ELECTRONIC SWITCH FOR CONTROLLING A DEVICE IN DEPENDENCY ON A SLEEP STAGE
First Claim
1. An electronic switch for controlling a device by switching a function of the device at least in dependency on a sleep stage of a human, the switch comprisingan EEG data interface configured to receive brain activity data from an EEG sensor configured to monitor electrical activity of the brain of the human during a training phase,an EEG sleep classifier configured to classify sleep stages of the human from the received brain activity data,a body data interface configured to receive body activity data from an alternative sensor configured to monitor a bodily function of the human both during the training phase and during a subsequent usage phase, the alternative sensor being different from the EEG sensor,an alternative sleep classifier and a machine learning system, the machine learning system being configured to train the alternative sleep classifier to classify a sleep stage of the human from the received body activity data, the learning system using sleep stages classified by the EEG sleep classifier and concurrent body activity data received from the alternative sensor as training data, wherein in the usage phase the device is controlled in dependency on sleep stages of the human classified by the alternative sleep classifier, andcontrol logic configured to at least determine that the classified sleep stage is one of a set of particular sleep stages and to switch a function of the device at least in dependency on said determination,the switch further comprising:
- a statistical unit configured todetermine a statistical measure of the received body activity data during the training phase and store it as a reference measure, and todetermine the statistical measure of the received body activity data during the usage phase; and
a drift detection unit configured to detect a drift of the statistical measure determined during the usage phase and the reference measure, and upon detecting the drift signaling a user for recalibration of the alternative sleep classifier.
1 Assignment
0 Petitions
Accused Products
Abstract
An electronic switch for controlling a device (170) by switching a function of the device at least in dependency on a sleep stage of a human, the switch comprising an EEG data interface configured to receive brain activity data from an EEG sensor (120) configured to monitor electrical activity of the brain of the human during a training phase, an EEG sleep classifier (125) configured to classify sleep stages of the human from the received brain activity data, a body data interface configured to receive body activity data from an alternative sensor (30) configured to monitor a bodily function of the human both during the training phase and during a subsequent usage phase, the alternative sensor being different from the EEG sensor, an alternative sleep classifier (135) and a machine learning system (140), the machine learning system being configured to train the alternative sleep classifier (135) to classify a sleep stage of the human from the received body activity data, the learning system using sleep stages classified by the EEG sleep classifier (125) and concurrent body activity data received from the alternative sensor as training data, wherein in the usage phase the device (170) is controlled in dependency on sleep stages of the human classified by the alternative sleep classifier (135), and control logic (150) configured to at least determine that the classified sleep stage is one of a set of particular sleep stages and to switch a function of the device at least in dependency on said determination.
14 Citations
15 Claims
-
1. An electronic switch for controlling a device by switching a function of the device at least in dependency on a sleep stage of a human, the switch comprising
an EEG data interface configured to receive brain activity data from an EEG sensor configured to monitor electrical activity of the brain of the human during a training phase, an EEG sleep classifier configured to classify sleep stages of the human from the received brain activity data, a body data interface configured to receive body activity data from an alternative sensor configured to monitor a bodily function of the human both during the training phase and during a subsequent usage phase, the alternative sensor being different from the EEG sensor, an alternative sleep classifier and a machine learning system, the machine learning system being configured to train the alternative sleep classifier to classify a sleep stage of the human from the received body activity data, the learning system using sleep stages classified by the EEG sleep classifier and concurrent body activity data received from the alternative sensor as training data, wherein in the usage phase the device is controlled in dependency on sleep stages of the human classified by the alternative sleep classifier, and control logic configured to at least determine that the classified sleep stage is one of a set of particular sleep stages and to switch a function of the device at least in dependency on said determination, the switch further comprising: -
a statistical unit configured to determine a statistical measure of the received body activity data during the training phase and store it as a reference measure, and to determine the statistical measure of the received body activity data during the usage phase; and a drift detection unit configured to detect a drift of the statistical measure determined during the usage phase and the reference measure, and upon detecting the drift signaling a user for recalibration of the alternative sleep classifier. - View Dependent Claims (2, 3, 4, 6, 7, 8, 9, 10, 11, 12)
-
-
5. (canceled)
-
13. A method for controlling a device by switching a function of the device at least in dependency on a sleep stage of a human, the method comprising
monitoring electrical activity of the brain of the human during a training phase, classifying sleep stages of the human from the monitored brain activity data by an electronic EEG sleep classifier, monitoring a bodily function of the human both during the training phase and during a subsequent usage phase, training an electronic alternative sleep classifier to classify a sleep stage of the human from the monitored body activity data, the learning system using sleep stages classified by the EEG sleep classifier and concurrent monitored body activity data as training data by a machine learning system, classifying sleep stages of the human from the monitored body activity data by the alternative sleep classifier, determining that the sleep stage classified by the alternative sleep classifier is one of a set of particular sleep stages, and switching a function of a device at least in dependency on said determination, the method further comprising: -
determining a statistical measure of the received body activity data during the training phase and store it as a reference measure; determining the statistical measure of the received body activity data during the usage phase; detecting a drift of the statistical measure determined during the usage phase and the reference measure; and upon detecting the drift signaling a user for recalibration of the alternative sleep classifier.
-
-
14. A computer program for controlling a device by switching a function of the device at least in dependency on a sleep stage of a human when the computer program is run on a computer, the computer program comprising computer program code means adapted to
receive brain activity data at an EEG data interface from an EEG sensor configured to monitor electrical activity of the brain of the human during a training phase, classify sleep stages of the human from the received brain activity data, receive body activity data from an alternative sensor configured to monitor a bodily function of the human both during the training phase and during a subsequent usage phase, train an alternative sleep classifier to classify a sleep stage of the human from the received body activity data, the learning system using sleep stages classified by the EEG sleep classifier and concurrent body activity data received from the alternative sensor as training data, classify sleep stages of the human from the monitored body activity data by the alternative sleep classifier, determine that the sleep stage classified by the alternative sleep classifier is one of a set of particular sleep stages, and switching a function of a device at least in dependency on said determination, the computer method further comprising computer program code means adapted to: -
determine a statistical measure of the received body activity data during the training phase and store it as a reference measure; determine the statistical measure of the received body activity data during the usage phase; detect a drift of the statistical measure determined during the usage phase and the reference measure; and upon detecting the drift signal a user for recalibration of the alternative sleep classifier. - View Dependent Claims (15)
-
Specification