Examining physical activity clustering using machine learning revealed a diversity of 24-hour step-counting patterns

Table 3 Step count amount and duration for each pattern

Pattern	Step count amount mean ± SD	Activity duration (hours) mean ± SD
All-Day (AD)	7020.0 ± 3271.4	14.29 ± 2.28
Bi-phasic (BP)	6178.2 ± 3102.1	14.54 ± 2.61
Morning (M)	6473.7 ± 4220.1	12.49 ± 3.97
Evening (E)	4871.0 ± 3091.9	10.91 ± 4.30
Irregular morning (IM)	2597.6 ± 3481.4	5.67 ± 5.39
Irregular night (IN)	3977.2 ± 5540.0	7.82 ± 6.48

Note Each step-counting pattern had different daily step counts. AD had the highest, followed by M and BP, then E. IN and IM had the lowest counts. In terms of duration, the BP pattern exhibited the longest activity duration per day, followed by AD, M and E patterns. IM and IN has the lowest duration of activity

ISSN: 2731-4391