Skip to main content

Advertisement

Table 3 Summary of classification accuracies for each classifier across all participants

From: Applying LDA-based pattern recognition to predict isometric shoulder and elbow torque generation in individuals with chronic stroke with moderate to severe motor impairment

  Dataset
Class EMG-TD Torque Load cell EMG + LC
EF 88 89 92 94
AB 76 85 87 90
ER 76 87 89 90
HAB 91 97 97 97
EE 89 97 98 97
AD 78 80 84 87
IR 76 76 83 87
HAD 90 96 96 98
Average 83 88 91 92
  1. EMG-TD refers to EMG time-domain features, Torque to the mean-absolute value (MAV) of torques generated at the shoulder and elbow only, load cell refers to MAV from the raw load cell data, and EMG + LC are the EMG time-domain features and the MAV from the raw load cell data combined together. Bold indicates ≥90% accuracy