MEDUSA Kernel 1.3 release. Changelog:

Breaking changes:

• Eliminated dependency from PyQt5

Major changes:

• Inclusion of bitwise reconstruction methods for c-VEP paradigms

Minor changes:

• Improvements in timeplot
• Fixed errors to serialize exceptions in tensorflow_integration module
• Fixed errors in bci.mi_paradigms

MEDUSA Kernel 1.2.5 release. Changelog:

Breaking changes:

• Parameter standard in function set_standard_montage from meeg.meeg.EEGChannelSet
• Module plots.topography_plots has been renamed to plots.head_plots
• Tensorflow integration is now a package extra. Install with this command 'pip install medusa-kernel[TF]'

Major changes:

• Artifact removing with ICA is now incldued
• Inclusion of a plot to show biosginals with events, conditions, etc compatible with recording app of MEDUSA Platform
• Updates in head_plots
• Improved integration of tensorflow. Tensorflow version has to be <= 2.11 to avoid problems with GPU in Windows

Minor changes:

• Error fixing in models of bci.mi_paradigms
• Error fixing in spatial.filetering.CSP
• Minor bugs fixed in connectivity metrics
• Improved compatibility of time plot with recordings from MEDUSA Platform
• The message of TF extras error has been updated
• Improved position of the sliders of the timeplot
• Fixed bug in artifact rejection for cvep spellers

MEDUSA Kernel 1.1.3 release. Changelog:

Breaking changes:

• The spectral analysis, nonlinear analysis and connectivity analysis functions (both phase and amplitude based) support as input signals with dimensions [n_epochs, n_samples, n_channels].
• Update of Motor Imagery module: Changes in the MIData class.
• Update in Neurofeedback module: Now includes pipelines for real-time functional connectivity calculation.
• Laplacian surface filter update: Improved filter design in automatic mode.

Major changes:

• The algorithms of the nonlinear analysis and connectivity analysis functions have been optimized and calculations are now faster.

Minor changes:

• Legacy package medusa.bci.remote has been eliminated
• Tensorflow versions fixed to avoid problems: tensorflow==2.11; tensorflow-probability==0.16

First major update of MEDUSA Kernel, a complete suite of functions for biosignal processing.

Breaking changes:

• Phase connectivity improved for real time calculation
• More functions accept both input shapes [epochs x time x channels] and [time x channels]
• Improved documentation

First public release of MEDUSA Kernel, a complete suite of functions for biosignal processing. Available in the Python Package Index (PyPI) repository.