Skip to main content

Advertisement

Fig. 3 | Journal of NeuroEngineering and Rehabilitation

Fig. 3

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

Fig. 3

a) Stacked bar graph of accuracies from the load cell based classifier for all classes and participants. Classes ordered from most accurate at the bottom to least accurate at the top. b) A simpler representation for the four worst classified classes. Participants rank ordered based on total accuracy of the presented classes. Black horizontal line represents a general cutoff for highly functional levels of classification accuracy (90%). Classification accuracy for these four lowest classes range from 50 to 99%, 42 to 95%, 48 to 99%, and 3 to 99% for External rotation, Abduction, Adduction, and Internal rotation respectively

Back to article page