Christian Herff

@HerffC

Assistant Professor @ Maastricht University interested in machine learning for brain-computer interfaces and neuroscience.

Vrijeme pridruživanja: siječanj 2017.

Medijski sadržaj

  1. 11. pro 2019.

    Jeremy Saal presenting our work on decoding navigational parameters from hippocampal sEEG at .

  2. 22. stu 2019.

    We also asked volunteers to perform a listening test and 66.7% of the reconstructed words could be identified correctly in a forced-choice test with 4 options.

    Prikaži ovu nit
  3. 22. stu 2019.

    The approach used also allows us to run the analysis with the three regions individually. Each of them performed above chance level, but M1 clearly provided most information for the decoding processes.

    Prikaži ovu nit
  4. 22. stu 2019.

    This simple and fast approach reconstructs very high quality audio using the patient's own voice. You can listen to a few examples in the supplementary material.

    Prikaži ovu nit
  5. 22. stu 2019.

    Our approach is based on Unit Selection, where the best fitting unit of speech is just concatenated to the output. We determine the best fitting unit of speech by comparing the cosine similarity of high-gamma activity. This video illustrates the approach:

    Prikaži ovu nit
  6. 22. stu 2019.

    In this study, we used a very simple method from the speech synthesis community to reconstruct natural, intelligible speech from intra-op ECoG in IFG, pre-motor and motor cortex.

    Prikaži ovu nit
  7. 14. stu 2019.

    In this article, we present a VR version of the n-back task (available at ) and use it to investigate workload in an immersive environment with EEG.

    Prikaži ovu nit
  8. 17. lis 2019.

    With Miguel Angrick from , and Jon Brumberg, we show our vision "Towards Restoration of Articulatory Movements: Functional Electrical Stimulation of Orofacial Muscles"

    Prikaži ovu nit
  9. 17. lis 2019.

    With Margot Heijmans, and we investigated "Evaluation of Parkinson’s Disease at Home: Predicting Tremor from Wearable Sensors"

    Prikaži ovu nit
  10. 17. lis 2019.

    Together with and we showed that fNIRS can be used for workload discrimination in VR: "Decoding Mental Workload in Virtual Environments: A fNIRS Study using an Immersive n-back Task"

    Prikaži ovu nit
  11. 7. lis 2019.

    Our prediction model achieves very good quality (AUC = 0.88) in a cross-validation. By analyzing the odd-ratios in the logistic regression, we can see which preoperative variables have the highest impact on the prediction.

    Prikaži ovu nit
  12. 7. lis 2019.

    For this, we divided our 90 patients into weak and strong responders:

    Prikaži ovu nit
  13. 7. lis 2019.

    In this study, we trained a logistic regression to predict the motor outcome of Deep Brain Stimulation one year after surgery from preoperative variables.

    Prikaži ovu nit
  14. 2. lis 2019.

    While auditory cortex activity mostly vanished during imagination, we observe a cluster of frontal electrodes that also tag the periodicity during imagined continuation of the rhythms. (Red is perception only, green is imagine only, blue is both).

    Prikaži ovu nit
  15. 2. lis 2019.

    In this study, we use an approach based on the periodicity of the signals to show how high-gamma activity in ECoG recordings tag drum rhythms during perception and rhythm imagination.

    Prikaži ovu nit
  16. 21. ruj 2019.

    Really appreciate this nice gesture by

  17. 17. ruj 2019.
  18. 15. ruj 2019.

    Had a great time at presenting a tutorial on "Biosignal-based speech processing, from silent speech to brain-computer interfaces" with .

  19. 26. srp 2019.

    Jeroen Habets is presenting our work on predicting DBS outcome from presurgical information at .

  20. 26. srp 2019.

    Ignite presentation of our work on workload detection in VR using fNIRS. This is joint work with from . The task is available at

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·