Processing electromagnetic interference signal using machine learning

Patent metadata

Field	Value
Publication number	US-10141929-B2
Application number	US-201615153573-A
Country	US
Kind code	B2
Filing date	May 12, 2016
Priority date	Aug 13, 2013
Publication date	Nov 27, 2018
Grant date	Nov 27, 2018

Abstract

In one embodiment, a method includes receiving, by an electrode of a device, a signal from a user's body. The received signal is based on an electromagnetic interference signal generated by an object that is external to the device. The method further includes determining, using machine learning applied to the received signal, one or more of the following: an identity of the object, an interaction between the user and the object, or a context surrounding the device.

First claim

What is claimed is:

1. A method comprising:
receiving, by an electrode of a device, a signal from a body of a user, the signal based on an electromagnetic interference signal generated by an object that is external to the device;
determining, by a computing device, one or more of the following based on machine learning applied to the received signal:
an identity of the object;
an interaction between the user and the object; or
a context surrounding the device; and
optimizing, based on the received signal, a classification model identifying a plurality of fingerprints, wherein optimizing the classification model comprises:
identifying a fingerprint corresponding to the received signal;
presenting to the user an identification of the fingerprint corresponding to the received signal;
receiving, from the user, input identifying whether the fingerprint corresponds to the received signal; and
updating the classification model based on the input.

2. The method of claim 1 , wherein identifying the object comprises:
accessing information in a data store associating the object with an electromagnetic interference signal or an aspect of an electromagnetic interference signal;
comparing the received signal with the information;
determining, based on the comparison, a similarity between the received signal and the data store; and
in response to the determined similarity, identifying the object associated with the information.

3. The method of claim 2 , further comprising using one or more machine learning algorithms and the received signal to update the information in the data store.

4. The method of claim 1 , wherein the electrode is part of a wearable device.

5. The method of claim 1 , further comprising identifying, based on the signal, a contact between the user and the object.

6. The method of claim 1 , wherein the object comprises an electronic device.

7. The method of claim 6 , wherein identifying, based on the signal, the device further comprises identifying an operating mode of the device.

8. The method of claim 1 , further comprising providing, based on the identified object, a notification to the user.

9. The method of claim 1 , wherein the machine learning applied to the received signal comprises the classification model identifying a plurality of fingerprints.

10. The method of claim 9 , wherein at least one of the plurality of fingerprints identifies one or more of:
a particular device;
a particular context of a particular device; or
a particular action of a particular device.

11. The method of claim 1 , further comprising determining, based on the received signal, one or more boundaries for one or more fingerprints of the classification model.

12. An apparatus comprising:
an electrode; and
one or more processors coupled to the electrode and configured to:
determine that a signal received by the electrode from a body of a user is based on an electromagnetic interference signal generated by an object that is external to the apparatus;
determine one or more of the following based on machine learning applied to the received signal:
an identity of the object;
an interaction between the user and the object; or
a context surrounding the apparatus; and

optimize, based on the received signal, a classification model identifying a plurality of fingerprints, wherein optimizing the classification model comprises:
identifying a fingerprint corresponding to the received signal;
presenting to the user an identification of the fingerprint corresponding to the received signal;
receiving, from the user, input identifying whether the fingerprint corresponds to the received signal; and
updating the classification model based on the input.

13. The apparatus of claim 12 , wherein the apparatus further comprises a wearable device.

14. The apparatus of claim 12 , wherein the machine learning applied to the received signal comprises a classification model identifying the plurality of fingerprints.

15. The apparatus of claim 14 , wherein at least one of the plurality of fingerprints identifies one or more of:
a particular device;
a particular context of a particular device; or
a particular action of a particular device.

16. One or more non-transitory computer-readable storage media embodying logic that is operable when executed by one or more processors to:
determine that a signal received by an electrode of a device from a body of a user is based on an electromagnetic interference signal generated by an object that is external to the device; and
determine one or more of the following based on machine learning applied to the received signal:
an identity of the object;
an interaction between the user and the object; or
a context surrounding the device; and

optimize, based on the received signal, a classification model identifying a plurality of fingerprints, wherein optimizing the classification model comprises:
identifying a fingerprint corresponding to the received signal;
presenting to the user an identification of the fingerprint corresponding to the received signal;
receiving, from the user, input identifying whether the fingerprint corresponds to the received signal; and
updating the classification model based on the input.

17. The method of claim 1 , wherein at least one of the plurality of fingerprints is associated with at least one of: a particular computing device, a particular location of the particular computing device, or a particular time.

18. The apparatus of claim 12 , wherein at least one of the plurality of fingerprints is associated with at least one of: a particular computing device, a particular location of the particular computing device, or a particular time.

19. The media of claim 16 , wherein at least one of the plurality of fingerprints is associated with at least one of: a particular computing device, a particular location of the particular computing device, or a particular time.

20. The media of claim 16 , wherein at least one of the plurality of fingerprints identifies one or more of:
a particular device;
a particular context of a particular device; or
a particular action of a particular device.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Rakova Bogdana
• Digman Mike
• Schoessler Philipp
• Salvador Martin
• Pacareu Sergi Consul
• Bau Olivier

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F1/163 Primary

  Wearable computers, e.g. on a belt · CPC title

• G06F3/046

  by electromagnetic means · CPC title

• G06N99/005

  Physics · mapped topic

• H03K17/962 Primary

  Capacitive touch switches · CPC title