Authors:
Rubén Blasco
;
Roberto Casas
;
Álvaro Marco
;
Victorián Coarasa
;
Yolanda Garrido
and
Jorge L. Falcó
Affiliation:
Instituto de Investigación en Ingeniería de Aragón, Universidad de Zaragoza, Spain
Keyword(s):
Fall detector, neural networks, ZigBee, wearable sensors, pattern recognition.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Data Manipulation
;
Devices
;
Health Engineering and Technology Applications
;
Health Information Systems
;
Human-Computer Interaction
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Theory and Methods
;
Wearable Sensors and Systems
Abstract:
Falls are one of the biggest concerns of elderly people. This paper addresses a fall detection system which uses an accelerometer to collect body accelerations, ZigBee to send relevant data when a fall might have happened and a neural network to recognize fall patterns. This method presents improved performance compared to traditional basic-threshold systems. Main advantage is that fall detection ratio is higher on neural network based systems. Another important issue is the high immunity to events not being falls, but with similar patterns (e.g. sitting in a sofa abruptly), usually confused with real falls. Minimization of these occurrences has big influence on the confidence the user has on the system.