Georgia Tech Research Corporation

Amazon Technologies, Inc.

University of Pittsburgh

James Rehg

Amit Kumar Agrawal

Ambrish Tyagi

Siddhartha Chandra

Shashank Tripathi

Joel Steven Schuman

Hiroshi Ishikawa

Gadi Wollstein

Visesh Chari

Yu-Ying Liu

Gregory D Abowd

Visesh Uday Kumar Chari

Omer T Inan

Panagiotis Tsiotras

Grady Williams

Karthir Prabhakar

Sangmin Oh

Ping Wang

Mei Chen

Md Mobashir Hasan Shandhi

Varol Burak Aydemir

Brian Goldfain

Paul Drews

Evangelos Theodorou

Systems and methods for measuring hemodynamic parameters with wearable cardiovascular sensing. An apparatus can include one or more sensors configured to measure an electrocardiogram signal of a user and one or more seismocardiogram (SCG) signals of the user, a memory and a processing system including one or more processors operatively coupled to the memory and the one or more sensors, and configured to receive the electrocardiogram and one or more SCG signals, and generate an assessment of heart health by determining one or more hemodynamic parameters based on the signals. The invention further includes a method for non-invasively monitoring heart health of a user including receiving an electrocardiogram signal from a first sensor of a wearable device, receiving one or more SCG signals from a second sensor of the wearable device, and generating the assessment of the heart health of the user by determining the one or more hemodynamic parameters.

Systems and methods for measuring hemodynamic parameters with wearable cardiovascular sensing

Techniques are generally described for object detection in image data. First image data comprising a three-dimensional model representing an object may be received. First background image data comprising a first plurality of pixel values may be received. A first feature vector representing the three-dimensional model may be generated. A second feature vector representing the first plurality of pixel values of the first background image data may be generated. A first machine learning model may generate a transformed representation of the three-dimensional model using the first feature vector. First foreground image data comprising a two-dimensional representation of the transformed representation of the three-dimensional model may be generated. A frame of composite image data may be generated by combining the first foreground image data with the first background image data.

Generation of synthetic image data using three-dimensional models

A method for determining a disease state transition path includes receiving a patient data having functional data and/or structural data related to a patient. Based on the patient data, a first disease state of a plurality of non-overlapping disease states each associated with a predetermined range of functional and/or structural degeneration values may be identified. A second, non-adjacent disease state of the plurality of disease states may be identified based on the patient data. A most probable path between the first disease state and the second disease state may be determined using a two dimensional continuous-time hidden Markov model.

Systems and methods for disease progression modeling

Techniques are generally described for object detection in image data. First image data comprising a first plurality of pixel values representing an object and a second plurality of pixel values representing a background may be received. First foreground image data and first background image data may be generated from the first image data. A first feature vector representing the first plurality of pixel values may be generated. A second feature vector representing a first plurality of pixel values of second background image data may be generated. A first machine learning model may determine a first operation to perform on the first foreground image data. A transformed representation of the first foreground image data may be generated by performing the first operation on the first foreground image data. Composite image data may be generated by compositing the transformed representation of the first foreground image data with the second background image data.

Generation of synthetic image data for computer vision models

An autonomous vehicle research system includes a vehicle having an attached frame and an engine. A sensing, control and data logging unit, mounted on the frame and in control communication with the engine senses vehicle operational parameters, controls the engine and to steering, and transmits operational data and log operational data. An operator control unit in communication with the sensing, control and data logging unit receives operational data from the sensing, control and data logging unit and presents visual real time display of the operational data. The operator control unit includes a manual cut-off switch that causes the engine to cease moving the vehicle. A remote control unit is manually switchable between a remote control mode and an autonomous control mode. In the remote control mode, the user controls the vehicle remotely. In the autonomous mode, the sensing, control and data logging unit controls the vehicle autonomously.

Autonomous vehicle research system

A method for providing improved performance in retrieving and classifying causal sets of events from an unstructured signal can comprise applying a temporal-causal analysis to the unstructured signal. The temporal-causal analysis can comprise representing the occurrence times of visual events from an unstructured signal as a set of point processes. An exemplary embodiment can comprise interpreting a set of visual codewords produced by a space-time-dictionary representation of the unstructured video sequence as the set of point processes. A nonparametric estimate of the cross-spectrum between pairs of point processes can be obtained. In an exemplary embodiment, a spectral version of the pairwise test for Granger causality can be applied to the nonparametric estimate to identify patterns of interactions between visual codewords and group them into semantically meaningful independent causal sets. The method can further comprise leveraging the segmentation achieved during temporal causal analysis to improve performance in categorizing causal sets.

Systems and methods for retrieving causal sets of events from unstructured signals

Systems and methods of analyzing an optical coherence tomography image of a retina are discussed. A 2-dimensional slice of the image can be aligned to produce an approximately horizontal image of the retina and an edge map based at least in part on the aligned slice. Also, at least one global representation can be determined based on a (multi-scale) spatial division, such as multi-scale spatial pyramid, on the slice and/or edge map. Creating the local features is based on the specified cell structure of the global representation. The local features can be constructed based on local binary pattern (LBP)-based features. Additionally, a slice can be categorized into one or more categories via one or more classifiers (e.g., support vector machines). Each category can be associated with at least one ocular pathology, and classifying can be based on the constructed global descriptors, which can include the LBP-based local descriptors.

Automated macular pathology diagnosis in three-dimensional (3D) spectral domain optical coherence tomography (SD-OCT) images

Growing community of inventors

Atlanta, GA, United States of America

James Rehg