General Electric Company

Nbcuniversal Media, LLC

General Electric Capital Corporation

Corey Nicholas Bufi

Peter Henry Tu

Piero Patrone Bonissone

Christopher Donald Johnson

Dashan Gao

Naresh Sundaram Iyer

John Michael Lizzi

Kunter Seref Akbay

Ting Yu

Kedar Anil Patwardhan

Yi Yao

Viswanath Avasarala

Paul Edward Cuddihy

Sahika Genc

Catherine Mary Graichen

Michael Shane Wilkinson

Zhaohui Harry Sun

Budhaditya Deb

Brian Nathan Dingman

Anthony James Hoogs

Anthony Christopher Anderson

Snehil Gambhir

Roderic Greene Collins

Kimberley Marie Mangino

Aaron Shaw Markham

Jeffrey Michael Ashe

Karl Dean Minto

Sidharth Abrol

Wrichik Basu

Jenny Marie Weisenberg

Prabhanjana Kalya

Melvin Kurt Simmons

David Anthony Czarnecki

Jenny Marie Weisenberg Williams

Nisam Palakkavalappil Rahiman

Seref Akbay Kunter

John Michael Jr Lizzi

A non-transitory computer-readable storage medium storing one or more processor-executable instructions wherein the one or more instructions, when executed by a processor of a controller, cause acts to be performed including receiving signals representative of pressure between respective compressor blade tips and a casing of a compressor at one or more stages, generating multiple patterns based on a permutation entropy window and the signals, identifying multiple pattern categories in the multiple patterns, determining a permutation entropy based on the multiple patterns and the multiple pattern categories, predicting an anomaly in the compressor based on the permutation entropy, comparing the multiple pattern categories to determined permutations of pattern categories when an anomaly is present in the compressor, and predicting a category of the anomaly based on the comparison of the multiple pattern categories to the determined permutation of pattern categories.

Systems and methods for compressor anomaly prediction

The system and method disclosed herein provides an integrated and automated workflow, sensor, and reasoning system that automatically detects breaches in protocols, appropriately alarms and records these breaches, facilitates staff adoption of protocol adherence, and ultimately enables the study of protocols for care comparative effectiveness. The system provides real-time alerts to medical personnel in the actual processes of care, thereby reducing the number of negative patient events and ultimately improving staff behavior with respect to protocol adherence.

System and method for protocol adherence

A method and system for identifying a source of a copied work that in one embodiment includes obtaining at least some portions of a reference work, collecting at least some portions of the suspect work, matching the suspect work with the reference work, wherein the matching includes temporally aligning one or more frames of the reference work and the suspect work, spatially aligning frames of the reference work and the suspect work, and detecting forensic marks in the suspect work by spatiotemporal matching with the reference work.

System and method for forensic analysis of media works

Methods, systems and non-transitory computer readable mediums that store instructions executable by one or more processors to perform a method for detecting a fallen person are presented. The present technique includes identifying a reference plane and a reference line in a designated space monitored using one or more range-controlled radars. These radars are coupled to one or more antennas configured to define fields of the range-controlled radars to one or more portions of the designated space, where at least one portion corresponds to the reference plane. The range-controlled radars detect presence of one or more parameters corresponding to a subject disposed in the designated space. The parameters, for example, include one or more physiological parameters and one or more motion parameters. The range-controlled radars then identify the subject as the fallen person if the one or more physiological parameters corresponding to the subject are detected proximate the reference plane.

Radar based systems and methods for detecting a fallen person

A method and system for detecting a fallen person is described. An initial range image corresponding to a field of view of a DAS is generated. Further, a reference plane disposed in the field of view is identified. Additionally, one or more regions in the initial range image indicative of one or more objects disposed above the reference plane in the field of view are determined. Further, the DAS regenerates a range image corresponding to the field of view after a determined time period. The regenerated range image is compared with the initial range image to determine if the regenerated range image comprises a new object disposed above the reference plane. The new object is determined to be the fallen person if a height of the new object is less than a determined height and a volume and/or a surface area of the new object is greater than a determined value.

Method and system for detecting a fallen person using a range imaging device

A system for generating a threat alert in an infrastructure component is provided. The system includes multiple acoustic sensors configured to detect a signal. The system also includes a processing circuitry including at least one analog-to-digital converter configured to digitize the signal. The processing circuitry also includes a digital signal processor configured to process the acoustic signal in a sequential routine. The sequential routine includes a noise filtering routine configured to filter background noise from the acoustic signal and generate a filtered signal. The sequential routine also includes a source identification routine configured to identify a source generating the acoustic signal based upon the filtered signal. The sequential routine further includes a threat analysis routine configured to detect a threat based upon the source identified and generate a threat level signal.

System and method for generating a threat alert

The invention provides a method and system to simulate a process of discrete tasks having a plurality of available resources associated therewith. The system may comprise a model database to store a plurality of models, each model including a plurality of task and resource parameters; a model portion in communication with the model database and configured to receive commands from a user, to retrieve one of the plurality of models and corresponding task and resource parameters in response to a user command, to receive input data corresponding to attributes of one or more task and resource parameters from a business database system, and to generate a simulation model based on the selected business database system and the input data; and a model server to perform a simulation of the process by processing the simulation model and to generate an output data file containing output data representative of the simulation.

System and method for simulating a discrete event process using business system data

The invention provides a system and method for identifying text in a word set. The method may include retrieving a target term set including a plurality of target terms; retrieving the word set including a plurality of text words; normalizing target terms in the target term set to generate normalized terms; normalizing text words in the word set to generate normalized words; comparing the normalized terms with the normalized words to determine (1) a first match between a first normalized term and a first normalized word; and (2) a second match between a second normalized term and a second normalized word. The method may further include determining a distance between a text word position of the first normalized word and a text word position of the second normalized word to determine if any relative positions satisfy threshold criteria, and identifying a first text word position and a second text word position as constituting possible identified text once a relative position of the text word position of the first normalized word and a text word position of the second normalized word satisfies the threshold criteria.

Method and system for event phrase identification

Growing community of inventors

Troy, NY, United States of America

Corey Nicholas Bufi