LoginSign Up
← Back to all sparks
R

ravetools

ANALYTICS
Velocity0.0

Signal and Image Processing Toolbox for Analyzing Intracranial Electroencephalography Data

github.com/dipterix/ravetools ↗

RAVE's signal-processing toolkit taught base R graphics to render lit 3D brain meshes.

neuroscienceieeg3d-renderingsignal-processingbase-r-graphics
◆Current state
ravetools supplies the signal processing and now the rendering primitives behind RAVE, a suite for analyzing intracranial electroencephalography. Its earlier releases built out Matlab-equivalent filtering, Welch spectra and wavelet tooling; 0.2.6 changes register entirely, adding plot_mesh_dotcloud and plot_mesh_polygon to draw 3D surface meshes in base R graphics with no rgl dependency, plus arbitrary clipping planes and per-mesh alpha.
◆Where it's heading
The package is absorbing the visualization layer that RAVE previously delegated to WebGL-backed renderers, and doing it in a way that works in headless and figure-generating contexts. Exporting ensure_mesh3d to coerce mesh3d, ieegio_surface, fs.surface and surf.asc into one canonical form makes ravetools the convergence point for surface formats across the wider toolchain — the sibling ieegio package shipped its own base R plot method within minutes of this release.
◆Prediction
Expect the base R renderers to pick up the features rgl users would miss next — richer materials, labeling and camera control — and for more of the RAVE stack to route surface handling through ensure_mesh3d.

◆Recent moves

  1. 2mo ago

    3D mesh rendering arrives in base R, without rgl

    ⚡ SPARK

    The release that widens ravetools from signal processing into rendering: two mesh renderers that run in base R graphics with no rgl dependency, plus a canonical surface coercion function. The sibling ieegio package added its own base R plot method the same morning, making this a coordinated move away from WebGL-only visualization.

    View source ↗
  2. 1y ago

    ravetools 0.2.1

    A release tag carrying no notes beyond a link to the external changelog, so nothing about its contents is visible from the feed itself. It sits in the four-year gap between the signal-processing era and the 0.2.6 rendering work.

    View source ↗
  3. 3y ago

    Stimulation interpolation and faster quantiles

    Adds interpolate_stimulation to detect and smooth over stimulation artifacts in recorded responses, plus fast_quantile and fast_mvquantile, and fixes a TinyThreads memory leak. The entry body is cumulative and also restates 0.0.7 and 0.0.6, where the Matlab-equivalent filters and multi-channel pwelch landed — the signal-processing foundation the package was built on before it turned to rendering.

    View source ↗