Cargando…

Fault Detection in Wireless Sensor Networks through the Random Forest Classifier

Wireless Sensor Networks (WSNs) are vulnerable to faults because of their deployment in unpredictable and hazardous environments. This makes WSN prone to failures such as software, hardware, and communication failures. Due to the sensor’s limited resources and diverse deployment fields, fault detect...

Descripción completa

Detalles Bibliográficos
Autores principales: Noshad, Zainib, Javaid, Nadeem, Saba, Tanzila, Wadud, Zahid, Saleem, Muhammad Qaiser, Alzahrani, Mohammad Eid, Sheta, Osama E.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6480196/
https://www.ncbi.nlm.nih.gov/pubmed/30939764
http://dx.doi.org/10.3390/s19071568
_version_ 1783413520628449280
author Noshad, Zainib
Javaid, Nadeem
Saba, Tanzila
Wadud, Zahid
Saleem, Muhammad Qaiser
Alzahrani, Mohammad Eid
Sheta, Osama E.
author_facet Noshad, Zainib
Javaid, Nadeem
Saba, Tanzila
Wadud, Zahid
Saleem, Muhammad Qaiser
Alzahrani, Mohammad Eid
Sheta, Osama E.
author_sort Noshad, Zainib
collection PubMed
description Wireless Sensor Networks (WSNs) are vulnerable to faults because of their deployment in unpredictable and hazardous environments. This makes WSN prone to failures such as software, hardware, and communication failures. Due to the sensor’s limited resources and diverse deployment fields, fault detection in WSNs has become a daunting task. To solve this problem, Support Vector Machine (SVM), Convolutional Neural Network (CNN), Stochastic Gradient Descent (SGD), Multilayer Perceptron (MLP), Random Forest (RF), and Probabilistic Neural Network (PNN) classifiers are used for classification of gain, offset, spike, data loss, out of bounds, and stuck-at faults at the sensor level. Out of six faults, two of them are induced in the datasets, i.e., spike and data loss faults. The results are compared on the basis of their Detection Accuracy (DA), True Positive Rate (TPR), Matthews Correlation Coefficients (MCC), and F1-score. In this paper, a comparative analysis is performed among the classifiers mentioned previously on real-world datasets. Simulations show that the RF algorithm secures a better fault detection rate than the rest of the classifiers.
format Online
Article
Text
id pubmed-6480196
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-64801962019-04-29 Fault Detection in Wireless Sensor Networks through the Random Forest Classifier Noshad, Zainib Javaid, Nadeem Saba, Tanzila Wadud, Zahid Saleem, Muhammad Qaiser Alzahrani, Mohammad Eid Sheta, Osama E. Sensors (Basel) Article Wireless Sensor Networks (WSNs) are vulnerable to faults because of their deployment in unpredictable and hazardous environments. This makes WSN prone to failures such as software, hardware, and communication failures. Due to the sensor’s limited resources and diverse deployment fields, fault detection in WSNs has become a daunting task. To solve this problem, Support Vector Machine (SVM), Convolutional Neural Network (CNN), Stochastic Gradient Descent (SGD), Multilayer Perceptron (MLP), Random Forest (RF), and Probabilistic Neural Network (PNN) classifiers are used for classification of gain, offset, spike, data loss, out of bounds, and stuck-at faults at the sensor level. Out of six faults, two of them are induced in the datasets, i.e., spike and data loss faults. The results are compared on the basis of their Detection Accuracy (DA), True Positive Rate (TPR), Matthews Correlation Coefficients (MCC), and F1-score. In this paper, a comparative analysis is performed among the classifiers mentioned previously on real-world datasets. Simulations show that the RF algorithm secures a better fault detection rate than the rest of the classifiers. MDPI 2019-04-01 /pmc/articles/PMC6480196/ /pubmed/30939764 http://dx.doi.org/10.3390/s19071568 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Noshad, Zainib
Javaid, Nadeem
Saba, Tanzila
Wadud, Zahid
Saleem, Muhammad Qaiser
Alzahrani, Mohammad Eid
Sheta, Osama E.
Fault Detection in Wireless Sensor Networks through the Random Forest Classifier
title Fault Detection in Wireless Sensor Networks through the Random Forest Classifier
title_full Fault Detection in Wireless Sensor Networks through the Random Forest Classifier
title_fullStr Fault Detection in Wireless Sensor Networks through the Random Forest Classifier
title_full_unstemmed Fault Detection in Wireless Sensor Networks through the Random Forest Classifier
title_short Fault Detection in Wireless Sensor Networks through the Random Forest Classifier
title_sort fault detection in wireless sensor networks through the random forest classifier
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6480196/
https://www.ncbi.nlm.nih.gov/pubmed/30939764
http://dx.doi.org/10.3390/s19071568
work_keys_str_mv AT noshadzainib faultdetectioninwirelesssensornetworksthroughtherandomforestclassifier
AT javaidnadeem faultdetectioninwirelesssensornetworksthroughtherandomforestclassifier
AT sabatanzila faultdetectioninwirelesssensornetworksthroughtherandomforestclassifier
AT wadudzahid faultdetectioninwirelesssensornetworksthroughtherandomforestclassifier
AT saleemmuhammadqaiser faultdetectioninwirelesssensornetworksthroughtherandomforestclassifier
AT alzahranimohammadeid faultdetectioninwirelesssensornetworksthroughtherandomforestclassifier
AT shetaosamae faultdetectioninwirelesssensornetworksthroughtherandomforestclassifier