FIGURE 6 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Download
View publication
| Illustration of data architecture to compute importance.

| Illustration of data architecture to compute importance.

Source publication
FIGURE 1 | Average event related potentials for (A) Subject B on C3...
FIGURE 2 | Illustration of feature extraction steps that include metric...
FIGURE 3 | Mean and standard deviation of the real and imaginary values...
FIGURE 4 | Average frequency component absolute differences in dB from...
+3 FIGURE 6 | Illustration of data architecture to compute importance.
Metric Learning in Freewill EEG Pre-Movement and Movement Intention Classification for Brain Machine Interfaces
Article
Full-text available
  • Jul 2022
Decoding movement related intentions is a key step to implement BMIs. Decoding EEG has been challenging due to its low spatial resolution and signal to noise ratio. Metric learning allows finding a representation of data in a way that captures a desired notion of similarity between data points. In this study, we investigate how metric learning can...
Cite
Download full-text

Context in source publication

Context 1
... that B ∈R d×p . Figure 6 illustrates a conceptual diagram to explain how the contribution of the input EEG channels, which we call here importance, is obtained from the transformations learned by the metric learning algorithms. ...