Table 4 Comparative results of SERDP-DLEOCE model with existing techniques.

From: Improving real-time emotion recognition system in assistive communication technologies for disabled persons using deep learning with equilibrium algorithm

Model

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

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

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

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

SERDP-DLEOCE

95.15

80.95

71.65

75.00

MGT-2

94.55

78.16

65.45

66.55

CGT-2

92.05

79.27

65.84

73.75

AraBERT

82.88

75.18

67.11

67.41

DenseNet201

77.36

77.54

67.35

66.36

EfficientNet-B3

79.27

76.28

68.40

72.53

ResNet50

78.75

73.04

67.83

74.70

NB + lexicon

69.85

70.33

68.02

73.41

Back to article page