Table 2.

Classification results with the best combination of features based on original pressure mats.

Class	RF	NB	SVM	MLP	k-NN
TP0	0.98	0.96	0.89	0.90	0.96
TP1	0.94	0.87	0.75	0.77	0.82
TP2	0.91	0.77	0.84	0.82	0.84
TP3	0.86	0.60	0.42	0.51	0.77
TP4	0.85	0.61	0.51	0.70	0.64
LFP0	0.97	0.94	0.86	0.91	0.95
LFP1	0.90	0.88	0.84	0.86	0.80
RFP0	0.92	0.85	0.82	0.83	0.84
RFP1	0.70	0.62	0.57	0.59	0.65
RFP2	0.61	0.53	0.50	0.53	0.57
Average	0.86	0.76	0.70	0.74	0.78
Time * (ms)	45	33	138	0.25	28

* Total prediction time for the three body parts for each frame.