Towards an Interpretable AI Framework for Advanced Classification of Unmanned Aerial Vehicles (UAVs)

Ekramul Haque, Kamrul Hasan, Imtiaz Ahmed, Md Sahabul Alam, Tariqul Islam

Research output: Chapter in Book/Entry/PoemConference contribution

1 Scopus citations

Abstract

With UAVs on the rise, accurate detection and identification are crucial. Traditional unmanned aerial vehicle (UAV) identification systems involve opaque decision-making, restricting their usability. This research introduces an RF-based Deep Learning (DL) framework for drone recognition and identification. We use cutting-edge eXplainable Artificial Intelligence (XAI) tools, SHapley Additive Explanations (SHAP), and Local Interpretable Model-agnostic Explanations(LIME). Our deep learning model uses these methods for accurate, transparent, and interpretable airspace security. With 84.59% accuracy, our deep-learning algorithms detect drone signals from RF noise. Most crucially, SHAP and LIME improve UAV detection. Detailed explanations show the model's identification decision-making process. This transparency and interpretability set our system apart. The accurate, transparent, and user-trustworthy model improves airspace security.

Original languageEnglish (US)
Title of host publication2024 IEEE 21st Consumer Communications and Networking Conference, CCNC 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages644-645
Number of pages2
ISBN (Electronic)9798350304572
DOIs
StatePublished - 2024
Event21st IEEE Consumer Communications and Networking Conference, CCNC 2024 - Las Vegas, United States
Duration: Jan 6 2024Jan 9 2024

Publication series

NameProceedings - IEEE Consumer Communications and Networking Conference, CCNC
ISSN (Print)2331-9860

Conference

Conference21st IEEE Consumer Communications and Networking Conference, CCNC 2024
Country/TerritoryUnited States
CityLas Vegas
Period1/6/241/9/24

Keywords

  • Airspace Security
  • Deep Learning
  • Drone Detection
  • Explainable AI
  • LIME
  • RF Signals
  • SHAP

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Towards an Interpretable AI Framework for Advanced Classification of Unmanned Aerial Vehicles (UAVs)'. Together they form a unique fingerprint.

Cite this