Fig. 5From: Integrated space–frequency–time domain feature extraction for MEG-based Alzheimer’s disease classificationComparison between two modalities and the effectiveness of their score-level fusions: Megn mean accuracy (3-NN) 65.43%, SD 0.0514; Grad mean accuracy (QBNC) 85.93%, SD 0.1089; Fusion mean accuracy: 88.33%, SD 0.1598Back to article page