Litcius/Paper detail

A Deep-Learning-Based Traffic Classification Method for 5G Aerial Computing Networks

Chen Chen, Ziye Liu, Yuejun Yu, Fan Jin, Wei Han, Stefano Berretti, Lei Liu, Qingqi Pei

2025IEEE Internet of Things Journal18 citationsDOI

Abstract

With the rapid progress made in aerial computing technology and the increased popularity of fifth-generation (5G) networks, uncrewed aerial vehicles (UAVs) have been playing a crucial role in real-time data collection, processing, and transmission. However, due to the diversity in traffic generated by UAVs in various mission scenarios, there is a significant challenge posed in traffic classification. Therefore, a novel traffic classification model is proposed in this article on the basis of the spatial attention-enhanced convolutional neural network (SAE-CNN). This model proves effective in improving classification accuracy and latency, particularly in the context of various 5G services, such as enhanced mobile broadband (eMBB), ultrareliable low-latency communication (URLLC), and Internet service. Also, a 5G heterogeneous network platform is built to collect UAV-related aerial computing data, with extensive experiments performed to verify the superior performance of the SAE-CNN model compared to other state-of-the-art methods. The experimental results demonstrate that the proposed approach enables effective traffic management and classification for the application of UAV in complex 5G environments.

Topics & Concepts

Computer scienceDeep learningArtificial intelligenceMachine learningComputer networkInternet Traffic Analysis and Secure E-votingTelecommunications and Broadcasting TechnologiesAdvanced Data and IoT Technologies
A Deep-Learning-Based Traffic Classification Method for 5G Aerial Computing Networks | Litcius