Table 3 Comparison analysis of AHARDP-DLSO approach with existing models18,19,37,38,39.

From: Advanced smart human activity recognition system for disabled people using artificial intelligence with snake optimizer techniques

Model

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

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

\(\:\varvec{R}\varvec{e}\varvec{c}{\varvec{a}}_{\varvec{l}}\)

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

AHARDP-DLSO

95.81

87.52

87.40

87.40

SVM

90.29

85.68

86.14

84.24

GRU

89.98

86.44

81.29

86.34

At-CapNet

92.33

82.12

85.73

84.16

CNN-LSTM

95.25

81.38

81.64

86.27

CNN Classifier

93.32

80.54

84.52

86.81

Baseline Model

89.55

85.06

86.58

83.73

VGG16 Model

89.32

85.64

80.74

85.75

Inception-V3

91.54

81.35

85.02

83.51

Xception Model

90.17

80.36

85.42

86.03

EfficientNet B0

89.11

85.25

84.52

83.26