Sidney R Primas

20220176545, Jun 9, 2022

Dec 6, 2020

17/113059

- San Francisco CA, US
Michael Dean Achelis - Walnut Creek CA, US
Lina Avancini Colucci - Los Altos CA, US
Sidney Rafael Primas - Los Altos CA, US
Andrew James Weitz - Bishop CA, US

B25J 9/00
G06F 3/01
G06N 20/00

A mobility augmentation system monitors a user's motor intent data and augments the user's mobility based on the monitored motor intent data. A machine-learned model is trained to identify an intended movement based on the monitored motor intent data. The machine-learned model may be trained based on generalized or specific motor intent data (e.g., user-specific motor intent data). A machine-learned model initially trained on generalized motor intent data may be re-trained on user-specific motor intent data such that the machine-learned model is optimized to the movements of the user. The system uses the machine-learned model to identify a difference between the user's monitored movement and target movement signals. Based on the identified difference, the system determines actuation signals to augment the user's movement. The actuation signals determined can be an adjustment to a currently applied actuation such that the system optimizes the actuation strategy during application.

20160220122, Aug 4, 2016

Jan 25, 2016

15/006096

Michael Edward Luna - Broadmoor Village CA, US
Thomas Alan Donaldson - Drews Cottage, GB
John M. Stivoric - Pittsburgh PA, US
Sidney Primas - Palo Alto CA, US

AliphCom - San Francisco CA

A61B 5/0205
A61B 5/11
A61B 5/00

One or more wearable devices may measure real-time blood pressure in a body using signals from multiple sensors including but not limited to a multi-axis accelerometer, a bioimpedance (BI) sensor, a capacitive touch sensor, an electrocardiography sensor (ECG), a ballistocardiograph sensor (BCG), a photoplethysmogram (PPG), a pulse oximetery sensor, and a phonocardiograph sensor (PCG), for example. Accelerometry data (e.g., from a multi-axis accelerometer or BCG sensor) may be used to derive effects of acceleration (e.g., gravity) on changes in blood pressure (e.g., due to changes in blood volume as measured using BI signals). The accelerometry data may be used to determine a baseline value for BI voltage signals that are indicative of diastolic and systolic blood pressure (e.g., in mmHg). Combinations of methods, such as BCG, ECG, PPG, blood pressure Pulse Wave and others may be used to determine pulse transit time (PTT), pulse arrival time (PAT), and pre-ejection period (PET). The wearable devices may be born on one or more body parts, such as the wrist, arm, leg, ankle, neck, chest, thorax, head, and ear.

20160066852, Mar 10, 2016

Nov 4, 2014

14/121948

Sylvia Hou-Yan Cheng - San Francisco CA, US
Michael Edward Smith Luna - San Jose CA, US
Sidney Primas - Mountain View CA, US
John M. Stivoric - Pittsburgh PA, US

AliphCom - San Francisco CA

A61B 5/00
A61B 5/117
A61B 5/16
A61B 5/04
A61B 5/0245
A61B 5/08

A strap band including a flexible wire bus having electrodes and wires coupled with the electrodes is described. The strap band may be coupled with a device that includes circuitry configured to drive signals on some of the electrodes and receive signals from pickup electrodes. Driven electrodes are coupled with drive signals at different frequencies that may be varied to increase or decrease signal penetration depth to sense different body structures positioned at different depths in a body portion be sensed. Different frequencies for different types of measurements may be selected to optimize sensing different biometric parameters, such as bio-impedance, galvanic skin response, hear rate, respiration, heart rate variability, hydration, inflammation, stress, and arousal in sympathetic nervous system at different depths (e.g., layers or strata) in the body portion, for example. A first set of driven/pickup electrodes may sense different biometric parameters than a second set of driven/pickup electrodes.

20150359491, Dec 17, 2015

Nov 4, 2014

14/121947

Michael Edward Smith Luna - San Jose CA, US
Sidney Primas - Mountain View CA, US
John M. Stivoric - Pittsburgh PA, US
Chris Singleton - Palm Harbor PA, US
Piyush Savalia - San Francisco CA, US
Prasad Panchalan - San Francisco CA, US
Sheila Nabanja - San Jose CA, US
Sylvia Hou-Yan Cheng - San Francisco CA, US
Ilyas Mohammad - San Francisco CA, US
Sumit Sharma - San Francisco CA, US

AliphCom - San Francisco CA

A61B 5/00
A61B 5/16
A61B 5/0205

Embodiments relate generally to a wearable device implementing a touch-sensitive interface in a metal pod cover and/or bioimpedance sensing to determine physiological characteristics, such as heart rate. According to an embodiment, a method includes receiving an amplified signal including a portion of the physiological-related signal component including data representing a physiological characteristic, the amplified signal being derived from bioimpedance signal based on an impedance value of a tissue, and identifying a magnitude of a portion of the physiological-related signal component. Also, the method can compare the magnitude of the portion against another magnitude of a data model (e.g., in a time-domain) to form a matched value. Also, the method can determine a confidence indicator value representative of a degree of likelihood that the matched value is representative of the physiological characteristic, and determining a value of the physiological characteristic based on the matched value and the confidence indicator value.

20150297145, Oct 22, 2015

Nov 4, 2014

14/121939

Michael Edward Smith Luna - San Jose CA, US
Sidney Primas - Mountain View CA, US
John M. Stivoric - Pittsburgh PA, US
Chris Singleton - Palm Harbor FL, US
Piyush Savalia - San Francisco CA, US
Prasad Panchalan - San Francisco CA, US
Sheila Nabanja - San Jose CA, US
Sylvia Hou-Yan Cheng - San Francisco CA, US
Ilyas Mohammad - San Francisco CA, US
Sumit Sharma - San Francisco CA, US

AliphCom - San Francisco CA

A61B 5/00
A61B 5/16
A61B 5/0205

Embodiments relate generally to a wearable device implementing a touch-sensitive interface in a metal pod cover and/or bioimpedance sensing to determine physiological characteristics, such as heart rate. According to an embodiment, a wearable device and method includes determining a drive current signal magnitude for a bioimpedance signal to capture data representing a physiological-related component, and selecting the drive current signal magnitude as a function of an impedance of a tissue. Further, the method can include driving the bioimpedance signal to that are configured to convey the bioimpedance signal to the tissue. Also, the method can receive the sensor signal from the tissue, adjust a gain for an amplifier, and apply the gain to data representing the physiological-related component. The method can include generating an amplified signal to include a portion of the physiological-related signal component that includes data representing a physiological characteristic.

20150282768, Oct 8, 2015

Nov 4, 2014

14/121943

Michael Edward Smith Luna - San Jose CA, US
Sidney Primas - Mountain View CA, US
John Stivoric - San Francisco CA, US

AliphCom - San Francisco CA

A61B 5/00
A61B 5/0205
A61B 5/053

Embodiments relate generally to wearable computing devices in capturing and deriving physiological characteristic data. More specifically, disclosed are one or more electrodes and methods to determine physiological characteristics using a wearable device (or carried device) and one or more sensors. In one embodiment, a method includes determining a drive signal magnitude for a bioimpedance signal to capture data representing a physiological-related component and selecting the drive signal magnitude as a function of an impedance of a tissue. The bioimpedance signal can be applied to electrodes that are configured to convey the bioimpedance signal to the tissue. In some cases, data representing a value a signal-to-noise (“SNR”) ratio may be adapted to form an adaptive signal-to-noise value. A portion of a received bioimpedance signal may be detected, the received bioimpedance signal being based on the adaptive signal-to-noise value. A physiological characteristic can be derived.