Copula based approach for measurement validity verification in wireless sensor networks

Sanaa Kawther Ghalem Bouabdellah Kechar 1 Ahcène Bounceur 2 Reinhardt Euler 2 Hammoudeh Mohammad Farid Lalem
2 Lab-STICC_UBO_CACS_MOCS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance, UBO - Université de Brest
Abstract : Outlier detection is the process of identifying the data objects that do not comply with the normal behavior of the defined data model. Used in automated data analysis, it ensures the desired data quality and reliability. This field has attracted increasing attention in the wireless sensor network domain, using methods from machine learning, data mining, and statistics literature. In this paper, we propose a novel outlier detection approach based on Copula theory. This powerful theory enables modeling the dependency between data measurements in a formal and statistical way.We have evaluated our proposed approach with a real world dataset. Our results show a detection rate of 85.90% and an error rate of 0.87% .
Type de document :
Communication dans un congrès
Second International Conference on Internet of Things, Data and Cloud Computing (ICC 2017), Mar 2017, Cambridge, United Kingdom
Liste complète des métadonnées

http://hal.univ-brest.fr/hal-01487535
Contributeur : Ahcène Bounceur <>
Soumis le : dimanche 12 mars 2017 - 16:44:03
Dernière modification le : mardi 16 janvier 2018 - 15:54:23

Identifiants

  • HAL Id : hal-01487535, version 1

Citation

Sanaa Kawther Ghalem, Bouabdellah Kechar, Ahcène Bounceur, Reinhardt Euler, Hammoudeh Mohammad, et al.. Copula based approach for measurement validity verification in wireless sensor networks. Second International Conference on Internet of Things, Data and Cloud Computing (ICC 2017), Mar 2017, Cambridge, United Kingdom. 〈hal-01487535〉

Partager

Métriques

Consultations de la notice

407