Wireless communication with the enormous demands of sensing ability have given rise to the integrated passive sensing and communication (IPSAC) technology. The main challenge of IPSAC is how to achieve high sensing and communication performance by integrating the passive sensing and communication demodulation. In this paper, we propose an integrated sensing and communication (ISAC) signal processing optimization scheme by jointly processing the pilot and data signals. To solve the optimization problem, we propose an ISAC signal processing algorithm based on iterative optimization, which alternates the passive sensing and channel reconstruction to realize target sensing. However, the hyper-parameter configuration of the iterative optimization algorithm influences the performance of target detection and communication demodulation. Recognizing this fact, we propose a model-driven ISAC network (ISAC-NET) that adopts the block-by-block signal processing method to improve the communication and sensing performance. The proposed ISAC-NET obtains suitable hyper-parameters by deep learning to guarantee the performance and convergence of communication and sensing signal processing. From the simulation results, ISAC-NET obtains better communication performance than the traditional signal demodulation algorithm, which is close to OAMP-Net2. Compared to the 2D-DFT algorithm, ISAC-NET demonstrates significantly enhanced sensing performance. In summary, ISAC-NET is a promising tool for the IPSAC systems.

Intelligent unmanned aerial vehicle (UAV) swarm may accomplish complex tasks through cooperation, relying on inter-UAV communications. This paper aims to improve the communication performance of intelligent UAV swarm system in the presence of jamming, by multi-parameter programming and reinforcement learning. This paper considers a communication system, where the communication between a UAV swarm and the base station is jammed by multiple interferers. Compared with the existing work, the UAVs in the system can exploit degree-of-freedom in frequency, motion and antenna spatial domain to optimize the communication quality in the receiving area. This paper proposes a modified Q-Learning algorithm based on multi-parameter programming, where a cost is introduced to strike a balance between the motion and communication performance of the UAVs. The simulation results show the effectiveness of the algorithm.

Aircraft is an important means of travel and the most convenient and fast vehicle in long-distance transportation. The aircraft engine is one of the most critical parts of an aircraft, and its reliability and safety are extremely important. In this paper, we consider that the operating conditions of aero-engines are complex and changeable, and a multi-resolution long short-term memory (MR-LSTM) model is proposed. The model can effectively predict the remaining useful life (RUL) of an aero-engine, which is a priority issue within the Prognostics and Health Management (PHM) framework - and thus it can support maintenance decisions. Sequences with multiple temporal resolutions are generated by a reconstruction of the decomposed wavelets. A two-layer LSTM model is then designed: 1) the first layer LSTM is used to learn attention at different time resolutions as well as to generate an integrated historical representation; 2) the second layer LSTM is used to learn the long and short-term time dependencies in the integrated historical representation. Experimental evaluations using the C-MAPSS datasets (FD002 and FD004) and the N-CMAPSS dataset showed that compared to other state-of-the-art RUL prediction methods, the FD002 sub-dataset showed a 12.1% reduction in RMSE and a 3.8% reduction in Score; the FD004 sub-dataset showed a 21.8% reduction in RMSE and a decreased by 62.1%; the RMSE of the N-CMAPSS dataset decreased by at most 25.8%.

Specific emitter identification (SEI) is a technology that extracts subtle features from signals sent by emitters to identify different individuals. It can effectively improve the security of the Industrial Internet of Things (IIoT) by acting on the physical layer of the Internet. Recent research on SEI has focused on deep learning (DL) models that can automatically learn effective inherent emitter features from raw signals. Nevertheless, training popular DL models is computationally expensive because of the numerous hyperparameters and nonscalable structures. This limits the application of DL-based SEI models in certain practical IIoT scenarios. To address this concern, we propose an adaptive broad learning (ABL) method to build a lightweight SEI model. In the proposed model, the raw signal samples are mapped to feature nodes, and the emitters are denoted as the output nodes. The hidden nodes are directly connected to the output nodes by a broad network. Through this flat structure, the size and calculation amount of the model can be effectively reduced. To further economize the computational cost, we designed an adaptive node expansion strategy for rapidly obtaining the optimal hyperparameters of the models. The results of experiments on real-world data prove the superiority of ABL over popular state-of-the-art DL-based SEI models.

Unauthorized underwater vehicles (UUVs) pose a serious threat to maritime security. To preserve maritime security, it is essential to pursue these UUVs. The majority of traditional pursuit methods are based on known environmental dynamics. However, the underwater environment is too complicated and unpredictable to describe these dynamics accurately. This study developed a novel online decision-making technique called multi-agent distributional soft actor-critic (MADA) to handle the issue of underwater cooperative pursuit. The method constructs a control-oriented framework based on multi-agent reinforcement learning that can map autonomous underwater vehicle (AUV) observations to pursuit actions. Multiple AUVs can combine to make prompt pursuit decisions. Then, the proposed method combines distributional soft actor-critic and curriculum learning to improve the success rates of multiple AUVs in pursuing UUVs. Experimental results show that the MADA can obtain a better cooperative pursuit strategy.

Existing researches on UAV networks mostly adopt omni-directional antenna pattern, which results in overlapping between coverage areas and bringing severe co-channel interference due to air-to-ground dominant line-of-sight (LOS) channels. Considering directional antennas that concentrate transmission power to small cells, this letter analyzes system performance of UAV-assisted networks with conic directional antenna model by deriving network coverage probability via stochastic geometry, where UAVs and macro base stations (MBSs) are deployed according to independent Poisson point process. Specifically, realistic and mathematically tractable directional antenna pattern is adopted that radiation gain is modeled by a continuous function of the elevation angle $\varphi $ and the directivity factor $\omega $ . In addition, the tradeoff between cell association and interference isolation is exploited by adjusting $\omega $ and UAV LOS/NLOS probabilities. Theoretical results show that, system coverage probability could be improved by 41% in urban environment when $\omega =6.2$ and UAV density $\lambda _{u}=300/k{m^{2}}$ .