Skip to main content

Table 5 MS-GCN robustness

From: Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks

Subjects

FP

Controls (k = 404)

0

Non-freezers (k = 423)

0

Freezers- (k = 195)

0

  1. Overview of MS-GCN’s robustness to false-positive FOG detections on the MoCap trials of the 14 healthy controls, 14 non-freezers, and 7 freezers that did not freeze in front of the cameras during the protocol. The letter k denotes the number of MoCap trials for each group
Back to article page

Journal of NeuroEngineering and Rehabilitation

ISSN: 1743-0003

Contact us