Welcome to EverybodyWiki ! Nuvola apps kgpg.png Sign in or create an account to improve, watchlist or create an article like a company page or a bio (yours ?)...

Gumpy

From EverybodyWiki Bios & Wiki
Jump to navigation Jump to search




Gumpy
Developer(s)Zied Tayeb et al
Initial releaseJanuary 28, 2018; 18 months ago (2018-01-28)
Repository
Written inPython 3
Engine
    Lua error in Module:Wd at line 1991: attempt to index local 'id' (a nil value).
Operating systemCross-platform
LicenseMIT
Websitegumpy.org

Gumpy is a open source Python 3 python software package for BCI (Brain-Computer Interface) developing and researching. This BCI toolbox could be used for EEG and EMG analysis, visualization and decoding, and it is suitable for performing online hybrid BCI experiments. More than that, Gumpy implements deep learning techniques such as CNN to enhance EEG/EMG decoding.[2]

Gumpy is not that independent: it heavily relies on other numerical and scientific libraries, for instance numpy, scipy, or scikit-learn.

Purpose of Developing[edit | edit source]

BCI researchers rely highly on EEG/EMG decoding, signal processing, feature extraction, etc. Thus, gumpy grasps things that researchers/developers need together in order to alleviate them from the pain of repeatedly code searching or 'reinventing wheels'. As a matter of fact, gumpy wraps existing functions mostly in such a way that researchers/developers can swiftly perform data analysis and implement new classifiers. As the author's words, one of gumpy's design principles was 'to make it easily extendable'.[3]

Components[edit | edit source]

Gumpy itself mainly contains six parts: dataset(gumpy.data), signal processing(gumpy.signal), plotting(gumpy.plot), feature extraction(gumpy.features), splitting(gumpy.split), classification(gumpy.classify).

Gumpy has deep learning models provided independently by gumpy-deeplearning (also under MIT license), to use them, one has to set the path to the models directory and import it. [4]

Features[edit | edit source]

  • New: Gumpy has been put forward at the year of 2018[1].
  • Versatile: Gumpy has assembled many commonly used models of BCI research/developping.
  • Free: Gumpy is under MIT license.
  • Handy: For beginners, gumpy provides a lot of instances[5] and datasets[6], even a set of video[7] on YouTube.

See also[edit | edit source]


Others articles of the Topic Free and open-source software : Phorum, AdoptOpenJDK, KLayout, Grav (CMS), Gede (software), TOPCAT (software), ChessFriend-Fire
Some use of "" in your query was not closed by a matching "".Some use of "" in your query was not closed by a matching "".

References[edit | edit source]

  1. 1.0 1.1 "A Python 3 toolbox to develop Brain-Computer Interfaces (BCI): gumpy-bci/gumpy". 13 December 2018 – via GitHub.
  2. http://gumpy.org/
  3. "A Python 3 toolbox to develop Brain-Computer Interfaces (BCI): gumpy-bci/gumpy". 13 December 2018 – via GitHub.
  4. "Deep Learning Models for Brain Computer Interfaces: gumpy-bci/gumpy-deeplearning". 10 September 2018 – via GitHub.
  5. http://gumpy.org/#orgbe35e57
  6. http://gumpy.org/#org75f77e3
  7. "YouTube". www.youtube.com.

External links[edit | edit source]


This article "Gumpy" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Gumpy. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.


Compte Twitter EverybodyWiki Follow us on https://twitter.com/EverybodyWiki !