Upper Arm Motion High-Density sEMG Recognition Optimization Based on Spatial and Time-Frequency Domain Features

Table 1

Different experimenter subjects in eight different motions using PCA spatial filter through the cumulative contribution rate to determine the number of principle component.

Select PCs	Mode 1	Mode 2	Mode 3	Mode 4	Mode 5	Mode 6	Mode 7	Mode 8	Average value
Subject 1	36	22	6	4	5	7	6	6	12
Subject 2	36	22	6	4	7	7	6	6	12
Subject 3	28	13	5	4	7	7	6	6	10
Subject 4	30	12	5	4	7	7	6	6	10
Subject 5	32	17	6	4	7	7	6	6	11
Subject 6	28	21	6	4	6	7	6	6	11