Fault Detection in Wireless Sensor Networks Through SVM Classifier
IEEE Sensors JournalPublished 8 November 2017
Salah Zidi, Tarek Moulahi, Bechir Alaya
Citations310
SJR quartileQ1
SJR score1.04
SNIP1.50
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Support vector machines (SVMs) classification method is used for fault detection in WSNs and can be easily executed at cluster heads to detect anomalous sensor.
Abstract
Wireless sensor networks (WSNs) are prone to many failures such as hardware failures, software failures, and communication failures. The fault detection in WSNs is a challenging problem due to sensor resources limitation and the variety of deployment field. Furthermore, the detection has to be precise to avoid negative alerts, and rapid to limit loss. The use of machine learning seems to be one of the most convenient solutions for detecting failure in WSNs. In this paper, support vector machines (SVMs) classification method is used for this purpose. Based on statistical learning theory, SVM is used in our context to define a decision function. As a light process in term of required resources, this decision function can be easily executed at cluster heads to detect anomalous sensor. The effectiveness of SVM for fault detection in WSNs is shown through an experimental study, comparing it to latest for the same application.
Keywords
Computer ScienceEngineering
TechnometricsStatistical Learning Theory
26,913 Citations1999Yuhai Wu, Vladimir Vapnik
Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Computer NetworksWireless sensor network survey
6,161 Citations2008Jennifer Yick, Biswanath Mukherjee +1 more
This survey presents a comprehensive review of the recent literature since the publication of a survey on sensor networks, and gives an overview of several new applications and then reviews the literature on various aspects of WSNs.
Computer CommunicationsFault detection of wireless sensor networks
233 Citations2008Myeong-Hyeon Lee, Yoon-Hwa Choi
Simulation results show that sensor nodes with permanent faults are identified with high accuracy for a wide range of fault rates, while most of the transient faults are tolerated with negligible performance degradation.
Journal of Network and Computer ApplicationsAn analysis of fault detection strategies in wireless sensor networks
186 Citations2016Thaha Muhammed, Riaz Ahmed Shaikh
Journal of Materials Processing TechnologyEMD-based pulsed TIG welding process porosity defect detection and defect diagnosis using GA-SVM
139 Citations2016Yiming Huang, Di Wu +3 more
Labelled data collection for anomaly detection in wireless sensor networks
139 Citations2010Shan Suthaharan, Mohammed Alzahrani +3 more
This group proposed an ellipsoid-based anomaly detection algorithm but demonstrated its performance using synthetic datasets and real Intel Berkeley Research Laboratory and Grand St. Bernard datasets which are not labeled with anomalies.
Expert Systems with ApplicationsProbabilistic fault detector for Wireless Sensor Network
84 Citations2013Bill Chun Piu Lau, W. M. Eden +1 more
A novel centralized hardware fault detection approach for a structured Wireless Sensor Network (WSN) based on Naive Bayes framework that analyzes the end-to-end transmission time collected at the sink to maximize the network's life.
IEEE Transactions on Parallel and Distributed SystemsA Time Efficient Approach for Detecting Errors in Big Sensor Data on Cloud
83 Citations2014Chi Yang, Chang Liu +3 more
A novel data error detection approach which exploits the full computation potential of cloud platform and the network feature of WSN to significantly reduce the time for error detection and location in big data sets generated by large scale sensor network systems with acceptable error detecting accuracy.
Wireless Personal CommunicationsFDS: Fault Detection Scheme for Wireless Sensor Networks
73 Citations2015Chafiq Titouna, Makhlouf Aliouat +1 more
A fault detection scheme (FDS) is proposed to identify faulty sensor nodes in Wireless Sensor Networks (WSN) and it is found that FDS performance outperforms that of FDWSN.
Fault Detection in Wireless Sensor Networks: A Machine Learning Approach
58 Citations2013Ehsan Ullah Warriach, Kenji Tei
This work develops a statistical approach to detect and identify faults in a WSN, which uses Hidden Markov Models (HMMs) to capture the fault-free dynamics of an environment and dynamics of faulty data.
Wireless Personal CommunicationsOutlier Detection Approach Using Bayes Classifiers in Wireless Sensor Networks
47 Citations2015Chafiq Titouna, Makhlouf Aliouat +1 more
A two-level sensor fusion-based outlier detection technique for WSN that is conducted locally inside the sensor nodes, while the second level is carried out in a level higher (e.g., in a cluster head or gateway).
Wireless NetworksKuiper test and autoregressive model-based approach for wireless sensor network fault diagnosis
36 Citations2014Xiaohang Jin, Tommy W. S. Chow +3 more
WSN anomaly detection model based on autoregressive (AR) model and Kuiper test-based passive diagnosis is proposed and results show that the proposed approach could differentiate WSNs normal conditions from faulty conditions.
Wireless NetworksFault detection and recovery scheme for routing and lifetime enhancement in WSN
34 Citations2015M. Yuvaraja, M. Sabrigiriraj
This work proposes to develop a fault detection and recovery scheme where the sink generates an agent packet and the Agent forms a query path towards the dead or faulty node.
Neural Processing LettersDistributed Fault Detection in Sensor Networks using a Recurrent Neural Network
28 Citations2013Oliver Obst
This work presents an approach that learns spatio-temporal correlations between different sensors, and makes use of the learned model to detect anomalous sensors by using distributed computation and only local communication between nodes.
Efficient fault node detection algorithm for wireless sensor networks
21 Citations2014Rama Ranjan Panda, Bhabani Sankar Gouda +1 more
This paper has proposed centralized robust fault detection algorithm to identify soft faulty sensor node present in the network and shows that the detection accuracy and false alarm rate performance is much better compared to the conventional algorithm.
Weighted distributed fault detection for wireless sensor networks Based on the distance
17 Citations2014Zhen Feng, Jing Qi Fu +1 more
In wireless sensor networks, this paper puts forward a distributed fault detection algorithm that takes into account the spatial correlation of network node, based on the way of weighted distance, and compares its own reading with the weighted value to judge the fault node.
Convex hull based clustering algorithm
12 Citations2013Foued Theljani, Kaouther Laabidi +2 more
A dynamic convex hull based clustering algorithm dealing with data appearing sequentially and an additional merge mechanism is proposed to avoid local optima drawbacks and improve performances.
Lecture notes in computer scienceDistributed and Efficient One-Class Outliers Detection Classifier in Wireless Sensors Networks
11 Citations2015Oussama Ghorbel, Mohamed Wassim Jmal +2 more
This paper proposes Distributed and Efficient One-class Outliers Detection Classifier (DEOODC) based on Mahalanobis Kernel used for outlier detection in wireless sensor networks (WSNs) and reports that the proposed method performs better in finding outliers in wireless Sensor networks when compared to the One-Class SVM detection approach.
Journal of Computer Networks and CommunicationsEnergy Efficient Distributed Fault Identification Algorithm in Wireless Sensor Networks
10 Citations2014Meenakshi Panda, Pabitra Mohan Khilar
A distributed fault identification algorithm is proposed here to find both hard and soft faulty sensor nodes present in wireless sensor networks, and can detect the most common byzantine faults.
Journal of Dynamic Systems Measurement and ControlTennessee Eastman Process Diagnosis Based on Dynamic Classification With SVDD
9 Citations2015Foued Theljani, Kaouther Laabidi +2 more
A fast SVDD dedicated for multiclassification problems with dynamic removal/insertion of informations according to adequate rules is proposed and assessed on some synthetic data to prove its effectiveness.
International Journal of Modelling Identification and ControlLeast squares support kernel machines (LS-SKM) for identification
8 Citations2012Mounira Tarhouni, Salah Zidi +2 more
The results reveal the accuracy and the robustness of the obtained model based on the proposed hybrid method, which combines several kernels in order to take advantage of their performances and reflect the fact that practical learning problems often involve multiple, heterogeneous data sources.
Security and Communication NetworksReliable relay‐based broadcasting through formal concept analysis for WSNs
5 Citations2016Tarek Moulahi, Sami Touil +2 more
An enhancement of this method, called reliable relay-based broadcasting RRB, is proposed, which improves RDS-MPR by considering a trusted index for each node, which is updated during the data gathering process at the sink node.
Textual extraction and classification for medical risk management: A new Risk Management Platform to manage undesired medical events
3 Citations2015Salah Zidi, Thibaut Julien +2 more
A semi-automatic system to deal with the undesired events that may happen in the medical field, based on algorithms of textual extraction and classifications, performs a preprocessing of undesiredEvents' declarations.
Systems monitoring based on dynamic classification with SVDD
2 Citations2013Foued Theljani, Kaouther Laabidi +2 more
This paper proposes a dynamic classification method based on modified version of the Support Vector Domain Description (SVDD) that supports evolving data and maintains dynamically the descriptive model and is applied on a hydraulic system consisting of three interconnected tanks.