Table 2 Fall detection outcome of the VTSAMRNN-FARS model under distinct epochs.

From: A vision transformer with recurrent neural network-based fall activity recognition system for disabled persons in smart IoT environments

Class labels

\(\:\varvec{A}\varvec{c}\varvec{c}{\varvec{u}}_{\varvec{y}}\)

\(\:\varvec{P}\varvec{r}\varvec{e}{\varvec{c}}_{\varvec{n}}\)

\(\:\varvec{S}\varvec{e}\varvec{n}{\varvec{s}}_{\varvec{y}}\)

\(\:\varvec{S}\varvec{p}\varvec{e}{\varvec{c}}_{\varvec{y}}\)

\(\:{\varvec{F}1}_{\varvec{s}\varvec{c}\varvec{o}\varvec{r}\varvec{e}}\)

Kappa

Epoch-500

 Fall

98.89

98.89

98.89

99.14

98.89

98.96

 Non-Fall

99.14

99.14

99.14

98.89

99.14

99.21

 Average

99.02

99.02

99.02

99.02

99.02

99.08

Epoch-1000

 Fall

98.89

99.26

98.89

99.43

99.07

99.14

 Non-Fall

99.43

99.15

99.43

98.89

99.29

99.35

 Average

99.16

99.20

99.16

99.16

99.18

99.24

Epoch-1500

 Fall

98.89

99.26

98.89

99.43

99.07

99.14

 Non-Fall

99.43

99.15

99.43

98.89

99.29

99.35

 Average

99.16

99.20

99.16

99.16

99.18

99.25

Epoch-2000

 Fall

99.26

99.26

99.26

99.43

99.26

99.31

 Non-Fall

99.43

99.43

99.43

99.26

99.43

99.48

 Average

99.34

99.34

99.34

99.34

99.34

99.40

Epoch-2500

 Fall

99.63

99.26

99.63

99.43

99.45

99.53

 Non-Fall

99.43

99.71

99.43

99.63

99.57

99.65

 Average

99.53

99.49

99.53

99.53

99.51

99.59

Epoch-3000

 Fall

99.63

99.63

99.63

99.71

99.63

99.69

 Non-Fall

99.71

99.71

99.71

99.63

99.71

99.78

 Average

99.67

99.67

99.67

99.67

99.67

99.73