Electronic switch for controlling a device in dependency on a sleep stage
An electronic switch for controlling a device 170 by switching a function of the device at least in dependence on a sleep stage of a human. The switch includes 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, and a body data interface configured to receive body activity data from an alternative sensor 130 configured to monitor a bodily function of the human both during the training phase and during a subsequent usage phase. The alternative sensor is different from the EEG sensor, and the electronic switch further includes 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 . A control logic 150 is 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.
1. A burglar alarm comprising:
an intrusion sensor for detecting an intrusion of a burglar;
a device configured to raise an alarm in response to the intrusion sensor detecting an intrusion; and
an electronic switch for controlling the device by switching a function of the device at least in dependency on a sleep stage of a human,
wherein the electronic switch comprises:
an electroencephalogram (EEG) sensor configured to monitor electrical activity of a brain of the human;
an EEG data interface configured to receive brain activity data from the EEG sensor during a training phase;
an EEG sleep classifier configured to classify sleep stages of the human from the received brain activity data;
an alternative sensor configured to monitor a bodily function of the human, the alternative sensor being different from the EEG sensor;
a body data interface configured to receive body activity data from the alternative sensor both during the training phase and during a subsequent usage phase;
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 machine 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;
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;
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,
wherein the control logic is configured to switch-on the device configured to raise an alarm.
2. The burglar alarm as claimed in claim 1 , wherein said electronic switch further comprises a clock configured to indicate a current time, the switch being configurable with a first switching time-period, the control logic being configured to switch the function when both:
a current time indicated by the clock is in the first switching period, and
the classified sleep stage is one of the set of particular sleep stages.
3. The burglar alarm as claimed in claim 2 , wherein the control logic is configured to switch the function when a current time indicated by the clock is at the end of the first switching period regardless of the classified sleep stage.
4. The burglar alarm as claimed in claim 1 , wherein the control logic is configured to defer switching until the classified sleep stage has remained in the set of particular sleep stages for a particular time period.
5. The burglar alarm as claimed in claim 1 , wherein
the EEG sensor is configured to monitor when placed in close proximity or direct contact to the head of the human, and
the alternative sensor is configured to monitor without direct contact with the human.
6. The burglar alarm as claimed in claim 1 , wherein the alternative sensor is configured to monitor at least one of respiration, heart and actigraph.
7. The burglar alarm as claimed in claim 1 , wherein the alternative sensor comprises a pressure sensor for positioning in or under a mattress.
8. An alarm clock comprising:
the burglar alarm as claimed in claim 1 ; and
a device configured to wake the human using audio and/or visual stimuli, wherein
the electronic switch is configurable with a first switching time period, and
the control logic is configured to switch-on the device to generate audio and/or video stimuli thereby waking the human.
9. The alarm clock as in claim 8 , wherein at least the device configured to wake the human is arranged for wearing in a human ear.