Prediction of Hand Movement Speed and Force from Single-trial EEG with Convolutional Neural Networks Ramiro Gatti a,b , Yanina Atum a , Luciano Schiaffino a , Mads Jochumsen d , Jos´ e Biurrun Manresa a,b,d,* a Laboratory for Rehabilitation Engineering and Neuromuscular and Sensory Research, Faculty of Engineering, National University of Entre R´ ıos, Oro Verde, Argentina b Institute for Research and Development in Bioengineering and Bioinformatics, CONICET-UNER, Oro Verde, Argentina c Center for Neuroplasticity and Pain, SMI R  , Aalborg University, Aalborg, Denmark d Center for Sensory-Motor Interaction, SMI R  , Aalborg University, Aalborg, Denmark Abstract Building accurate movement decoding models from brain signals is crucial for many biomedical applications. Decoding specific movement features, such as speed and force, may provide additional useful information at the expense of increasing the complexity of the decoding problem. Recent attempts to predict movement speed and force from the electroencephalogram (EEG) achieved clas- sification accuracy levels not better than chance, stressing the demand for more accurate prediction strategies. Thus, the aim of this study was to improve the prediction accuracy of hand movement speed and force from single-trial EEG signals recorded from healthy volunteers. A strategy based on convolutional neural networks (ConvNets) was tested, since it has previously shown good performance in the classification of EEG signals. ConvNets achieved an overall accuracy of 84% in the classification of two different levels of speed and force (4- class classification) from single-trial EEG. These results represent a substantial improvement over previously reported results, suggesting that hand movement speed and force can be accurately predicted from single-trial EEG. Keywords: Convolutional neural networks, hand movement, movement prediction, multi-class classification, single-trial EEG. 1. Introduction Decoding brain signals to predict movements is useful in many research ar- eas, such as neuromechanics, neuroscience and robotics [1]. Furthermore, it is ∗ Corresponding author Email addresses: rgatti@ingenieria.uner.edu.ar (Ramiro Gatti), yatum@ingenieria.uner.edu.ar (Yanina Atum), lschiaffino@ingenieria.uner.edu.ar (Luciano Schiaffino), mj@hst.aau.dk (Mads Jochumsen), jbiurrun@hst.aau.dk (Jos´ e Biurrun Manresa) Preprint submitted to Applied Soft Computing November 6, 2019 . CC-BY-NC-ND 4.0 International license under a not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available The copyright holder for this preprint (which was this version posted November 7, 2019. ; https://doi.org/10.1101/492660 doi: bioRxiv preprint