Skip to main content


Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Fig. 2 | Journal of NeuroEngineering and Rehabilitation

Fig. 2

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

Fig. 2

Figure a, d, g, j, m, p, s and v: For each balance task, the K-means clustering method was used to cluster participants in two groups (cluster A for yellow dots and cluster B for purple dots) based on three standardized parameters of silhouette and dispersion (see the three axes). Figure b, e, h, k, n, q, t and w: the outcome of the K-means clustering methods based on the ’Maximum speed of the centroid’ parameter is plotted as a function of the age and volume of physical activity of the participants. The dot color discriminates the two clusters A vs B (yellow vs purple). Figure c, f, i, l, o, r, u and x: Time required to perform the TUG test for the cluster A (yellow) and B (purple). Clusters A and B were formed using the ’Maximum speed of the centroid’ parameter, and only elderly people are represented here

Back to article page