Deep Learning for RF-Based Drone Detection and Identification: A Multi-Channel 1-D Convolutional Neural Networks Approach
Author | Allahham M.S. |
Author | Khattab T. |
Author | Mohamed A. |
Available date | 2022-04-21T08:58:26Z |
Publication Date | 2020 |
Publication Name | 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies, ICIoT 2020 |
Resource | Scopus |
Identifier | http://dx.doi.org/10.1109/ICIoT48696.2020.9089657 |
Abstract | Commercial unmanned aerial vehicles, or drones, are getting increasingly popular in the last few years. The fact that these drones are highly accessible to public may bring a range of security and technical issues to sensitive areas such as airfields and military bases. Consequently, drone detection and state identification are becoming very crucial and essential for governments and security agencies. This paper proposes a deep learning based approach for drone detection, type identification and state identification using a multi-channel 1-dimensional convolutional neural network. The deep learning model is trained utilizing a publicly published database for drone's radio frequency signals. The proposed model can be used to produce new features that can represent the whole dataset in a more compact form which enables the use of classical machine learning algorithms for classification. 2020 IEEE. |
Language | en |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Subject | Aircraft detection Antennas Classification (of information) Commercial vehicles Convolution Convolutional neural networks Drones Internet of things Learning algorithms Learning systems Detection and identifications Learning models Learning-based approach Multi channel Radiofrequency signals Security agencies Sensitive area State identification Deep learning |
Type | Conference Paper |
Pagination | 112-117 |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
-
Computer Science & Engineering [2288 items ]
-
Electrical Engineering [2616 items ]