/or electrical simulation to specific regions of the brain for the targeted user movement or cognitive function. Using sensors and transducers 1030 that convert electrical signals to a tactile sensation such as pressure, vibration, electrical stimulation (including all types of waveform signal), temperature, or airflow, such synchronized haptic and/or electrical simulations for the targeted rehabilitation routines (such as bodily movement or cognitive functions) will improve the overall effectiveness of such rehabilitation routines.”)
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have combined the method of training a brain interface and/or brain state encoder/decoder to conduct a task based on the brain state as in Pilly with determining a brain state of a brain using a scanner and transducer as in O’Brien with using a transducer to scan a the posterior parietal cortex region of the brain as in Fainstain in order to analyze the part of the brain that is involved in transforming visual information into motor commands. (Fainstain - Par. 0040, last sentence)
Regarding claim 13, it is directed to a system or apparatuses to implement the method of steps set forth in claim 3. Pilly and Fainstain teach the claimed method of steps in claim 3. Therefore, Pilly and Fainstain teach the system or apparatuses, to implement the claimed method of steps, in claim 13.
Claims 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Pilly in view of Esmaeili (US PG Pub No. 20230293116), herein “Esmaeili,” with a provisional filing date of March 18, 2022.
Regarding claim 5,
The previously cited reference(s) teach the limitations of claim 1 which claim 5 depends. The reference(s) do not teach a time period of use such as days. However, Esmaeili teaches that the first time is between 1 and 900 days from the second time. (Par. 0056: “In some embodiments, the virtual assist device may include a set of discrete wearable EEG sensors (e.g., capacitive sensors) embedded within a communication unit (e.g. Bluetooth® headset, earbuds, etc.) that may be configured to: (i) detect electrical activity of the brain (e.g., the .Math.voltage generated by neurons firing) through the skull, (ii) digitally filter these EEG signals to remove noise, and (iii) pass the filtered EEG signals to the device (e.g., UE), which may (iv) use a machine learning model (pre-trained e.g., hundreds of thousands or millions of other data points) to determine the command (e.g., “yes,” “no,” “left,” “right,” “up,” “down,” “option 1”, “option 2”, or the like) facilitating control of the UE and a quick and discrete way of parsing through incoming notifications. In some examples, the EEG sensors may comprise one or more of dry, semi-dry, or wet sensors.” Par. 0032: “In some embodiments, the agent may be configured to accept one or more inputs via a device (e.g., microphone, haptic input receiver, or a UE (e.g., touch screen, smartphone, cell phone, tablet, laptop, computer, or other computing device)). The input may be received by the agent in the form of clicking buttons or touching the touchscreen in order to perform tasks that may make the day-to-day life of a user easier.” See also Par. 0008, 0032, 0049, 0057, 0067, and 0070.)
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have combined the method of training a brain interface and/or brain state encoder/decoder to conduct a task based on the brain state as in Pilly with sensing brain activity, training a model using the signals, and to use as commands for day to day use as in Esmaeili in order to respond to a phone or other user device and use EEG signals to respond to the user device without touching the device.
Regarding claim 15, it is directed to a system or apparatuses to implement the method of steps set forth in claim 5. Pilly and Esmaeili teach the claimed method of steps in claim 5. Therefore, Pilly and Esmaeili teach the system or apparatuses, to implement the claimed method of steps, in claim 15.
Claims 7 and 17 rejected under 35 U.S.C. 103 as being unpatentable over Pilly in view of Provenza et al. (US PG Pub No. 20210106830), herein “Provenza.”
Regarding claim 7,
The previously cited reference(s) teach the limitations of claim 1 which claim 7 depends. The reference(s) do not teach magnetic resonance imaging. However, Provenza teaches that wherein the pre-training brain state data are images produced by functional magnetic resonance imaging of the brain of the subject. (Par. 0047: “FIG. 11 shows an example of a functional Magnetic Resonance Imaging (fMRI) response of a subject while performing the MSIT task.” Par. 0050: “FIG. 14 shows an example of electrode positions within particular brain regions located using an Electrode Labeling Algorithm (ELA) in conjunction with a pre-operative Magnetic Resonance Imaging (MRI) scan and a post-operative Computed Tomography (CT) scan.” Par. 0135: “FIG. 11 shows an example of a functional Magnetic Resonance Imaging (fMRI) response of a subject while performing the MSIT task…” )
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have combined the method of training a brain interface and/or brain state encoder/decoder to conduct a task based on the brain state as in Pilly with using an magnetic resonance imaging to determine a task as in Provenza in order to determine particular brain regions that are associated with a particular task. (Par. 0050, Abstract, and Par. 0012)
Regarding claim 17, it is directed to a system or apparatuses to implement the method of steps set forth in claim 7. Pilly and Provenza teach the claimed method of steps in claim 7. Therefore, Pilly and Provenza teach the system or apparatuses, to implement the claimed method of steps, in claim 17.
Claims 8, 9, 18, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Pilly in view of Yao (US PG Pub. No. 20250164387), herein “Yao,” with a provisional filing date of 01/06/2022.
Regarding claim 8,
The previously cited reference(s) teach the limitations of claim 1 which claim 8 depends. The reference(s) do not teach scanning a brain and producing a 2D or 3D image. However, Yao teaches that the brain state data input is one of a 2D image or a 3D image. (Par. 0096: “By using Raman-based dual-wavelength exaction and water-immersible polygon-scanner (or other scanners provided for herein), UFF-PAM can capture the hemodynamic changes in the brain or other tissue types.” Par. 0073: “3D volumetric PA imaging can be achieved by the fast polygon scanning operating at up to approximately 16 kHz, and slow scanning with a motorized stage operating at up to approximately 10 Hz (e.g., V-528, PI; maximum speed, about 250 mm/s). For each facet image provided by the polygon scanner 2446 along the horizontal axis with a step size of approximately 10 μm, the motorized stage provides one step along the orthogonal axis with a step size of approximately 10 μm.” See also Par. 0081.)
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have combined the method of training a brain interface and/or brain state encoder/decoder to conduct a task based on the brain state as in Pilly with using a scanner that images the brain in two or three dimensions as in Yao in order to provide repeated cross-sectional scans (B-scans) wherein individual facet images can be stitched together into a final composite image so the spatial resolution can be improved (Par. 0073 and 0064)
Regarding claim 9,
The previously cited reference(s) teach the limitations of claim 1 which claim 9 depends. The reference(s) do not teach more than one image. However, Yao teaches that the brain state data input is one of a sequence of images used to decode the brain state. (Par. 0064: “According to at least some embodiments, each facet of a polygon scanner provides an independent image of the same target with relatively low spatial resolution, by confocally scanning an excitation laser light and the resultant ultrasound waves. In the example case of a 12-facet polygon scanner, a total of 12 images are acquired per revolution. The image acquired by the second facet is slightly shifted compared with the image acquired by the first facet, and so on. By stitching all the individual facet images together into a final composite image, the spatial resolution can be improved.”)
Regarding claims 18 and 19, they are directed to a system or apparatuses to implement the method of steps set forth in claims 8 and 9, respectively. Pilly and Yao teach the claimed method of steps in claims 8 and 9. Therefore, Pilly and Yao teach the system or apparatuses, to implement the claimed method of steps, in claims 18 and 19.
Claims 10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Pilly in view of Butte et al. (US PG Pub No. 20170290515), herein “Butte.”
Regarding claim 10,
The previously cited reference(s) teach the limitations of claim 1 which claim 10 depends. The reference(s) do not teach performing principal component (PCA) and linear discriminant analysis (LDA). However, Butte teaches that wherein the decoder module performs principal component (PCA) and linear discriminant analysis (LDA) to predict movement direction from the brain state data. (Par. 0161: “The classifier 1310 may search the SLMs for two or more data groups in order to identify whether there are specific matrix elements with statistically significant difference. A non-limiting example of this test can be performed by a t-test of the null hypothesis (that data in the vectors x and y are independent random samples from normal distributions with equal means and equal but unknown variances). This test may confirm that data with no statistical significance difference between the two groups is not input into the machine learning algorithm. This leaves the SLM elements with maximum discriminating power. Non-limiting examples of classifiers 1310 which may be used to classify an unknown biomolecule based on the confirmed training sets include Principal Component Analysis and/or Linear discriminant Analysis.” Examiner’s Note – See also Norman cited in the conclusion section that was published on November 18, 2021.)
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have combined the method of training a brain interface and/or brain state encoder/decoder to conduct a task based on the brain state as in Pilly with using training sets include Principal Component Analysis and Linear discriminant Analysis as in Butte in order to classify and provide mapping of the brain for the motor and speech functions and enhance diagnostically relevant information. (Par. 0178)
Regarding claim 20, it is directed to a system or apparatuses to implement the method of steps set forth in claim 10. Pilly and Butte teach the claimed method of steps in claim 10. Therefore, Pilly and Butte teach the system or apparatuses, to implement the claimed method of steps, in claim 20.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Yao (US PG Pub. No. 20250164387), cited for claim 8 and with a provisional filing date of 01/06/2022 may also teach the elements of claim 2 in paragraph 0012: “The scanner assembly can include an ultrasound transducer. In at least some such embodiments, the scanner assembly can also include a multimode optical fiber.”
Provenza et al. (US PG Pub No. 20210106830), cited for claim 7 and is on point with the instant application and may teach the elements of claim 1 where training a module using tasks and then controlling a effector such as a prosthetic limb using motor machine interface(s). (Par. 0182)
Bhugra et al. (US Patent No. 11,534,358) may also teach the elements in claim 5 in Col. 2, lines 29 – 44; Col. 20, lines 5 – 28; Col. 24, lines 10 – 21; Col. 25, lines 62 – 9; Col. 27, line 50 – 12 – used in daily life.)
Norman et al. (US PG Pub No. 20210353439), published on November 18, 2021, also teaches the elements of claim 10: (Par. 0216: “Embodiment 15. The system of claim 12, wherein process the plurality of ultrasound images, in real-time, to determine a task phase of a cognitive state of the subject comprises process the plurality of ultrasound images according to a trained machine learning algorithm, the trained machine learning algorithm based on class-wise principal component analysis (CPCA) and linear discriminant analysis (LDA).” Par. 0124, 0136, 0158, 0193, and Embodiment 19.)
Contreras-Vidal et al. (US PG Pub No. 20210353439) teaches “a noninvasive brain computer interface (BCI) system includes an electroencephalography (EEG) electrode array configured to acquire EEG signals generated by a subject. The subject observes movement of a stimulus. A computer is coupled to the EEG electrode array and configured to collected and process the acquired EEG signals. A decoding algorithm is used that analyzes low-frequency (delta band) brain waves in the time domain to continuously decode neural activity associated with the observed movement.” (Abstract) The BCI is trained using EEG signals with a reduced training time; see Par. 0035: “A noninvasive BCI system according to another aspect of the present invention continuously decodes imagined or actual movements from EEG signals with substantially reduced training time by a subject. In one implementation, the system decodes neural activity of movements in at least two dimensions.”
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHAD G ERDMAN whose telephone number is (571)270-0177. The examiner can normally be reached Mon - Fri 7am - 3pm or 4pm EST..
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kenneth Lo can be reached at (571) 272-9774. 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.
/CHAD G ERDMAN/Primary Examiner, Art Unit 2116
Prosecution Insights