Journal: Journal of Neural Engineering
Article Title: Beta-band power classification of go/no-go arm-reaching responses in the human hippocampus
doi: 10.1088/1741-2552/ad5b19
Figure Lengend Snippet: Top-left panel: Averaged beta-band (13–30 Hz) power spectral density half-violin plots. During the pre-processing stage, beta-band power magnitude measures from hippocampal contacts were used for both the ‘Go’ and ‘No-go’ conditions as input features. Top-right panel: Clusters were extracted by principal component analysis from all frequency bins within the beta-band power (13–30 Hz) and gray-matter contacts in the hippocampus, the first two principal components were used for cross-validated DA. Bottom panel: Silhouette score box plots from all participants grouped by ‘Combined’ (gray), ‘Go’ (green), and ‘No-go’ (red) trials.
Article Snippet: The Silhouette score (calculated using the Matlab function ‘silhouette’) measures how closely a data point resides within its own cluster (cohesion or tightness), as well as how distinct the same data point is from other clusters (separation).
Techniques: