Sleep profiling system with feature generation and auto-mapping

A method for modelling sleep profiles for an individual including:

• measuring a brain wave for the individual;
• extracting a predetermined number of spectral power ratios of the brain wave;
• processing the predetermined number of spectral power ratios to extract spectral envelope features of the brain wave;
• and
• extracting Gaussian parameters of the brain wave to form a sleep feature space for profiling sleep of the individual.

A method for profiling sleep of an individual including:

• defining a first sleep feature space for the individual;
• measuring a brain wave for the individual during the individual's sleep and generating a second sleep feature space representative of the measured brain wave;
• mapping the second sleep feature space to the first sleep feature space by comparing the brain wave and a previous brain wave measurement used to define the first sleep feature space;
• modelling the first sleep feature space using recognized neural network patterns corresponding to each of a plurality of sleep stages;
• and
• deriving a sleep profile for the individual from sleep stages by applying the modelled sleep feature space to the mapped sleep feature space.

A method for profiling sleep of an individual including:

• defining a sleep feature space comprising spectral power and envelope features for the individual;
• measuring a brain wave for the individual during the individual's sleep;
• mapping features of a further sleep feature space acquired from the brain wave measurement to the spectral power and envelope features;
• modelling the mapped sleep features in response to recognized neural network patterns corresponding to each of a plurality of sleep stages derived from recognizing the neural network patterns from the sleep feature space;
• and
• deriving a sleep profile for the individual from sleep stages determined in response to the modelled mapped sleep feature space and the brain wave of the individual.

A method for profiling sleep of an individual including:

• defining a first sleep feature space for the individual using training data;
• measuring a brain wave for the individual during the individual's sleep and generating a second sleep feature space representative of the measured brain wave;
• mapping the second sleep feature space by comparing the first sleep feature space with the second sleep feature space;
• modelling the first sleep feature space using recognized neural network patterns corresponding to each of a plurality of sleep stages;
• and
• deriving a sleep profile for the individual from sleep stages by applying the modelled sleep feature space to the mapped sleep feature space.