Analysis of Fault Classifiers to Detect the Faults and Node Failures in a Wireless Sensor Network
Technology evaluation in the electronics field leads to the great development of Wireless Sensor Networks (WSN) for a variety of applications. The sensor nodes are deployed in hazardous environments, and they are operated by isolated battery sources. Network connectivity is purely based on power ava...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/10/1609 |
| _version_ | 1797500235845468160 |
|---|---|
| author | S. Gnanavel M. Sreekrishna Vinodhini Mani G. Kumaran R. S. Amshavalli Sadeen Alharbi Mashael Maashi Osamah Ibrahim Khalaf Ghaida Muttashar Abdulsahib Ans D. Alghamdi Theyazn H. H. Aldhyani |
| author_facet | S. Gnanavel M. Sreekrishna Vinodhini Mani G. Kumaran R. S. Amshavalli Sadeen Alharbi Mashael Maashi Osamah Ibrahim Khalaf Ghaida Muttashar Abdulsahib Ans D. Alghamdi Theyazn H. H. Aldhyani |
| author_sort | S. Gnanavel |
| collection | DOAJ |
| description | Technology evaluation in the electronics field leads to the great development of Wireless Sensor Networks (WSN) for a variety of applications. The sensor nodes are deployed in hazardous environments, and they are operated by isolated battery sources. Network connectivity is purely based on power availability, which impacts the network lifetime. Hence, power must be used wisely to prolong the network lifetime. The sensor nodes that fail due to power have to detect quickly to maintain the network. In a WSN, classifiers are used to detect the faults for checking the data generated by the sensor nodes. In this paper, six classifiers such as Support Vector Machine, Convolutional Neural Network, Multilayer Perceptron, Stochastic Gradient Descent, Random Forest and Probabilistic Neural Network have been taken for analysis. Six different faults (Offset fault, Gain fault, Stuck-at fault, Out of Bounds, Spike fault and Data loss) are injected in the data generated by the sensor nodes. The faulty data are checked by the classifiers. The simulation results show that the Random Forest detected more faults and it also outperformed all other classifiers in that category. |
| first_indexed | 2024-03-10T03:59:59Z |
| format | Article |
| id | doaj.art-6d88fa7752cc43da994c51bc87258472 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T03:59:59Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-6d88fa7752cc43da994c51bc872584722023-11-23T10:47:43ZengMDPI AGElectronics2079-92922022-05-011110160910.3390/electronics11101609Analysis of Fault Classifiers to Detect the Faults and Node Failures in a Wireless Sensor NetworkS. Gnanavel0M. Sreekrishna1Vinodhini Mani2G. Kumaran3R. S. Amshavalli4Sadeen Alharbi5Mashael Maashi6Osamah Ibrahim Khalaf7Ghaida Muttashar Abdulsahib8Ans D. Alghamdi9Theyazn H. H. Aldhyani10Department of Computing Technologies, School of Computing, SRM Institute of Science and Technology, Kattankulathur 603203, IndiaDepartment of Computer Science and Engineering, School of Computing, Sathyabama Institute of Science and Technology, Chennai 600119, IndiaDepartment of Computer Science and Engineering, School of Computing, Sathyabama Institute of Science and Technology, Chennai 600119, IndiaSaveetha School of Engineering, Chennai 602105, IndiaSathyabama Institute of Science and Technology, Chennai 600119, IndiaDepartment of Software Engineering, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi ArabiaDepartment of Software Engineering, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi ArabiaAl-Nahrain Nano Renewable Research Center, Al-Nahrain University, Baghdad 10072, IraqDepartment of Computer Engineering, University of Technology, Baghdad 10066, IraqComputer Engineering and Science Department, College of Computer Science and Information Technology, Al Baha University, Al-Baha 42331, Saudi ArabiaApplied College in Abqaiq, King Faisal University, P.O. Box 400, Al-Ahsa 31982, Saudi ArabiaTechnology evaluation in the electronics field leads to the great development of Wireless Sensor Networks (WSN) for a variety of applications. The sensor nodes are deployed in hazardous environments, and they are operated by isolated battery sources. Network connectivity is purely based on power availability, which impacts the network lifetime. Hence, power must be used wisely to prolong the network lifetime. The sensor nodes that fail due to power have to detect quickly to maintain the network. In a WSN, classifiers are used to detect the faults for checking the data generated by the sensor nodes. In this paper, six classifiers such as Support Vector Machine, Convolutional Neural Network, Multilayer Perceptron, Stochastic Gradient Descent, Random Forest and Probabilistic Neural Network have been taken for analysis. Six different faults (Offset fault, Gain fault, Stuck-at fault, Out of Bounds, Spike fault and Data loss) are injected in the data generated by the sensor nodes. The faulty data are checked by the classifiers. The simulation results show that the Random Forest detected more faults and it also outperformed all other classifiers in that category.https://www.mdpi.com/2079-9292/11/10/1609support vector machine (SVM)convolutional neural network (CNN)multilayer perceptron (MLP)stochastic gradient descent (SGD)random forest (RF) and probabilistic neural network (PNN) |
| spellingShingle | S. Gnanavel M. Sreekrishna Vinodhini Mani G. Kumaran R. S. Amshavalli Sadeen Alharbi Mashael Maashi Osamah Ibrahim Khalaf Ghaida Muttashar Abdulsahib Ans D. Alghamdi Theyazn H. H. Aldhyani Analysis of Fault Classifiers to Detect the Faults and Node Failures in a Wireless Sensor Network Electronics support vector machine (SVM) convolutional neural network (CNN) multilayer perceptron (MLP) stochastic gradient descent (SGD) random forest (RF) and probabilistic neural network (PNN) |
| title | Analysis of Fault Classifiers to Detect the Faults and Node Failures in a Wireless Sensor Network |
| title_full | Analysis of Fault Classifiers to Detect the Faults and Node Failures in a Wireless Sensor Network |
| title_fullStr | Analysis of Fault Classifiers to Detect the Faults and Node Failures in a Wireless Sensor Network |
| title_full_unstemmed | Analysis of Fault Classifiers to Detect the Faults and Node Failures in a Wireless Sensor Network |
| title_short | Analysis of Fault Classifiers to Detect the Faults and Node Failures in a Wireless Sensor Network |
| title_sort | analysis of fault classifiers to detect the faults and node failures in a wireless sensor network |
| topic | support vector machine (SVM) convolutional neural network (CNN) multilayer perceptron (MLP) stochastic gradient descent (SGD) random forest (RF) and probabilistic neural network (PNN) |
| url | https://www.mdpi.com/2079-9292/11/10/1609 |
| work_keys_str_mv | AT sgnanavel analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT msreekrishna analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT vinodhinimani analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT gkumaran analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT rsamshavalli analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT sadeenalharbi analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT mashaelmaashi analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT osamahibrahimkhalaf analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT ghaidamuttasharabdulsahib analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT ansdalghamdi analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork AT theyaznhhaldhyani analysisoffaultclassifierstodetectthefaultsandnodefailuresinawirelesssensornetwork |