The recent technological advances in sensor miniaturization and embedded processing have provided new challenges and possibilities to the field of wearable computing. Two research areas are particularly interested by this innovation: healthcare technology applications that are devoted to analyzing the daily activities of a person to evaluate their general health, and personal dead reckoning (PDR) systems that focus on the analysis of the person's movements to keep track of his/her position in dangerous environments and situations. The identification of suitable algorithms and techniques to process wearable sensors data is a research challenge that must be overcome for both areas. The possibility to compare different solutions over public test benches is crucial to this aim. For this reason, we present the human odometry outdoor data set (HOOD), a public data set for the PDR systems and the wearable human activity recognition folder (WHARF), a public repository for human activity recognition (HAR), composed of over 1,000 acceleration recordings referring to 14 daily activities, and a MATLAB library allowing the creation and validation of acceleration models of the activities.

Wearable inertial sensors: applications, challenges, and public test benches

BRUNO, BARBARA;MASTROGIOVANNI, FULVIO;SGORBISSA, ANTONIO
2015-01-01

Abstract

The recent technological advances in sensor miniaturization and embedded processing have provided new challenges and possibilities to the field of wearable computing. Two research areas are particularly interested by this innovation: healthcare technology applications that are devoted to analyzing the daily activities of a person to evaluate their general health, and personal dead reckoning (PDR) systems that focus on the analysis of the person's movements to keep track of his/her position in dangerous environments and situations. The identification of suitable algorithms and techniques to process wearable sensors data is a research challenge that must be overcome for both areas. The possibility to compare different solutions over public test benches is crucial to this aim. For this reason, we present the human odometry outdoor data set (HOOD), a public data set for the PDR systems and the wearable human activity recognition folder (WHARF), a public repository for human activity recognition (HAR), composed of over 1,000 acceleration recordings referring to 14 daily activities, and a MATLAB library allowing the creation and validation of acceleration models of the activities.
File in questo prodotto:
File Dimensione Formato  
RASMAG2015.pdf

accesso chiuso

Tipologia: Documento in versione editoriale
Dimensione 3.06 MB
Formato Adobe PDF
3.06 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/818706
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 32
  • ???jsp.display-item.citation.isi??? 23
social impact