Consumer IoT device deployment optimisation through deep learning: a CNN-LSTM solution for traffic classification and service identification
by Imane Chakour; Sajida Mhammedi; Cherki Daoui; Mohamed Baslam
International Journal of Ad Hoc and Ubiquitous Computing (IJAHUC), Vol. 45, No. 2, 2024

Abstract: The internet of things (IoT) has revolutionised our world, connecting devices and creating a more intelligent and interconnected environment. However, managing and utilising the vast amount of data generated by these devices is a major challenge. To address this, we propose a novel approach in this article that combines convolutional neural networks (CNNs) with long short-term memory (LSTM) networks to optimise IoT device deployment. The process involves data preparation, defining and training a deep learning model on preprocessed data, and using the trained model to categorise network traffic from IoT devices. Our experimental results demonstrate exceptional accuracy of over 99.99%. We evaluate the model's performance using classification metrics and compare it with commonly used traffic predictive models. Additionally, our approach provides valuable insights into the services offered by IoT devices by analysing their traffic patterns, distinguishing between monitoring, home automation, and appliance usage.

Online publication date: Thu, 22-Feb-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Ad Hoc and Ubiquitous Computing (IJAHUC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com