Table 1.
Participant characteristics (mean and standard deviation).
Table 2.
Features derived from raw sensor data.
Table 3.
Class distributions at each level.
Table 4.
Features selected for able bodied participants.
Table 5.
Features selected for senior participants.
Table 6.
Features selected for stroke participants.
Table 7.
Common features selected across populations using CFS.
Table 8.
Classifier accuracy with all features and with selected feature subset using CFS.
Table 9.
Confusion Tables for all populations at Level 3 using all features and feature subsets selected by CFS (each instance represents 1 second).
Table 10.
Common features between populations using FCBF.
Table 11.
Classifier accuracy with all features and with selected feature subset using FCBF.
Table 12.
Common features ranked in the top ten across populations using Relief-F.