Ramesh Srinivasan

This study improves EEG-based classification of imagined images and image reconstruction using a modified neural network with an attention module and GAN.

This paper develops a complex-valued Gaussian Graphical Model of MEG coherence constrained by structural connectivity, showing it can infer structural influence and outperform alternatives.

This paper uses a CNN on EEG power spectra to predict drowsiness during propofol anesthesia, achieving 96.47% test accuracy.

This study links the timing of readiness potentials to evidence accumulation in decision-making, showing that RP duration predicts decision time and reflects response selection in the motor system.

The paper uses TMS-EEG and dynamic community detection to analyze how brain network reconfigurations differ in alpha and beta frequency bands following stimulation.

The paper shows that N200 latency in EEG tracks visual encoding time and response time in perceptual decision making, with a linear relationship and slope of 1.

The paper develops a biophysical framework to interpret EEG data across multiple spatial scales, categorizing sources as genuine, equivalent, or representative.

The paper examines brain network structure during working memory tasks and finds that network properties established during encoding predict performance in accuracy and response time.