Etienne Combrisson

PhD student under the direction of Aymeric Guillot ( CRIS ) and Karim Jerbi ( CocoLab ), I mainly work on motor states / directions decoding using intracranial EEG data. To this end, we search for neural features and test their accuracy using machine-learning algorithms.

We developed several Python tools respectively for neural features extraction and classification (Brainpipe) and visualization (Visbrain)





  • Advanced : French (mother tongue), English
  • Intermediate : German
  • Notions : Spanish, Italian
  • Programming

  • Advanced : Python (mother tongue), Matlab, LateX, Julia
  • Intermediate : OpenGL, HTML/CSS, JavaScript, Shell
  • Notions : C/C++, R, Presentation
  • Neuroscience

  • Advanced : EEG and intracranial EEG
  • Intermediate : MEG, spikes, brain physiology (espacially motor area)
  • Notions : MRI, fNIRS
  • Signal processing

  • Filtering, hilbert, wavelet, convolution, fft, bipolarization, spectrogram, amplitude, phase...
  • Machine Learning

  • Classifiers (LDA, SVM, KNN, Naïve Bayes, Random Forest...)
  • Cross-validation and over-fitting
  • Feature selection
  • Neural Netwoks, and notions of Deep Learning
  • Others

  • Guitar player / composition / mixing and mastering
  • French pool
  • Soroban
  • Publications

  • Combrisson E, Perrone-Bertolotti M, Soto JL, Kahane P, Lachaux JP, Guillot A, Jerbi K. (2017). Predicting movement intentions from local field potentials in humans: What neuronal decoding tells us about motor encoding. (In prep.)
  • Combrisson E, Perrone-Bertolotti M, Soto JL, Alamian G, Kahane P, Lachaux JP, Guillot A, Jerbi K. (2017). From intentions to actions: Neural oscillations encode motor processes through phase, amplitude and phase-amplitude coupling. NeuroImage, 147, 473-487.
  • Combrisson, E., & Jerbi, K. (2015). Exceeding chance level by chance: The caveat of theoretical chance levels in brain signal classification and statistical assessment of decoding accuracy. Journal of neuroscience methods, 250, 126-136.

  • Alamian G., Hincapié AS., Combrisson E., Thiery T., Martel V., Althukov D., Jerbi K. (2017). Alterations of Intrinsic Brain Connectivity Patterns in Depression and Bipolar Disorders: A Critical Assessment of MEG-based Evidence, Frontiers in Psychiatry, 1664-0640
  • Lajnef T., O’Reilly C., Combrisson E., Chaibi S., Eichenlaub JB., Ruby P., Aguera PE., Samet M., Kachouri A., Frenette S., Carrier J., Jerbi K. (2017). Meet Spinky: An open-source Spindle and K-complex detection toolbox validated on the open-access Montreal Archive of Sleep Studies (MASS). Frontiers in Neuroinformatics, 11, 15.
  • Bastin J., Deman P., David O., Gueguen M., Benis D., Minotti L., Hoffman D., Combrisson E., Kujala J., Perrone-Bertolotti M., Kahane P., Lachaux JP., Jerbi J. (2016). Direct recordings from human anterior insula reveal its leading role within the error-monitoring network. Cerebral Cortex, bhv352.
  • Jerbi, K., Combrisson, E., Dalal, S. S., Vidal, J. R., Hamamé, C. M., Bertrand, O., Berthoz A., Kahane P., Lachaux JP. (2013). Decoding cognitive states and motor intentions from intracranial EEG: How promising is high-frequency brain activity for brain-machine interfaces?.
  • Python projects


    [ Neural features and machine-learning ]

    Brainpipe is a python package for features extraction and classification (using the excellent Scikit-learn ).

  • Neural features : Power / Phase / Amplitude / Filtered signals / ERP / Phase-Amplitude Coupling (PAC) / ERPAC / PLF / PLV / Prefered Phase...
  • Classification : simple wrapper of Scikit-Learn single / multi features with some extra features.
  • Statictics : embedded statistics for all the feature types and machine-learning
  • Parallel computing : using Joblib, every feature / classification can be achieved in parallel.
  • Visualization: simple and colorfull visualization tools (plot signals with deviation / 2D plot with stats for good looking pictures...)
  • Extra tools : brainpipe come with some extra tools to simplify analysis (like bpstudy in order to manage sevral datasets and path and facilitate collaborations)

  • Download on and checkout the documentation


    [ Neuroscientific visualization ]

    Visbrain is python package dedicated the visualization (essentially for neuroscientific data) and using the GPU ( Vispy ). This project contains several graphical user interface.

  • Brain : MNI brain (plot sources / connectivity / Gyrus & Brodmann Areas...), cortical projection, bundling...
  • Sleep : Analyse sleep data (load *.eeg and *.edf and plot channels, spectrogram and hypnogram / hypnogram edition / spindles, REM and peak detection...). This module is developed with my dear friend Raphael Vallat
  • Ndviz : Visualization of N-dimentional data (as line / marker / histogram / image / spectrogram...)

  • Download on and checkout the documentation


    [ iPython jupyter workspace ]

    iPywksp is a "Matlabl like" workspace embedded inside Jupyter notebook. This package is experimental, but it works and might be usefull for python & Jupyter beginners.

  • Workspace : Inspect variable values (default python format supported and NumPy arrays.)
  • File : Save and load variables
  • Plot : Make some basic plot.
  • Size : The workspace is extendable which mean that it can be small / medium / large or automatically hide when the mouse is out of the workspace.

  • Download on .


    Phone: (+33) 6-29-91-27-96