Skip to main content

Table 2 Results of the K-Means algorithm for each task with one or three parameters among ’Maximum speed of the centroid’ (Centroid max speed), ’Maximum body dispersion’ (Body dispersion) and ’Variability of the horizontal centroid’ (Centroid variability). The model considered as relevant was the one with which all elderly participants were clustered in the same group. The table presents the number of young participants in cluster A and cluster B (cluster A - cluster B)

From: Fast and automatic assessment of fall risk by coupling machine learning algorithms with a depth camera to monitor simple balance tasks

Tasks

Centroid variability

Centroid max speed

Body dispersion

3 parameters

1

5 - 39

16 - 28

31 - 13

38 - 6

2

7 - 37

15 - 29

22 - 22

19 - 25

3

31 - 13

11 - 33

31 - 13

10 - 34

4

10 - 34

0 - 44

3 - 41

1 - 43

5

2 - 42

3 - 41

3 - 41

3 - 41

6

1 - 43

3 - 41

1 - 43

1 - 43

7

5 - 39

4 - 40

9 - 35

35 - 9

8

0 - 44

0 - 44

0 - 44

0 - 44