In the field of Internet of Things (IoT), uncrewed aerial vehicle (UAV) swarms are widely used to assist IoT communication due to their simple deployment, high mobility and high cost effectiveness to help improve IoT network coverage and topological flexibility. However, due to the openness of UAV swarm network, UAV nodes are vulnerable to malicious attacks and fail, especially some key nodes, which will seriously degrade the network performance. To solve this problem, a key node identification model based on graph convolutional network (GCN), named KNIGCN, is proposed. Specifically, the topology model of UAV cluster network is first built based on flying ad hoc network (FANET) communication architecture and Dijkstra’s algorithm, then node criticality labels in the network are made by means of traffic statistics, and finally KNIGCN model is used to predict the criticality scores of each node and sort them so as to screen out a certain number of key nodes. The experimental results show that the model has good performance of key node identification. Compared with traditional methods, the proposed method makes a more reasonable judgment of node criticality, and the key nodes identified have a more important impact on network performance. Moreover, the proposed scheme can effectively improve the identification speed of key nodes in large-scale, complex or dynamically changing topology of UAV cluster networks. It can provide an effective scheme for maintaining the security and stability of UAV swarm network communication.

Radio frequency fingerprint (RFF), which comes from the imperfect hardware, is a potential feature to ensure the security of communication. With the development of deep learning (DL), DL-based RFF identification methods have made excellent and promising achievements. However, on one hand, existing DL-based methods require a large amount of samples for model training. On the other hand, the RFF identification method is generally less effective with limited amount of samples, while the auxiliary dataset and the target dataset often needs to have similar data distribution. To address the data-hungry problems in the absence of auxiliary datasets, in this paper, we propose a supervised contrastive learning (SCL)-based RFF identification method using data augmentation and virtual adversarial training (VAT), which is called “SCACNN”. First, we analyze the causes of RFF, and model the RFF identification problem with augmented dataset. A non-auxiliary data augmentation method is proposed to acquire an extended dataset, which consists of rotation, flipping, adding Gaussian noise, and shifting. Second, a novel similarity radio frequency fingerprinting encoder (SimRFE) is used to map the RFF signal to the feature coding space, which is based on the convolution, long-short-term-memory, and a fully connected deep neural network (CLDNN). Finally, several secondary classifiers are employed to identify the RFF feature coding. The simulation results show that the proposed SCACNN has greater identification ratio than the other classical RFF identification methods. Moreover, the identification ratio of the proposed SCACNN achieves an accuracy of 92.68% with only 5% samples.

With the development of the Internet of Things (IoT), the IoT devices are increasing day by day, resulting in increasingly scarce spectrum resources. At the same time, many IoT devices are facing inevitable malicious attacks. The cognitive Radio-enabled IoT (CR-IoT) is proposed as an effective method for spectrum resource allocation and risk monitoring in the IoT. The signal detection and modulation recognition are the key technologies for CR-IoT, addressing the problem of multisignal detection and automatic modulation classification (AMC) is one of the prerequisites for realizing secure dynamic spectrum access. Based on sliding window and deep learning (DL), this study proposes a multisignal frequency domain detection and recognition method. The frequency spectrum of the time-domain overlapping signal is obtained through the fast Fourier transform (FFT), and the frequency spectrum is segmented based on the signal energy detection method. Finally a complex convolutional neural network (CNN) is constructed for the identification of signal spectrum information. The proposed method can recognize 264 time-domain aliasing and frequency-closed signals with an accuracy of 97.3% under the influence of −2 dB corresponding to the noise of the calibration signal. In addition, the proposed method eliminates the influence of bandwidth, which can effectively detect and recognize the signal types of each component in the frequency band. This method has wide applicability and provides an effective scheme for the IoT cognitive technology.

Phase-generated carrier (PGC) demodulation technology has been widely used in fiber-optic interferometric sensors system in recent years. Nonlinear errors caused by interference noise and parasitic amplitude modulation (AM) are key factors that affect the reliability of traditional PGC demodulation system based on arctangent (PGC-Arctan) algorithm. In order to enhance the reliable performance of PGC demodulation system under the conditions of low signal-to-noise ratio (SNR) and high parasitic AM interference, an ellipse fitting algorithm based on the Gauss–Newton iteration (GNI) is proposed, which is called the PGC-Arctan-GNI demodulation algorithm. The proposed algorithm uses the Euclidean distance to accurately estimate the geometric parameters of ellipse, which can correct the nonlinear distortion of the demodulated signal. In addition, the PGC demodulation system designed based on GNI algorithm has the advantages of strong antinoise ability, good antiparasitic AM ability, and widely dynamic range of the input signal amplitude. Experimental results show that, compared with the direct demodulation algorithm and the ellipse fitting algorithm based on the least squares (LS) method, the SINAD value of the proposed algorithm is always greater than 30 dB and higher than the other two algorithms under the condition of low SNR. Under the condition that the parasitic AM index$m$changes from 0 to 0.5, the signal-to-noise and distortion ratio (SINAD) curve of the proposed algorithm is more stable than the curves of the other two algorithms, and the fluctuation range of the SINAD value does not exceed 3 dB. This algorithm also has a wider input signal amplitude range than the LS algorithm. Especially, when the amplitude of the measured signal is less than$\pi$/2, the relative amplitude error of the GNI algorithm is less than 2% and significantly smaller than the LS algorithm. Finally, the demodulation results using real measured data in the actual system show that the frequency and amplitude of the demodulated signal are same as the original signal. At the same time, the SNIAD value of this system reaches 67.40 dB, the spurious-free dynamic range value reaches 68.82 dB, and the total harmonic distortion value reaches -68.40 dB@1 KHz. In summary, the proposed PGC-Arctan-GNI algorithm can eliminate system nonlinear errors caused by the parasitic AM, harmonics, and noise interference by estimating the ellipse parameters, thereby effectively enhancing the stability and reliability of the PGC demodulation system.

Compared with the fixed frequency signal, the carrier frequency of frequency hopping (FH) signal is controlled by the pseudo-random codes, so it has better concealment and anti-interference. As an important parameter of FH communication, the modulation mode of FH signal can provide powerful support for combat response, such as identification of friend or foe attribute, positioning and jamming guidance, intelligence information extraction, etc. However, there is still a big gap in modulation recognition of FH signals at the domestic and foreign countries. In this paper, a modulation recognition method of FH signal based on time-frequency transform is proposed. The time-frequency images of different modulation types of FH signals are obtained by SPWVD time-frequency transform, and then the time-frequency images are denoised by convolution autoencoder. Finally, the denoised images are sent to convolution neural network for feature extraction and classification recognition. Simulation experiments prove that the proposed method achieves a good classification effect at low signal-to-noise ratios (SNRs), and achieves a recognition rate of 93.67% at -2dB.

Heading estimation using inertial sensors built‐in smartphones has been considered as a central problem for indoor pedestrian navigation. For practical daily lives, it is necessary for heading estimation to allow an unconstrained use of smartphones, which means the varying device carrying positions and orientations. As a result, three special human body motion states, namely, random hand movements, carrying position transitions, and user turns, are introduced. However, most existing heading estimation approaches neglect the three motion states, which may render large estimation errors. We propose a robust heading estimation system adapting to the unconstrained use of smartphones. A novel detection and classification method is developed to detect the three motion states timely and discriminate them accurately. For normal working, the user heading is estimated by a PCA‐based approach. If a user turn occurs, it is estimated by adding horizontal heading change to previous user heading directly. If one of the other two motion states occurs, it is obtained by averaging estimation results of the adjacent normal walking steps. Finally, an outlier filtering algorithm is developed to smooth the estimation results. Experimental results show that our approach is capable of handling the unconstrained situation of smartphones and outperforms previous approaches in terms of accuracy and applicability.

Accuracy performance of WiFi fingerprinting positioning systems deteriorates severely when signal attenuations caused by human body are not considered. Previous studies have proposed WiFi fingerprinting positioning based on user orientation using compasses built in smartphones. However, compasses always cannot provide required accuracy of user orientation estimation due to the severe indoor magnetic perturbations. More importantly, we discover that not only user orientations but also smartphone carrying positions may affect signal attenuations caused by human body greatly. Therefore, we propose a novel WiFi fingerprinting positioning approach considering both user orientations and smartphone carrying positions. For user orientation estimation, we deploy Rotation Matrix and Principal Component Analysis (RMPCA) approach. For carrying position recognition, we propose a robust Random Forest classifier based on the developed orientation invariant features. Experimental results show that the proposed WiFi positioning approach may improve positioning accuracy significantly.