Skip to main content
. 2018 Apr 1;18(4):1055. doi: 10.3390/s18041055

Table 8.

Comparison of activity recognition accuracy without (1D CNN only) and with test data sharpening (1D CNN+Sharpen). The bold numbers indicate the highest accuracy for each model.

Dataset (Model) Class 1D CNN Only (%) 1D CNN + Sharpen (%)
OPPORTUNITY (Up) 2 91.28 91.63
UCI HAR (Dynamic) 3 97.98 98.70
UCI HAR (Static) 3 96.60 96.67