In the last years, the extensive use of smart objects embedded in the physical world, in order to monitor and record physical or environmental conditions, has increased rapidly. In this scenario, heterogeneous devices are connected together into a network. Data generated from such system are usually stored in a database, which often shows a lack of semantic information and relationship among devices. Moreover, this set can be incomplete, unreliable, incorrect and noisy. So, it turns out to be important both the integration of information and the interoperability of applications. For this reason, ontologies are becoming widely used to describe the domain and achieve efficient interoperability of information system. An example of the described situation could be represented by Ambient Assisted Living context, which intends to enable older or disabled people to remain living independently longer in their own house. In this contest, human activity recognition plays a main role because it could be considered as starting point to facilitate assistance and care for elderly. Due to the nature of human behavior, it is necessary to manage the time and spatial restrictions. So, we propose a framework that implements a novel methodology based on the integration of an ontology for representing contextual knowledge and a Complex Event Processing engine for supporting timed reasoning. Moreover, it is an infrastructure where knowledge, organized in conceptual spaces (based on its meaning) can be semantically queried, discovered, and shared across applications. In our framework, benefits deriving from the implementation of a domain ontology are exploited into different levels of abstrac- tion. Thereafter, reasoning techniques represent a preprocessing method to prepare data for the final temporal analysis. The results, presented in this paper, have been obtained applying the methodology into AALISABETH, an Ambient Assisted Living project aimed to monitor the lifestyle of old people, not suffering from major chronic diseases or severe disabilities.

Human Activity Recognition using a Semantic Ontology-Based Framework

CULMONE, Rosario;GIULIODORI, PAOLO;QUADRINI, MICHELA
2015-01-01

Abstract

In the last years, the extensive use of smart objects embedded in the physical world, in order to monitor and record physical or environmental conditions, has increased rapidly. In this scenario, heterogeneous devices are connected together into a network. Data generated from such system are usually stored in a database, which often shows a lack of semantic information and relationship among devices. Moreover, this set can be incomplete, unreliable, incorrect and noisy. So, it turns out to be important both the integration of information and the interoperability of applications. For this reason, ontologies are becoming widely used to describe the domain and achieve efficient interoperability of information system. An example of the described situation could be represented by Ambient Assisted Living context, which intends to enable older or disabled people to remain living independently longer in their own house. In this contest, human activity recognition plays a main role because it could be considered as starting point to facilitate assistance and care for elderly. Due to the nature of human behavior, it is necessary to manage the time and spatial restrictions. So, we propose a framework that implements a novel methodology based on the integration of an ontology for representing contextual knowledge and a Complex Event Processing engine for supporting timed reasoning. Moreover, it is an infrastructure where knowledge, organized in conceptual spaces (based on its meaning) can be semantically queried, discovered, and shared across applications. In our framework, benefits deriving from the implementation of a domain ontology are exploited into different levels of abstrac- tion. Thereafter, reasoning techniques represent a preprocessing method to prepare data for the final temporal analysis. The results, presented in this paper, have been obtained applying the methodology into AALISABETH, an Ambient Assisted Living project aimed to monitor the lifestyle of old people, not suffering from major chronic diseases or severe disabilities.
2015
262
File in questo prodotto:
File Dimensione Formato  
intsys_v8_n12_2015_13.pdf

accesso aperto

Descrizione: Article
Tipologia: Versione Editoriale
Licenza: Dominio pubblico
Dimensione 1.94 MB
Formato Adobe PDF
1.94 MB Adobe PDF Visualizza/Apri

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/11581/386669
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact