Title
Study Of The Detection Of Falls Using The Svm Algorithm, Different Datasets Of Movements And Anova
Abstract
Falls are becoming a major public health problem, which is intensified by the aging of the population. Falls are one of the main causes of death among the elderly and in population groups that develop risk activities. In this sense, technologies can provide solutions to improve this situation. In this work we have analyzed different repositories of movements and falls designed to test decision algorithms in automatic fall detection systems. The objectives of the study are: firstly, to clarify what are the characteristics of the most significant accelerometry signals to identify a fall and secondly, to analyze the possibility of extrapolating the learning achieved with a certain database when tested with another one. As a novelty with respect to other works in the literature, the statistical significance of the results has been systematically evaluated by the analysis of variance (ANOVA).
Year
DOI
Venue
2019
10.1007/978-3-030-17938-0_37
BIOINFORMATICS AND BIOMEDICAL ENGINEERING, IWBBIO 2019, PT I
Keywords
DocType
Volume
Fall detection system, Inertial sensors, Smartphone, Accelerometer, Machine learning, Supervised learning, ANOVA, Datasets of movements
Conference
11465
ISSN
Citations 
PageRank 
0302-9743
0
0.34
References 
Authors
0
3