IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection

With advancements in engineering and science, the application of smart systems is increasing, generating a faster growth of the IoT network traffic. The limitations due to IoT restricted power and computing devices also raise concerns about security vulnerabilities. Machine learning-based techniques...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Laura Vigoya, Diego Fernandez, Victor Carneiro, Francisco J. Nóvoa
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	IoT sensors dataset validation machine learning intrusion detection systems analysis Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/2af890f3c1fe49feb1715305b98ff4c3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2af890f3c1fe49feb1715305b98ff4c3
record_format	dspace
spelling	oai:doaj.org-article:2af890f3c1fe49feb1715305b98ff4c32021-11-25T17:25:22ZIoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection10.3390/electronics102228572079-9292https://doaj.org/article/2af890f3c1fe49feb1715305b98ff4c32021-11-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/22/2857https://doaj.org/toc/2079-9292With advancements in engineering and science, the application of smart systems is increasing, generating a faster growth of the IoT network traffic. The limitations due to IoT restricted power and computing devices also raise concerns about security vulnerabilities. Machine learning-based techniques have recently gained credibility in a successful application for the detection of network anomalies, including IoT networks. However, machine learning techniques cannot work without representative data. Given the scarcity of IoT datasets, the DAD emerged as an instrument for knowing the behavior of dedicated IoT-MQTT networks. This paper aims to validate the DAD dataset by applying Logistic Regression, Naive Bayes, Random Forest, AdaBoost, and Support Vector Machine to detect traffic anomalies in IoT. To obtain the best results, techniques for handling unbalanced data, feature selection, and grid search for hyperparameter optimization have been used. The experimental results show that the proposed dataset can achieve a high detection rate in all the experiments, providing the best mean accuracy of 0.99 for the tree-based models, with a low false-positive rate, ensuring effective anomaly detection.Laura VigoyaDiego FernandezVictor CarneiroFrancisco J. NóvoaMDPI AGarticleIoTsensorsdataset validationmachine learningintrusion detection systemsanalysisElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2857, p 2857 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	IoT sensors dataset validation machine learning intrusion detection systems analysis Electronics TK7800-8360
spellingShingle	IoT sensors dataset validation machine learning intrusion detection systems analysis Electronics TK7800-8360 Laura Vigoya Diego Fernandez Victor Carneiro Francisco J. Nóvoa IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection
description	With advancements in engineering and science, the application of smart systems is increasing, generating a faster growth of the IoT network traffic. The limitations due to IoT restricted power and computing devices also raise concerns about security vulnerabilities. Machine learning-based techniques have recently gained credibility in a successful application for the detection of network anomalies, including IoT networks. However, machine learning techniques cannot work without representative data. Given the scarcity of IoT datasets, the DAD emerged as an instrument for knowing the behavior of dedicated IoT-MQTT networks. This paper aims to validate the DAD dataset by applying Logistic Regression, Naive Bayes, Random Forest, AdaBoost, and Support Vector Machine to detect traffic anomalies in IoT. To obtain the best results, techniques for handling unbalanced data, feature selection, and grid search for hyperparameter optimization have been used. The experimental results show that the proposed dataset can achieve a high detection rate in all the experiments, providing the best mean accuracy of 0.99 for the tree-based models, with a low false-positive rate, ensuring effective anomaly detection.
format	article
author	Laura Vigoya Diego Fernandez Victor Carneiro Francisco J. Nóvoa
author_facet	Laura Vigoya Diego Fernandez Victor Carneiro Francisco J. Nóvoa
author_sort	Laura Vigoya
title	IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection
title_short	IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection
title_full	IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection
title_fullStr	IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection
title_full_unstemmed	IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection
title_sort	iot dataset validation using machine learning techniques for traffic anomaly detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/2af890f3c1fe49feb1715305b98ff4c3
work_keys_str_mv	AT lauravigoya iotdatasetvalidationusingmachinelearningtechniquesfortrafficanomalydetection AT diegofernandez iotdatasetvalidationusingmachinelearningtechniquesfortrafficanomalydetection AT victorcarneiro iotdatasetvalidationusingmachinelearningtechniquesfortrafficanomalydetection AT franciscojnovoa iotdatasetvalidationusingmachinelearningtechniquesfortrafficanomalydetection
_version_	1718412339435274240

IoT Dataset Validation Using Machine Learning Techniques for Traffic Anomaly Detection

Ejemplares similares