The growing popularity of unmanned aerial vehicle (UAV) attracts significant research interests and applications including low-altitude and airborne vehicles. Since there is no declared spectrum allocated to UAV communications, opportunistic transmission has been commonly considered as an important way for supporting UAV communications. When sharing the same spectrum with other users such as satellites and mobile base stations, accurate spectrum sensing and allocation are of critical importance for UAV communications to avoid serious interference. As the UAVs can constantly move to different locations with various spectrum environments, the spectrum decision may be invalid only in a short period, leading to require fast spectrum sensing. Furthermore, an UAV needs to predict possible temporal and spatial vacations of the spectrum. In this case, the spectrum prediction has a high dimensional state space which is notoriously difficult to solve. In this paper, some other issues such as how to determine the spectrum processing time and how to detect the primary signals with high priority to avoid interference, are also discussed. Finally, a fast spectrum sensing algorithm is proposed to improve the energy detection performance by optimizing the error estimation and a constant ratio of missed detection. Our proposed algorithm does not require high computational capability and can achieve relatively accurate sensing in low signal-to-noise ratio scenarios.

Jamming will seriously affect the detection ability of radar, so it is essential to suppress the jamming of radar echoes. Interrupted-sampling repeater jamming (ISRJ) based on a digital-radio-frequency-memory (DRFM) device can generate false targets at the victim radar by the interception and repeating of the radar transmission signal, which is highly correlated with the true target signal. ISRJ can achieve main lobe jamming and has both deception and oppressive jamming effects, so it is difficult for the existing methods to suppress this jamming effectively. In this paper, we propose a deep-learning-based anti-jamming network, named MSMD-net (Multi-stage Multi-domain joint anti-jamming depth network), for suppressing ISRJ main lobe jamming in the radar echo. In the first stage of MSMD-net, considering that the target signal is difficult to detect under a high jamming-to-signal ratio (JSR), we propose a preprocessing method of limiting filtering on the time-frequency domain to reduce the JSR using the auxiliary knowledge of radar. In the second stage, taking advantage of the discontinuity of the jamming in the time domain, we propose a UT-net network that combines the U-net structure and the transformer module. The UT-net performs target feature extraction and signal reconstruction in the signal time-frequency domain and preliminarily realizes the suppression of the jamming component. In the third stage, combined with phase information, a one-dimensional complex residual convolution U-net network (ResCU-net) is constructed in the time domain to realize jamming filtering and signal recovery further. The experimental results show that MSMD-net can obtain the best jamming suppression effect under different transmitted signals, different jamming modes, and different jamming parameters.

With the ever-growing number of networked devices and a higher likelihood of having lineof-sight communication most of the time, location estimation of a blind node in the 5th generation Ultra-Dense Networks (UDNs) system has gained considerable attention in recent years. One of main factors for accurate location estimates in 5G UDN is node randomness. Several location methods and their performance analyses have been addressed for localization in 5G UDN. Although the distribution of reference nodes (RNs) is considered in the literature, the information on spatial node distribution is only used to evaluate the average performance and is not utilized in the location methods. In this paper, a Cramer–Rao lower bound (CRLB) and three location estimators including the iterative, closed-form, and hybrid algorithms are proposed for localization in 5G UDN with randomly distributed RNs. Both range measurements and prior information on spatial node distribution are utilized for the proposed location methods and CRLB. Moreover, some characteristics of the CRLB for 5G UDN localization are derived in this paper. Detail comparison between the proposed CRLB and the previous performance study on CRLB for 5G UDN is given. Theoretical analysis proves that the proposed CRLB for the case with randomly distributed RNs is smaller than the average CRLB for the case with fixed location RNs. The top and bottom bounds of the proposed CRLB in the cases with low and high signal noise ratios are also given. Performance evaluation shows that the proposed methods perform better than the conventional methods only based on range measurements and can asymptotically attain the CRLB.

The localization of a sensor in wireless sensor networks (WSNs) has now gained considerable attention. Since the transmit power and path loss exponent (PLE) are two critical parameters in the received signal strength (RSS) localization technique, many RSS-based location methods, considering the case that both the transmit power and PLE are unknown, have been proposed in the literature. However, these methods require a search process, and cannot give a closed-form solution to sensor localization. In this paper, a novel RSS localization method with a closed-form solution based on a two-step weighted least squares estimator is proposed for the case with the unknown transmit power and uncertainty in PLE. Furthermore, the complete performance analysis of the proposed method is given in the paper. Both the theoretical variance and Cramer-Rao lower bound (CRLB) are derived. The relationships between the deterministic CRLB and the proposed stochastic CRLB are presented. The paper also proves that the proposed method can reach the stochastic CRLB.

Existing deep learning algorithms for synthetic aperture radar (SAR) image recognition are performed with offline data. These methods must use all data to retrain the entire model when new data are added. However, facing the real application environment with growing data, retraining consumes much time and memory space. Class-Incremental Learning (CIL) addresses this problem that deep learning faces in streaming data. The goal of CIL is to enable the model to continuously learn new classes without using all data to retrain the model while maintaining the ability to recognize previous classes. Most of the CIL methods adopt a replay strategy to realize it. However, the number of retained samples is too small to carry enough information. The replay strategy is still trapped by forgetting previous knowledge. For this reason, we propose a CIL method for SAR images based on self-sustainment guidance representation. The method uses the vision transformer (ViT) structure as the basic framework. We add a dynamic query navigation module to enhance the model’s ability to learn the new classes. This module stores special information about classes and uses it to guide the direction of feature extraction in subsequent model learning. In addition, the method also comprises a structural extension module to defend the forgetting of old classes when the model learns new knowledge. It is constructed to maintain the representation of the model in previous classes. The model will learn under the coordinated guidance of old and new information. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that our method performs well with remarkable advantages in CIL tasks. This method has a better accuracy rate and performance dropping rate than state-of-the-art methods under the same setting and maintains the ability of incremental learning with fewer replay samples. Additionally, experiments on a popular image dataset (CIFAR100) also demonstrate the scalability of our approach.

Two main difficulties for the accurate direction of arrival (DOA) estimation in a distributed sensor system are grating lobes and system synchronization. Different from the traditional phased array system based on single carrier frequency, this paper designs a novel architecture for distributed sensor system using dual carrier frequency measurements. Both two carrier frequencies are combined and transmitted simultaneously in the proposed architecture. Instead of single carrier frequency $f_1$ in the traditional method, the frequency separation $f_2-f_1$ is used in the proposed algorithm to determine a maximum unambiguous DOA estimate. Since $f_2-f_1$ is much less than $f_1$ and the choice of $f_2-f_1$ is more flexible, the proposed method can provide an unambiguous DOA estimate in the whole field of view (FOV) for arbitrary element spacing and a looser requirement on system synchronization than the traditional method based on single carrier frequency. For a case with $f_1=3$ Ghz, $f_2-f_1=150$ Mhz and 10 times element spacing, there is no grating lobe for the proposed method in the whole FOV $[-\pi /2,\pi /2]$, whereas the traditional method has many grating lobes and the FOV of the traditional method without grating lobes is only ${5.73}^{\circ }$. To obtain the same combining efficiency in this case, the requirement on the positioning error of the proposed method is 0.4 m and the location error of the traditional method must be smaller than 0.02 m. Hence, the proposed method can greatly reduce hardware requirements. The performances of the proposed architecture for the cases with perfect and imperfect system synchronizations are evaluated in terms of the average beampattern and combining efficiency, respectively. Some characteristics of the derived beampattern and combining efficiency are also presented in the paper.