Methods and systems for channel identification using manifolds of an ear-electroencephalography (ear-eeg) signal

A system, comprising:

• a memory storing instructions;
• one or more communication interfaces;
• and
• one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to:
• receive in real time, a first signal and a second signal generated as a neural response of a user to at least one of a plurality of stimuli actions from each of a plurality of channels within a wearable Ear-electroencephalography (Ear-EEG) device worn by the user, wherein the plurality of stimuli actions are indicative of a context from day-to-day activities of the user obtained automatically from the wearable Ear-EEG device, and wherein the second signal is indicative of a resting or a non-resting state of the user;
• preprocessing one of:
• (i) the first signal and (ii) the second signal using a plurality of preprocessing techniques to obtain a preprocessed signal;
• segment the preprocessed signal into a plurality of data segments following an onset of the second signal, wherein the plurality of data segments indicate epochs of a plurality of window lengths;
• extract a plurality of manifold features from each of the plurality of data segments, wherein the plurality of manifold features support in (i) determining a structure of data and (ii) identifying one or more complex dynamic characteristics of the first signal the second signal;
• classify each of the plurality of data segments into (i) a first category and a (ii) a second category based on the plurality of manifold features using an unsupervised clustering model, wherein the first category indicates a first set of channels from the plurality of channels within the wearable Ear-EEG device which capture an electroencephalogram (EEG) data and the second category indicates a second set of channels from the plurality of channels within the wearable Ear-EEG device which capture a non-electroencephalogram (EEG) data;
• and
• select the plurality of data segments classified into the first category to identify the first set of channels which capture the electroencephalogram (EEG) data for monitoring a status representing health condition of the user.

One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause:

• receiving in real time, a first signal and a second signal generated as a neural response of a user to at least one of a plurality of stimuli actions from each of a plurality of channels within a wearable Ear-electroencephalography (Ear-EEG) device worn by the user, wherein the plurality of stimuli actions are indicative of a context from day-to-day activities of the user obtained automatically from the wearable Ear-EEG device, and wherein the second signal is indicative of a resting or a non-resting state of the user;
• preprocessing one of:
• (i) the first signal and (ii) the second signal using a plurality of preprocessing techniques to obtain a preprocessed signal;
• segmenting the preprocessed signal into a plurality of data segments following an onset of the second signal, wherein the plurality of data segments indicate epochs of a plurality of window lengths;
• extracting a plurality of manifold features from each of the plurality of data segments, wherein the plurality of manifold features support in (i) determining a structure of data and (ii) identifying one or more complex dynamic characteristics of the first signal the second signal;
• classifying each of the plurality of data segments into (i) a first category and a (ii) a second category based on the plurality of manifold features using an unsupervised clustering model, wherein the first category indicates a first set of channels from the plurality of channels within the wearable Ear-EEG G device which capture an electroencephalogram (EEG) data and the second category indicates a second set of channels from the plurality of channels within the wearable Ear-EEG device which capture a non-electroencephalogram (EEG) data;
• and
• selecting the plurality of data segments classified into the first category to identify the first set of channels which capture the electroencephalogram (EEG) data for monitoring a status representing health condition of the user.