Artifact detection · qEEG

Every artifact, found and labeled.

WaveFM, our EEG foundation model, labels every channel and time window as eye, muscle, chewing, shiver, electrode or clean. Flagged segments are excluded by your study's rules, or repaired where the study needs it.

Talk to us → How it works
example_recording.edf Artifacts labeled
Fig. 1 Artifacts labeled by type, per channel and time window. Illustration, not patient data or model output.
  • Eye
  • Muscle
  • Chewing
  • Shiver
  • Electrode

01 What it finds

Five artifact types, told apart.

  • Eye

    Blinks and eye movements, strongest over the front of the head.

  • Muscle

    Face, jaw and neck tension: fast, high-amplitude noise.

  • Chewing

    Rhythmic bursts from jaw movement.

  • Shiver

    Rhythmic tremor from cold or tension.

  • Electrode

    Pops, drifts and loose contacts.

02 How it works

Upload, label, exclude.

Step 1 Upload A standard EEG file, to our cloud Step 2 Label WaveFM marks every channel and window Step 3 Exclude Or repair, if your study needs it Step 4 Export Analysis-ready EEG and a map of every change Step 1 Upload Step 2 Label with WaveFM Step 3 Exclude (or repair) Step 4 Export
Fig. 2 From raw recording to analysis-ready EEG
i.

Any headset

WaveFM works with any montage and any number of channels, so it fits the equipment you already use.

ii.

Consistent

The same rules for every recording, every time. No more two reviewers giving two answers.

iii.

Fully traceable

The original recording is always stored, and every excluded or repaired segment is marked.

03 qEEG analysis

Then the analysis, on clean data.

Keep the metrics you already use, or let us run the analysis: band power and ratios, standard qEEG, functional connectivity, group statistics and figures ready for publication.

Every result comes from data that passed the artifact step, so results stay comparable between sessions and sites. The report also records which artifact types were removed, so you can see what each metric was exposed to.

Node importance

Scalp map showing which electrode regions carried the most weight in one example recording

Functional connectivity · edge importance

Connectivity graph between electrodes showing which connections carried the most weight in one example recording
Fig. 3 Example report panels from our graph model, one test case from a public EEG dataset. Colors show where weight is highest within this recording, not values to compare between people.

Research use only. Not for diagnosis. Report contents are agreed with each customer.

Let's talk about your EEG data.

Tell us about your recordings and your study. We'll tell you how WaveFM can help.

Contact us →