Detecting live tissues using signal analysis

Patent metadata

Field	Value
Publication number	US-10537253-B2
Application number	US-201615298003-A
Country	US
Kind code	B2
Filing date	Oct 19, 2016
Priority date	Feb 25, 2016
Publication date	Jan 21, 2020
Grant date	Jan 21, 2020

Abstract

In one embodiment, a method includes accessing first time-series data based on electromagnetic radiation in a first spectrum and second time-series data based on electromagnetic radiation in a second spectrum. The method also includes comparing the first time-series data with the second time-series data and determining, based on the comparison, (1) whether a stopping condition associated with a device has occurred or (2) whether a discarding condition associated with the first time-series data or the second time-series data has occurred.

First claim

What is claimed is:

1. A system comprising: a non-transitory computer-readable memory comprising instructions; and one or more processors coupled to the memory and operable to execute the instructions to:
access first time-series data based on electromagnetic radiation in a first spectrum detected by one or more sensors of a wearable computing device;
access second time-series data based on electromagnetic radiation in a second spectrum detected by the one or more sensors of the wearable computing device;
compare the first time-series data with the second time-series data;
determine, based on the comparison:
whether a stopping condition associated with the wearable device has occurred; or
whether a discarding condition associated with the first time-series data or the second time-series data has occurred; and

either
in response to a determination that the stopping condition associated with the client computing device has occurred, generate an instruction to reduce a power level of a bio-sensor of the wearable computing device; or
in response to a determination that a discarding condition associated with the first time-series data or the second time-series data has occurred, generate an instruction to discard at least some data gathered by the bio-sensor of the client computing device.

2. The system of claim 1 , wherein the wearable device comprises:
a mobile phone;
a smart watch;
a fitness tracker;
a wristband;
a necklace;
a head-worn device;
a piece of clothing;
a ring; or
a chest drape.

3. The system of claim 1 , wherein the wearable device comprises:
the non-transitory computer-readable memory;
the one or more processors; and
a first sensor configured to:
detect the electromagnetic radiation in the first spectrum, and
generate the first time-series data based on the detected electromagnetic radiation.

4. The system of claim 1 , wherein the first time-series data or the second time-series data comprise photoplethysmographic (“PPG”) data.

5. The system of claim 1 , wherein the one or more processors are further operable to execute the instructions to:
calculate a variance for the first time-series data within a specified timeframe; or
calculate a variance for the second time-series data within a specified timeframe.

6. The system of claim 1 , wherein the one or more processors operable to execute the instructions to compare the first time-series data with the second time-series data comprise one or more processors operable to execute the instructions to calculate a co-variance between the first time-series data and the second time-series data within a specified timeframe.

7. The system of claim 6 , wherein the one or more processors operable to execute the instructions to determine whether the stopping condition or the discarding condition has occurred comprise one or more processors operable to execute the instructions to:
calculate a local average co-variance between the first time-series data and the second time-series data, wherein the local average co-variance is calculated with an exponentially weighted moving average filter;
calculate a ratio of the local average co-variance to the co-variance between the first time-series data and the second time-series data within the specified timeframe; and
determine whether the calculated ratio changes by a magnitude that is greater than a threshold magnitude.

8. The system of claim 1 , wherein the one or more processors are further operable to execute the instructions to:
calculate a ratio of an average pulsatile amplitude associated with the first set of time series data to an average non-pulsatile value of the first set of time series data within a specified timeframe; and
determine whether the stopping condition or the discarding condition occurs by comparing the calculated ratio with a range of expected ratio.

9. The system of claim 1 , wherein the one or more processors are further operable to execute the instructions to:
calculate a mutual information (“MI”) value between the first time-series data and a delayed image of the first time-series data within a specified timeframe, wherein the delayed image is generated by adding a delay to each data point of the first time-series data; and
determine whether the stopping condition or the discarding condition has occurred by comparing the calculated MI value with a threshold MI value.

10. The system of claim 9 , wherein the delay is based on a heart rate of a user of the device.

11. The system of claim 1 , wherein the one or more processors are further operable to execute the instructions to turn off the device in response to a determination that the stopping condition has occurred.

12. The system of claim 1 , wherein the instruction to reduce a power level of the bio-sensor comprises an instruction for the bio-sensor to stop gathering data.

13. The system of claim 1 , wherein the one or more processors are further operable to execute the instructions to record time data associated with the determination that the discarding condition has occurred.

14. The system of claim 13 , wherein the one or more processors are further operable to execute the instructions to discard one or more data points associated with the first time-series data or the second time-series data, wherein the discarded data points were collected by the bio-sensor within a time period defined based at least in part on the recorded time data associated with the discarding condition.

15. The system of claim 1 , wherein the one or more processors are further operable to execute the instructions to turn on the wearable computing device in response to a triggering event, wherein the triggering event comprises:
a change in a signal generated by an accelerometer associated with the wearable computing device;
a change in a proximity sensor signal associated with the wearable computing device;
a change in a PPG signal associated with the wearable computing device; or
an interaction of a user with the wearable computing device.

16. One or more computer-readable non-transitory storage media embodying software that is operable when executed by a processor to:
access first time-series data based on electromagnetic radiation in a first spectrum detected by one or more sensors of a wearable computing device;
access second time-series data based on electromagnetic radiation in a second spectrum detected by the one or more sensors of the wearable computing device;
compare the first time-series data with the second time-series data;
determine, based on the comparison:
whether a stopping condition associated with the wearable device has occurred; or
whether a discarding condition associated with the first time-series data or the second time-series data has occurred; and

either
in response to a determination that the stopping condition associated with the client computing device has occurred, generate an instruction to reduce a power level of a bio-sensor of the wearable computing device; or
in response to a determination that a discarding condition associated with the first time-series data or the second time-series data has occurred, generate an instruction to discard at least some data gathered by the bio-sensor of the client computing device.

17. The media of claim 16 , wherein the software is further operable when executed by the processor to:
calculate a variance for the first time-series data within a specified timeframe; or
calculate a variance for the second time-series data within a specified timeframe.

18. The media of cla

Assignees

• Samsung Electronics Co Ltd

Inventors

• Jain Jawahar
• Wortham Cody
• Young James
• Sadi Sajid
• Mistry Pranav

Classifications

• A61B5/0022

  Monitoring a patient using a global network, e.g. telephone networks, internet · CPC title

• A61B5/02116 Primary

  of pulse wave amplitude (A61B5/02225 takes precedence) · CPC title

• A61B5/0086

  using infrared radiation · CPC title

• G16H40/63 Primary

  for local operation · CPC title

• A61B5/6898

  Portable consumer electronic devices, e.g. music players, telephones, tablet computers · CPC title