The Spatial and Temporal Resolution of Motor Intention in Multi-Target Prediction
Authors: Marie Dominique Schmidt, Ioannis Iossifidis
Organizations: Robotics and BCI Laboratory, Institute of Computer Science, Ruhr West University of Applied Science Mülheim an der Ruhr, Germany · Institute for Neural Computation Ruhr-University Bochum, Bochum, Germany
Reaching for grasping, and manipulating objects are essential motor functions in everyday life. Decoding human motor intentions is a central challenge for rehabilitation and assistive technologies. This study focuses on predicting intentions by inferring movement direction and target location from multichannel electromyography (EMG) signals, and investigating how spatially and temporally accurate such information can be detected relative to movement onset. We present a computational pipeline that combines data-driven temporal segmentation with classical and deep learning classifiers in order to analyse EMG data recorded during the planning, early execution, and target contact phases of a delayed reaching task. Early intention prediction enables devices to anticipate user actions, improving responsiveness and supporting active motor recovery in adaptive rehabilitation systems. Random Forest achieves 80% accuracy and Convolutional Neural Network 75% accuracy across 25 spatial targets, each separated by 14∘ azimuth/altitude. Furthermore, a systematic evaluation of EMG channels, feature sets, and temporal windows demonstrates that motor intention can be efficiently decoded even with drastically reduced data. This work sheds light on the temporal and spatial evolution of motor intention, paving the way for anticipatory control in adaptive rehabilitation systems and driving advancements in computational approaches to motor neuroscience.
Figures & tables
Figure 1: Experimental setup and task structure: a) VR environment from the participant’s perspective. b) target classes. c) placement of motion capture markers and EMG electrodes. d) EMG and End-EFfector trajectory, with vertical lines at task events. e) EEF trajectory. f) task event timeline with colored markers indicating task states.
Figure 2: Random Forest: a) prediction for all participants based on the entire reach and all channels and features. b) confusion matrix across all subjects.
Figure 3: Random forest for 12 targets: a) target distribution c) performance per subject.
Figure 4
Figure 5: Random Forest feature analysis a) contribution of features. b) performance comparison between models based on different numbers of features and channels c) correlation matrix exemplary for 15 features and 10 channels.
Figure 6
Figure 7: Random Forest classification results: a) based on different points in time. b) pre-motion across participants. c) classification for a reduced number of classes 4 . d) class distribution.
Figure 8: Comparison of CNN confusion matrices: a) predicting 25 targets. b) two outputs for column and row. c) two separate CNNs predicting either row or column.
Department of Engineering Science University of Toronto · Computer and Mathematical Sciences University of Toronto Scarborough · Department of Computer Science University of Toronto +3