Developing a system that can automatically detect health changes using transfer times of older adults

Table 7 Comparison of the results on training- and validation set (when the dataset contains two trends both trends are evaluated separately)

Training scenarios^a		Validation scenarios^b
Detection Rate (DR)
T r _SU	100 %	V _SU	100 %
T r _US	100 %	V _US	100 %
T r _SUS		V _SUS
S →U	100 %	S →U	100 %
U →S	100 %	U →S	100 %
T r _USU		V _USU
U →S	100 %	S →U	100 %
S →U	100 %	U →S	100 %
Average Run Length (ARL)
T r _SU	8.05±3.62	V _SU	7.70±3.34
T r _US	12.95±4.31	V _US	10.95±3.59
T r _SUS		V _SUS
S→U	7.65±4.10	S →U	8.35±3.59
U →S	11±4.30	U →S	12.45±5.25
T r _USU		V _USU
U →S	10.15±5.96	U →S	10±3.54
S →U	8±5.58	S →U	8.10±2.88
Average number of false alarms per week (FPR)
T r _S	0.15±0.17	V _S	0.16±0.07
T r _U	0.11±0.07	V _U	0.14±0.06
T r _SU	0.20±0.10	V _SU	0.20±0.07
T r _US	0.18±0.07	V _US	0.17±0.07
T r _SUS	0.23±0.08	V _SUS	0.20±0.08
T r _USU	0.23±0.07	V _USU	0.20±0.08