No abstract

Spectrum sensing is the key problem for Cognitive Radio (CR) systems. A method based on the Peak-to-Average Amplitude-Ratio (PAAR) of the Spatial Spectrum (SS) of the received signals is proposed to sense the available spectrum for the cognitive users with the help of the multiple antennas at the receiver of the cognitive users. The greatest advantage of the new method is that it requires no information of the noise power and is free of the noise power uncertainty. Both the simulation and the analytical results show that the proposed method is robust to noise uncertainty, and greatly outperform the classical Energy Detector (ED) method.

Along with social distancing, wearing masks is an effective method of preventing the transmission of COVID-19 in the ongoing pandemic. However, masks occlude a large number of facial features, preventing facial recognition. The recognition rate of existing methods may be significantly reduced by the presence of masks. In this paper, we propose a method to effectively solve the problem of the lack of facial feature information needed to perform facial recognition on people wearing masks. The proposed approach uses image super-resolution technology to perform image preprocessing along with a deep bilinear module to improve EfficientNet. It also combines feature enhancement with frequency domain broadening, fuses the spatial features and frequency domain features of the unoccluded areas of the face, and classifies the fused features. The features of the unoccluded area are increased to improve the accuracy of recognition of masked faces. The results of a cross-validation show that the proposed approach achieved an accuracy of 98% on the RMFRD dataset, as well as a higher recognition rate and faster speed than previous methods. In addition, we also performed an experimental evaluation in an actual facial recognition system and achieved an accuracy of 99%, which demonstrates the effectiveness and practicability of the proposed method.INDEX TERMS Face recognition with mask, convolutional neural network, frequency domain widening, bilinear module, RMFRD dataset.

Summary The target recognition for satellite communication (satcom) is generally regarded as the cutting edge of electronic countermeasure research. This work is dedicated to the investigation on the theory and experiment of satellite communication target recognition on the basis of systematical analysis of satcom signal emission, propagation, and reception. The authors elaborate on the fingerprint analysis, feature extraction, and identification of satcom emitters by utilizing the nonlinearities of high‐power microwave vacuum amplifier (HPA). The mechanism of the external subtle features of satcom signal will be also discussed in detail. To acquire the qualified features that precisely represent the individual emitter, higher‐order statistics technique is introduced to implement the feature extraction, and the supervised probabilistic neural network classifier is established to execute the recognition of testing satcom samples. In testing phase, there are a total of 4000 sampling signals with BPSK modulation and variable carrier to noise ratio (CNR) originated by eight types of satcom transmitters setting for the experiment to verify the authors' viewpoints. Thanks to the fine training data set and subsequent well‐extracted features, the PNN classifier had not fail us and finally achieved satisfactory accuracy of more than 94% at CNR level of 10 dB. Those expected results will help to enhance the ability of battlefield surveillance and situational awareness that is of paramount importance in academic research and military application.

Under the severe situation of the COVID-19 pandemic, masks cover most of the effective facial features of users, and their head pose changes significantly in a complex environment, which makes the accuracy of head pose estimation in some systems such as safe driving systems and attention detection systems impossible to guarantee. To this end, we propose a powerful four-branch feature selective extraction network (FSEN) structure, in which three branches are used to extract three independent discriminative features of pose angles, and one branch is used to extract composite features corresponding to multiple pose angles. By reducing the dimension of high-dimensional features, our method significantly reduces the amount of computation while improving the estimation accuracy. Our convolution method is an improved spatial channel dynamic convolution (SCDC) that initially enhances the extracted features. Additionally, we embed a regional information exchange network (RIEN) after each convolutional layer in each branch to fully mine the potential semantic correlation between regions from multiple perspectives and learn and fuse this correlation to further enhance feature expression. Finally, we fuse the independent discriminative features of each pose angle and composite features from the three directions of channel, space, and pixel to obtain perfect feature expression for each pose angle, and then obtain the head pose angle. We conducted extensive experiments on the controlled environment datasets and a self-built real complex environment dataset (RCE) and the results showed that our method outperforms state-of-the-art single-modality methods and performs on par with multimodality-based methods. This shows that our network meets the requirements of accurate head-pose estimation in real complex environments such as complex illumination and partial occlusion.INDEX TERMS Head pose estimation, four-branch feature selective extraction, regional information exchange network, spatial channel dynamic convolution, multiple feature fusion, complex environment.