Disclosed herein is a multi-supervised deep framework that can automatically detect, segment, and classify abnormal cervical cells. The multi-supervised framework has semi-supervised, weakly-supervised and unsupervised modes which are effective in detecting cervical cells and classifying the cells as being normal or abnormal. The various modes address the situation in which labelled training data is sparse compared to unlabeled training data.
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersectionsConnectivity analysis, e.g. of connected components
Disclosed herein are devices comprising stretchable interdigitated electrode arrays and methods for fabricating the devices. The devices are capable of acting as elongation sensors by sensing a change in the capacitance of the device as the distance between the interdigitated fingers changes when the device is elongated or compressed. The device may be coupled to other devices such as to be able to sense elongation or compression of the coupled device. The interdigitated fingers of the device are supported by a substrate and may be fabricated using traditional microfabrication techniques.
B81B 3/00 - Devices comprising flexible or deformable elements, e.g. comprising elastic tongues or membranes
B81C 1/00 - Manufacture or treatment of devices or systems in or on a substrate
G01B 7/16 - Measuring arrangements characterised by the use of electric or magnetic techniques for measuring the deformation in a solid, e.g. by resistance strain gauge
3.
MONOTONIC AMPLITUDE PULSE TRAINS FOR NON-INVASIVE NEUROSTIMULATION
A method of delivering a non-invasive neurostimulation using a Monotonic Amplitude Pulse Train is more charge-efficient than using conventional, uniform waveforms. Monotonic Amplitude Pulse Trains optimize the amplitudes of individual pulses in a train to reduce the total energy required to provide neural stimulation by as much as 50%.
Disclosed herein is a multi-supervised deep framework that can automatically detect, segment, and classify abnormal cervical cells. The multi-supervised framework has semi-supervised, weakly-supervised and unsupervised modes which are effective in detecting cervical cells and classifying the cells as being normal or abnormal. The various modes address the situation in which labelled training data is sparse compared to unlabeled training data.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/766 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Disclosed herein is a framework for modeling the global floorplanning problem as a semi-definite programming (SDP) problem with an inner product between the target matrix and a direction matrix replacing the rank constraint. The framework is global optimal if an appropriate direction matrix is chosen, which is calculated using a convex iteration algorithm that decomposes the problem into two SDP sub-problems.
A low-cost and highly controllable roll-to-roll templated deposition method for fabricating a nanostructured film comprising: creating a stacked structure comprising a conductive substrate, a porous template disposed on the substrate, an ion-conductive layer formed of a porous scaffold or a polymer gel containing electrolytes disposed on the template, and an anode disposed on the ion-conductive layer; providing rollers on the anode; applying pressure to the stacked structure via the rollers so that the first porous template conforms and stays attached to the substrate; applying galvanic potential between the metal anode and the conductive substrate to grow a nanostructure from the substrate into the porous template by electrochemical deposition; and removing the porous template by chemical dissolution or chemical etching to obtain the nanostructured film. Tube rollers comprising, radially, tubes, electrolytes, and anodes may replace the rollers, electrolytes, and anodes. The nanostructured film may also grow on both sides of the substrate.
B29C 59/04 - Surface shaping, e.g. embossingApparatus therefor by mechanical means, e.g. pressing using rollers or endless belts
B05D 1/28 - Processes for applying liquids or other fluent materials performed by transfer from the surfaces of elements carrying the liquid or other fluent material, e.g. brushes, pads, rollers
B05B 13/04 - Means for supporting workArrangement or mounting of spray headsAdaptation or arrangement of means for feeding work the spray heads being moved during operation
7.
SYSTEMS AND METHODS FOR GENERATING DESIGNS USING ANALOGICS WITH LEARNING MODELS
Systems, methods, and other embodiments described herein relate to generating designs using learning models for analogics that process text and sketch-based inputs. In one embodiment, a method includes estimating analogical suggestions using a transformer model for a text prompt having design parameters. The method also includes generating an image using a learning model for an expression selected from the analogical suggestions and a sketched stroke inputted. The method also includes manipulating a modified sketch by the learning model and the modified sketch is derived from a sketched conversion of the image by an edge model.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
8.
ENHANCED INTERACTIVE WRITING TOOL THAT ALLOWS WRITERS TO DRAFT AND REVISE A TEXT AUTHENTICALLY AND EFFICIENTLY USING A LARGE LANGUAGE MODEL WHILE REDUCING ACADEMIC MISCONDUCT
The present invention relates to a method and system for generating coherent Al generated text from text segments using an interactive generative artificial intelligence software whereby text segments are concatenated to predefined natural language sentences to generate coherent Al generated text from the selected text without adding new ideas. The Al generated text can be traced back to the original text segment and the quality of the Al generated text can be rated.
Provided is a system, method, and device for manufacturing. A manufacturing device includes at least one sensor, at least one end-effector member configured to add and/or subtract material to manufacture an object, and at least one computing device in communication with the at least one sensor, and a control system for the at least one end-effector member, the at least one computing device configured to scan each layer of a plurality of layers of an object manufactured by the end-effector member and modify at least one layer of the plurality of layers based on comparing at least one scan of the at least one layer or at least one previous layer to a 3D representation of the at least one layer or the at least one previous layer.
Various implementations disclosed herein include devices, systems, and methods that predict a face configuration or hand pose of a user. For example, a device may include a structure and one or more antennas positioned on a portion of the structure. The device is worn on a head of a user. An associated process may be enabled to interpret data from the one or more antennas to discriminate deformation of a tissue geometry of at least one body portion of a user when the device is worn on the head of the user. The data from the one or more antennas may be associated with one or more impedance characteristics.
Provided is a system and method for pipe monitoring. The system includes a sensor arrangement comprising a visual sensor, an inertial sensor, and a laser projector, and at least one processor configured to: project a laser on an inner surface of a pipe with the laser projector; emit light with a light-emitting device on the inner surface of the pipe; capture a plurality of frames of the inner surface of the pipe with the visual sensor, wherein at least a subset of frames of the plurality of frames is captured while the laser is projected on the inner surface, and wherein the at least a subset of frames or a different subset of frames is captured while the light illuminates the inner surface; and generate a 3D reconstruction of the inner surface of the pipe based on the plurality of frames.
Various implementations disclosed herein include devices, systems, and methods that predict a face configuration or hand pose of a user. For example, a device may include a structure and one or more antennas positioned on a portion of the structure. The device is worn on a head of a user. An associated process may be enabled to interpret data from the one or more antennas to discriminate deformation of a tissue geometry of at least one body portion of a user when the device is worn on the head of the user. The data from the one or more antennas may be associated with one or more impedance characteristics.
G06F 3/01 - Input arrangements or combined input and output arrangements for interaction between user and computer
A61B 5/0507 - Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fieldsMeasuring using microwaves or radio waves using microwaves or terahertz waves
A61B 5/00 - Measuring for diagnostic purposes Identification of persons
G06V 40/16 - Human faces, e.g. facial parts, sketches or expressions
H01Q 1/27 - Adaptation for use in or on movable bodies
G06V 40/20 - Movements or behaviour, e.g. gesture recognition
Provided are extension devices and systems, including an extending truss including a plurality of cells, each cell including a first scissor extender including a first member and a second member rotationally connected to the first member at an off-center point along a longitudinal axis of the first member, a second scissor extender connected to the first scissor extender, the second scissor extender including a first member and a second member rotationally connected to the first member, and a third scissor extender connected to the first scissor extender, the third scissor extender including a first member and a second member rotationally connected to the first member.
A method of training a deep neural network, such as would be used in facial recognition, includes training the deep neural network to normalize feature vectors to a learned value representing a radius of a multi-dimensional hypersphere using a convex augmentation of the primary loss function.
Systems, methods, and other embodiments described herein relate to identifying and generating mechanisms from natural processes by a learning model for accelerating design development. In one embodiment, a method includes identifying mechanisms for a design task using a prompt transformer with seeds from biological processes, and the prompt transformer forms a taxonomy tree using the mechanisms. The method also includes generating functional solutions that expand sparse branches of the taxonomy tree for the mechanisms using the prompt transformer. The method also includes clustering the mechanisms using text embedding for the design task. The method also includes inspecting the mechanisms with the prompt transformer to select a solution associated with the design task.
An implantable hybrid advanced molecular manufacturing regulator device containing engineered cells delivering cancer therapeutics to a subject. The device comprises a conductive scaffold in communication with a control module; a biochemical sensor module in communication with the control module; an oxygenator configured to produce oxygen and disposed inside the conductive scaffold; and at least one engineered cells encapsulation disposed in association with the conductive scaffold; wherein the at least one engineered cells encapsulation encapsulates engineered cells; wherein the engineered cells are configured to produce at least one cancer therapeutic agent; wherein the device is implantable.
In some aspects, the present disclosure pertains to methods for the electrochemical production of NH3 from nitrogen gas and a hydrogen-containing molecule in an electrochemical cell that comprises a cathode, an anode and a lithium-ion-containing electrolyte disposed between the cathode and the anode. The electrochemical cell is operated under conditions such that lithium ions in the electrolyte are converted to lithium metal at the cathode, the lithium metal reacting with nitrogen gas to form Li3N, and the Li3N reacting with protons in a proton donor to form NH3, lithium ions and a deprotonated proton donor. Moreover, the proton donor has a Kamlet-Taft alpha parameter (α) greater than 0.7 and a Kamlet-Taft beta parameter (β) greater than 0.5. Other aspects of the present disclosure pertain to systems for electrochemical production of NH3.
A computing a measure quantifying the influence of a concept defined by a concept model on classifications of a target model. This may include computing for sensor data in an evaluation set the output of a similarity function applied to the output of a target model and the output of a concept model.
A manufacturing method for making a plurality of microneedle arrays (MNAs) includes: dispensing a polymer resin into a plurality of wells of at least one mold by an automated dispenser comprising at least one dispensing nozzle; centrifuging the at least one mold to distribute the dispensed polymer resin within the plurality of wells of the at least one mold; curing, solidifying, and/or drying the polymer resin within the plurality of wells of the at least one mold; and removing individual molded MNA parts from the at least one mold with at least one electromechanical mover controlled by at least one computer processor. A mold for making a plurality of the MNAs and a high-throughput manufacturing system for making the MNAs using the mold are also provided.
A system and method allow interaction with a mobile device using finger pointing gestures. The mobile device includes an imaging device having a field of view that contains an object of interest. The system and method are capable of identifying the object of interest in image data captured by the imaging device by casting a ray from a finger of user, who is pointing to the object using traditional pointing gestures. Verbal utterances spoken by the user can be captured and used to provide context about the object of interest.
Disclosed herein is a system and method for implementing a personalized ultrasound neuromodulation system and methods with neural sensing of personalized electrophysiological data, guiding ultrasound targeting and dosage using such personalized data. Specific ultrasound transducer solutions are provided for various neural targets that enable the low-intensity focused ultrasound to modulate the central nervous system and peripheral nervous systems to treat a variety of neurological and mental disorders. A portable ultrasound console device, a wearable guiding apparatus and a compact solution for effectively and safely enabling point-of-care neuromodulation, e.g., home healthcare, are provided. Further methods for ultrasound waveform customization are also described to improve effectiveness of ultrasound neuromodulation.
G16H 20/40 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
Disclosed herein is a novel system and method for detecting, localizing, and correcting configuration upsets of an SRAM-based FPGA design caused by radiation exposure. The radiation-hardened FPGA uses embedded strike sensors distributed throughout the FPGA fabric, coupled with an error handler to correct the upsets using a redundant on-chip copy of the configuration.
Systems, methods, and other embodiments described herein relate improve the estimation of poses within an environment including multiple people and uncalibrated cameras. In one embodiment, a method includes acquiring sensor data including images with depth information of a surrounding environment that includes multiple people. The method includes determining 2D poses and 3D features for the people according to the sensor data. The method includes generating camera poses using at least the depth information and the features for cameras that generated the images. The method includes generating 3D poses for the people according to the camera poses and the 3D features. The method includes providing the 3D poses of the people.
Disclosed herein is a posture-invariant brain-computer interface (BCI), including a neural decoder that effectively provides correct motion intent signals even as the user changes posture, a method of training the neural decoder using a supervised learning method to predict intended effector motion from training data collected in multiple postures, and a system using the trained neural decoder to effect intended motions on an effector.
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
G16H 20/70 - ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
25.
System, Method, and Computer Program Product for Optical Vibration Sensing
Provided are systems, methods, and computer program products for optical vibration sensing. The system includes a first visual sensor, a second visual sensor, and at least one processor in communication with the first visual sensor and the second visual sensor, the at least one processor configured to: capture at least one first image comprising at least one light on at least one object with the first visual sensor, capture at least one second image comprising the at least one light on the at least one object with the second visual sensor, and determine a vibration of the at least one object based on the at least one light captured in the at least one first image and the at least one second image.
H04N 23/45 - Cameras or camera modules comprising electronic image sensorsControl thereof for generating image signals from two or more image sensors being of different type or operating in different modes, e.g. with a CMOS sensor for moving images in combination with a charge-coupled device [CCD] for still images
H04N 23/55 - Optical parts specially adapted for electronic image sensorsMounting thereof
H04N 23/56 - Cameras or camera modules comprising electronic image sensorsControl thereof provided with illuminating means
A high-density bioprobe array is provided comprising conductive or optical shanks. A method of making high-density bioprobe arrays also is provided. A bioprobe system using the array also is provided.
G01N 27/30 - Electrodes, e.g. test electrodesHalf-cells
H05K 3/00 - Apparatus or processes for manufacturing printed circuits
H05K 3/12 - Apparatus or processes for manufacturing printed circuits in which conductive material is applied to the insulating support in such a manner as to form the desired conductive pattern using printing techniques to apply the conductive material
Disclosed herein are various embodiments of electrodes using nanowire structures to increase the columbic efficiency and voltage output of a battery. The electrodes may include, for example, a copper foil layer and copper nanowires protruding from a surface of the copper foil layer or from both surfaces of the copper foil layer.
Additive manufacturing methods, additive manufacturing systems (100), support material for additive manufacturing, and products thereof are provided. For example, the additive manufacturing methods includes depositing a structure material into a support material (108) based on a first computer model of an object, thereby forming a first portion of the object in the support material. The structure material exhibits a viscosity in a range of 1 mPa*s to 5000 mPa*s (1 cP to 5,000 cP) at 25 degrees Celsius. The support material exhibits a density in a range of 1.05 g/mL to 3 g/mL. The method includes repeating the depositing of the structure material as necessary to additively form the object.
Additive manufacturing methods, additive manufacturing systems, structure materials for additive manufacturing, and products thereof are provided. The structure material includes at least 1 mg/mL of a bio-compatible polymer, a solvent, at least 10 million cells/mL, and a polymerization inhibitor.
Aspects of the invention are drawn towards a wound healing device, such as a single or multi-component patch, comprising a first component and a second component, as well as cells capable of producing a plurality of therapeutic agents (e.g., cytokines). The wound healing device may be used in a manner to coordinate the release of the therapeutic agents, either temporally or geographically, to provide customized support of the wound healing process.
Provided are systems, methods, and devices for imaging using wireless network signals. The system includes a first set of wireless network antennas, a second set of wireless network antennas, and at least one computing device, the at least one computing device configured to initiate, with a first wireless network adapter, bidirectional communication of network packets between the first set of wireless network antennas and the second set of wireless network antennas, extract channel state information from the network packets after they are received by the first set of wireless network antennas and the second set of wireless network antennas, and generate an image of at least one entity in the space defined between the first set of wireless network antennas and the second set of wireless network antennas based on inputting the channel state information into a machine-learning model.
Provided herein is a computer-implemented method of determining blood pressure in a patient, including steps of transmitting light into a patient's limb distal to an occlusion point, receiving, first data relating to a pressure applied to occlude a patient's limb, receiving second data relating to a parameter of the transmitted light at a first time point during occlusion of the patient's limb, receiving third data relating to the parameter of the transmitted light at a second time point after perfusion of the patient's limb has resumed, comparing the second data to the third data determine a characteristic of the transmitted light, and determining the patient's systolic blood pressure based at least on the first data and the characteristic of the transmitted light.
A61B 5/021 - Measuring pressure in heart or blood vessels
A61B 5/1455 - Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value using optical sensors, e.g. spectral photometrical oximeters
Provided are systems, methods, and devices for scratch tracking. The system includes a wearable device configured to be worn on an appendage of an entity, the wearable device comprising at least one accelerometer and at least one motion sensor, and a computing device in communication with the at least one accelerometer and the at least one motion sensor, the computing device configured to receive first sensor data from the at least one accelerometer and second sensor data from the at least one motion sensor, wherein the first sensor data and the second sensor data are different, and determine at least one scratch metric based on inputting the first sensor data and the second sensor data into at least one machine-learning model.
G16H 50/20 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
34.
CHOLESTEROL-OLIGONUCLEOTIDE TETHERS WITH APTAMERS FOR LIGAND DISPLAY AND EXTRACELLULAR VESICLE FUNCTIONALIZATION
Provided herein are Treg-derived extracellular vesicles (EVs) modified with an aptamer that binds an affinity-tagged protein. The affinity-tagged protein may be CTLA4, such that the Treg EVs target B7-dislaying cells, such as T-cells, B-cells, APCs, dendritic cells, or macrophage. The CTLA4-modified Treg EVs are useful in reducing an immune response, such as in transplantation patients, cancer patients, autoimmune disease patients, or inflammatory disease patients.
C12N 15/115 - Aptamers, i.e. nucleic acids binding a target molecule specifically and with high affinity without hybridising therewith
A61K 47/69 - Medicinal preparations characterised by the non-active ingredients used, e.g. carriers or inert additivesTargeting or modifying agents chemically bound to the active ingredient the non-active ingredient being chemically bound to the active ingredient, e.g. polymer-drug conjugates the conjugate being characterised by physical or galenical forms, e.g. emulsion, particle, inclusion complex, stent or kit
C12N 15/11 - DNA or RNA fragmentsModified forms thereof
Provided herein are methods, nucleic acids, transformed yeast cells, and kits useful for rapid and effective multiplexed identification of nanobody binding to a target protein domain.
A multiplexing electrochemical point-of-care biosensing device that provides picomolar level accuracy and high selectivity and which requires only seconds to provide the response. The biosensing device is capable of being mass manufactured due to a molding process used to fabricate the working electrode of the device, which consists of an array of micropillars coated with a biosensitive material.
A61B 5/1468 - Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value using chemical or electrochemical methods, e.g. by polarographic means
A61B 5/1486 - Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value using chemical or electrochemical methods, e.g. by polarographic means using enzyme electrodes, e.g. with immobilised oxidase
37.
SYSTEM, METHOD, AND DEVICE FOR ENTITY DETECTION AND IMAGING USING WIRELESS NETWORK SIGNALS
Provided are systems, methods, and devices for imaging using wireless network signals. The system includes a first set of wireless network antennas, a second set of wireless network antennas, and at least one computing device configured to broadcast, with the first wireless network adapter from the first plurality of wireless network antennas, first network packets in an environment, broadcast, with the second wireless network adapter from the second plurality of wireless network antennas while the first wireless network adapter broadcasts the first network packets, second network packets in the environment, extract channel state information for the first network packets and second network packets after they are received, and detect at least one entity in the environment based on inputting the channel state information into at least one machine-learning model.
Provided are systems, methods, and computer program products for generating modified light emissions. The system includes at least one signal receiver arranged on a vehicle, at least one sensor arranged on the vehicle, at least one lighting system arranged on the vehicle, and at least one processor in communication with the at least one signal receiver, the at least one sensor, and the at least one lighting system, the at least one processor configured to: receive a first signal with the at least one signal receiver; receive sensor data from the at least one sensor; determine lighting data based on the first signal; generate a modified light emission by geometrically transforming the lighting pattern based on the sensor data; and control the at least one lighting system to output the modified light emission.
B60Q 1/08 - Arrangement of optical signalling or lighting devices, the mounting or supporting thereof or circuits therefor the devices being primarily intended to illuminate the way ahead or to illuminate other areas of way or environments the devices being headlights adjustable, e.g. remotely-controlled from inside vehicle automatically
B60Q 1/14 - Arrangement of optical signalling or lighting devices, the mounting or supporting thereof or circuits therefor the devices being primarily intended to illuminate the way ahead or to illuminate other areas of way or environments the devices being headlights having dimming means
39.
SYSTEM AND METHOD FOR IDENTIFYING MISPLACED PRODUCTS IN A SHELF MANAGEMENT SYSTEM
Disclosed herein is a system and method of identifying misplaced products on a retail shelf using a feature extractor trained to extract features from images of products on the shelf and output identifying information regarding the product in the product image. The extracted features are compared to extracted features in a product library and a best fit is obtained. A misplaced product is identified if the identifying information produced by the feature extractor fails to match the identifying information associated with the best fit features from the product library.
G06Q 10/087 - Inventory or stock management, e.g. order filling, procurement or balancing against orders
G06F 16/583 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
G06F 18/2113 - Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
G06F 18/214 - Generating training patternsBootstrap methods, e.g. bagging or boosting
G06F 18/28 - Determining representative reference patterns, e.g. by averaging or distortingGenerating dictionaries
G06V 10/40 - Extraction of image or video features
G06V 10/75 - Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video featuresCoarse-fine approaches, e.g. multi-scale approachesImage or video pattern matchingProximity measures in feature spaces using context analysisSelection of dictionaries
G06V 20/52 - Surveillance or monitoring of activities, e.g. for recognising suspicious objects
H04N 7/18 - Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
40.
Error Evaluation Platform using Field Programmable Gate Array Based Emulation
Disclosed herein is a platform comprising a hardware compiler framework to directly instrument an RTL representation of an input design with a fault injection processor enabling the execution of arbitrary error injection requests from the user and communication with the design under test to target specific design sections for fault injection.
A tactile interaction device uses a plurality of shape-changing tactile elements that are driven by electro-osmotic flow of a fluid. An electric filed applied to a pumping membrane by two electrodes is responsible for inducing a flow of the liquid. Multiple tactile elements can be used on the device to permit localized tactile feedback to a user. The device is adapted to be in contact with the user's skin, such as a finger or hand.
Methods providing reliable and non-invasive ways to suppress spreading depolarization waves leading to cortical spreading depression are disclosed. A stimulation signal is applied at the location of and surrounding the location of the spreading depolarization and the amplitude and focal point of the stimulation signal are randomly varied, causing suppression of the spreading depolarization wave.
Disclosed herein is a highly energy-efficient architecture targeting the ultra-low-power sensor domain. The architecture achieves high energy-efficiency while maintaining programmability and generality. The invention introduces vector-dataflow execution, allowing the exploitation of the dataflows in a sequence of vector instructions and to amortize instruction fetch and decode over a whole vector of operations. The vector-dataflow architecture allows the invention to avoid costly vector register file accesses, thereby saving energy.
A method of controlling navigation of a device in an environment using machine learning (ML) models includes receiving visual and audio observation data of the environment as sensed by the device, determining classification scores for objects and regions in the environment based on the visual and audio observation data, encoding visual information based on the classification scores, determining audio-semantic feature embeddings based at least in part on the classification scores, the audio-semantic feature embeddings indicating spatial relationships between objects in the environment, between regions in the environment, and between objects and regions in the environment, and determining and outputting, based on the encoded visual information and the audio-semantic feature embeddings, a state representation corresponding to a state of the device within the environment.
A system includes a machine-learning network. The network includes an input interface configured to receive input data from a sensor. The processor is programmed to receive the input data, generate a perturbed input data set utilize the input data, wherein the perturbed input data set includes perturbations of the input data, denoise the perturbed input data set utilizing a denoiser, wherein the denoiser is configured to generate a denoised data set, send the denoised data set to both a pre-trained classifier and a rejector, wherein the pre-trained classifier is configured to classify the denoised data set and the rejector is configured to reject a classification of the denoised data set, train, utilizing the denoised input data set, the a rejector to achieve a trained rejector, and in response to obtaining the trained rejector, output an abstain classification associated with the input data, wherein the abstain classification is ignored for classification.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/84 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using probabilistic graphical models from image or video features, e.g. Markov models or Bayesian networks
46.
KNOWLEDGE-DRIVEN SCENE PRIORS FOR SEMANTIC AUDIO-VISUAL EMBODIED NAVIGATION
A method of controlling navigation of a device in an environment using machine learning (ML) models includes receiving visual and audio observation data of the environment as sensed by the device, determining classification scores for objects and regions in the environment based on the visual and audio observation data, encoding visual information based on the classification scores, determining audio-semantic feature embeddings based at least in part on the classification scores, the audio-semantic feature embeddings indicating spatial relationships between objects in the environment, between regions in the environment, and between objects and regions in the environment, and determining and outputting, based on the encoded visual information and the audio-semantic feature embeddings, a state representation corresponding to a state of the device within the environment.
G06V 10/77 - Processing image or video features in feature spacesArrangements for image or video recognition or understanding using pattern recognition or machine learning using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]Blind source separation
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
47.
SYSTEM AND METHOD FOR PREDICTING AND OPTIMIZING CHEMICAL MIXTURES
The disclosed invention is an end-to-end differentiable mixture physics model that combines physics-based models and GDL models, where the GDL models are designed to transform the molecular species, compositions and environment conditions to physical coefficients for use in the physics-based models.
G16C 20/30 - Prediction of properties of chemical compounds, compositions or mixtures
G16C 20/70 - Machine learning, data mining or chemometrics
H01M 10/0564 - Accumulators with non-aqueous electrolyte characterised by the materials used as electrolytes, e.g. mixed inorganic/organic electrolytes the electrolyte being constituted of organic materials only
H01M 4/38 - Selection of substances as active materials, active masses, active liquids of elements or alloys
G16B 40/00 - ICT specially adapted for biostatisticsICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
Provided herein are systems, methods, and computer program products using tumor phylogeny, mutation rates, and machine learning to produce a clinical projection, such as patient survival, risk of malignancy, and therapeutic options. The method includes generating sequence variation data that identifies, characterizes, or quantifies at least one mutation in tumor sequence data of a tumor of a patient. The method also includes generating a phylogenic tree depicting clonal evolution of cells in the tumor of the patient. The method further includes determining at least one feature of the phylogenic tree including at least one value quantifying rates of mutation and/or at least one value representing at least one aspect of a structure of the phylogenic tree. The method further includes training a machine learning model to be configured to generate a projection for the patient comprising a clinical outcome or disease progression.
G16B 20/20 - Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
G16B 10/00 - ICT specially adapted for evolutionary bioinformatics, e.g. phylogenetic tree construction or analysis
G16B 30/00 - ICT specially adapted for sequence analysis involving nucleotides or amino acids
G16B 40/00 - ICT specially adapted for biostatisticsICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
49.
LIPID NANOPARTICLE FORMULATIONS CONTAINING HUMAN MILK SUGARS
Methods and materials for lipid nanoparticle delivery of nucleic acids are provided herein. For example, compositions containing human milk oligosaccharides in combination with lipid nanoparticles having nucleic acid cargoes are provided herein, as are methods that include administering, to mammals in need thereof, human milk oligosaccharides and lipid nanoparticles that carry nucleic acid cargoes.
Disclosed herein is a method for delivery stimulation to targeted deep brain structures by supplementing existing method using external electrodes with transnasal electrodes, disposed, for example, in the olfactory cleft and within the hyenoid sinus, or, more broadly, in the nasal cavity and/or in the sinuses, including, but not limited to, the frontal, ethmoidal, sphenoid sinus, etc. The method allows stimulation and/or sensing in deep brain regions which can be inaccessible from the scalp or for which existing methods are ineffective in targeting. The method can also be used for power delivery to implants that might be placed inside the brain or on its surface.
Disclosed herein is a system and method for formally verifying the safety of the Federal Railroad Administration freight train kinematics model with all its relevant forces and parameters, including track slope and curvature, airbrake propagation, and resistive forces as computed by the Davis equation.
Provided herein are engineered lipid-bound vesicles for cytosolic delivery of an exogenous secreted, cell surface receptor-binding signaling molecule. Also provided herein are methods of making and using the engineered lipid-bound vesicles, and devices comprising the lipid-bound vesicles.
Computer systems and computer-implemented methods identify potential discrepancies between data practice disclosures made in a data practice policy and a data practice label for a data system. The data system collects or captures data about or for a user of the data system or any other person The method can also comprise the step of comparing, by the computer system, the prediction for the given data practice with an entry in the data practice label for the data system to identify a possible discrepancy between the prediction and the data practice label. The classifier can be trained via machine learning to make the predictions. The classifier could comprise a classifier for each data practice covered by the data label or a foundation model, such as large language model, that is adapted to make the predictions about a data system's data practice label.
A method discloses receiving, at a cross-attention layer of a model, first text data describing a first object and second text data describing a first scene, wherein the first text data includes a description of a location of the first object, utilizing the model with cross-attention layers, concatenating the first text data and the second text data to generate a prompt; generating, a broadcasted location mask constructed from at least the location; generating, a broadcasted all-one matrix associated with the second text data described the first scene; computing a key matrix and a value matrix utilizing separate linear projections of the prompt; computing a query matrix utilizing linear projections; generating a broadcasted location matrix in response to concatenating the broadcasted location mask and the broadcasted all-one matrix; generating a cross-attention map utilizing the query matrix, the key matrix, and the broadcasted location matrix; and outputting a final image.
A computer-implemented method includes converting tabular data to a text representation, generating metadata associated with the text representation of the tabular data, outputting one or more natural language data descriptions indicative of the tabular data in response to utilizing a large language model (LLM) and zero-shot prompting of the metadata and text representation of the tabular data, outputting one or more summaries utilizing the LLM and appending a prompt on the one or more natural language data descriptions, selecting a single summary of the one or more summaries in response to the single summary having a smallest validation rate, receiving a query associated with the tabular data, outputting one or more predictions associated with the query, and in response to meeting a convergence threshold with the one or more predictions generated from the one or more iterations, output a final prediction associated with the query.
University of Pittsburgh - Of the Commonwealth System of Higher Education (USA)
CARNEGIE MELLON UNIVERSITY (USA)
Inventor
Powell, Marc Philip
Capogrosso, Marco
Weber, Douglas J.
Verma, Nikhil
Gerszten, Peter C.
Pirondini, Elvira
Sorensen, Erynn
Carranza Urquizo, Erick Fabrizio
Fisher, Lee
Abstract
Disclosed herein are methods for treating impairment of a limb in a subject. Particular methods comprise applying a therapeutically effective amount of an electrical stimulus to dorsal roots, dorsal rootlets, or dorsal root ganglia, of sensory neurons innervating the limb of the subject, wherein the impairment is a motor impairment and/or a proprioception impairment due to neurological disorder or injury, the electrical stimulus is applied with one or more electrodes controlled by a neurostimulator, and the one or more electrodes are implanted in the epidural space at the dorsolateral aspect of the spinal cord and proximate to the dorsal roots or dorsal rootlets of the sensory neurons innervating the limb of the subject, or the one or more electrodes are implanted proximate to dorsal root ganglia of sensory neurons innervating the limb of the subject.
A strain sensor utilizes an ohmic-based contact switch to detect strain. The sensor can be incorporated into other structures, such as an artificial flapping wing, to detect strain and other parameters, including air flow disturbances. The sensors are fabricated using an additive manufacturing process, with a layer of gold or other conductive material applied for electrical conductivity and UV laser ablation for electrical isolation. The sensor design incorporates mechanical amplification, converting small strains into larger displacements that close contact pads, resulting in an ohmic switch activated at a specific strain threshold. Unlike traditional sensors, the switch provides a high or low state output directly without the need for additional amplification or post-processing. The device can detect disturbances in flapping wing cycles and obtain yaw rotation information, with potential applications in other aircraft for disturbance detection.
B81B 3/00 - Devices comprising flexible or deformable elements, e.g. comprising elastic tongues or membranes
B81C 1/00 - Manufacture or treatment of devices or systems in or on a substrate
G01L 1/22 - Measuring force or stress, in general by measuring variations in ohmic resistance of solid materials or of electrically-conductive fluidsMeasuring force or stress, in general by making use of electrokinetic cells, i.e. liquid-containing cells wherein an electrical potential is produced or varied upon the application of stress using resistance strain gauges
58.
MULTIDIMENSIONAL 3D GRAPHENE-BASED HIGH-PERFORMANCE CATALYSTS
A hybrid graphene material includes a functional group to expand the use of graphene in various applications. The hybrid material may include a substrate, such as silicon nanowires, where the graphene is fabricated on the surface of the substrate with an out-of-plane topography. Functional groups can be added to the graphene and affect the electrical, chemical, or photo characteristics of the hybrid material.
A system uses a sensing membrane to determine a fluid flow of a working fluid through the membrane. The system detects an electrical current generated by a fluid flowing through the sensing membrane and correlates the current to bulk flow. The sensing membrane can also be used to induce fluid flow by applying a current to the membrane. In alternative embodiments, separate sensing membranes and actuating membranes can be used in the same enclosures to permit sensing and actuating simultaneously.
G01F 1/38 - Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow by using mechanical effects by measuring pressure or differential pressure the pressure or differential pressure being created by the use of flow constriction the pressure or differential pressure being measured by means of a movable element, e.g. diaphragm, piston, Bourdon tube or flexible capsule
G01F 1/56 - Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow by using electric or magnetic effects
G01F 1/64 - Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow by using electric or magnetic effects by measuring electrical currents passing through the fluid flowMeasuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow by using electric or magnetic effects by measuring electrical potential generated by the fluid flow, e.g. by electrochemical, contact, or friction effects
G01N 15/08 - Investigating permeability, pore volume, or surface area of porous materials
A haptic device uses a group of electroosmotic pumps arranged in an array to provide tactile feedback to a user of a virtual/augmented reality system. The electroosmotic pumps are arranged in defined patterns, forming an array of haptic pixels. The pumps pressurize a working fluid to cause a displacement of a flexible membrane in contact with the working fluid. A controller can be used to address individual pumps of the array and to provide simulate effects such as texture, object compliance, detents and buttons, and to provide haptic animations.
A high gravimetric and volumetric power density heat exchanger is provided for high-temperature and high-pressure applications with counter-flowing hot and cold agents that enter via respective inlet headers, transit parallel and adjacent flow passages, and exit via respective outlet headers. One or more headers for conveying one of the substances may be situated within the flow of the other substance. Structures within the flow passages promote the transfer of heat while limiting pressure drop on one or both sides. The structures may include microscale pins, an array of pins (with specified aspect ratios and spacing), a lattice of interconnected pins, parallel ridges, and/or other features. Through an additive manufacturing process, the headers are monolithically integrated into the heat exchanger instead of being separately constructed and attached.
F28D 9/00 - Heat-exchange apparatus having stationary plate-like or laminated conduit assemblies for both heat-exchange media, the media being in contact with different sides of a conduit wall
Disclosed herein is a method for determining a physically unclonable function of a pixel array using the dark count rate of events at each pixel to form a dark count map. The dark count map serves as a signature of the array from which a set of authentication keys may be generated to provide verification of images generated by the pixel array. Multiple dark count maps from which multiple key sets can be generated may be provided for the pixel array by varying the perimeter gate voltage of each pixel.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
Internally-coated three-dimensional materials including a porous scaffold having an internal pore system including internal pores and interconnected interior channels in open communication with an exterior surface of the porous scaffold, and a functional internal conformal coating including 0D materials, 1D materials, and/or 2D materials in contact with interior surfaces of the internal pores and the interconnected interior channels, and the coating may be characterized by an interconnected three-dimensional network that is electrically conductive and/or electrochemically active. Methods of making and using the materials are also described.
Methods of controlling a computing system based on wiggling and/or other types of continuous multidirectional gesturing. In some embodiments, the methods monitor user gesturing for the occurrence of a recognizable item-action gesture that a user has made without having provided any other input to the computing system and then take one or more actions in response to recognizing the item-action gesture. In some embodiments, the actions include identifying one or more on-display item underlying the item-action gesture, duplicating the identified item(s) to one or more target locations, and adding one or more visual indicia to the identified on-display item(s), among other things In some embodiments, a user can append an item-action gesture with one or more action extensions that each cause the computing system to take one or more additional actions concerning the identified on-display item(s). Software for performing one or more of the disclosed methodologies is also disclosed.
G06F 3/04883 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
Disclosed herein is a novel deep learning-based source imaging framework for imaging ictal oscillations from high-density electrophysiological recordings in drug-resistant focal epilepsy patients. A neural mass model producing ictal oscillations was used to generate synthetic training data having spatio-temporal-spectra features indicative of ictal oscillations. The synthetic training data was then used to train the deep learning-based source imaging framework to image and localize brain source patches exhibiting ictal oscillations, based on an input of EEG data.
Provided are systems and methods for swept-angle interferometry. A system includes a light source configured to emit at least one beam having at least two wavelengths, a beam steering device configured to steer the at least one beam across at least one axis of motion, a lens arranged in an optical path between the beam steering device and a target of the at least one beam, the lens having a focal plane, and a relay lens arranged in the optical path between the beam steering device and the lens.
67.
SYSTEM AND METHOD FOR CONTROLLING SATELLITES IN ORBIT
Provided are systems and methods for controlling a plurality of satellites. A system includes at least one computing device configured to determine a control plan based on a target separation in along-track and cross-track directions for a plurality of satellites including at least a first satellite and a second satellite, the control plan including at least one drag modulation parameter for each satellite, control the first satellite to lower an orbital altitude of the first satellite based on the at least one drag modulation parameter, such that a mean motion and nodal precession rate of the first satellite increases, based on the control plan and after lowering the orbital altitude of the first satellite, and control the second satellite to lower an orbital altitude of the second satellite based on the at least one drag modulation parameter to achieve the target separation.
A method of forming a three-dimensional structure using droplet-based freeform printing is provided. The method includes depositing a structural material through one or more nozzles onto a surface of a substrate by droplet-based freeform printing, such as inkjet printing, to form one or more three-dimensional structures including a smooth surface and one or more cross-sectional dimensions. The structural material undergoes a liquid-to-solid transition after deposition of the structural material, and the one or more cross-sectional dimensions are controlled by a droplet ejection frequency. A method of fabricating a matrix including a three-dimensional structure including forming a negative three-dimensional template using droplet-based freeform printing, depositing, such as casting, a matrix material over the negative three-dimensional template and at least a portion of the surface of the substrate and solidifying the matrix material to form a matrix including the one or more three-dimensional structures of the negative template is also provided.
B29C 64/112 - Processes of additive manufacturing using only liquids or viscous materials, e.g. depositing a continuous bead of viscous material using individual droplets, e.g. from jetting heads
A method and apparatus for degrading a hypodermal tissue scaffold involves exposing the scaffold to a low-intensity focused ultrasonic beam such as to burst gas vesicles trapped in the silk fibroin from which scaffold is constructed. The rate of degradation van be controlled using ultrasonic beams of varying intensities. In one embodiment, the ultrasonic beams are administered trans-dermally to a hypodermal scaffold.
Various systems and process for fabricating customized medical devices via the freeform reversible embedding of suspended hydrogels process are disclosed. The mechanical properties of the fabricated objects can be controlled according to the manner or orientation in which the structure material is deposited into the support material and the three-dimensional movement of the extruder assembly. Further, the dimensions of the fabricated objects can be validated by adding a contrast agent to the structure material, obtaining a three-dimensional reconstruction of the fabricated object, and then comparing the three-dimensional reconstruction to the computer model upon which the fabricated object is based. These and other techniques are described herein.
B29C 64/386 - Data acquisition or data processing for additive manufacturing
A61B 5/00 - Measuring for diagnostic purposes Identification of persons
A61B 5/055 - Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fieldsMeasuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
Disclosed herein is a novel pseudoinverse estimation system and method that adapts regression techniques to directly estimate one or more pseudo inverses of a neuromodulation pathway, thereby circumventing the need of inverting an estimated forward model to design an electrical waveform that elicits a desired neural response. This is accomplished by the learning of a restricted domain that restricts the potential stimuli required to produce the desired neural response. Also disclosed herein is an adaptive, data-driven method providing a more selective design of an electrical waveform to elicit the desired neural response.
This document describes systems and methods for integrated mechanical loading of tissue. The system includes a three-dimensional tissue comprising organic material. The system includes a strip of bendable material. The strip includes a first region proximate to a first end of the strip coupled to the tissue. The strip includes a second region near a second end of the strip for coupled to the tissue, the second end being opposite the first end, wherein the tissue exerts a force on the strip to bend the strip, the force caused by contraction of the tissue, and wherein the strip exerts a stress on the tissue.
Light based additive manufacturing systems, methods of manufacture thereof, and products formed therefrom are provided. The additive manufacturing system comprises a material deposition region (102), a light emitter (104), a conduit (106), a carriage assembly (108), and a processor (110). The material deposition region is capable to hold a first material that is at least partially photoactivatable. The conduit is capable to transmit light from the light emitter to an end of the conduit and is capable to be disposed within the material deposition region. The carriage assembly is capable to move, rotate, or a combination thereof, the conduit within the material deposition region. The processor is in signal communication with the light emitter, conduit, carriage assembly, or a combination thereof, in order to selectively photoactive the first material using the end of the conduit, according to a first computer model, to additively form an object made of the first material.
B29C 64/135 - Processes of additive manufacturing using only liquids or viscous materials, e.g. depositing a continuous bead of viscous material using layers of liquid which are selectively solidified characterised by the energy source therefor, e.g. by global irradiation combined with a mask the energy source being concentrated, e.g. scanning lasers or focused light sources
This document describes systems and method of embedded printing for additive manufacturing. A print material is printed into a support material. The print material and the support material each have a fluid phase and a solid phase. The print material transitions from the fluid phase to the solid phase based on a fluid-fluid interaction with the support material. One or more parameters of the support material can be adjusted to cause a diffusion rate of the print material into the support material during the fluid-fluid interaction to be less than a threshold value. Multiple print materials can be printed into the support material simultaneously.
B29C 64/106 - Processes of additive manufacturing using only liquids or viscous materials, e.g. depositing a continuous bead of viscous material
B29C 64/165 - Processes of additive manufacturing using a combination of solid and fluid materials, e.g. a powder selectively bound by a liquid binder, catalyst, inhibitor or energy absorber
Disclosed herein is a system and method for matching products detected in an image of a shelf. The match or non-match of the products is then used to make a determination that the products are correctly positioned on the shelf of if the positioning of the products represents a plug or spread situation.
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersectionsConnectivity analysis, e.g. of connected components
G06F 18/214 - Generating training patternsBootstrap methods, e.g. bagging or boosting
G06T 7/73 - Determining position or orientation of objects or cameras using feature-based methods
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 20/20 - ScenesScene-specific elements in augmented reality scenes
Materials and methods for conducting an atom transfer radical polymerization in the presence of oxygen by interlocking enzymatic activities are provided herein.
C08F 4/10 - Metallic compounds other than hydrides and other than metallo-organic compoundsBoron halide or aluminium halide complexes with organic compounds containing oxygen of alkaline earth metals, zinc, cadmium, mercury, copper, or silver
C08F 4/26 - Metallic compounds other than hydrides and other than metallo-organic compoundsBoron halide or aluminium halide complexes with organic compounds containing oxygen of manganese, iron group metals, or platinum group metals
C08F 220/28 - Esters containing oxygen in addition to the carboxy oxygen containing no aromatic rings in the alcohol moiety
Disclosed herein is a method for defining a model of a trusted IoT security gateway architecture based on a microhypervisor, wherein evaluation of the model provides a guarantee that the correct security protections are applied to each IoT device's network traffic at all times, including when under attack. The models defined in accordance with the method disclosed herein are used to verify security gateway architectures that provide robust trust properties to a broad range of legacy hardware platforms utilizing existing software with a reasonable performance overhead.
G06F 21/53 - Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems during program execution, e.g. stack integrity, buffer overflow or preventing unwanted data erasure by executing in a restricted environment, e.g. sandbox or secure virtual machine
Systems and devices to measure atmospheric gaseous reactive gases that may form atmospheric aerosol particles may generally includes a reactor in fluid communication with a particle counter. The reactor may include a first inlet configured to receive a continuous flow of a first fluid and a second inlet configured to receive a continuous flow of a second fluid. The reactor may include a first outlet in fluid communication with the particle counter to detect a reaction product of the first fluid and second fluid. The reaction product may include 1-3 nanometer particles. The reactor may include a second outlet to exhaust any remaining portion of the reaction product flow from the reactor. Methods of making and using the systems and devices to measure atmospheric gaseous reactive gases that may form atmospheric aerosol particles are also described.
A method of manufacturing a porous part includes controlled freeze casting of a slurry. After freezing, a solvent in the slurry is removed by sublimation and the remaining material is sintered to form the porous part. Spatial and temporal control of thermal conditions at the boundary and inside of the mold can be controlled to create parts with controlled porosity, including size, distribution, and directionality of the pores. Porous parts with near-net-shape from ceramics, metals, polymers and other materials and their combinations can be created.
B22F 1/107 - Metallic powder containing lubricating or binding agentsMetallic powder containing organic material containing organic material comprising solvents, e.g. for slip casting
B22F 3/22 - Manufacture of workpieces or articles from metallic powder characterised by the manner of compacting or sinteringApparatus specially adapted therefor for producing castings from a slip
B28B 1/00 - Producing shaped articles from the material
B29C 39/02 - Shaping by casting, i.e. introducing the moulding material into a mould or between confining surfaces without significant moulding pressureApparatus therefor for making articles of definite length, i.e. discrete articles
A tactile sensor utilizes a magnet embedded in an elastomer and a magnetometer for measuring a strength of a magnetic field emitted by the magnet. The elastomer may include two layers, with a first layer having a lower modulus than the second layer. When two layers are used, the magnet can be positioned at an interface between the layers. The use of a softer outer layer increases the sensitivity of the sensor. Sensitivity can be further increased by including features or a pattern of features on the surface of the elastomer. The features, which can be similar to fingerprints on a human hand, are adapted to provide vibrational information caused by the surface roughness of a material. The sensor provides material characterization and can be used to identify the material in contact with the sensor. The sensor can be fabricated using molding techniques.
B25J 13/08 - Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
G01B 7/24 - Measuring arrangements characterised by the use of electric or magnetic techniques for measuring the deformation in a solid, e.g. by resistance strain gauge using change in magnetic properties
G01L 1/12 - Measuring force or stress, in general by measuring variations in the magnetic properties of materials resulting from the application of stress
G01L 5/169 - Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring several components of force using magnetic means
Disclosed herein is a system and method for the automatic detection of persons engaged in the open carry of firearms at a venue. The system and method comprise strategically placed cameras at the venue which are connected to edge devices which extract frames from video generated by the cameras. The video frames are sent to a server for analysis by an AI/ML model trained to detect firearms and, specifically, to detect persons carrying firearms. If a person wielding a firearm is detected in any image, an alert is raised and local authorities are automatically contacted. The system is designed to run continuously such as to be able to quickly detect a person in a venue carrying a firearm.
Disclosed herein is an Overmoded Bulk Acoustic Resonator (OBAR) and a solidly-mounted OBAR (SBAR), which operate in a partially transduced 2nd overtone split between piezoelectric and electrode layers using dual all metal Bragg mirrors. The devices may be deployed in a series configuration. The devices have arbitrarily thick electrodes to minimize ohmic loss and bandwidths high enough to meet filtering requirements of 5G networks. The devices provide sharp filtering which can be performed directly at each antenna element in a form factor much smaller than the half-wavelength separation between adjacent antenna elements required when using electromagnetic resonators.
Disclosed herein is a system and method for data augmentation for general object recognition which preserves the class identity of the augmented data. The system comprises an image recognition network an image generation network that take as input ground truth images and classes respectively and which generates a predicted class and an augmented image. A discriminator evaluates the predicted class and augmented image and provides feedback to the image recognition network and the image generation network.
Disclosed herein is a framework for the modeling and design of materials based on differentiable programming, where the models can be trained by gradient-based optimization. Within this framework, all the components are differentiable and can be seamlessly integrated and unified with deep learning. The framework can design and optimize materials for a variety of applications.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
85.
DEVICE AND METHOD FOR IMPROVED POLICY LEARNING FOR ROBOTS
A computer-implemented method of learning a policy for an agent. The method includes: receiving an initialized first neural network, in particular a Q-functionor value-function, an initialized second neural network, auxiliary parameters, and the initialized policy; repeating the following steps until a termination condition is fulfilled: sampling a plurality of pairs of states, actions, rewards and new states from a storage. Sampling actions for the current states, and actions for the new sampled states; computing features from a penultimate layer of the first neural network based on the sampled states and actions and updating the second neural network and the auxiliary parameters as well as updating parameters the first neural network using a re-weighted loss.
The present disclosure relates to structures and methods of use of textiles for protection, and more particularly. relates to single layer knitted structures that can be worn as garments to block mosquito bites. The knit structures of the present embodiments can include single layer structures having a unique geometric combination of yarn properties and textiles to block mosquito bites in a single. comfortable layer of fabric. The knit structures can include one or more controllable parameters that can be adjusted to increase and/or decrease the bite blocking ability of the knit structure.
Disclosed herein is a system and method for reducing false positives in object detection frameworks. A human form view of objects detected by the object detection framework and indicates the object is a false positive. When an indication of a false positive been received, a feature representation of displayed object stored in the gallery. During an inference or testing phase, the gallery is searched for a feature representation matching the feature representation of the detected objects, and, if a match is found, the detected object is deemed to be a false positive and is not displayed to the user.
G06V 10/778 - Active pattern-learning, e.g. online learning of image or video features
G06V 10/75 - Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video featuresCoarse-fine approaches, e.g. multi-scale approachesImage or video pattern matchingProximity measures in feature spaces using context analysisSelection of dictionaries
88.
System and Method for Prediction of Molecular Dynamics and Chemical Properties Using Equivariant Neural Operators
Disclosed herein is a system and method using an equivariant neural network for predicting quantum mechanical charge density. The equivariant neural network serves as a surrogate for the density-functional theory used to calculate a selfconsistent field and predicts the central observable charge density, which, in addition to enabling force calculations, can also accelerate DFT itself and compute a full range of chemical properties.
UNIVERSITY OF PITTSBURGH - OF THE COMMONWEALTH SYSTEM OF HIGHER EDUCATION (USA)
CARNEGIE MELLON UNIVERSITY (USA)
Inventor
Ohodnicki, Paul Richard
Shen, Sheng
Abstract
A near-field probe (and associated method) compatible with near-infrared electromagnetic radiation and high temperature applications above 300°° C. (or 500° C. in some applications) includes an optical waveguide and a photonic thermal emitting structure comprising a near-field thermally emissive material coupled to or part of the optical waveguide. The photonic thermal emitting structure is structured and configured to emit near-field energy responsive to at least one environmental parameter of interest, and the near-field probe is structured and configured to enable extraction of the near-field energy to a far-field by coupling the near-field energy into one or more guided modes of the optical waveguide.
A system includes an inertial sensing device having an inertial sensor and plurality of stress sensors configured to measure stress applied to the inertial sensing device, and at least one computing device configured to: receive sensor data from the inertial sensor and the plurality of stress sensors; and determine a drift compensation of the inertial sensor based on the sensor data. Other systems, methods, and devices are disclosed.
G01D 3/036 - Measuring arrangements with provision for the special purposes referred to in the subgroups of this group mitigating undesired influences, e.g. temperature, pressure on measuring arrangements themselves
B81B 7/02 - Microstructural systems containing distinct electrical or optical devices of particular relevance for their function, e.g. microelectro-mechanical systems [MEMS]
G01P 15/02 - Measuring accelerationMeasuring decelerationMeasuring shock, i.e. sudden change of acceleration by making use of inertia forces
G01P 21/00 - Testing or calibrating of apparatus or devices covered by the other groups of this subclass
THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOIS (USA)
Inventor
Bao, Zhipeng
Tokmakov, Pavel
Wang, Yuxiong
Gaidon, Adrien David
Hebert, Martial
Abstract
A method for learning a representation of a sequence of frames includes encoding, via an encoder network, the sequence of frames to obtain a set of feature maps and extracting, a motion-guided slot learning mechanism, mid-level features from the set of feature maps. The method further includes quantizing the mid-level features via a vector quantization process to obtain a set of tokens, and decoding, via a decoder network, the tokens to obtain a reconstructed sequence of frames. The method still further includes optimizing a combination of a reconstruction loss and a motion loss to train the encoder and decoder networks.
G06T 7/246 - Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
92.
METHOD FOR DIVERSE SEQUENTIAL POINT CLOUD FORECASTING
A method for sequential point cloud forecasting is described. The method includes training a vector-quantized conditional variational autoencoder (VQ-CVAE) framework to map an output to a closest vector in a discrete latent space to obtain a future latent space. The method also includes outputting, by a trained VQ-CVAE, a categorical distribution of a probability of V vectors in a discrete latent space in response to an input previously sampled latent space and past point cloud sequences. The method further includes sampling an inferred future latent space from the categorical distribution of the probability of the V vectors in the discrete latent space. The method also includes predicting a future point cloud sequence according to the inferred future latent space and the past point cloud sequences. The method further includes denoising, by a denoising diffusion probabilistic model (DDPM), the predicted future point cloud sequences according to an added noise.
Disclosed herein is a system architecture that structures commodity heterogeneous interconnected computing platforms around universal object abstractions, which are fundamental system abstractions and building blocks that provides practical and provable end-to-end guarantees of security, correctness, and timeliness for the platform.
In an example, a method may include deforming a first ray associated with a dynamic object at a first time using a first neural network and a latent code to obtain a deformed ray. The method may also include obtaining a hyperspace code associated with the first ray by inputting the first ray, the first time, and the latent code into a second neural network. The method may further include sampling one or more points from the deformed ray. The method may also include combining the sampled points and the hyperspace code into a network input. The method may further include inputting the network input into a third neural network to obtain RGB values for rendering images of a three-dimensional scene representative of the dynamic object at a second time.
Computer-based systems and methods for discovering neighborhood clusters in a geographic region, where the clusters have a mix of venues and are determined based on venue check-in data. The mix of venues for the clusters may be based on the social similarity between pairs of venues; or emblematic of certain neighborhood typologies; or emblematic of temporal check-in pattern types; or combinations thereof. The neighborhood clusters that are so discovered through venue-check in data could be used for many commercial and civic purposes.
Disclosed herein is a method for optimizing electrode placement that directly exploits the thresholding phenomenon of neurons. The method employs a loss function which only becomes non-zero when the electric field is above a user-specified threshold in the cancel region, thereby allowing for fields which can have significant non-zero current in the cancel region, but still provide more focused neural activation.
Methods and systems are for generating a process map for forming a structure, the process map usable for controlling additive manufacturing with the structure. The methods and systems are configured for obtaining a value of at least one process parameter for controlling thermo-fluid dynamics of the structure for melting material; heating, in accordance with the value of the at least one process parameter, the structure; obtaining a high-speed imaging of a melt pool; determining changes in a topological shape of the melt pool from the imaging; determining an absence or a presence of a defect in the structure representing whether the material is successful added to the structure; and generating a process map that correlates the value of the at least one process parameter to the absence or the presence of the defect in the structure.
Provided are systems, methods, and apparatuses for passive light interferometry. A system includes a mirror, a first sensor arranged to capture light from a light source reflected by the mirror, a controller in communication with the first sensor, the controller configured to cause rotation of the mirror based on movement of the light, an interferometer arranged in an optical path of the light source reflected by the mirror, and a beam splitter arranged in an optical path between the mirror and the interferometer.
A method for detecting an application progress and handling an application failure in a distributed system. The method includes: monitoring an interaction between modules of at least one application, the at least one application being deployed across different physical nodes, the interaction being carried out by exchanging messages between the modules using a message broker, the monitoring being carried out at least partially using the message broker; detecting the application progress based on the monitoring; initiating a failure handling based on the detecting.
A method for providing a secondary backup application as a backup for a primary application, particularly for a predictive standby in distributed systems. The method includes the following steps are carried out by a predictive standby manager: receiving application-specific state data, the application-specific state data being obtained from monitoring a state of the primary application; receiving platform-specific state data, the platform-specific state data being obtained from monitoring a state of at least one platform that executes the primary application; initiating a backup process for using the secondary backup application based on the received application-specific state data and the platform-specific state data.
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
