Apple Inc.

Stephen P Jackson

Hung A Pham

Vinay R Majjigi

Karthik Jayaraman Raghuram

Ronald Keryuan Huang

Nikolas T Vitt

Anil K Kandangath

Adeeti V Ullal

Yann Jerome Julien Renard

Colin M Ely

Trevor J Ness

William C Lukens

Rex Tyler Ehman

Jiahui Liang

Shannon X Yang

William Scott Lee

Telford Earl Forgety, Iii

Mandeep Gill

Jeanny Wang

Alexander Singh Alvarado

Mrinal Agarwal

Anh N Phan

Shameek P Ganguly

Robert William Mayor

Lei Wang

Brad G Boozer

Ryan C Perkins

Michael P Dal Santo

Isaac Thomas Miller

Bharath Narasimha Rao

Umamahesh Srinivas

Richard B Warren

Xing Tan

Aditya Narain Srivastava

Pejman Lotfali Kazemi

Kumar Gaurav Chhokra

William J Bencze

James P Ochs

Jonathan M Beard

Craig H Mermel

Benjamin A Detwiler

Sunny K Chow

Sunny Kai Pang Chow

Parisa Dehleh Hossein Zadeh

David W Robison

Daniela M Deschamps

Christina Selle

Rebecca J Russell

Robin T Guers

Ryan P Kent

Sriram Venkateswaran

Henry Choi

Glenn D Macgougan

Ping-Ko Chiu

Omar Aziz

Tejal Bhamre

Megan L Banh

Alvaro J Melendez Hasbun

Ethan Goolish

Tianye Sun

Richard G Liu

David Ojeda Avellaneda

Vinay R Majigi

Lauren Schutz

Pedro O Varangot

Fatemeh Ghafoori

Rebecca L Clarkson

Cheng Jia

Yi-Wen Liao

Alexandru Popovici

Aniket Aranake

Yi Wen Liao

Paul D Bryan

Embodiments are disclosed for crash detection on one or more mobile devices (e.g., smartwatch and/or smartphone). In some embodiments, a method comprises: detecting, with at least one processor, a crash event on a crash device; extracting, with the at least one processor, multimodal features from sensor data generated by multiple sensing modalities of the crash device; computing, with the at least one processor, a plurality of crash decisions based on a plurality of machine learning models applied to the multimodal features; and determining, with the at least one processor, that a severe vehicle crash has occurred involving the crash device based on the plurality of crash decisions and a severity model.

Crash detection on mobile device

In an example method, a mobile device obtains sample data generated by one or more sensors over a period of time, where the one or more sensors are worn by a user. The mobile device determines that the user has fallen based on the sample data, and determines, based on the sample data, a severity of an injury suffered by the user. The mobile device generates one or more notifications based on the determination that the user has fallen and the determined severity of the injury.

Detecting falls using a mobile device

An electronic device includes a housing sidewall defining an opening and a display component, such as a display cover, disposed in the opening to form a gap between the housing sidewall and the display component. In at least one example, the cavity is defined by the sidewall and the display cover with the cavity in fluid communication with an external environment through the gap. In at least one example, an epoxy component at least partially defines the cavity and can be in direct contact with the housing sidewall.

Electronic device

An electronic watch may include a housing at least partially defining an interior cavity divided into at least a first volume and a second volume, a pressure-sensing component positioned within the first volume, a speaker positioned within the first volume, a processor positioned within the second volume, a battery positioned within the second volume, and a barometric vent that allows air pressure equalization between the first volume and an external environment.

Electronic watch with barometric vent

Described herein are techniques to enable a mobile device to perform multi-source estimation of an altitude for a location. A baseline altitude may be determined at ground level for a location and used to calibrate a barometric pressure sensor on the mobile device. The calibrated barometric pressure sensor can then estimate changes in altitude relative to ground level based on detected pressure differentials, allowing a relative altitude to ground to be determined. Baseline calibration for the barometric sensor calibration can be performed to determine an ambient ground-level barometric pressure.

Location of interest altitude and determining calibration points

Embodiments described herein provide for an electronic device comprising a set of classifiers that can determine whether the electronic device is likely on an airplane. Upon a determination that the electronic device is likely on an airplane, one or more wireless radios on the electronic device (e.g., an ultra-wideband ranging radio, a cellular radio, etc.) may be disabled or a prompt can be displayed to enable a user to place the device into airplane mode.

Context-based disabling wireless radios while on an airplane

An electronic device may include a motion sensor for detecting movement of the electronic device and a pressure sensor for detecting changes in elevation of the electronic device. Applications that run on the electronic device such as health and fitness applications may use motion sensor and pressure sensor data to track a user's physical activity. For example, processing circuitry in the electronic device may use the motion sensor to track a user's steps and the pressure sensor to track changes in the user's elevation. The processing circuitry may determine whether the user is climbing stairs based on the user's step rate and the user's changes in elevation. When the processing circuitry determines that the user is climbing stairs, the processing circuitry may use the pressure sensor and motion sensor to track and store the number of flights of stairs climbed by the user.

Electronic devices with pressure sensors for characterizing motion

The present disclosure relates to systems and methods of estimating energy expenditure of a user while swimming. A processor circuit of a user device can estimate a speed of the user based on a stroke rate and a stroke length. The processor circuit can estimate an efficiency of the user. The processor circuit can classify a swimming style of the user. The processor circuit can determine energy expenditure of the user based on the speed, the efficiency, and the style. The processor circuit can also detect glides of the user and adjust the energy expenditure.

Systems and methods of swimming calorimetry

Measurements can be obtained from sensors to determine a state of a device. The state can be used to determine whether to provide an alert. For example, after a first alert is provided, it can be determined that the device is not accessible to the user based on the determined state, and a second alert can be suppressed at a specified time after providing the first alert. The sensor measurements can be monitored after suppressing the second alert, and a state engine can detect a change in a state based on subsequent sensor measurements. If the state change indicates that the device is accessible to the user the second alert can be provided to the user. Alerts can be dismissed based on a change in state. A first device can coordinate alerts sent to or to be provided by a second device by suppressing or dismissing such alerts.

Sending smart alerts on a device at opportune moments using sensors

Aspects of the subject technology relate to electronic devices with pressure sensors. Pressure sensor occlusion may be detected based on a comparison of a variance of pressure data from the pressure sensor with a variance of acceleration data from an accelerometer of the device. If a ratio of the pressure data variance to the acceleration data variance is above a threshold, occlusion may be identified. Data from other sensors in the device or in an external device, or other features of the pressure data, may be used to identify a type of occlusion.

Pressure sensor occlusion mitigation systems and methods

Growing community of inventors

San Francisco, CA, United States of America

Stephen P Jackson