Skip to main content

Table 13 Comparative accuracy analysis for activity recognition using semi-population calibration approach

From: CAPHAR: context-aware personalized human activity recognition using associative learning in smart environments

Subjects

RF

HMM

ECOC (AB)

LSTM

AL

Subject 1

34.37%

39.05%

38.30%

42.37%

56.95%

Subject 2

32.09%

37.53%

39.47%

39.36%

54.52%

Subject 3

27.52%

29.87%

35.72%

39.59%

52.17%

Subject 4

30.65%

32.78%

39.48%

38.41%

53.19%

Subject 5

19.87%

14.52%

25.25%

26.02%

44.25%

Subject 6

30.73%

30.96%

39.30%

36.25%

55.00%

Subject 7

36.18%

39.76%

42.67%

42.63%

61.45%