Wireless sensor network (WSN) always comes up with the need of deploying either mobile or immobile sensor nodes or both. Wireless communication among these nodes is crucial and it requires identifying the location of these nodes within a specific region. Global positioning system (GPS) is widely used for location tracking. However, when it comes to WSN, GPS has its limitations, due to its high power consumption and the overhead of additional hardware cost. The research challenge here lies in the efficient location tracking of wireless sensor nodes, especially in closed indoor and outdoor environments. This paper comes up with a simple and easy-to-implement technique using artificial neural networks (ANNs) to manipulate the location of the sensor nodes. In this paper, the back-propagation network training algorithm for providing supervised learning to multilayer perceptron is generalized to synthesize the WSN and gives out 2D Cartesian coordinates of the nodes. The technique is both cost-efficient and achieves 98% accuracy.

Node localization for indoor tracking using artificial neural network

Deb, Novarun;Cortesi, Agostino;Chaki, Nabendu
2018-01-01

Abstract

Wireless sensor network (WSN) always comes up with the need of deploying either mobile or immobile sensor nodes or both. Wireless communication among these nodes is crucial and it requires identifying the location of these nodes within a specific region. Global positioning system (GPS) is widely used for location tracking. However, when it comes to WSN, GPS has its limitations, due to its high power consumption and the overhead of additional hardware cost. The research challenge here lies in the efficient location tracking of wireless sensor nodes, especially in closed indoor and outdoor environments. This paper comes up with a simple and easy-to-implement technique using artificial neural networks (ANNs) to manipulate the location of the sensor nodes. In this paper, the back-propagation network training algorithm for providing supervised learning to multilayer perceptron is generalized to synthesize the WSN and gives out 2D Cartesian coordinates of the nodes. The technique is both cost-efficient and achieves 98% accuracy.
2018
3rd IEEE International Conference on Fog and Mobile Edge Computing, FMEC 2018
File in questo prodotto:
File Dimensione Formato  
Paper_slice.pdf

accesso aperto

Tipologia: Documento in Pre-print
Licenza: Accesso libero (no vincoli)
Dimensione 506.08 kB
Formato Adobe PDF
506.08 kB Adobe PDF Visualizza/Apri

I documenti in ARCA 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/10278/3702277
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 0
social impact