Applications

One principle, different signals.

What BioRLE-1 compresses is not specific to the heart. It is specific to a shape of signal — long predictable stretches interrupted by short, dense events — and to a context: expensive links and small batteries. Wherever those two conditions repeat, the technique transfers.

The common principle

Three conditions that make compression worth it.

01

The signal is sparse

Most of the record is rest or baseline. The information concentrates in short events. Compressing the predictable part is nearly free.

02

Moving data is expensive

There is a radio, a limited battery or a memory that fills up. Transporting the data costs more than acquiring it.

03

Fidelity has a hard bound

"Close enough" does not cut it. You have to declare and verify how much error is allowed, because someone will make a decision from that signal.

Domains

Where we are and where we are heading

Only what is validated appears as available. Everything else is marked as roadmap on purpose.

Cardiac monitoring

Diagnostic and screening ECG, Holter-style recorders, cardiac patches and wearables, clinical telemetry. This is the domain BioRLE-1 was designed and validated for, and the one for which the reference model, verification vectors and integration support exist.

ProductBioRLE-1
StatusValidated · tape-out ready
Available asOpen core + integration licence
On the roadmap

Industrial telemetry and IoT

Machine vibration monitoring, battery-powered remote sensors, asset condition monitoring. The profile is the same as in a cardiac monitor: a signal that is mostly at rest with short events that do matter, and a radio link that dominates the power budget.

Actual status: there is no released product for this domain. The architecture anticipates it and we are evaluating pilot projects with partners who can contribute representative signals. If you work in this space and want to take part in an early evaluation, get in touch.

Your signal is not on the list?

Describe its shape — sample rate, resolution, how sparse it is, how expensive it is to transmit — and we will tell you frankly whether the approach applies.