A machine learning approach for user localization exploiting connectivity data

Risultato della ricerca: Article

11 Citazioni (Scopus)

Abstract

The growing popularity of Location-Based Services (LBSs) has boosted research on cheaper and more pervasive localization systems, typically relying on such monitoring equipment as Wireless Sensor Networks (WSNs), which allow to re-use the same instrumentation both for monitoring and for localization without requiring lengthy off-line training. This work addresses the localization problem, exploiting knowledge acquired in sample environments, and extensible to areas not considered in advance. Localization is turned into a learning problem, solved by a statistical algorithm. Additionally, parameter tuning is fully automated thanks to its formulation as an optimization problem based only on connectivity information. Performance of our approach has been thoroughly assessed based on data collected in simulation as well as in actual deployment.
Lingua originaleEnglish
pagine (da-a)125-134
Numero di pagine10
RivistaEngineering Applications of Artificial Intelligence
Volume50
Stato di pubblicazionePublished - 2016

Fingerprint

Learning systems
Location based services
Monitoring
Wireless sensor networks
Tuning

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cita questo

@article{8482918741664131b775483fc2f9d8f5,
title = "A machine learning approach for user localization exploiting connectivity data",
abstract = "The growing popularity of Location-Based Services (LBSs) has boosted research on cheaper and more pervasive localization systems, typically relying on such monitoring equipment as Wireless Sensor Networks (WSNs), which allow to re-use the same instrumentation both for monitoring and for localization without requiring lengthy off-line training. This work addresses the localization problem, exploiting knowledge acquired in sample environments, and extensible to areas not considered in advance. Localization is turned into a learning problem, solved by a statistical algorithm. Additionally, parameter tuning is fully automated thanks to its formulation as an optimization problem based only on connectivity information. Performance of our approach has been thoroughly assessed based on data collected in simulation as well as in actual deployment.",
keywords = "Artificial Intelligence, Control and Systems Engineering, Electrical and Electronic Engineering, Range-free localization, Support vector machines, Wireless sensor networks",
author = "Pietro Cottone and {Lo Re}, Giuseppe and Salvatore Gaglio and Marco Ortolani",
year = "2016",
language = "English",
volume = "50",
pages = "125--134",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - A machine learning approach for user localization exploiting connectivity data

AU - Cottone, Pietro

AU - Lo Re, Giuseppe

AU - Gaglio, Salvatore

AU - Ortolani, Marco

PY - 2016

Y1 - 2016

N2 - The growing popularity of Location-Based Services (LBSs) has boosted research on cheaper and more pervasive localization systems, typically relying on such monitoring equipment as Wireless Sensor Networks (WSNs), which allow to re-use the same instrumentation both for monitoring and for localization without requiring lengthy off-line training. This work addresses the localization problem, exploiting knowledge acquired in sample environments, and extensible to areas not considered in advance. Localization is turned into a learning problem, solved by a statistical algorithm. Additionally, parameter tuning is fully automated thanks to its formulation as an optimization problem based only on connectivity information. Performance of our approach has been thoroughly assessed based on data collected in simulation as well as in actual deployment.

AB - The growing popularity of Location-Based Services (LBSs) has boosted research on cheaper and more pervasive localization systems, typically relying on such monitoring equipment as Wireless Sensor Networks (WSNs), which allow to re-use the same instrumentation both for monitoring and for localization without requiring lengthy off-line training. This work addresses the localization problem, exploiting knowledge acquired in sample environments, and extensible to areas not considered in advance. Localization is turned into a learning problem, solved by a statistical algorithm. Additionally, parameter tuning is fully automated thanks to its formulation as an optimization problem based only on connectivity information. Performance of our approach has been thoroughly assessed based on data collected in simulation as well as in actual deployment.

KW - Artificial Intelligence

KW - Control and Systems Engineering

KW - Electrical and Electronic Engineering

KW - Range-free localization

KW - Support vector machines

KW - Wireless sensor networks

UR - http://hdl.handle.net/10447/191072

M3 - Article

VL - 50

SP - 125

EP - 134

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

ER -