An Efficient Internet Traffic Classification System Using Deep Learning for IoT

Basit Öğe Kaydı
dc.authoridUmair, Muhammad Basit/0000-0003-2616-6749
dc.authoridIqbal, Zeshan/0000-0003-4545-4092
dc.authoridnebhen, jamel/0000-0002-8610-3451
dc.authoridMehmood, Raja Majid/0000-0002-2284-0479
dc.authoridBilal, Muhammad/0000-0003-4221-0877
dc.contributor.authorUmair, Muhammad Basit
dc.contributor.authorIqbal, Zeshan
dc.contributor.authorBilal, Muhammad
dc.contributor.authorNebhen, Jamel
dc.contributor.authorAlmohamad, Tarik Adnan
dc.contributor.authorMehmood, Raja Majid
dc.date.accessioned2024-09-29T16:07:59Z
dc.date.available2024-09-29T16:07:59Z
dc.date.issued2022
dc.departmentKarabük Üniversitesien_US
dc.description.abstractInternet of Things (IoT) defines a network of devices connected to the internet and sharing a massive amount of data between each other and a central location. These IoT devices are connected to a network therefore prone to attacks. Various management tasks and network operations such as security, intrusion detection, Quality-of-Service provisioning, performance monitoring, resource provisioning, and traffic engineering require traffic classification. Due to the ineffectiveness of traditional classification schemes, such as port-based and payload-based methods, researchers proposed machine learning-based traffic classification systems based on shallow neural networks. Furthermore, machine learning-based models incline to misclassify internet traffic due to improper feature selection. In this research, an efficient multi-layer deep learning based classification system is presented to overcome these challenges that can classify internet traffic. To examine the performance of the proposed technique, Moore-dataset is used for training the classifier. The proposed scheme takes the pre-processed data and extracts the flow features using a deep neural network (DNN). In particular, the maximum entropy classifier is used to classify the internet traffic. The experimental results show that the proposed hybrid deep learning algorithm is effective and achieved high accuracy for internet traffic classification, i.e., 99.23%. Furthermore, the proposed algorithm achieved the highest accuracy compared to the support vector machine (SVM) based classification technique and k-nearest neighbours (KNNs) based classification technique.en_US
dc.description.sponsorshipXiamen University Malaysia Research Fund (XMUMRF) [XMUMRF/2019-C3/IECE/0007]en_US
dc.description.sponsorshipThis work has supported by the Xiamen University Malaysia Research Fund (XMUMRF) (Grant No: XMUMRF/2019-C3/IECE/0007) .en_US
dc.identifier.doi10.32604/cmc.2022.020727
dc.identifier.endpage422en_US
dc.identifier.issn1546-2218
dc.identifier.issn1546-2226
dc.identifier.issue1en_US
dc.identifier.scopus2-s2.0-85118531249en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage407en_US
dc.identifier.urihttps://doi.org/10.32604/cmc.2022.020727
dc.identifier.urihttps://hdl.handle.net/20.500.14619/7294
dc.identifier.volume71en_US
dc.identifier.wosWOS:000717617700025en_US
dc.identifier.wosqualityQ3en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherTech Science Pressen_US
dc.relation.ispartofCmc-Computers Materials & Continuaen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectDeep learningen_US
dc.subjectinternet traffic classificationen_US
dc.subjectnetwork traffic managementen_US
dc.subjectQoS aware application classificationen_US
dc.titleAn Efficient Internet Traffic Classification System Using Deep Learning for IoTen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu