Methods, systems, and devices, including computer programs encoded on a computer storage medium are provided for combined dynamic causal modeling and biophysics modeling of brain function. In particular, the disclosed methods of modeling brain function can be used to integrate brain function measurements by two or more methods, such as functional neuroimaging and electrophysiology. Sequential model fitting is used to improve modeling accuracy to generate a more comprehensive model of brain neuronal circuitry.

A method of detecting an improvement in a seizure condition of a patient includes identifying a first EEG synchronization of the seizure condition of the patient; applying a therapy configured to improve the seizure condition of the patient; and identifying a second EEG synchronization of the seizure condition of the patient subsequent to application of the therapy, wherein an improvement of the seizure condition of the patient is demonstrated by a reduced EEG synchronization of the patient such that the second EEG synchronization is less than the first EEG synchronization.

A method of detecting an improvement in a seizure condition of a patient includes identifying a first EEG synchronization of the seizure condition of the patient; applying a therapy configured to improve the seizure condition of the patient; and identifying a second EEG synchronization of the seizure condition of the patient subsequent to application of the therapy, wherein an improvement of the seizure condition of the patient is demonstrated by a reduced EEG synchronization of the patient such that the second EEG synchronization is less than the first EEG synchronization.

A method of managing and reducing the recall frequency of disturbing dreams comprises monitoring (100; 200; 300) electroencephalography (EEG) activity of a subject, detecting (102; 206; 302) an indicator of a disturbing dream of the subject based on power in a theta or alpha band of the EEG activity of the subject, and providing stimulation (104; 212; 308) to the subject at a frequency lower than the theta band in response to detecting the indicator of the disturbing dream.

A method of managing and reducing the recall frequency of disturbing dreams comprises monitoring (100; 200; 300) electroencephalography (EEG) activity of a subject, detecting (102; 206; 302) an indicator of a disturbing dream of the subject based on power in a theta or alpha band of the EEG activity of the subject, and providing stimulation (104; 212; 308) to the subject at a frequency lower than the theta band in response to detecting the indicator of the disturbing dream.

The present invention provides a system for implementing a logistic regression classification mechanism to measure and assess a depth of anesthesia of an animal subject based on electroencephalography (EEG), which includes a signal pre-processor, an epoch generator, a feature extractor, a classifier, and a predictor. Related method of how to pre-process the raw data of EEG signal, epoch generation thereof, feature extraction from each epoch, classification based on extracted features, and prediction of different states of the animal subject based on a prediction decision mechanism is also provided. Classification accuracy of the present invention for 1-second and 10% overlapping epochs is about 94% with an average total system delay of about 12 μs and low on-chip power consumption. The present system is entirely optimized, which leads to a 100% accurate channel prediction after a 7-second run-time on average.

The present invention provides a system for implementing a logistic regression classification mechanism to measure and assess a depth of anesthesia of an animal subject based on electroencephalography (EEG), which includes a signal pre-processor, an epoch generator, a feature extractor, a classifier, and a predictor. Related method of how to pre-process the raw data of EEG signal, epoch generation thereof, feature extraction from each epoch, classification based on extracted features, and prediction of different states of the animal subject based on a prediction decision mechanism is also provided. Classification accuracy of the present invention for 1-second and 10% overlapping epochs is about 94% with an average total system delay of about 12 μs and low on-chip power consumption. The present system is entirely optimized, which leads to a 100% accurate channel prediction after a 7-second run-time on average.

A method for determining the intention of a user of a vehicle to brake or accelerate, comprising: acquiring (100) a plurality of EEG signals on the user, applying (101) a predetermined spatial filter on the plurality of EEG signals so as to obtain a target EEG component, detecting (102) a spectral pattern in the EEG component corresponding to an intention to brake or detecting a phase pattern in the EEG component corresponding to an intention to accelerate.

A method for determining the intention of a user of a vehicle to brake or accelerate, comprising: acquiring (100) a plurality of EEG signals on the user, applying (101) a predetermined spatial filter on the plurality of EEG signals so as to obtain a target EEG component, detecting (102) a spectral pattern in the EEG component corresponding to an intention to brake or detecting a phase pattern in the EEG component corresponding to an intention to accelerate.

Typically, high NREM stage N3 sleep detection accuracy is achieved using a frontal electrode referenced to an electrode at a distant location on the head (e.g., the mastoid, or the earlobe). For comfort and design considerations it is more convenient to have active and reference electrodes closely positioned on the frontal region of the head. This configuration, however, significantly attenuates the signal, which degrades sleep stage detection (e.g., N3) performance. The present disclosure describes a deep neural network (DNN) based solution developed to detect sleep using frontal electrodes only. N3 detection is enhanced through post-processing of the soft DNN outputs. Detection of slow-waves and sleep micro-arousals is accomplished using frequency domain thresholds. Volume modulation uses a high-frequency/low-frequency spectral ratio extracted from the frontal signal.