Context-awareness for multi-sensor data fusion in smart environments

Risultato della ricerca: Other

10 Citazioni (Scopus)

Abstract

Multi-sensor data fusion is extensively used to merge data collected by heterogeneous sensors deployed in smart environments. However, data coming from sensors are often noisy and inaccurate, and thus probabilistic techniques, such as Dynamic Bayesian Networks, are often adopted to explicitly model the noise and uncertainty of data. This work proposes to improve the accuracy of probabilistic inference systems by including context information, and proves the suitability of such an approach in the application scenario of user activity recognition in a smart home environment. However, the selection of the most convenient set of context information to be considered is not a trivial task. To this end, we carried out an extensive experimental evaluation which shows that choosing the right combination of context information is fundamental to maximize the inference accuracy.
Lingua originaleEnglish
Pagine377-391
Numero di pagine15
Stato di pubblicazionePublished - 2016

Fingerprint

Multi-sensor Data Fusion
Smart Environments
Sensor data fusion
Context-awareness
Sensors
Bayesian networks
Probabilistic Inference
Dynamic Bayesian Networks
Sensor
Activity Recognition
Smart Home
Inaccurate
Experimental Evaluation
Trivial
Maximise
Uncertainty
Scenarios
Context
Model

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cita questo

@conference{e36c8c27dc6948c1abe202ffe1b8db78,
title = "Context-awareness for multi-sensor data fusion in smart environments",
abstract = "Multi-sensor data fusion is extensively used to merge data collected by heterogeneous sensors deployed in smart environments. However, data coming from sensors are often noisy and inaccurate, and thus probabilistic techniques, such as Dynamic Bayesian Networks, are often adopted to explicitly model the noise and uncertainty of data. This work proposes to improve the accuracy of probabilistic inference systems by including context information, and proves the suitability of such an approach in the application scenario of user activity recognition in a smart home environment. However, the selection of the most convenient set of context information to be considered is not a trivial task. To this end, we carried out an extensive experimental evaluation which shows that choosing the right combination of context information is fundamental to maximize the inference accuracy.",
author = "Pierluca Ferraro and {De Paola}, Alessandra and Salvatore Gaglio and {Lo Re}, Giuseppe",
year = "2016",
language = "English",
pages = "377--391",

}

TY - CONF

T1 - Context-awareness for multi-sensor data fusion in smart environments

AU - Ferraro, Pierluca

AU - De Paola, Alessandra

AU - Gaglio, Salvatore

AU - Lo Re, Giuseppe

PY - 2016

Y1 - 2016

N2 - Multi-sensor data fusion is extensively used to merge data collected by heterogeneous sensors deployed in smart environments. However, data coming from sensors are often noisy and inaccurate, and thus probabilistic techniques, such as Dynamic Bayesian Networks, are often adopted to explicitly model the noise and uncertainty of data. This work proposes to improve the accuracy of probabilistic inference systems by including context information, and proves the suitability of such an approach in the application scenario of user activity recognition in a smart home environment. However, the selection of the most convenient set of context information to be considered is not a trivial task. To this end, we carried out an extensive experimental evaluation which shows that choosing the right combination of context information is fundamental to maximize the inference accuracy.

AB - Multi-sensor data fusion is extensively used to merge data collected by heterogeneous sensors deployed in smart environments. However, data coming from sensors are often noisy and inaccurate, and thus probabilistic techniques, such as Dynamic Bayesian Networks, are often adopted to explicitly model the noise and uncertainty of data. This work proposes to improve the accuracy of probabilistic inference systems by including context information, and proves the suitability of such an approach in the application scenario of user activity recognition in a smart home environment. However, the selection of the most convenient set of context information to be considered is not a trivial task. To this end, we carried out an extensive experimental evaluation which shows that choosing the right combination of context information is fundamental to maximize the inference accuracy.

UR - http://hdl.handle.net/10447/218460

UR - https://link.springer.com/chapter/10.1007%2F978-3-319-49130-1_28

M3 - Other

SP - 377

EP - 391

ER -