Patents Assigned to Carnegie Mellon
-
Patent number: 12178591Abstract: A system is configured for receiving force data including at least one value indicating the amount of the force applied to the portion of the user and at least one value indicating a direction of the force applied to the portion of the user; obtaining mapping data specifying at least one relation between values of force applied to the portion of the user and changes in a functional responsiveness, functional and/or structural integrity, or both the functional responsiveness and the functional and/or structural integrity of the brain at one or more locations in the brain; estimating, based on the mapping data and the force data, an amount of force loading at one or more particular locations in the brain; and generating, based on the estimating, output data representing an amount of the damage to the brain at the one or more particular locations in the brain.Type: GrantFiled: August 5, 2021Date of Patent: December 31, 2024Assignee: Carnegie Mellon UniversityInventors: Bradford Mahon, Adnan Hirad
-
Patent number: 12182668Abstract: A method to classify sensor data with improved robustness against label noise. A predicted label may be computed for a novel input with improved robustness against label noise by estimating a label which is most likely under repeated application of a base training function to the training labels incorporating noise according to a noise level and subsequent application of a base classifier configured according to the base prediction function to the novel input.Type: GrantFiled: September 18, 2020Date of Patent: December 31, 2024Assignees: ROBERT BOSCH GMBH, CARNEGIE MELLON UNIVERSITYInventors: Elan Kennar Rosenfeld, Ezra Maurice Winston, Frank Schmidt, Jeremy Zieg Kolter
-
Patent number: 12178588Abstract: A novel method for using the widely-used electroencephalography (EEG) systems to detect and localize silences in the brain is disclosed. The method detects the absence of electrophysiological signals, or neural silences, using noninvasive scalp electroencephalography (EEG) signals. This method can also be used for reduced activity localization, activity level mapping throughout the brain, as well as mapping activity levels in different frequency bands. By accounting for the contributions of different sources to the power of the recorded signals and using a hemispheric baseline approach and a convex spectral clustering framework, the method permits rapid detection and localization of regions of silence in the brain using a relatively small amount of EEG data.Type: GrantFiled: January 11, 2024Date of Patent: December 31, 2024Assignee: Carnegie Mellon UniversityInventors: Pulkit Grover, Alireza Chamanzar, Marlene Behrmann Cohen
-
Patent number: 12182707Abstract: Disclosed herein is a system and method for novel neural architecture search using a random graph network backbone to facilitate the creation of an efficient network structure. The method utilizes reinforcement learning algorithms to build a complex relationship between intra-connections (i.e., links between blocks in a random graph network) and extra-connections (i.e., links among blocks across the random graphs network) for discovering an efficient random neural architecture.Type: GrantFiled: February 18, 2022Date of Patent: December 31, 2024Assignee: Carnegie Mellon UniversityInventors: Marios Savvides, Thanh Hai Phan, Zhiqiang Shen, Akshay Chawla
-
Patent number: 12174179Abstract: The present invention provides microfluidic pScreen™ devices for quantifying the concentration of DNA fragments in a liquid sample by using magnetic-responsive silica micro-beads and nonmagnetic-responsive silica micro-beads. The devices of the present invention allow for rapid, simple and inexpensive quantification of DNA fragment concentration in a sample. The devices do not require complex instrumentation and can be performed in less than three minutes. Moreover, they are compatible with complex samples including, without limitation, unpurified PCR amplification products, and thus can be expected to seamlessly integrate into various common molecular biology techniques and workflows.Type: GrantFiled: December 2, 2019Date of Patent: December 24, 2024Assignee: CARNEGIE MELLON UNIVERSITYInventors: Alberto Gandini, James F. Antaki, Byron Wang Chuan, Joie N. Marhefka, Juha-Pekka Mattila, Eliseo Salas
-
Publication number: 20240416125Abstract: 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.Type: ApplicationFiled: June 13, 2024Publication date: December 19, 2024Applicant: CARNEGIE MELLON UNIVERSITYInventors: Mats Forssell, Yuxin Guo, Yuhyun Lee, Vishal Jain, Chaitanya Goswami, Ariel Feldman, Neil Ashim Mehta, Boyle C. Cheng, Pulkit Grover
-
Patent number: 12165068Abstract: 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 the radius of a multi-dimensional hypersphere using a convex augmentation of the primary loss function.Type: GrantFiled: February 28, 2019Date of Patent: December 10, 2024Assignee: Carnegie Mellon UniversityInventors: Marios Savvides, Dipan Kumar Pal, Yutong Zheng
-
Patent number: 12167210Abstract: A system and method implementing an acoustic mapping suite that equips intelligent vehicles with the ability to identify and respond to primary sounds of interest in their environment. The invention performs sound separation, localization and classification techniques, while also generating a sound-based map of the vicinity as well as making inferences and qualitative assessments about sound sources with information over time.Type: GrantFiled: February 23, 2022Date of Patent: December 10, 2024Assignee: Carnegie Mellon UniversityInventors: Raganathan Rajkumar, Swapnil Das
-
Patent number: 12164926Abstract: 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.Type: GrantFiled: October 13, 2021Date of Patent: December 10, 2024Assignee: Carnegie Mellon UniversityInventors: Brandon Lucia, Nathan Beckmann, Graham Gobieski
-
Patent number: 12166203Abstract: A process for the formation of a deformable battery electrode includes mixing a metal component including at least one of a metal or a metal alloy, a polymer component, and a dispersant component to create a mixture. The method further includes heated the mixture to a temperature above the melting point of the metal or the metal alloy and agitating the mixture to form a dispersion of the (molten) metal or the metal alloy in the mixture. The method further includes cooling the mixture to a temperature below the melting point of the metal or the metal alloy to form a stabilized dispersion of the metal or the metal alloy. The polymer component includes a polymer having a melting point equal to or below that of the metal or the metal alloy and a glass transition temperature sufficiently low that the stabilized dispersion is deformable.Type: GrantFiled: December 17, 2019Date of Patent: December 10, 2024Assignee: CARNEGIE MELLON UNIVERSITYInventors: Krzysztof Matyjaszewski, Jay F. Whitacre, Sipei Li, Francesca Lorandi
-
Publication number: 20240399152Abstract: 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.Type: ApplicationFiled: September 9, 2022Publication date: December 5, 2024Applicants: University of Pittsburgh - Of the Commonwealth System of Higher Education, CARNEGIE MELLON UNIVERSITYInventors: Marc Philip Powell, Marco Capogrosso, Douglas J. Weber, Nikhil Verma, Peter C. Gerszten, Elvira Pirondini, Erynn Sorensen, Erick Fabrizio Carranza Urquizo, Lee Fisher
-
Publication number: 20240400375Abstract: 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.Type: ApplicationFiled: June 5, 2024Publication date: December 5, 2024Applicant: Carnegie Mellon UniversityInventors: Regan Kubicek, Sarah Bergbreiter, Mahnoush Babaei, Alison I. Weber, Sukjun Kim, Tom Daniel
-
Publication number: 20240400394Abstract: 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.Type: ApplicationFiled: October 13, 2022Publication date: December 5, 2024Applicant: Carnegie Mellon UniversityInventors: Itzhaq Cohen-Karni, Raghav Garg, Daniel J. San Roman, Inkyu Lee, Yingqiao Wang, Samuel Gershanok, Mabel Bartlett, Xudong Ji, Jonathan Rivnay
-
Publication number: 20240396724Abstract: 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.Type: ApplicationFiled: May 23, 2024Publication date: November 28, 2024Applicant: CARNEGIE MELLON UNIVERSITYInventors: Md. Sakibur Rahman Sajal, Marc Dandin
-
Publication number: 20240393056Abstract: 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.Type: ApplicationFiled: January 27, 2022Publication date: November 28, 2024Applicants: The Regents of the University of California, Carnegie Mellon UniversityInventors: Vinod Narayanan, Erfan Rasouli, Anthony D. Rollett, Ines-Noelly T. Tano, Ziheng Wu, Sreedev Das, Nicholas Lamprinakos, Tracey L. Ziev, Parth Trilochan Vaishnav, Junwon Seo, Srujana Rao Yarasi
-
Patent number: 12154354Abstract: Provided are methods for labeling ultrasound data. The method may include training a convolutional neural network (CNN) based on ultrasound data. The ultrasound data may include ultrasonic waveform data (e.g., radio frequency (RF) waveform data). An RF input of each downsampling layer of a plurality of downsampling layers in the CNN may be downsampled. The RF input may include RF waveform data for an ultrasound. Tissues in the ultrasound may be segmented based on an output of the CNN. A system is also disclosed.Type: GrantFiled: June 12, 2020Date of Patent: November 26, 2024Assignee: Carnegie Mellon UniversityInventors: John Galeotti, Gautam Rajendrakumar Gare, Jiayuan Li, Ricardo Luis Rodriguez
-
Patent number: 12151798Abstract: An aquatic vessel, illustratively a pontoon boat including a thruster system is disclosed. The aquatic vessel executes a process to automatically position the aquatic vessel relative to a target location such as a mooring implement. Exemplary mooring implements include a dock, a slip, or a lift.Type: GrantFiled: September 27, 2020Date of Patent: November 26, 2024Assignees: Polaris Industries Inc., Carnegie Mellon UniversityInventors: Andrew C. Schmid, Michael J. Fuchs, Blair A. Donat, Gabriel A. Marshall, Bradley R. Fishburn, Herman Herman, Prasanna Kannappan, Matthew Glisson, Krishna Pandravada, Suryansh Saxena, Louis Hiener, Nishant Pol, Gabriel Goldman, Karl Muecke
-
Patent number: 12154319Abstract: Provided is a method of training a machine-learning-based artificial intelligence (AI) model to handle diverse types of motions occurring during image acquisition, including capturing image data including motion between an imaging device and tissue, modifying the captured image data, resulting in modified image data, by at least one of: altering an amount of time between any two frames; removing a subsequence of frames from the captured image data; and adding a subsequence of one or more new frames to the captured image data, and training a machine-learning-based AI model based on the modified image data. Other systems and methods are also described.Type: GrantFiled: November 15, 2021Date of Patent: November 26, 2024Assignee: Carnegie Mellon UniversityInventors: Edward Chen, John Galeotti, Howie Choset
-
Publication number: 20240382136Abstract: 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.Type: ApplicationFiled: June 24, 2024Publication date: November 21, 2024Applicant: CARNEGIE MELLON UNIVERSITYInventors: Rui SUN, Abbas SOHRABPOUR, Bin He
-
Publication number: 20240366835Abstract: 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.Type: ApplicationFiled: April 26, 2022Publication date: November 7, 2024Applicant: CARNEGIE MELLON UNIVERSITYInventors: Rosalyn ABBOTT-BEAUREGARD, Megan DEBARI