Compartir
Título
Improve Quality of Service for the Internet of Things using Blockchain & Machine Learning Algorithms.
Autor
Facultad/Centro
Área de conocimiento
Título de la revista
Internet of Things
Datos de la obra
Lawrence Nforh Chesuh, L.; Fernández Díaz, R. Á.; Alija Pérez, J. M.; Benavides Cuéllar, M. D. C.; Alaiz Moretón, H. (2024). Improve Quality of Service for the Internet of Things using Blockchain & Machine Learning Algorithms.. Internet of Things,
Editor
Elsevier
Fecha
2024
ISSN
2542-6605
Abstract
[EN] The quality of service (QoS) parameters in IoT applications plays a prominent role in determining the performance of an application. Considering the significance and popularity of IoT systems, it can be predicted that the number of users and IoT devices are going to increase exponentially shortly. Therefore, it is extremely important to improve the QoS provided by IoT applications to increase their adaptability. Majority of the IoT systems are characterized by their heterogeneous and diverse nature. It is challenging for these systems to provide high-quality access to all the connecting devices with uninterrupted connectivity. Considering their heterogeneity, it is equally difficult to achieve better QoS parameters. Artificial intelligence-based machine learning (ML) tools are considered a potential tool for improving the QoS parameters in IoT applications. This research proposes a novel approach for enhancing QoS parameters in IoT using ML and Blockchain techniques. The IoT network with Blockchain technology is simulated using an NS2 simulator. Different QoS parameters such as delay, throughput, packet delivery ratio, and packet drop are analyzed. The obtained QoS values are classified using different ML models such as Naive Bayes (NB), Decision Tree (DT), and Ensemble, learning techniques. Results show that the Ensemble classifier achieves the highest classification accuracy of 83.74% compared to NB and DT classifiers.
Materia
Palabras clave
Peer review
SI
URI
DOI
Collections
- Untitled [5590]
Files in this item
Tamaño:
894.5
xmlui.dri2xhtml.METS-1.0.size-kilobytes
Formato:
Adobe PDF