Bodymedia, Inc.

Carnegie Mellon University

Google Inc.

Other

X Development LLC

Aliphcom

Zivio Technologies LLC

Hewlett-packard Development Company, L.p.

Nextsense, Inc.

John Michael Stivoric

Eric Teller

Christopher D Kasabach

Christopher D Pacione

David Andre

Jonathan Farringdon

Suresh Vishnubhatla

Raymond Pelletier

Scott Klaus Boehmke

Scott A Safier

John L Moss

Craig B Liden

Chris Dominick Kasabach

Francine Duskey Gemperle

Margaret A McCormack

Jonathan Alexander Ross

James A Gasbarro

John A Monocello, Iii

Vanessa Sica

Jeffrey Francis Williams

Vanessa Sica Kasabach

James Hanlon

Francine Gemperle

Gregory T Kovacs

Daniel P Siewiorek

Asim Smailagic

Drew Anderson

Michelle Christensen

Stacy L Wolff

Kevin L Massaro

Valiuddin Y Ali

Russell N Mirov

Lee E Weiss

Jacques L Gagne

Raymond Louis Gradwohl

Kenneth G Robertson

Christopher Edward Hoover

Ryan Butterfoss

Grace Taixi Brentano

Rebecca Radkoff

Nisarg Vyas

Jason Williams

Jay Kothari

Randall W Casciola

Mark Handel

Mark Zaremsky

Melvin Chua

Neal Spruce

Steve Shassberger

Anthony B Rorke

Ajay Chaturvedi

Nick Robertson

Lam Thanh Nguyen

Salil Vijaykumar Pradhan

Gennady Yakovievitch Neplotnik

Scott J Cape

Zoey Zweber

Donna Wolf

Scott K Boehmke

Steve Menke

Eric Hsiung

Christopher Hoover

Margaret A Mccormack

Scott Safier

Kenneth Robertson

A method for allocating resources for a machine learning model is disclosed. A machine learning model to be executed on a special purpose machine learning model processor is received. A computational data graph is generated from the machine learning model. The computational dataflow graph represents the machine learning model which includes nodes, connector directed edges, and parameter directed edges. The operations of the computational dataflow graph is scheduled and then compiled using a deterministic instruction set architecture that specifies functionality of a special purpose machine learning model processor. An amount of resources required to execute the computational dataflow graph is determined. Resources are allocated based on the determined amounts of resources required to execute the machine learning model represented by the computational dataflow graph.

Allocating resources for a machine learning model

Implementations are directed to improving network anti-fragility. In some aspects, a method includes receiving parameter data from a network of nodes, the parameter data comprising attributes, policies, and action spaces for each node in the network of nodes; configuring one or more interruptive events on one or more nodes included in the network of nodes; determining a first action of each node in the network of nodes in response to the one or more interruptive events; determining a first performance metric, for each node, that corresponds to the first action, wherein the first performance matric is determined based on at least a first reward value associated with the first action; continuously updating the first action in an iterative process to obtain a final action, wherein a performance metric corresponding to the final action satisfies a performance threshold, and transmitting the final action for each node to the network of nodes.

Anti-fragile network

The technology involves scaffold structures used for in-ear sensor systems. Such systems that can perform biometric signal detection or act as a human-computer interface. Scaffolding arrangements minimize the amount of material placed in the ear while providing a secure fitting device that can be worn for hours, days or longer in order to provide maximal benefit to the wearer. The scaffolding includes a 'C'-shaped arcuate curvature for at least part of the housing. This configuration can act as a natural leaf spring to help maintain the housing in contact with different points along the ear. Sensors are located along various points of the scaffolding for use in different diagnostic situations. Different components of an on-board sensor input and processing system can be distributed along different parts of the scaffolding. Such structures beneficially minimize ambient sound occlusion and avoid the need of an exterior strap or clip worn around the ear.

Minimal material ear sensor system

Systems and devices are disclosed herein that provide or relate to modular accessory devices for a wearable device, such as a glasses-style head-mountable device (HMD). Illustrative systems may include a first frame component having an accessory slot accessible via an entry point on a transverse surface of the first frame component, a second frame component movably coupled to the first frame component, and one or more accessory devices that each have a slot-mating feature shaped for insertion into and removal from the accessory slot via the entry point. The second frame component may be movable between a first position in which the second frame component blocks access to the entry point, and a second position in which the second frame component allows access to the entry point.

Modular accessory systems for wearable devices

The methods and systems described herein may involve determining at least one lifeotype of at least one individual, analyzing the at least one lifeotype, and delivering content to at least one individual based on the analysis. The methods and systems described herein may involve providing a game, determining at least one lifeotype of at least one player of the game, analyzing the at least one lifeotype, and affecting the game play based on the analysis. The methods and systems described herein may involve providing an interactive space, determining at least one lifeotype of at least one individual in the space, analyzing the at least one lifeotype, and modifying at least one attribute of the space based on the analysis.

Using aggregated sensed data of individuals to predict the mental state of an individual

Wearable monitoring device

Systems and methods using a wearable device to determine an individuals daily routine

The invention comprises systems, methods, and devices capable of deriving and predicting the occurrence of a number of physiological and conditional states and events based on sensed data. The systems, methods, and devices utilize the predicted and derived states for a number of health and wellness related applications including the administering therapy and providing actionable data for lifestyle and health improvement.

Apparatus using temperature data to make predictions about an individual

The invention comprises an apparatus for determining the contextual or physiological status of the individual wearing the apparatus. The apparatus is designed to be consumable or disposable. In most embodiments the invention comprises an adhesive housing. In some embodiments, two different sensors are secured to the housing. The apparatus is in electronic communication with a processing unit that can derive analytical status data by using the data received from the two sensors. In some embodiments, the processing unit is programmed to control other devices, or is programmed to trigger an event. In still other embodiments, the apparatus is in electronic communication with a separate computing device, which may contain the processing unit.

Adhesively mounted apparatus for determining physiological and contextual status

Various methods and apparatuses for measuring a state parameter of an individual using signals based on one or more sensors are disclosed. In one embodiment, a first set of signals is used in a first function to determine how a second set of signals is used in one or more second functions to predict the state parameter. In another embodiment, first and second functions are used where the state parameter or an indicator of the state parameter may be obtained from a relationship between the first function and the second function. The state parameter may, for example, include calories consumed or calories burned by the individual. Various methods for making such apparatuses are also disclosed.

Method and apparatus for identifying and reporting a physiological condition of an individual utilizing physiological and contextual parameters

Method and apparatus for deriving and reporting a physiological status of an individual utilizing physiological parameters and user input

The invention is a wireless communications device, such as a cellular telephone, having sensors to generate data indicative of a physiological or contextual parameters of a user. A processor on the wireless communications device is adapted derive physiological state information of the user from the contextual or physiological parameters. The apparatus may include a central monitoring unit remote from the sensors for storing data and transmitting data to a recipient.

Multi-sensor system, device, and method for deriving human status information

Growing community of inventors

Pittsburgh, PA, United States of America

John Michael Stivoric