Compatibility archive

Projects

Current research systems are listed first. A minimal archive keeps externally linked legacy project URLs valid.

NeuroStimEnv

Closed-loop brain stimulation as a computational control problem

Full project →

NeuroStimEnv is an open-source simulation framework for combining biophysical neural circuits, simulated EEG, transcranial stimulation and reinforcement learning for treatment discovery.

It integrates NEURON, LFPy and SimNIBS and supports reinforcement-learning formulations in which neural activity provides observations and stimulation parameters define treatment actions.

Technical summary

  • Biophysically detailed depression and healthy cortical microcircuits
  • A 1,000-neuron case study evaluated at 0.025 ms temporal resolution
  • MPI/HPC experiments reported using 624 CPU processes
Closed-loop NeuroStimEnv workflow: a human cortical microcircuit produces simulated EEG observations; a reinforcement-learning agent selects stimulation actions that feed back into the circuit. NEURON, LFPy and SimNIBS provide circuit, signal and stimulation modelling.
The simulation loop: neural activity provides observations, a learning agent chooses stimulation parameters, and the circuit responds. This framework supports computational experiments; it is not clinical validation.
Reinforcement LearningComputational NeuroscienceEEGNEURONSimNIBSLFPy
Paper (opens in a new tab)Code (opens in a new tab)

CAPSML / G2P2C

Towards fully closed-loop artificial pancreas systems

Full project →

A research ecosystem for learning adaptive insulin-dosing strategies that reduce dependence on manual meal announcements and carbohydrate estimation.

G2P2C combines reinforcement-learning policy optimization with glucose dynamics modelling and short-horizon planning. CAPSML exposes the research through an interactive simulation platform, while GluCoEnv and RL4T1D provide reusable open-source research infrastructure.

Technical summary

  • A POMDP formulation for insulin dosing without meal announcements
  • Policy optimization augmented with learned glucose dynamics and short-horizon planning
  • Reusable simulation and RL infrastructure in GluCoEnv and RL4T1D, with interactive analysis in CAPSML
An illustrative in-silico glucose-control experiment. Blue shows sensed glucose, red marks meals, and green shows insulin delivery. Use the playback controls to pause or replay the animation. These are simulated signals, not patient data.
Reinforcement LearningSequential Decision-MakingControlPOMDPsPyTorchBiomedical AI
Paper (opens in a new tab)CAPSML (opens in a new tab)G2P2C (opens in a new tab)GluCoEnv (opens in a new tab)RL4T1D (opens in a new tab)

Open-source research systems

Reusable infrastructure for simulation and sequential decision-making

Full project →

A set of public research systems for virtual Type 1 Diabetes experiments, reinforcement-learning benchmarks and interactive analysis.

GluCoEnv, RL4T1D and CAPSML make physiological simulation, algorithm comparison and result inspection available beyond a single paper implementation.

Technical summary

  • Vectorized PyTorch environments for virtual Type 1 Diabetes subjects
  • Online and offline RL experiment infrastructure
  • Configurable scenarios, sensors, pumps and benchmark controllers
Open SourcePyTorchSimulationOffline RLBenchmarking
CAPSML (opens in a new tab)GluCoEnv (opens in a new tab)RL4T1D (opens in a new tab)

Earlier projects

ArchiveDiabetes prediction from PPG and physiological characteristicsOpen
ArchiveFlisma wearable throwing-injury analysisOpen
ArchiveClardia family health assistantOpen
ArchiveAnalyzing skewed distributionsOpen
ArchiveGym Tracker IoT weight scaleOpen
ArchiveRampage line-following robotOpen