Patents by Inventor Andreas Spanias

Andreas Spanias has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20250148342
    Abstract: A novel approach for computing efficiently quantum based signal autocorrelations includes example designs associated with quantum circuits for computing the quantum autocorrelation of the signal. Importantly, to compensate for unique challenges associated with quantum signal processing (particularly regarding probabilistic measurements that result from QFT and IQFT operations), normalization and denormalization steps ensure that quantum measurement results are comparable to ranges that would be obtained with classical autocorrelation computation methods. In addition, because probabilistic measurements resulting from QFT and IQFT operations lose important phase information, lost phase information can be restored following measurement using QFT and IQFT.
    Type: Application
    Filed: November 4, 2024
    Publication date: May 8, 2025
    Applicant: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Aradhita Sharma, Glen Uehara, Andreas Spanias
  • Patent number: 12293291
    Abstract: A system for time series analysis using attention models is disclosed. The system may capture dependencies across different variables through input embedding and may map the order of a sample appearance to a randomized lookup table via positional encoding. The system may capture capturing dependencies within a single sequence through a self-attention mechanism and determine a range of dependency to consider for each position being analyzed. The system may obtain an attention weighting to other positions in the sequence through computation of an inner product and utilize the attention weighting to acquire a vector representation for a position and mask the sequence to enable causality. The system may employ a dense interpolation technique for encoding partial temporal ordering to obtain a single vector representation and a linear layer to obtain logits from the single vector representation. The system may use a type dependent final prediction layer.
    Type: Grant
    Filed: July 5, 2023
    Date of Patent: May 6, 2025
    Assignees: Arizona Board of Regents on Behalf of Arizona State University, Lawrence Livermore National Security, LLC
    Inventors: Andreas Spanias, Huan Song, Jayaraman J. Thiagarajan, Deepta Rajan
  • Publication number: 20250094528
    Abstract: A system implements a modeling (ClassGP) and an optimization (ClassBO) framework that models heterogeneous functions with knowledge of individual partitions within classes, i.e., heterogeneous functions including non-stationary functions which can be divided into locally stationary functions over partitions of input space with an active stationary function in each partition. The framework constructs a class likelihood for the class by combining log marginal likelihoods associated with each partition of the plurality of partitions within the class. The framework aims to improve analysis of systems that are characterized by a discrete and finite number of “classes” of behaviors.
    Type: Application
    Filed: September 19, 2024
    Publication date: March 20, 2025
    Applicant: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Mohit Malu, Giulia Pedrielli, Gautam Dasarathy, Andreas Spanias
  • Publication number: 20250077923
    Abstract: Quantum circuits for QFT and Inverse QFT (IQFT) are disclosed that can be applied for use in signal and speech, analysis synthesis and compression. A unique method perceptual selection of QFT components is also outlined.
    Type: Application
    Filed: June 24, 2024
    Publication date: March 6, 2025
    Applicant: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Andreas Spanias, Aradhita Sharma, Leslie Miller, Glen Uehara
  • Patent number: 12244266
    Abstract: Various embodiments of a system and associated method for detecting and classifying faults in a photovoltaic array using graph-based signal processing.
    Type: Grant
    Filed: May 12, 2021
    Date of Patent: March 4, 2025
    Assignee: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Jie Fan, Sunil Rao, Gowtham Muniraju, Cihan Tepedelenlioglu, Andreas Spanias
  • Publication number: 20240249147
    Abstract: A system for Positive and Unlabeled (PU) learning is tailored specifically for a deep learning framework. The system incorporates an adaptive asymmetric loss function based on Modified Logistic Regression paired with a simple linear transform of an output. When only positive and unlabeled images are available for training, the system results in an inductive classifier where no estimate of the class prior is required.
    Type: Application
    Filed: January 22, 2024
    Publication date: July 25, 2024
    Inventors: Kristen Jaskie, Nolan Vaughn, Vivek Sivaraman Narayanaswamy, Sahba Zaare, Joseph Marvin, Andreas Spanias
  • Publication number: 20240153103
    Abstract: Tracking-based motion deblurring via coded exposure is provided. Fast object tracking is useful for a variety of applications in surveillance, autonomous vehicles, and remote sensing. In particular, there is a need to have these algorithms embedded on specialized hardware, such as field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs), to ensure energy-efficient operation while saving on latency, bandwidth, and memory access/storage. In an exemplary aspect, an object tracker is used to track motion of one or more objects in a scene captured by an image sensor. The object tracker is coupled with coded exposure of the image sensor, which modulates photodiodes in the image sensor with a known exposure function (e.g., based on the object tracking). This allows for motion blur to be encoded in a characteristic manner in image data captured by the image sensor. Then, in post-processing, deblurring is performed using a computational algorithm.
    Type: Application
    Filed: November 21, 2023
    Publication date: May 9, 2024
    Applicant: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Suren Jayasuriya, Odrika Iqbal, Andreas Spanias
  • Patent number: 11929086
    Abstract: Various embodiments of a system and methods for audio source separation via multi-scale feature learning are disclosed.
    Type: Grant
    Filed: December 14, 2020
    Date of Patent: March 12, 2024
    Assignees: Arizona Board of Regents on Behalf of Arizona State University, Lawrence Livermore National Security, LLC
    Inventors: Vivek Sivaraman Narayanaswamy, Andreas Spanias, Jayaraman Thiagarajan, Sameeksha Katoch
  • Patent number: 11880984
    Abstract: Tracking-based motion deblurring via coded exposure is provided. Fast object tracking is useful for a variety of applications in surveillance, autonomous vehicles, and remote sensing. In particular, there is a need to have these algorithms embedded on specialized hardware, such as field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs), to ensure energy-efficient operation while saving on latency, bandwidth, and memory access/storage. In an exemplary aspect, an object tracker is used to track motion of one or more objects in a scene captured by an image sensor. The object tracker is coupled with coded exposure of the image sensor, which modulates photodiodes in the image sensor with a known exposure function (e.g., based on the object tracking). This allows for motion blur to be encoded in a characteristic manner in image data captured by the image sensor. Then, in post-processing, deblurring is performed using a computational algorithm.
    Type: Grant
    Filed: June 15, 2021
    Date of Patent: January 23, 2024
    Assignee: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Suren Jayasuriya, Odrika Iqbal, Andreas Spanias
  • Publication number: 20230342611
    Abstract: A system for time series analysis using attention models is disclosed. The system may capture dependencies across different variables through input embedding and may map the order of a sample appearance to a randomized lookup table via positional encoding. The system may capture capturing dependencies within a single sequence through a self-attention mechanism and determine a range of dependency to consider for each position being analyzed. The system may obtain an attention weighting to other positions in the sequence through computation of an inner product and utilize the attention weighting to acquire a vector representation for a position and mask the sequence to enable causality. The system may employ a dense interpolation technique for encoding partial temporal ordering to obtain a single vector representation and a linear layer to obtain logits from the single vector representation. The system may use a type dependent final prediction layer.
    Type: Application
    Filed: July 5, 2023
    Publication date: October 26, 2023
    Inventors: Andreas Spanias, Huan Song, Jayaraman J. Thiagarajan, Deepta Rajan
  • Patent number: 11783847
    Abstract: Various embodiments of a system and associated method for audio source separation based on generative priors trained on individual sources. Through the use of projected gradient descent optimization, the present approach simultaneously searches in the source-specific latent spaces to effectively recover the constituent sources. Though the generative priors can be defined in the time domain directly, it was found that using spectral domain loss functions leads to good-quality source estimates.
    Type: Grant
    Filed: December 29, 2021
    Date of Patent: October 10, 2023
    Assignees: Lawrence Livermore National Security, LLC, Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Vivek Sivaraman Narayanaswamy, Jayaraman Thiagarajan, Rushil Anirudh, Andreas Spanias
  • Patent number: 11769055
    Abstract: Various embodiments of systems and methods for attention models with random features for multi-layered graph embeddings are disclosed.
    Type: Grant
    Filed: January 10, 2020
    Date of Patent: September 26, 2023
    Assignees: Arizona Board of Regents on Behalf of Arizona State University, Lawrence Livermore National Security, LLC
    Inventors: Uday Shanthamallu, Jayaraman Thiagarajan, Andreas Spanias, Huan Song
  • Patent number: 11765609
    Abstract: A system estimates spectral radius and leverages local updates from neighboring nodes in a wireless network to iteratively update state values of each node in the network and estimate a spectral radius of the network with guaranteed convergence. A method associated with the system method is a distributed method that efficiently converges to an invertible function of the spectral radius based only on local communications of the network for digital communication models in the presence and/or absence of packet loss, as opposed to conventional centralized methods.
    Type: Grant
    Filed: June 11, 2021
    Date of Patent: September 19, 2023
    Assignee: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Andreas Spanias, Cihan Tepedelenlioglu, Gowtham Muniraju
  • Publication number: 20230291203
    Abstract: A system reconfigures a photovoltaic array used in solar energy based on observed shading conditions to determine an optimal topology of the photovoltaic array to maximize power output. Specifically, the system is designed to reconfigure a photovoltaic array when the photovoltaic array is partially shaded. The system uses a neural network model to determine a topology that maximizes power output of the photovoltaic array based on irradiance data obtained from the photovoltaic array.
    Type: Application
    Filed: March 14, 2023
    Publication date: September 14, 2023
    Applicant: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Vivek Sivaraman Narayanaswamy, Rajapandian Ayyanar, Cihan Tepedelenlioglu, Andreas Spanias
  • Patent number: 11699079
    Abstract: A system for time series analysis using attention models is disclosed. The system may capture dependencies across different variables through input embedding and may map the order of a sample appearance to a randomized lookup table via positional encoding. The system may capture capturing dependencies within a single sequence through a self-attention mechanism and determine a range of dependency to consider for each position being analyzed. The system may obtain an attention weighting to other positions in the sequence through computation of an inner product and utilize the attention weighting to acquire a vector representation for a position and mask the sequence to enable causality. The system may employ a dense interpolation technique for encoding partial temporal ordering to obtain a single vector representation and a linear layer to obtain logits from the single vector representation. The system may use a type dependent final prediction layer.
    Type: Grant
    Filed: January 22, 2020
    Date of Patent: July 11, 2023
    Assignees: Arizona Board of Regents On Behalf Of Arizona State University, Lawrence Livermore National Security. LLC
    Inventors: Andreas Spanias, Huan Song, Jayaraman J. Thiagarajan, Deepta Rajan
  • Patent number: 11694431
    Abstract: Various embodiments of a cyber-physical system for providing cloud prediction for photovoltaic array control are disclosed herein.
    Type: Grant
    Filed: September 20, 2021
    Date of Patent: July 4, 2023
    Assignee: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Sameeksha Katoch, Pavan Turaga, Andreas Spanias, Cihan Tepedelenlioglu
  • Patent number: 11621668
    Abstract: Solar array fault detection, classification, and localization using deep neural nets is provided. A fault-identifying neural network uses a cyber-physical system (CPS) approach to fault detection in photovoltaic (PV) arrays. Customized neural network algorithms are deployed in feedforward neural networks for fault detection and identification from monitoring devices that sense data and actuate each individual module in a PV array. This approach improves efficiency by detecting and classifying a wide variety of faults and commonly occurring conditions (e.g., eight faults/conditions concurrently) that affect power output in utility scale PV arrays.
    Type: Grant
    Filed: May 6, 2020
    Date of Patent: April 4, 2023
    Assignee: Arizona Board of Regents on behalf of Arizona State University
    Inventors: Sunil Srinivasa Manjanbail Rao, Andreas Spanias, Cihan Tepedelenlioglu
  • Patent number: 11616471
    Abstract: Various embodiments for a connection topology reconfiguration technique for photovoltaic (PV) arrays to maximize power output under partial shading and fault conditions using neural networks are disclosed herein.
    Type: Grant
    Filed: February 21, 2020
    Date of Patent: March 28, 2023
    Assignee: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Vivek Sivaraman Narayanaswamy, Andreas Spanias, Rajapandian Ayyanar, Cihan Tepedelenlioglu
  • Publication number: 20230062528
    Abstract: Various embodiments of a system and associated method for detection of COVID-19 and other respiratory diseases through classification of audio samples are disclosed herein. The system utilizes features directly extracted from the coughing audio and develops automated diagnostic tools for COVID-19. In particular, the present application discusses a novel modification of a deep neural network architecture by using log-mel spectrograms of the audio excerpts and by optimizing a combination of binary cross-entropy and focal loss parameters. One embodiment of the system achieved an average validation AUC of 82.23% and a test AUC of 78.3% at a sensitivity of 80.49%.
    Type: Application
    Filed: August 12, 2022
    Publication date: March 2, 2023
    Applicant: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Sunil Rao, Vivek Sivaraman Narayanaswamy, Michael Esposito, Andreas Spanias
  • Patent number: 11586905
    Abstract: A method including receiving an input data set. The input data set can include one of a feature domain set or a kernel matrix. The method also can include constructing dense embeddings using: (i) Nyström approximations on the input data set when the input data set comprises the kernel matrix, and (ii) clustered Nyström approximations on the input data set when the input data set comprises the feature domain set. The method additionally can include performing representation learning on each of the dense embeddings using a multi-layer fully-connected network for each of the dense embeddings to generate latent representations corresponding to each of the dense embeddings. The method further can include applying a fusion layer to the latent representations corresponding to the dense embeddings to generate a combined representation. The method additionally can include performing classification on the combined representation. Other embodiments of related systems and methods are also disclosed.
    Type: Grant
    Filed: October 5, 2018
    Date of Patent: February 21, 2023
    Assignees: ARIZONA BOARD OF REGENTS ON BEHALF OF ARIZONA STATE UNIVERSITY, LAWRENCE LIVERMORE NATIONAL SECURITY, LLC
    Inventors: Huan Song, Jayaraman Thiagarajan, Andreas Spanias