Hierarchical Learning Framework for UAV Detection and Identification

Medaiyese, Olusiji O; Ezuma, Martins; Lauf, Adrian P.; Adeniran, Ayodeji

doi:10.1109/jrfid.2022.3157653

Cited by 20 publications

(23 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applications of transient signal detection include radar, microwave radiometry, radio astronomy, underwater acoustics, and RF fingerprinting [1][2][3][4][5][6]. Methods have included traditional signal processing and, more recently, the application of machine learning techniques [6]. We summarize a number of methods here, grouping them by method rather than by application.…”

Section: Overview Of State-of-the-artmentioning

confidence: 99%

Assessment of Techniques for Detection of Transient Radio-Frequency Interference (RFI) Signals: A Case Study of a Transient in Radar Test Data

Durden,

Vilnrotter,

Shaffer

2023

Eng

View full text Add to dashboard Cite

The authors present a case study of the investigation of a transient signal that appeared in the testing of a radar receiver. The characteristics of the test conditions and data are first discussed. The authors then proceed to outline the methods for detecting and analyzing transients in the data. For this, they consider several methods based on modern signal processing and evaluate their utility. The initial method used for identifying transients is based on computer vision techniques, specifically, thresholding spectrograms into binary images, morphological processing, and object boundary extraction. The authors also consider deep learning methods and methods related to optimal statistical detection. For the latter approach, since the transient in this case was chirp-like, the method of maximum likelihood is used to estimate its parameters. Each approach is evaluated, followed by a discussion of how the results could be extended to analysis and detection of other types of transient radio-frequency interference (RFI). The authors find that computer vision, deep learning, and statistical detection methods are all useful. However, each is best used at different stages of the investigation when a transient appears in data. Computer vision is particularly useful when little is known about the transient, while traditional statistically optimal detection can be quite accurate once the structure of the transient is known and its parameters estimated.

show abstract

Section: Overview Of State-of-the-artmentioning

confidence: 99%

Assessment of Techniques for Detection of Transient Radio-Frequency Interference (RFI) Signals: A Case Study of a Transient in Radar Test Data

Durden,

Vilnrotter,

Shaffer

2023

Eng

View full text Add to dashboard Cite

show abstract

“…In addition, there are also studies using other more complex analysis tools such as wavelet transform [35], phase space reconstruction [36], and other methods [37] to construct RFF features. For example, there is the latest research to decompose the signal by using Hilbert-Huang transform and wavelet packet transform, and then extract features from the time-frequency-energy domain of the signal [8].…”

Section: Steady-state-based Rffmentioning

confidence: 99%

“…Therefore, RFF offers a new approach to wireless device identification and authentication [7]. [8] As shown in Fig. 1, the RF signal has noticeable signal power state changes at the moment of transmit power switching.…”

Section: Introductionmentioning

confidence: 99%

Radio Frequency Fingerprint Identification Based on Logarithmic Power Cosine Spectrum

et al. 2022

View full text Add to dashboard Cite

With the development of new Internet of Things (IoT) applications, such as unmanned ground vehicle (UGV), unmanned aerial vehicle (UAV), and unmanned surface vessel (USV), the security of wireless device identification is getting more and more attention. The radio frequency fingerprint (RFF) technology utilizes the unique hardware characteristics of the device for identity authentication, which overcomes the security risks of traditional authentication schemes based on distributable keys. In this paper, we propose an RFF identification scheme based on logarithmic power cosine spectrum for transient signals.We use the sliding window variance trajectory-based posterior probability density detection algorithm to improve the efficiency of transient signal detection, then adopt the discrete Fourier transform to extract the logarithmic envelope power spectrum of the transient signal, after that utilize the cosine transform to compresses the frequency domain features, and finally construct the 7-dimensional RFF feature vector. For the application scenario of USV, we acquire the radio frequency signals of 7 marine automatic identification systems (AIS) as the test dataset. The experimental results show that the proposed scheme can achieve ideal recognition accuracy using a Support Vector Machine as the classifier. Meanwhile, we use Principal Component Analysis to verify that the 7-dimensional RFF feature vector has good distinguishability for different wireless devices.

show abstract

“…Similarly, UAVs are used to carry out cybercrimes, for instance , utilizing UAV to eavesdrop on mobile phone users and hence violating the confidentiality of unsuspecting users sensitive data (Alajmi et al, 2017) . In addition, UAV can be used for a variety of illegal activities e.g., spying, terrorism (Chamola et al, 2021), illegal surveillance (Medaiyese et al, 2021), drug trafficking, fire arm smuggling and so on. With the current rise of UAVs misuse, these have open doors to a new era where finding effective and intelligent UAV detection and identification becomes a research challenge.…”

Section: Introductionmentioning

confidence: 99%

“…However, the drawback of their work was that it is time consuming. Medaiyese et al, (2021) developed a system for UAV detection and classification that is effective even in the presence of other wireless signal. Their technique exploited steady state RF signals transmitted by UAV and it flight controller.…”

Section: Introductionmentioning

confidence: 99%

Development of an Optimised Neural Network Model for RF Based UAV Detection and Identification

Donatus¹,

Dere²,

Donatus³

et al. 2023

dujopas

View full text Add to dashboard Cite

The rapid popularity of Unmanned Aerial Vehicles (UAVs) or drones is due to its great promise for various commercial and recreational applications. Moreover, technological advancements has made UAVs both affordable and versatile, it is able to perform task considered difficult and dangerous with high mobility, low cost and safely. Despite these advantageous applications and future potentials, UAVs are regrettably also used for malicious activities such as cyber-attack (i.e., eavesdropped the mobile phone of unsuspecting users), terrorism, drug trafficking and violation of security of restricted or sensitive areas. In order to overcome these aforementioned challenges, various UAV detection and identification techniques were developed by researchers in the past. Conventional techniques have inherent weakness such as poor performance in the presence of low visibility, less effective in an environment with high ambient noise and are also adversely affected by weather conditions. All these and more constitute major setback in UAV detection and identification. Similarly, RF sensing employed are usually based on traditional machine learning and statistical methods which are less effective in their capacity to successfully capture the rich information present in complex unstructured RF signal. To this end, a deep learning approach is proposed as a possible solution that is capable of achieving high accuracy in detection with less training time. To verify the effectiveness of our proposed convolutional neural network architecture, it was evaluated on the popular open source dataset, the DRONE RF dataset. Our empirical results demonstrates that our proposed CNN model outperformed state-of- the -art results using the same DRONE RF dataset.

show abstract

Hierarchical Learning Framework for UAV Detection and Identification

Cited by 20 publications

References 30 publications

Assessment of Techniques for Detection of Transient Radio-Frequency Interference (RFI) Signals: A Case Study of a Transient in Radar Test Data

Assessment of Techniques for Detection of Transient Radio-Frequency Interference (RFI) Signals: A Case Study of a Transient in Radar Test Data

Radio Frequency Fingerprint Identification Based on Logarithmic Power Cosine Spectrum

Development of an Optimised Neural Network Model for RF Based UAV Detection and Identification

Contact Info

Product

Resources

About