Fall Detection by Recognizing Patterns in Direction Changes of Constraining Forces: Tagungsband der eHealth2012

Stefan Steidl; Cornelia Schneider; Michael Hufnagl; Ammenwerth Elske; Hörbst Alexander; Hayn Dieter; Schreier Günter

Fall Detection by Recognizing Patterns in Direction Changes of Constraining Forces: Tagungsband der eHealth2012

Stefan Steidl
, Cornelia Schneider
, Michael Hufnagl
, Ammenwerth Elske (Editor)
, Hörbst Alexander (Editor)
, Hayn Dieter (Editor)
, Schreier Günter (Editor)

Salzburg Research Forschungsgesellschaft mbH

Research output: Contribution to conference › Paper › peer-review

Abstract

The severe consequences accidental falls may cause for elderly have pushed the development of mobility safeguarding systems. Threshold based fall detection algorithms in smartphones have shortcomings as accelerometer values from different devices are hardly comparable. In this work, a pattern-recognition procedure is presented whose main input consists of the change of direction of the constraining force that is exerted on an accelerometer attached laterally on the hip area. The algorithm makes use of fast wavelet decomposition and support vector machine theory.

Original language	German
Pages	27-32
Number of pages	6
Publication status	Published - 2012
Externally published	Yes

Cite this

@conference{70cf02c2a1e14086ab3af39f49afd3c0,

title = "Fall Detection by Recognizing Patterns in Direction Changes of Constraining Forces: Tagungsband der eHealth2012",

abstract = "The severe consequences accidental falls may cause for elderly have pushed the development of mobility safeguarding systems. Threshold based fall detection algorithms in smartphones have shortcomings as accelerometer values from different devices are hardly comparable. In this work, a pattern-recognition procedure is presented whose main input consists of the change of direction of the constraining force that is exerted on an accelerometer attached laterally on the hip area. The algorithm makes use of fast wavelet decomposition and support vector machine theory.",

keywords = "accelerometer data, fall detection, fast wavelet decomposition, pattern recognition, support vector machines",

author = "Stefan Steidl and Cornelia Schneider and Michael Hufnagl and Ammenwerth Elske and H{\"o}rbst Alexander and Hayn Dieter and Schreier G{\"u}nter",

year = "2012",

language = "Deutsch",

pages = "27--32",

}

TY - CONF

T1 - Fall Detection by Recognizing Patterns in Direction Changes of Constraining Forces

T2 - Tagungsband der eHealth2012

AU - Steidl, Stefan

AU - Schneider, Cornelia

AU - Hufnagl, Michael

A2 - Elske, Ammenwerth

A2 - Alexander, Hörbst

A2 - Dieter, Hayn

A2 - Günter, Schreier

PY - 2012

Y1 - 2012

N2 - The severe consequences accidental falls may cause for elderly have pushed the development of mobility safeguarding systems. Threshold based fall detection algorithms in smartphones have shortcomings as accelerometer values from different devices are hardly comparable. In this work, a pattern-recognition procedure is presented whose main input consists of the change of direction of the constraining force that is exerted on an accelerometer attached laterally on the hip area. The algorithm makes use of fast wavelet decomposition and support vector machine theory.

AB - The severe consequences accidental falls may cause for elderly have pushed the development of mobility safeguarding systems. Threshold based fall detection algorithms in smartphones have shortcomings as accelerometer values from different devices are hardly comparable. In this work, a pattern-recognition procedure is presented whose main input consists of the change of direction of the constraining force that is exerted on an accelerometer attached laterally on the hip area. The algorithm makes use of fast wavelet decomposition and support vector machine theory.

KW - accelerometer data

KW - fall detection

KW - fast wavelet decomposition

KW - pattern recognition

KW - support vector machines

M3 - Papier

SP - 27

EP - 32

ER -