No abstract

We designed and implemented a deep learning based RF signal classifier on the Field Programmable Gate Array (FPGA) of an embedded software-defined radio platform, DeepRadio TM , that classifies the signals received through the RF front end to different modulation types in real time and with low power. This classifier implementation successfully captures complex characteristics of wireless signals to serve critical applications in wireless security and communications systems such as identifying spoofing signals in signal authentication systems, detecting target emitters and jammers in electronic warfare (EW) applications, discriminating primary and secondary users in cognitive radio networks, interference hunting, and adaptive modulation. Empowered by low-power and low-latency embedded computing, the deep neural network runs directly on the FPGA fabric of DeepRadio TM , while maintaining classifier accuracy close to the software performance. We evaluated the performance when another SDR (USRP) transmits signals with different modulation types at different power levels and DeepRadio TM receives the signals and classifies them in real time on its FPGA. A smartphone with a mobile app is connected to DeepRadio TM to initiate the experiment and visualize the classification results. With real radio transmissions over the air, we show that the classifier implemented on DeepRadio TM achieves high accuracy with low latency (microsecond per sample) and low energy consumption (microJoule per sample), and this performance is not matched by other embedded platforms such as embedded graphics processing unit (GPU).

The family B G protein-coupled glucagon-like peptide 1 (GLP-1) receptor is an important drug target for treatment of type 2 diabetes. Like other family members, the GLP-1 receptor is a glycosylated membrane protein that contains three potential sites for N-linked glycosylation within the functionally important extracellular amino-terminal domain. However, the roles for each potential site of glycosylation in receptor biosynthesis, trafficking, and function are not known. In this work, we demonstrated that tunicamycin inhibition of glycosylation of the GLP-1 receptor expressed in CHO cells interfered with biosynthesis and intracellular trafficking, thereby eliminating natural ligand binding. To further investigate the roles of each of the glycosylation sites, site-directed mutagenesis was performed to eliminate these sites individually and in aggregate. Our results showed that mutation of each of the glycosylation sites individually did not interfere with receptor expression on the cell surface, ligand binding, and biological activity. However, simultaneous mutation of two or three glycosylation sites resulted in almost complete loss of GLP-1 binding and severely impaired biological activity. Immunostaining studies demonstrated receptor biosynthesis but aberrant trafficking, with most of the receptor trapped in the endoplasmic reticulum and golgi compartments and little of the receptor expressed on the cell surface. Interestingly, surface expression, ligand binding, and biological activity of these mutants improved significantly when biosynthesis was slowed using low temperature (30 degrees C). These data suggest that N-linked glycosylation of the GLP-1 receptor is important for its normal folding and trafficking to the cell surface.

We present the DeepWiFi protocol, which hardens the baseline WiFi (IEEE 802.11ac) with deep learning and sustains high throughput by mitigating out-of-network interference. DeepWiFi is interoperable with baseline WiFi and builds upon the existing WiFi's PHY transceiver chain without changing the MAC frame format. Users run DeepWiFi for i) RF front end processing; ii) spectrum sensing and signal classification; iii) signal authentication; iv) channel selection and access; v) power control; vi) modulation and coding scheme (MCS) adaptation; and vii) routing. DeepWiFi mitigates the effects of probabilistic, sensing-based, and adaptive jammers. RF front end processing applies a deep learningbased autoencoder to extract spectrum-representative features. Then a deep neural network is trained to classify waveforms reliably as idle, WiFi, or jammer. Utilizing channel labels, users effectively access idle or jammed channels, while avoiding interference with legitimate WiFi transmissions (authenticated by machine learning-based RF fingerprinting) resulting in higher throughput. Users optimize their transmit power for low probability of intercept/detection and their MCS to maximize link rates used by backpressure algorithm for routing. Supported by embedded platform implementation, DeepWiFi provides major throughput gains compared to baseline WiFi and another jamming-resistant protocol, especially when channels are likely to be jammed and the signal-to-interference-plus-noise-ratio is low.

No abstract