Search Results - maryam+shanechi

6 Results Sort By:

Cross-Session EEG Normalization via ​ SSVEP-Based Linear Calibration

Uses steady-state visually evoked potentials (SSVEPs) as endogenous reference signals for cross-session EEG calibration. Creates a subject-specific linear mapping that aligns raw EEG recordings to a common neural baseline. Reduces the impact of session dependent recording differences to support consistent longitudinal EEG analysis. Abstract This...

2020-083 - Neural Modeling with a Novel Preferential Subspace Identification Process

Neurological disorder treatment Mental health treatment Neuroscience research Abstract USC researchers have developed preferential subspace identification (PSID), an innovative algorithm designed to model neural activity while prioritizing behaviorally relevant dynamics. In experiments with two monkeys performing reach and grasp tasks, PSID revealed...

Published: 2/3/2026 Inventor(s): Maryam Shanechi, Omid Sani

2020-079 - A Geometric Paradigm for Nonlinear Modeling and Control of Neural Dynamics

Neuroscience research Treatment of mental disorders, including depression, anxiety, and addiction Abstract USC researchers have developed a geometric paradigm for nonlinear dynamic modeling and closed-loop control of neural population activity and related mental states. Based on modeling the low-dimensional nonlinear geometric space of neural population...

Published: 3/11/2026 Inventor(s): Maryam Shanechi

2017-227 - Decoding Neuropsychiatric States From Multi-Site Brain Network Activity

Closed-loop brain stimulation for neurological disorders Abstract USC researchers have developed a technique to identify time-variant linear state-space models (SSMs), as well as an adaptive identification algorithm to calculate-variant SSMs and track non-stationarity in brain network dynamics. This method will allow for improved closed-loop electrical...

2016-234 - Generalized Binary Noise Brain Stimulation

Deep brain stimulation for conditions including Parkinson's disease, epilepsy, and major depression Abstract USC researchers have developed a technique for efficiently identifying input-output dynamics in brain networks to improve closed-loop stimulation systems and BMIs. Utilizing a Generalized Binary Noise (GBN) modulated stimulation pattern,...

2016-030 - Adaptive brain-machine interface allows anesthesia control

Anesthesia management Anesthesia delivery Abstract USC researchers have developed a brain-machine interface (BMI) that can automate drug delivery with precision and enable more efficient control of anesthetics. This adaptive algorithm delivers a drug based on real-time feedback of a patient’s EEG activity. The BMI takes the neural recordings...