Support vector machine based energy aware routing in wireless sensor networks

Khan, Feeza; Memon, Saira; Jokhio, Sana Hoor

doi:10.1109/icrai.2016.7791218

Cited by 25 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM can deal with both linear and nonlinear questions and is more useful in large datasets. To address different problems such as routing [64], localization [65], fault diagnosis [66], congestion control [67], and communication issues [68], SVM is added to WSNs.…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Machine Learning Methods for Intrusive Detection of Wormhole Attack in Mobile Ad Hoc Network (MANET)

Abdan

Seno

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

A wormhole attack is a type of attack on the network layer that reflects routing protocols. The classification is performed with several methods of machine learning consisting of K -nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), linear discrimination analysis (LDA), naive Bayes (NB), and convolutional neural network (CNN). Moreover, we used nodes’ properties for feature extraction, especially nodes’ speed, in the MANET. We have collected 3997 distinct (normal 3781 and malicious 216) samples that comprise normal and malicious nodes. The classification results show that the accuracy of the KNN, SVM, DT, LDA, NB, and CNN methods are 97.1%, 98.2%, 98.9%, 95.2%, 94.7%, and 96.4%, respectively. Based on our findings, the DT method’s accuracy is 98.9% and higher than other ways. In the next priority, SVM, KNN, CNN, LDA, and NB indicate high accuracy, respectively.

show abstract

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Machine Learning Methods for Intrusive Detection of Wormhole Attack in Mobile Ad Hoc Network (MANET)

Abdan

Seno

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…SVM can deal with both linear and non-linear questions and is more useful in large datasets. To address different problems such as routing [33], localization [34], fault detection [35], congestion control [36], and communication issues [37], SVM is added to WSNs.…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Machine Learning Methods for Intrusive Detection of Wormhole Attack in Mobile Ad-Hoc Network (MANET)

Abdan

Seno

2021

Preprint

View full text Add to dashboard Cite

A wormhole attack is a type of attack on the network layer which reflects the issue of routing protocols. The classification is performed with several methods of machine learning consisting of K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), Linear Discrimination Analysis (LDA), Naive Bayes (NB), and Convolutional neural network (CNN). Moreover, for feature extraction, we used the properties of nodes, especially nodes speed in the MANET. We have collected 3997 distinct (normal 3781 and malicious 216) samples that comprise normal and malicious samples. Results of the classification show that the accuracy of KNN, SVM, DT, LDA, NB, and CNN methods are 97.1%, 98.2%, 98.9%, 95.2%, 94.7%, and 96.4%, respectively. Based on our findings, the DT method's accuracy is 98.9% and higher than other methods. In the next priority, SVM, KNN, CNN, LDA, and NB indicate high accuracy, respectively.

show abstract

“…For example, there is SVM based localization technique Fast-(SVM) [22] and Naive convex hull algorithm [23] for connectivity and coverage technique. There is another SVMs classification method [13] for fault detection and Efficient SV based clustering protocol [24] for secure routing techniques. SVM is best suited for malicious behaviour detection in VANET system [25].…”

Section: ) Support Vector Machine (Svm)mentioning

confidence: 99%

Role of Machine Learning in WSN and VANETs

Gillani

Niaz

Tayyab

2021

IJECER

View full text Add to dashboard Cite

Dynamic nature of Vehicular Ad-hoc Networks (VANETs) and Wireless Sensor Networks (WSN) makes them hard to deal accordingly. For such dynamicity, Machine learning (ML) approaches are considered favourable. ML can be described as the process or method of self-learning without human intervention that can assist through various tools to deal with heterogeneous data to attain maximum beneﬁts from the network. In this paper, a quick summary of primary ML concepts are discussed along with several algorithms based on ML for WSN and VANETs. Afterwards, ML based WSN and VANETs application, open issues, challenges of rapidly changing networks and various algorithms in relation to ML models and techniques are discussed. We have listed some of the ML techniques to take additional consideration of this emergent ﬁeld. A summary is given for ML techniques application with their complexities to cover on open issues to kick start further research investigation. This paper provides excellent coverage of state-of-the-art ML applications that are being used in WSN and VANETs with their comparative analysis.

show abstract

Support vector machine based energy aware routing in wireless sensor networks

Cited by 25 publications

References 3 publications

Machine Learning Methods for Intrusive Detection of Wormhole Attack in Mobile Ad Hoc Network (MANET)

Machine Learning Methods for Intrusive Detection of Wormhole Attack in Mobile Ad Hoc Network (MANET)

Machine Learning Methods for Intrusive Detection of Wormhole Attack in Mobile Ad-Hoc Network (MANET)

Role of Machine Learning in WSN and VANETs

Contact Info

Product

Resources

About