Movements of the same upper limb can be
classiﬁed from low-frequency time-domain
Patrick Ofner1, Andreas Schwarz1, Joana Pereira1, Gernot R. M¨uller-Putz1
1Institute of Neural Engineering, Graz University of Technology, Graz, Austria
A neuroprosthesis can restore movement functions of spinal cord injured
persons. It beneﬁts from a brain-computer interface (BCI) with a high
number of control classes. However, classical sensorimotor rhythm-based
BCIs can often only provide less than 3 classes, and new types of BCIs
need to be developed. We investigated whether low-frequency time-
domain signals can be used to classify hand/arm movements of
the same limb. A BCI relying on the imagination of such movements
may be used to control a neuroprosthesis more naturally and provide a
higher number of control classes.
15 healthy subjects
hand open/close, supination/pronation, and elbow extension/ﬂexion
61 EEG channels + joint angles (for movement onset detection)
Figure 1: Left: Subjects executed movements using an Armeo Spring rehabili-
tation device (Hocoma, Switzerland). Right: These movements were classiﬁed.
Figure 2: Sequence of a trial.
0.3 - 3 Hz 4-th order zero-phase Butterworth ﬁlter
shrinkage regularized linear discriminant analysis (sLDA) classiﬁer
1-vs-1 classiﬁcation strategy
calculation of sLDA patterns  in source space, see Figure 3
Figure 3: Patterns are calculated from each 1-vs-1 classiﬁer; subsequently scaled
and transformed into the source space; then we calculated the absolute value and
averaged over patterns. Finally, we averaged over time from -0.5 s to 0.5 s relative
to movement onset.
average classiﬁcation accuracy: maximum of 41 % (7 % standard
deviation) at 0.125 s, see Figure 4
signiﬁcance level of the average classiﬁcation accuracy: 18 %
signiﬁcance level of the classiﬁcation accuracy for each subject: 24 %
α= 0.05, Bonferroni corrected wrt. the length of the presented time
all subjects reached signiﬁcant classiﬁcation accuracies
the confusion matrix in Figure 4 indicates that movements involving
the same joints (e.g. hand open vs hand close) are less discriminable
than movements involving diﬀerent joints (e.g. hand open vs arm ex-
-2 -1.5 -1 -0.5 0 0.5 1 1.5
Fle Ext Sup Pro Clo Opn
Figure 4: Left: Subjects’ classiﬁcation accuracies (time locked to movement on-
set); the bold line is the grand average. Solid line is the chance level is; the dashed
line is the signiﬁcance level for the grand average. Right: Confusion matrix with
Figure 5: Classiﬁer pattern averaged over all subjects. Blue corresponds to zero,
red to the maximum value. Only signiﬁcant voxels wrt. the reference period (-2 s
to 1 s) are colored (α= 0.05, Wilcoxon signed rank test, Bonferroni corrected wrt.
the number of EEG channels).
We have shown that low-frequency time domain signals can be used
to discriminate between diﬀerent movements of the same
upper limb. Movement accuracies peak after the movement onset but
reach signiﬁcantly high classiﬁcation accuracies before the movement on-
set. This shows that upcoming movements can be classiﬁed from the
movement planning phase. This is crucial for a BCI applicable for
end users with SCI who cannot execute all movements anymore. Fur-
thermore, movements involving diﬀerent joints are better disciminable
than movements involving the same joints.
1. X Liao, D Yao, D Wu, and C Li, Combining Spatial Filters for the Classiﬁcation of Single-Trial EEG in a Finger Movement Task IEEE Trans
Biomed Eng, 54(5), 821-831, 2007
This work is supported by the European ICT Programme
Project H2020-643955 ”MoreGrasp” and the ERC Con-
solidator Grant ERC-681231 ”Feel Your Reach”.