In this paper, we propose an unmanned aerial vehicle (UAV) and bird recognition scheme with signal processing and deep learning for integrated sensing and communications (ISAC) system. We first provide the basic scene of low-altitude targets monitoring, and formulate the motion equations and echo signals for UAVs and birds. Next, we extract the centralized micro-Doppler (cmD) spectrum and the high resolution range profile (HRRP) of the low-altitude target from the echo signals. Then we design a dual feature fusion enabled low-altitude target recognition network with convolutional neural network (CNN), which employs both the images of cmD spectrum and HRRP as inputs to jointly distinguish between UAV and bird. Meanwhile, we generate 237600 cmD and HRRP image samples to train, validate, and evaluate the designed low-altitude target recognition network. The proposed scheme is termed asAirGuard, whose effectiveness has been demonstrated by simulation results.

Precoding in massive multiple-input-multiple-output (mMIMO) systems relies on accurate estimation of downlink channel state information (CSI). However, when the number of antennas is large, obtaining CSI data incurs significant pilot and feedback overhead. In this paper, we propose a transformer based precoding network (TPN) that infers the future precoding matrices by exploring the time-frequency characteristic of historical wireless channels. Next, we design a suitable precoding matrix switching scheme based on channel correlation to further reduce the pilot overhead. Moreover, we leverage the network pruning technique to reduce the computational complexity of the proposed TPN. Simulations demonstrate that the sum-rate can be improved by 15% compared with the traditional zero-order holding method.

The utilization of unmanned aerial vehicles (UAVs) for communication data collection across all areas can be modeled as a complete coverage path planning (CCPP) problem. To address the challenge of lengthy coverage time in traditional CCPP algorithms, we propose a weighted balanced graph partitioning based complete coverage path planning scheme (WBGPP), which consists of two sub-algorithm: weighted balanced graph partitioning (Weighted B-GRAP) and single agent path planning (SAPP). The Weighted B-GRAP algorithm can decompose the multi-UAV CCPP problem into multiple single UAV CCPP problems by assigning each UAV a responsibility area according to its capability. Then, we optimize the backtracking strategy through breadth-first search and design a SAPP algorithm to reduce the number of repeated visits and shorten the coverage time. The simulation results show that the proposed WBGPP scheme effectively reduce the coverage time of multiple UAVs in CCPP problems and can be applied to various maps.

In this paper, we investigate the correlation between the sub-6GHz channel and the millimeter wave (mmWave) chan-nel, and then predict the mmWave downlink hybrid beamforming (HBF) matrices directly from the sub-6GHz uplink channel, based on a sophisticatedly designed deep learning architecture. Specifically, the neural network structure consists of three functional modules: the feature extraction module extracts channel features from a large amount of channel data, the feature fusion module combines multidimensional features, and the prediction module generates the HBF matrix. Moreover, we develop a power constraint module for digital domain and a constant modulus constraint module for analog domain to ensure that the output of the network satisfies the characteristics of HBF. Simulation results show that the proposed sub-6GHz assisted HBF algorithm without mmWave channel estimation saves 75% of channel state information compared to the method using mmWave pilot resources directly. Furthermore, to facilitate deployment, we design a low-complexity structure that achieves a remarkable reduction of 98.52% in parameters and 22.93% in computations.

Millimeter-wave (mmWave) communications with abundant spectrum resources have become an enabling technology for high throughput, ultra-reliable, and low latency communications (URLLC). Since the mmWave signal is sensitive to blockage, accurate base station (BS) selection is the premise of achieving the URLLC. In this paper, we propose a multi-view images assisted proactive BS selection scheme that can predict the optimal BS for the user in the next frame. The proposed scheme utilizes vision sensing and thus does not require the entire pilot resources, such that the latency caused by seeding and receiving pilots reduces. In addition, we design a multitask learning strategy and a prior knowledge based fine tuning method to ensure the accuracy and reliability of BS selection. Simulation results in an outdoor environment demonstrate the superior performance of the proposed scheme in terms of both the accuracy and the robustness.

In this paper, we consider the moving target sensing problem for integrated sensing and communication (ISAC) sys-tems in clutter environment. Scatterers produce strong clutter, deteriorating the performance of ISAC systems in practice. Given that scatterers are typically stationary and the targets of interest are usually moving, we here focus on sensing the moving targets. Specifically, we adopt a scanning beam to search for moving target candidates. For the received signal in each scan, we employ high-pass filtering in the Doppler domain to suppress the clutter within the echo, thereby identifying candidate moving targets according to the power of filtered signal. Then, we adopt root-MUSIC-based algorithms to estimate the angle, range, and radial velocity of these candidate moving targets. Subsequently, we propose a target detection algorithm to reject false targets. Simulation results validate the effectiveness of these proposed methods.

Millimeter-wave (mmWave) communications with abundant spectrum resources have become an enabling technology for high throughput, ultra-reliable, and low latency communications (URLLC). Since the mmWave signal is sensitive to blockage, accurate base station (BS) selection and beam searching are the premises of achieving the URLLC. In this paper, we consider the mmWave communications systems where mobile users are served by the roadside unit (RSU). We propose a multi-camera view based proactive RSU selection and beam searching scheme that can predict the optimal RSU for the user in the next frame and search the corresponding beam pair. The proposed scheme utilizes vision sensing and reduces training resources. In addition, the visual information of multiple views makes the selection of the optimal RSU more accurate and reliable compared to the existing single view technologies. Simulation results in an outdoor environment show the superior performance of the proposed scheme in terms of predicting accuracy and achievable rate.

Integrated sensing and communications (ISAC) has been deemed as a key technology for the sixth generation (6G) wireless communications systems. In this paper, we explore the inherent clustered nature of wireless users and design a multi-user based environment reconstruction scheme. Specifically, we first select users based on the estimation precision of channel’s multipath, including the line-of-sight (LOS) and the non-line-of-sight (NLOS) paths, to enhance the accuracy of environment reconstruction. Then, we develop a fusion strategy that merges communications signalling with camera image to increase the accuracy and robustness of environment reconstruction. The simulation results demonstrate that the proposed algorithm can achieve a remarkable sensing accuracy of centimeter level, which is about 17 times better than the scheme without user selection. Meanwhile, the fusion of communications data and vision data leads to a threefold accuracy improvement over the image only method, especially under challenging weather conditions like raining and snowing.

In order to reduce the downlink training overhead of mmWave communications, we propose a novel downlink beamforming strategy using the uplink sub-6GHz channel and downlink mmWave pilots that are sent from a few active antennas. Specifically, we design a novel dual-input neural network architecture, called FusionNet, to merge the sub-6GHz channel and the channel of a few active mmWave antennas. The proposed fusion model could intelligently adjust the attention paid (by the neural network) for sub-6GHz channel and mmWave channel by an attention mechanism. The output of the FusionNet represents the probability for each beam being the optimal one. We also propose an antenna selection model that can choose better active antennas to send the downlink pilots, in which the gradient of antenna selection vector is approximated by that of an antenna probability vector. Simulation results demonstrate the superior performance of the proposed strategy compared to the existing one that purely relies on the sub-6GHz information or compared to the shallow model that directly adds uniform pilots.

A critical bottleneck of massive multiple-input multiple-output (MIMO) system is the huge training overhead caused by downlink transmission, like channel estimation, downlink beamforming and covariance observation. In this paper, we propose to use the channel state information (CSI) of a small number of antennas to extrapolate the CSI of the other antennas and reduce the training overhead. Specifically, we design a deep neural network that we call an antenna domain extrapolation network (ADEN) that can exploit the correlation function among antennas. We then propose a deep learning (DL) based antenna selection network (ASN) that can select a limited antennas for optimizing the extrapolation, which is conventionally a type of combinatorial optimization and is difficult to solve. We trickly designed a constrained degradation algorithm to generate a differentiable approximation of the discrete antenna selection vector such that the back-propagation of the neural network can be guaranteed. Numerical results show that the proposed ADEN outperforms the traditional fully connected one, and the antenna selection scheme learned by ASN is much better than the trivially used uniform selection.