Fall detection is an important task in telemedicine.In this paper an approach based on supervised knowledge extraction is presented. A fall recordings database is analyzed offline and a set of IF...THEN rules is obtained. This way, also selection of the most relevant features for fall assessment is automatically carried out. The approach is embedded within a real-time mobile monitoring system, and is used to discriminate in real time normal daily activities from falls. If the data collected in real time by wearable sensors of the system allow recognizing a fall, suitable alarms are automatically generated.
Effective Supervised Knowledge Extraction for an mHealth System for Fall Detection
Giovanna Sannino;Ivanoe De Falco;Giuseppe De Pietro
2014
Abstract
Fall detection is an important task in telemedicine.In this paper an approach based on supervised knowledge extraction is presented. A fall recordings database is analyzed offline and a set of IF...THEN rules is obtained. This way, also selection of the most relevant features for fall assessment is automatically carried out. The approach is embedded within a real-time mobile monitoring system, and is used to discriminate in real time normal daily activities from falls. If the data collected in real time by wearable sensors of the system allow recognizing a fall, suitable alarms are automatically generated.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
