Processing electromagnetic interference signal using machine learning
AssigneeSamsung Electronics Co., Ltd.
InventorsBogdana Rakova, Mike Digman, Philipp Schoessler, Martin Salvador, Sergi Consul Pacareu, Olivier Bau
Life of this patent
Estimating the term…
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.
Claims20
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.
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.
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.
Dependencies are inferred from the claim text.