University of Washington

Ironwood Cyber Inc.

Eric C Larson

Shwetak N Patel

James Anthony Fogarty

Jon E Froehlich

Mitchell A Thornton

Gabriel Adam Cohn

Mayank Goel

Timothy B Campbell

Michael Taylor

Lilian De Greef

James A Taylor

Nathan Srirama

Aviraj Sinha

Theodore Manikas

James W Stout

Shih-Yen Liu

Tien-Jui Lee

Erik Gabrielsen

Travis Siems

Ian Johnson

Described herein are methods, systems, and platforms comprising neural networks for control system anomaly detection.

Control system anomaly detection using neural network consensus

By monitoring pressure transients in a liquid within a liquid distribution system using only a single sensor, events such as the opening and closing of valves at specific fixtures are readily detected. The sensor, which can readily be coupled to a faucet bib, transmits an output signal to a computing device. Each such event can be identified by the device based by comparing characteristic features of the pressure transient waveform with previously observed characteristic features for events in the system. These characteristic features, which can include the varying pressure, derivative, and real Cepstrum of the pressure transient waveform, can be used to select a specific fixture where a valve open or close event has occurred. Flow to each fixture and leaks in the system can also be determined from the pressure transient signal. A second sensor disposed at a point disparate from the first sensor provides further event information.

Sensing events affecting liquid flow in a liquid distribution system

Gyroscope data can be used to generate upsampled signal. Multiple mobile devices are spaced apart from each other in a spatial arrangement. Each mobile device includes a gyroscope sensor to detect mechanical vibrations caused by signals originating within a vicinity of a mobile device that includes the gyroscope sensor. Each mobile device includes one or more respective processors to receive representations of the mechanical vibrations sensed by the gyroscope sensor at a sampling frequency, and transmit the representations received at the sampling frequency as a respective vibration signal associated with sampling times. The signal processor is coupled to the multiple mobile devices. The signal processor generates a processed upsampled signal by interleaving the vibration signal received from each mobile device and processing the interleaved signal using one or more machine learning filters, and transmitting the processed upsampled signal.

Generating upsampled signal from gyroscope data

Examples of the present invention utilize principal component analysis (PCA) to detect cough sounds in an audio stream. Comparison of all or portions of the audio stream with a cough model may be conducted. The cough model may include a number of basis vectors may be based on initial portions of known coughs. The initial portions may be non-user specific, and accordingly the cough model may be used to detect coughs across individuals. Moreover, examples of the present invention may reconstruct the cough sounds from stored features such that the cough sounds are reconstructed but the reconstruction techniques used may be insufficient to reconstruct speech sounds that may also have been recorded, which may increase user privacy.

Cough detecting methods and devices for detecting coughs

Systems, methods, and devices are provided for estimating bilirubin levels. In one aspect, a method for estimating the level of bilirubin in a patient includes receiving image data for at least one image including a region of the patient's skin and a color calibration target. Color-balanced image data for the skin region is generated based on a subset of the image data corresponding to the color calibration target and the skin region. The bilirubin level in the patient is estimated based on the color-balanced image data for the skin region.

Systems, devices, and methods for estimating bilirubin levels

Devices, system, and methods generate expiratory flow-based pulmonary function data by processing a digital audio file of sound of a subject's forced expiratory maneuver. A mobile device configured to generate expiratory flow-based pulmonary function data includes a microphone, a processor, and a data storage device. The microphone is operable to convert sound of the subject's forced expiratory maneuver into a digital data file. The processor is operatively coupled with the microphone. The data storage device is operatively coupled with the processor and stores instructions that, when executed by the processor, cause the processor to process the digital data file to generate expiratory flow-based pulmonary function data for assessing pulmonary function of the subject. The sound of the subject's forced expiratory maneuver can be converted into the digital data file without contact between the subject's mouth and the mobile device.

Sound-based spirometric devices, systems and methods

Examples of automatic valve shutoff systems are described which may include an actuation device including an actuator and a valve attachment portion. The valve attachment portion may be configured for attachment with an existing valve in a fluid or compressible gas supply line. The system may further include a controller coupled to the actuation device, wherein the controller is configured to initiate a valve shutoff process in response to a wireless signal. Wake-up circuitry may be coupled to the controller and configured to monitor the supply line for vibrations and activate the controller in response to the vibrations.

Automatic valve shutoff device and methods

Growing community of inventors

Seattle, WA, United States of America

Eric C Larson