Table 5 Error analysis of IPOIAR-DPRNN approach with existing techniques.

From: Enhancing indoor activity recognition for disabled persons using multi head self attention recurrent neural network with improved pelican algorithm

Methods

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

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

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

\(\:{\varvec{F}}_{\varvec{m}\varvec{e}\varvec{a}\varvec{s}\varvec{u}\varvec{r}\varvec{e}}\)

Multi-part bag-of-poses

17.85

18.95

21.50

19.78

RF-PCA

10.33

17.29

18.16

23.98

HAR3DS-Lie Group

9.12

19.54

15.47

20.57

LMMML-Skelets

6.58

18.28

19.57

23.49

Lie group + CNN

7.00

18.04

16.60

22.17

Skeletal BoW

5.66

19.58

23.01

18.44

HDS-SP

4.12

23.71

22.66

15.50

SJACHA-3DCNN

3.24

14.74

19.12

16.99

YOLOv5

9.67

16.63

17.57

23.22

CNN

8.36

18.98

14.87

19.95

ConvLSTM

5.92

17.58

18.79

22.85

IPOIAR-DPRNN

2.89

12.90

13.06

13.02