Virtual Adversarial Training-Based Semisupervised Specific Emitter Identification

Deep learning is a new direction of research for specific emitter identification (SEI). Radio frequency (RF) fingerprints of the emitter signal are small and sensitive to noise. It is difficult to assign labels containing category information in noncooperative communication scenarios. This makes network models obtained by conventional supervised learning methods perform unsatisfactorily, leading to poor identification performance. To address this limitation, this paper proposes a semisupervised SEI algorithm based on bispectrum analysis and virtual adversarial training (VAT). Bispectrum analysis is performed on RF signals to enhance individual discriminability. A convolutional neural network (CNN) is used for RF fingerprint extraction. We used a small amount of labelled data to train the CNN in an adversarial manner to improve the antinoise performance of the network in a supervised model. Virtual adversarial samples were calculated for VAT, which made full use of labelled and large unlabelled training data to further improve the generalization capability of the network. Results of numerical experiments on a set of six universal software radio peripheral (USRP; model B210) devices demonstrated the stable and fast convergence performance of the proposed method, which exhibited approximately 90% classification accuracy at 10 dB. Finally, the classification performance of our method was verified using other evaluation metrics including receiver operating characteristic and precision-recall.

Measurement of EM field immunity of VCO-based ADCs in 28nm CMOS technology

Internet-of-things (IoT) devices are compact and low power. A voltage-controlled oscillator (VCO) based analog-to-digital converter (ADC) benefits from scaled CMOS transistors in representing analog signals in the time domain and therefore meets those demands. However, we find the potential drawback of VCO-based ADCs for the electromagnetic susceptibility (EMS) to radio-frequency (RF) disturbances that are essentially present in IoT environment. It is exhibited that the single and even differential designs of VCO-based ADC suffer from the EMS by RF disturbance, which behaves differently from the known common-mode noise rejection. A 28-nm CMOS 10-bit VCO-ADC prototype exhibit the sensitivity against RF signals in the widely used 2.4 GHz frequency band.

RF Signal-Based UAV Detection and Mode Classification: A Joint Feature Engineering Generator and Multi-Channel Deep Neural Network Approach

With the proliferation of Unmanned Aerial Vehicles (UAVs) to provide diverse critical services, such as surveillance, disaster management, and medicine delivery, the accurate detection of these small devices and the efficient classification of their flight modes are of paramount importance to guarantee their safe operation in our sky. Among the existing approaches, Radio Frequency (RF) based methods are less affected by complex environmental factors. The similarities between UAV RF signals and the diversity of frequency components make accurate detection and classification a particularly difficult task. To bridge this gap, we propose a joint Feature Engineering Generator (FEG) and Multi-Channel Deep Neural Network (MC-DNN) approach. Specifically, in FEG, data truncation and normalization separate different frequency components, the moving average filter reduces the outliers in the RF signal, and the concatenation fully exploits the details of the dataset. In addition, the multi-channel input in MC-DNN separates multiple frequency components and reduces the interference between them. A novel dataset that contains ten categories of RF signals from three types of UAVs is used to verify the effectiveness. Experiments show that the proposed method outperforms the state-of-the-art UAV detection and classification approaches in terms of 98.4% and F1 score of 98.3%.

XGest: Enabling Cross-Label Gesture Recognition with RF Signals

Extensive efforts have been devoted to human gesture recognition with radio frequency (RF) signals. However, their performance degrades when applied to novel gesture classes that have never been seen in the training set. To handle unseen gestures, extra efforts are inevitable in terms of data collection and model retraining. In this article, we present XGest, a cross-label gesture recognition system that can accurately recognize gestures outside of the predefined gesture set with zero extra training effort. The key insight of XGest is to build a knowledge transfer framework between different gesture datasets. Specifically, we design a novel deep neural network to embed gestures into a high-dimensional Euclidean space. Several techniques are designed to tackle the spatial resolution limits imposed by RF hardware and the specular reflection effect of RF signals in this model. We implement XGest on a commodity mmWave device, and extensive experiments have demonstrated the significant recognition performance.

For RF Signal-Based UAV States Recognition, Is Pre-processing Still Important At The Era Of Deep Learning?

Unmanned Aerial Vehicles (UAVs, also called drones) have been widely deployed in our living environments for a range of applications such as healthcare, agriculture, and logistics. Despite their unprecedented advantages, the increased number of UAVs and their growing threats demand high-performance management and emergency control strategies. To accurately detect a UAV's working state including hovering and flying, data collection from Radio Frequency (RF) signals is a key step of these strategies and has thus attracted significant research interest. Deep neural networks (DNNs) have been applied for UAV state detection and shown promising potentials. While existing work mostly focuses on improving the DNN structures, we discover that RF signals' pre-processing before sending them to the classification model is as important as improving the DNN structures. Experiments on a dataset show that, after applying proposed pre-processing methods, the 10-time average accuracy is improved from 46.8% to 91.9%, achieving nearly 50% gain comparing with the benchmark work using the same DNN structure. This work also outperforms the state-of-the-art CNN models, confirming the great potentials of data pre-processing for RF-based UAV state detection.

For RF Signal-Based UAV States Recognition, Is Pre-processing Still Important At The Era Of Deep Learning?

Unmanned Aerial Vehicles (UAVs, also called drones) have been widely deployed in our living environments for a range of applications such as healthcare, agriculture, and logistics. Despite their unprecedented advantages, the increased number of UAVs and their growing threats demand high-performance management and emergency control strategies. To accurately detect a UAV's working state including hovering and flying, data collection from Radio Frequency (RF) signals is a key step of these strategies and has thus attracted significant research interest. Deep neural networks (DNNs) have been applied for UAV state detection and shown promising potentials. While existing work mostly focuses on improving the DNN structures, we discover that RF signals' pre-processing before sending them to the classification model is as important as improving the DNN structures. Experiments on a dataset show that, after applying proposed pre-processing methods, the 10-time average accuracy is improved from 46.8% to 91.9%, achieving nearly 50% gain comparing with the benchmark work using the same DNN structure. This work also outperforms the state-of-the-art CNN models, confirming the great potentials of data pre-processing for RF-based UAV state detection.

Study and Simulation of Transporting Radio Frequency Signals over Free Space Optics for Achieving High Data Rate and Power Saving

The remarkable technology for seamless integration of wireless and optical networks is radio frequency signals over Free Space Optics (FSO). This research study and simulation examine the design and evaluation performance of Radio Frequency over FSO (RF-FSO) wireless communication technology. These systems are implemented through medium communication link ranges to overcome excessive sensitivity of atmosphere medium and meet the requirements of a wide variety of optical wireless applications. There are two ways to achieve the application of the design mentioned above. The first way is the application of the Three modulation schemes of technology that is Amplitude shift keying (ASK), Quadrature amplitude modulation (QAM), and Quadrature phase-shift keying (QPSK) of digital modulation. The design of these modulation schemes is realized by using optiwave software to study the transmission of RF signals over the FSO channel and compare the three modulation techniques into the RF-FSO system. RF signals with the frequency range from (20 to 60) GHz is used in RF-FSO system and many carrier optical signals where the higher RF has a wider bandwidth to carrying larger information. To increase the transmission of data rates Wavelength Division Multiplexing (WDM) technology is used. The second way is based on a mathematical model which has been proposed for this study. This mathematical model calculates optimal beacon period (BI), and optimal listen interval (LI) to preventing the overlapping of time between the signals and the decrease in the required power. Using different weather conditions samples, the simulation results revealed that the best performance of the RF-FSO system is from link range, and the receiver is more sensitive. The simulation results are as follows: Two independent channels are transmitted 20 Gbps over ranges from (263 m to 6.55 km), while four channels are transmitted 40 Gbps over ranges from (257 m to 5.95 km), and eight independent channels transmit 80 Gbps over distance from (203 m to 5.2 km)

RF-based low-SNR classification of UAVs using convolutional neural networks

Unmanned Aerial Vehicles (UAVs), or drones, which can be considered as a coverage extender for Internet of Everything (IoE), have drawn high attention recently. The proliferation of drones will raise privacy and security concerns in public. This paper investigates the problem of classification of drones from Radio Frequency (RF) fingerprints at the low Signal-to-Noise Ratio (SNR) regime. We use Convolutional Neural Networks (CNNs) trained with both RF time-series images and the spectrograms of 15 different off-the-shelf drone controller RF signals. When using time-series signal images, the CNN extracts features from the signal transient and envelope. As the SNR decreases, this approach fails dramatically because the information in the transient is lost in the noise, and the envelope is distorted heavily. In contrast to time-series representation of the RF signals, with spectrograms, it is possible to focus only on the desired frequency interval, i.e., 2.4 GHz ISM band, and filter out any other signal component outside of this band. These advantages provide a notable performance improvement over the time-series signals-based methods. To further increase the classification accuracy of the spectrogram-based CNN, we denoise the spectrogram images by truncating them to a limited spectral density interval. Creating a single model using spectrogram images of noisy signals and tuning the CNN model parameters, we achieve a classification accuracy varying from 92% to 100% for an SNR range from -10 dB to 30 dB, which significantly outperforms the existing approaches to our best knowledge.