MobileNet for Differential Constellation Trace Figure

Ran, Xueqin; Yan, Tianfeng; Cai, Teli

doi:10.1109/iccsn52437.2021.9463655

Cited by 2 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On both datasets, our network achieves AUC values of 0.9999 and 0.9915, respectively, indicating that our network is very close to being a "perfect classifier". Using ResNet-50 as the baseline, our method still achieves a competitive accuracy of 83.00%, which is 2.55% and 4.2% better than MobileNetV3 [49] and GoogLenet [46], respectively, on the LoRa dataset. ICAM [45] and ARFNet [19] also utilize spatial and channel attention mechanisms.…”

Section: Comparison and Discussionmentioning

confidence: 93%

“…As the distance increases and the SNR decreases, the accuracy of this approach gradually declines. [51] 62.55 33.60 AlexNet [46] 57.25 33.80 GoogLenet [46] 62.05 37.10 ResNet-50 [25] 66.90 37.70 ICAM [45] 66.20 33.75 MobileNetV3 [49] 66.35 37.50 ours 68.40 39.30…”

Section: Impact Of Distancementioning

confidence: 99%

“…In order to evaluate the influence of SNR on RF fingerprinting recognition, we also carried out experiments under different SNR levels in the range of [0, 25] dB at a step of 5 dB using the Zigbee dataset. Figure 8 draws the accuracy curves using CNN [33], SCNN [51], AlexNet [46], GoogLenet [46], ResNet-50 [25], ICAM [45], MobileNetV3 [49], and our method for different SNR levels. It can be seen that as the SNR decreases, all the accuracies degrade.…”

Section: Impact Of Snrmentioning

confidence: 99%

See 2 more Smart Citations

Fine-Grained Radio Frequency Fingerprint Recognition Network Based on Attention Mechanism

Zhang,

Hu,

Jiang

et al. 2023

Entropy

View full text Add to dashboard Cite

With the rapid development of the internet of things (IoT), hundreds of millions of IoT devices, such as smart home appliances, intelligent-connected vehicles, and wearable devices, have been connected to the network. The open nature of IoT makes it vulnerable to cybersecurity threats. Traditional cryptography-based encryption methods are not suitable for IoT due to their complexity and high communication overhead requirements. By contrast, RF-fingerprint-based recognition is promising because it is rooted in the inherent non-reproducible hardware defects of the transmitter. However, it still faces the challenges of low inter-class variation and large intra-class variation among RF fingerprints. Inspired by fine-grained recognition in computer vision, we propose a fine-grained RF fingerprint recognition network (FGRFNet) in this article. The network consists of a top-down feature pathway hierarchy to generate pyramidal features, attention modules to locate discriminative regions, and a fusion module to adaptively integrate features from different scales. Experiments demonstrate that the proposed FGRFNet achieves recognition accuracies of 89.8% on 100 ADS-B devices, 99.5% on 54 Zigbee devices, and 83.0% on 25 LoRa devices.

show abstract