Determining mental states based on biometric data
Inventors
Alcaide, Ramses Eduardo • Stanley, David • Padden, Dereck • HAMET, James • Molnar, Adam • Alders, Jamie • Candassamy, Jegan • Srinivas, Arjun Daniel
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12602112-B2
Publication Date
2026-04-14
Expiration Date
Abstract
Various embodiments of an apparatus, methods, systems and computer program products described herein are directed to an Analytics Engine that receives one more signal files that include neural signal data of a user based on voltages detected by one or more electrodes on a set of headphones worn by a user. The Analytics Engine preprocesses the data, extracts features from the received data, and feeds the extracted features into one or more machine learning models to generate determined output that corresponds to at least one of a current mental state of the user and a type of facial gesture performed by the user. The Analytics Engine sends the determined output to a computing device to perform an action based on the determined output.
Core Innovation
The invention describes an analytics engine that passively monitors a user using electrodes on a set of headphones worn by the user, where the electrodes detect voltages corresponding to EEG signals and EMG signals, and optionally ECG signals, to generate determined output related to the user’s mental state and facial gestures. The analytics engine receives one or more signal files of data based on the detected voltages, and at least one electrode is a first electrode configured to detect both an EEG signal and an EMG signal.
The invention extracts features from the received data and feeds the extracted features into one or more machine learning models to generate a determined output that corresponds to at least one of a current mental state of the user and a type of one or more facial gestures performed by the user. Feature extraction includes extracting EEG features based at least on EEG signals detected by the first electrode and extracting EMG features based at least on EMG signals detected by the first electrode.
EEG features are used to determine a current level of focus, attentiveness, and cognitive load using corresponding machine learning models, while EMG features are used in a facial gesture machine learning model for determining a type of facial gesture from a plurality of types of facial gestures. The determined output is sent to a computing device to perform an action based on the determined output.
Claims Coverage
The independent claim coverage includes three independent claims: a computer-implemented method, a system, and a computer program product. Across the independent claims, the coverage centers on a headphones-electrode voltage signal pipeline that extracts EEG and EMG features, feeds them into machine learning models to generate a determined output for mental state and facial gesture type, and sends that output to a computing device to perform an action.
Headphones electrode voltage signal reception for EEG and EMG
Receiving one or more signal files of data based on voltages detected by one or more electrodes on a set of headphones worn by a user, wherein at least one of the electrodes comprises a first electrode for detecting both an EEG signal and an EMG signal.
Machine learning based feature extraction and determined output for mental state and facial gesture type
Extracting features from the received data and feeding the extracted features into one or more machine learning models to generate a determined output that corresponds to at least one of a current mental state of the user and a type of one or more facial gestures performed by the user, wherein extracting features comprises extracting one or more EEG features based at least on EEG signals detected by the first electrode; feeding at least one of the extracted EEG features into at least one of a first machine learning model for determining a current level of focus of the user, a second machine learning model for determining a current level of attentiveness of the user and a third machine learning model for determining a current level of cognitive load of the user; extracting EMG features based at least on EMG signals detected by the first electrode; and feeding one or more of the extracted EMG features into a facial gesture machine learning model for determining a type of facial gesture from a plurality of types of facial gestures.
Sending determined output to computing device to perform an action
Sending the determined output to a computing device to perform an action based on the determined output.
Taken together, the independent claims require receiving voltage-based signal files from headphones electrodes where a first electrode detects both EEG and EMG, extracting EEG features to feed focus, attentiveness, and cognitive-load models and extracting EMG features to feed a facial-gesture classification model, and sending the determined output to a computing device to perform an action.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?