Fault‐Tolerant Prediction‐Based Scheme for Target Tracking in Wireless Sensor Networks

N. Demigha O. Badache M. Aissani A. Mellouk 1
1 CIR
LISSI - Laboratoire Images, Signaux et Systèmes Intelligents
Abstract : Fault-tolerance is an important function in target tracking application using wireless sensor networks. We propose in this paper, an efficient fault-tolerant approach for target tracking that prevents the loss of the target. Instead of using a single prediction mechanism, our approach uses a multi-level incremental prediction technique that adjusts the prediction precision of the target movement. The responsible node of target detection uses multiple historical information pieces to calculate multi-level predictions which have different precision levels according to the number of information pieces used. Thanks to our parametric prediction model, our approach increases the prediction success rate and decreases the target loss frequency compared to basic approaches that use simple prediction models.
Keywords : Fault tolerance Target tracking Peer to peer computing Wireless sensor networks Energy efficiency Error correction Predictive models Surveillance Synchronization Protocols
Type de document :
Communication dans un congrès
Proc. Of the IEEE Global Communications Conference (GLOBECOM), 2009, Honolulu, United States. pp.1-5, 2009
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-01678656
Contributeur : Lab Lissi <>
Soumis le : mardi 9 janvier 2018 - 11:53:14
Dernière modification le : mercredi 20 février 2019 - 21:49:53

Identifiants

  • HAL Id : hal-01678656, version 1

Collections

UPEC-UPEM | LISSI

Citation

N. Demigha, O. Badache, M. Aissani, A. Mellouk. Fault‐Tolerant Prediction‐Based Scheme for Target Tracking in Wireless Sensor Networks. Proc. Of the IEEE Global Communications Conference (GLOBECOM), 2009, Honolulu, United States. pp.1-5, 2009. 〈hal-01678656〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

22

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD