Active Research in
Biomedical Engineering
We are an early-stage engineering lab. These are the problems we are actively working on — the algorithms we are designing, the hardware we are building, and the clinical systems we are trying to close the loop on.
Research tracks
Computational Software & Signal Processing
Turning raw physiological signal into defensible, low-latency inference.
We build the computational layer that sits between noisy biosignal acquisition and a clinician-facing conclusion. The work spans digital signal processing, predictive physiological modelling, and real-time telemetry pipelines designed to hold their timing budget under realistic noise and motion artefact.
- Digital signal processing for ECG, PPG, EMG and impedance modalities
- Predictive physiological modelling and state-space estimation
- Low-latency telemetry and streaming inference pipelines
Embedded Biomedical Hardware & Sensor Systems
Custom acquisition hardware where off-the-shelf instrumentation runs out.
We design the acquisition layer ourselves when commercial instruments cannot meet the requirements. That means custom sensor interfaces, front-end instrumentation, microfluidics for sample handling, and the firmware that makes the whole assembly behave as one instrument.
- Biosensing front-ends and analog instrumentation design
- Microfluidic sample handling and assay integration
- Custom firmware and real-time embedded systems
Closed-Loop Clinical Engineering
Diagnostic rigs and human-machine interface frameworks where the loop closes.
The most ambitious track: systems that sense, decide and act as an integrated loop rather than a chain of separate components. This covers intelligent diagnostic rigs and human-machine interface frameworks — the places where a modelling error stops being a software bug and starts being a clinical event.
- Intelligent diagnostic rig architecture and bench design
- Human-machine interface frameworks and control-loop design
- System-level safety case and hazard analysis (ISO 14971)
Working on Something Adjacent?
Most of our best leads come from researchers who arrived with a problem we had not framed the same way. If you have a sensing problem, a model that will not deploy, or a bench you need built, we want to hear it.