Multi-label UAV sound classification using Stacked Bidirectional LSTM

Utebayeva, Dana; Almagambetov, Akhan; Alduraibi, Manal; Temirgaliyev, Yelmurat; Ilipbayeva, Lyazzat; Marxuly, S.

doi:10.1109/irc.2020.00086

Cited by 17 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The result suggested that the benefits of using GAN to augment datasets outweighed the drawbacks in drone detection and drone classification. Utebayeva et al [36] were the first group to use Long Short-Term Memory (LSTM) to classify drone sound. They extracted the sound features by MFCC, but the details of the configuration were ambiguous.…”

Section: Drone Classificationmentioning

confidence: 99%

“…In this paper, we utilize MFCC-related features as the acoustic fingerprint for drone authentication. Previous work has already shown that MFCC is an effective method for extracting features from drone audio [5,8,17,18,20,21,[35][36][37]. This motivated us to use MFCC in our work.…”

Section: Our Contribution Compared To Prior Workmentioning

confidence: 99%

“…However, the configuration details of MFCC were not clear enough in many works mentioned above. Most of the works did not provide specific details on the number of used filters [5,8,17,20,21,[35][36][37]. Furthermore, some authors did not mention the segmented frame length [5,[35][36][37] and the frame overlap ratio of segmented frames [5,17,[35][36][37].…”

Section: Our Contribution Compared To Prior Workmentioning

confidence: 99%

“…Most of the works did not provide specific details on the number of used filters [5,8,17,20,21,[35][36][37]. Furthermore, some authors did not mention the segmented frame length [5,[35][36][37] and the frame overlap ratio of segmented frames [5,17,[35][36][37]. Some works did not mention the number of used features [36,37].…”

Section: Our Contribution Compared To Prior Workmentioning

confidence: 99%

“…Furthermore, some authors did not mention the segmented frame length [5,[35][36][37] and the frame overlap ratio of segmented frames [5,17,[35][36][37]. Some works did not mention the number of used features [36,37]. In addition, none of them discussed the effectiveness of DMFCC and DDMFCC [16] in drone sound analysis.…”

Section: Our Contribution Compared To Prior Workmentioning

confidence: 99%

See 4 more Smart Citations

Drone Authentication via Acoustic Fingerprint

Diao

Zhang

Zhao

et al. 2022

Proceedings of the 38th Annual Computer Security Applications Conference

View full text Add to dashboard Cite

As drones become widely used in different applications, drone authentication becomes increasingly important due to various security risks, e.g., drone impersonation attacks. In this paper, we propose an idea of drone authentication based on Mel-frequency cepstral coefficient (MFCC) using an acoustic fingerprint that is physically embedded in each drone. We also point out that the uniqueness of the drone's sound comes from the combination of bodies (motors) and propellers. In the experiment with 8 drones, we compare the authentication accuracy of different feature extraction settings. Three kinds of different sound features are used: MFCC, delta MFCC (DMFCC), and delta-delta MFCC (DDMFCC). We choose the feature extraction settings and the sound features according to the best authentication result. In the experiment with 24 drones, we compare the closed set authentication performance of eight machine learning methods in terms of recall under the influence of additive white Gaussian noise (AWGN) with different levels of signal-to-noise ratio (SNR). Furthermore, we conduct an open set drone authentication experiment. Our results show that Quadratic Discriminant Analysis (QDA) outperforms other methods in terms of the highest average recall (94.19%) in the authentication of registered drones and the third highest average recall (82.35%) in the authentication of unregistered drones. CCS CONCEPTS• Security and privacy → Authentication; • Computing methodologies → Machine learning.

show abstract

Section: Drone Classificationmentioning

confidence: 99%