IIT Indore · Mehta Family School of BSBE
Advancing brain health through neural signals & AI
Research
Envelope-based changepoint segmentation of seizures, seizure-network dynamics for localisation, and presurgical MEG-derived network-control metrics in temporal lobe epilepsy, across non-invasive and intracranial (EEG, MEG, SEEG) recordings.
Data-driven whole-brain connectome markers of trait impulsivity, using connectome-based predictive modelling linking brain networks to individual differences in behaviour.
Explainable models (SHAP, feature-importance) and leakage-aware validation that reveal which physiological patterns drive a prediction, not accuracy alone.
Publications
Biomedical Physics & Engineering Express · 2026
Subject-independent emotion recognition with EEG bispectral quadratic phase coupling features and explainable machine learningKumar H, Ganapathy N, Puthankattil SD, Swaminathan R
DOI ↗
Annals of Biomedical Engineering · 2026
Three-Phase Seizure Segmentation in Stereotactic EEG Using Envelope-Based Multivariate Changepoint AnalysisKumar H, Seshadri NPG, Martinez D, Najm I, Alexopoulos A, Bulacio JC, Serletis D, Krishnan B
DOI ↗
Human Brain Mapping · 2024
Functional Brain Networks of Trait Impulsivity: A Connectome-Based Predictive Modeling AnalysisHüpen P, Kumar H, Swaminathan R, Habel U, Wagels L
DOI ↗
Principal Investigator
Mehta Family School of Biosciences & Biomedical Engineering, IIT Indore
Biomedical signal processing, neurotechnology, and machine learning: EEG/SEEG/MEG, seizure characterisation, affective computing, and brain-network analysis. Previously a postdoctoral fellow at Cleveland Clinic Epilepsy Center, USA and, during his PhD, a DAAD Bi-National Guided Research Fellow and guest scientist at University Hospital RWTH Aachen, Germany. Integrated B.Tech–M.Tech in Biomedical Engineering, IIIT Allahabad; PhD, IIT Madras.
Openings
PhD
Fully engaged doctoral research in neural signal processing, epilepsy, or AI for neuroscience.
M.Tech
Thesis projects on EEG/MEG analysis, brain networks, or interpretable machine learning.
Undergraduate
Project and internship roles for curious students across engineering and brain health.
News
New paper on identifiability of spectral graph model parameters in clinical MEG published in IEEE Transactions on Biomedical Engineering.
AI-NE Lab established at IIT Indore within the Mehta Family School of Biosciences & Biomedical Engineering.
MEG-derived network control metrics for temporal lobe epilepsy accepted at Epilepsia.
