Verily Life Sciences LLC

Google Inc.

Raphael Cendrillon

Ali Shoeb

Mark Murphy

Christopher Towles Lengerich

Michele Morara

The present invention is directed to a wearable fitness and/or heart rate monitoring device which includes motion detecting sensor(s), a galvanic skin response (GSR) sensor, a user input interface, or any combination thereof. The device accounts for signal noise, produced when an individual passes thru varying exercise states, by filtering out the motion of the individual using a 3-axis accelerometer. The invention also provides for systems and methods of operating the monitor which extracts and/or stores true or correct heart rate values from the heartbeat waveform signal observed from a PPG.

Portable monitor for heart rate detection

Methods, systems, and apparatus, including computer-readable media, for making power adjustments in self-organizing networks. In some implementations, signal quality data is received for user devices that each communicate wirelessly with at least one base station in a set of base stations. Transmission power data indicating transmission power levels of the base stations is also received. Based on the signal quality data and the transmission power data, signal quality levels for the user devices are determined for different times corresponding to different combinations of transmission power levels of the base stations. Channel attenuation levels are estimated based on differences among signal quality levels of the multiple user devices corresponding to the different combinations of transmission power levels of the base stations. Operating parameters are provided to one or more of the base stations based on the estimated channel attenuation levels.

Power adjustments for self-organizing networks

Systems and methods are provided for determining the frequency of a cardiovascular pulse based on a photoplethysmographic measurement of blood in a portion of subsurface vasculature. A plurality of samples of the photoplethysmographic signal are obtained and a frequency spectrum determined based on a first set of the plurality of samples. A frequency is determined based on a maximum frequency component of the frequency spectrum. Further, a confidence level of the determined frequency of the maximum frequency component is determined based on the magnitude of the maximum frequency component and the overall energy in the frequency spectrum. A pulse rate is then determined by updating a predicted pulse rate of a second, earlier set of the plurality of samples based on the frequency of the maximum frequency component and the determined confidence level.

Method for improving accuracy of pulse rate estimation

A method of identifying network faults includes receiving subscriber statuses of customer premises equipment (CPE) of a communication network represented as a tree having a root node and leaf nodes. Each leaf node corresponds to a CPE. For each CPE, the method includes: (i) determining a conditional probability of the subscriber status of the CPE for each sub-tree in the network tree; (ii) determining a joint probability of the subscriber status of the CPE for every sub-tree in the network tree; (iii) determining a joint probability of the subscriber status of the CPE for every residual tree in the network tree; and (iv) determining a Bayesian posterior probability of a cut at each leaf node, given the subscriber status of the CPE. The method further includes determining a network node status topology indicating node statuses of nodes of the network tree based on the determined Bayesian posterior probabilities.

Growing community of inventors

Mountain View, CA, United States of America

Raphael Cendrillon