Automated detection of sleep and waking states

A method comprising:

• accessing, from an electrode being in operable connection to a computing device, signal data indicative of brain activity of a subject over a particular time period;
• generating, based on the signal data and by one or more data processors, spectrogram data comprising a power estimated for each frequency band of a set of frequency bands;
• generating, by the one or more data processors, normalized spectrogram data by processing the spectrogram data using a first normalization function, wherein the first normalization function is configured to:
• for each frequency band of the set of frequency bands:
• generate a first normalization parameter based on powers in the spectrogram for the frequency band across a set of time bins in the particular time period;
• and
• normalize the powers of the frequency band in the spectrogram using the first normalization parameter;
• generating, by the one or more data processors, a doubly normalized spectrogram data by processing the normalized spectrogram data using a second normalization function, wherein the second normalization function is configured to:
• for each time bin of the set of time bins:
• generate a second normalization parameter based on powers in the normalized spectrogram for the time bin across the set of frequency bands;
• and
• normalize the powers of the time bin in the normalized spectrogram using the second normalization parameter;
• generating, by the one or more data processors, at least one parameter indicative of sleep stage based on the doubly normalized spectrogram data;
• and
• determining, by the one or more data processors, a classification of pathological condition of the subject by comparing the at least one parameter to one or more reference parameters indicative of sleep stages associated with other subjects with known classifications of the pathological condition, wherein the pathological condition includes one of epilepsy, Alzheimer's disease, depression, brain trauma, insomnia, restless leg syndrome, or sleep apnea.

A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors to perform operations comprising:

• accessing, from an electrode being in operable connection to a computing device, signal data indicative of brain activity of a subject over a particular time period;
• generating, based on the signal data, spectrogram data comprising a power estimated for each frequency band of a set of frequency bands;
• generating normalized spectrogram data by processing the spectrogram data using a first normalization function, wherein the first normalization function is configured to:
• for each frequency band of the set of frequency bands:
• generate a first normalization parameter based on powers in the spectrogram for the frequency band across a set of time bins in the particular time period;
• and
• normalize the powers of the frequency band in the spectrogram using the first normalization parameter;
• generating a doubly normalized spectrogram data by processing the normalized spectrogram data using a second normalization function, wherein the second normalization function is configured to:
• for each time bin of the set of time bins:
• generate a second normalization parameter based on powers in the normalized spectrogram for the time bin across the set of frequency bands;
• and
• normalize the powers of the time bin in the normalized spectrogram using the second normalization parameter;
• generating at least one parameter indicative of sleep stage based on the doubly normalized spectrogram data;
• and
• determining that the at least one parameter is consistent with a classification of pathological condition of the subject, wherein the determination is based on comparing the at least one parameter to one or more reference parameters indicative of sleep stages associated with other subjects with known classifications of the pathological condition, wherein the pathological condition includes one of epilepsy, Alzheimer's disease, depression, brain trauma, insomnia, restless leg syndrome, or sleep apnea.