#NeuroRA2
A Python Toolbox of Representational Analysis from Multimodal Neural Data
Overview
Representational Similarity Analysis (RSA) has become a popular and effective method to measure the representation of multivariable neural activity in different modes.
NeuroRA is an easy-to-use toolbox based on Python, which can do some works about RSA among nearly all kinds of neural data, including behavioral, EEG, MEG, fNIRS, sEEG, ECoG, fMRI and some other neuroelectrophysiological data.
In addition, users can do Inter-Subject Correlation (ISC), Classification-based EEG Decoding and a novel cross-temporal RSA (CTRSA) on NeuroRA.
Installation
pip install neurora2
Paper
Lu, Z., & Ku, Y. (2020). NeuroRA: A Python toolbox of representational analysis from multi-modal neural data. Frontiers in Neuroinformatics. 14:563669. doi: 10.3389/fninf.2020.563669
Website & How to use
See more details at the NeuroRA website.
You can read the Documentation here or download the Tutorial here to know how to use NeuroRA.
Required Dependencies:
- Numpy: a fundamental package for scientific computing.
- SciPy: a package that provides many user-friendly and efficient numerical routines.
- Scikit-learn: a Python module for machine learning.
- Matplotlib: a Python 2D plotting library.
- NiBabel: a package prividing read +/- write access to some common medical and neuroimaging file formats.
- Nilearn: a Python module for fast and easy statistical learning on NeuroImaging data.
- MNE-Python: a Python software for exploring, visualizing, and analyzing human neurophysiological data.
Features
-
Calculate the Representational Dissimilarity Matrix (RDM)
-
Calculate the Cross-Temporal RDM (RDM)
-
Calculate the Representational Similarity based on RDMs
-
Conduct Cross-Temporal RSA (CTRSA)
-
Conduct Classification-based EEG decoding
-
Calculate the Inter-Subject Correlation (ISC)
-
Conduct Statistical Analysis
-
Save the RSA result as a NIfTI file for fMRI
-
Plot the results
About NeuroRA
If you have any question, find some bugs or have some useful suggestions while using, you can email me and I will be happy and thankful to know.
My email address:
[email protected] / [email protected]
My personal homepage:
https://zitonglu1996.github.io
评论