What We Study

Our
Research

Three interlocking pillars — Energy Systems, Computational Foundations, and Medical Systems. Every project flows through all three layers.

Energy Systems

Primary focus. Developing next-generation clean energy infrastructure aligned with India's National Hydrogen Mission and National Biofuel Mission.

MSME CoE · IISc Bengaluru

Green Hydrogen from Seawater

Nano-catalysts, selective membranes, and concentrated solar power for efficient seawater electrolysis. Approved for incubation at IISc MSME Centre of Excellence. Real pathway to scalable clean hydrogen.

₹15,00,000 Ref: IDEAKR-026059
NAIN 2.0 · Startup Karnataka

BIOLOOP

Closed-loop CO₂ capture to biofuel system. Carbon captured and converted to biodiesel through a continuous biological architecture. First cycle efficiency analysis complete — unexpected thermodynamic gains recorded.

₹1,00,000 Active · Featured DD Chandana
NAIN 2.0 · Startup Karnataka

Urjawave

High-intensity PEM electrolyzer hydrogen platform. Modelling photovoltaic-electrolyzer coupling efficiency under variable solar irradiance. Target: continuous 24-hour hydrogen production.

₹2,00,000 Active · PEM Platform

Computational Foundations

The intellectual backbone. Not generic AI — purpose-built computational frameworks powering every applied project in the collective.

01

Bayesian Systems

Probabilistic inference frameworks for temporal data, diagnostic systems, and signal processing. Informative prior construction from population-level datasets. The engine behind our medical work.

Pure Research
02

Temporal Modelling

Hierarchical Bayesian models for non-stationary time series with long-range dependencies. Applicable to ECG sequences, energy output prediction, and complex signal analysis.

Applied Maths
03

Signal Intelligence

Reinforcement learning, NLP, and ML infrastructure for scientific problems. Purpose-built models for cardiac signal classification and solar irradiance forecasting.

RL · ML · NLP

Medical Systems

Applied computational medicine. Built on Bayesian and temporal foundations. Quantifying uncertainty rather than hiding it.

01

Arrhythmia Modelling

Bayesian priors from population-level ECG datasets for cardiac arrhythmia detection. 18% improvement over frequentist baseline in early trials. Expanding dataset coverage and prior refinement.

Cardiology
02

ECG Signal Processing

Probabilistic ECG interpretation frameworks that surface uncertainty as a feature. Bayesian diagnostic formulations for robust clinical decision support.

Signal Processing
03

EEG Analysis

Advanced EEG signal analysis using temporal inference systems from our Bayesian foundations. Long-range dependency modelling for non-stationary neural time series.

Neuroscience