Benefitting from the vast spatial degrees of freedom, the amalgamation of integrated sensing and communication (ISAC) and massive multiple-input multiple-output (MIMO) is expected to simultaneously improve spectral and energy efficiencies as well as the sensing capability. However, a large number of antennas deployed in massive MIMO-ISAC raises critical challenges in acquiring both accurate channel state information and target parameter information. To overcome these two challenges with a unified framework, we first analyze their underlying system models and then propose a novel tensor-based approach that addresses both the channel estimation and target sensing problems. Specifically, by parameterizing the high-dimensional communication channel exploiting a small number of physical parameters, we associate the channel state information with the sensing parameters of targets in terms of angular, delay, and Doppler dimensions. Then, we propose a shared training pattern adopting the same time-frequency resources such that both the channel estimation and target parameter estimation can be formulated as a canonical polyadic decomposition problem with a similar mathematical expression. On this basis, we first investigate the uniqueness condition of the tensor factorization and the maximum number of resolvable targets by utilizing the specific Vandermonde structure. Then, we develop a unified tensor-based algorithm to estimate the parameters including angles, time delays, Doppler shifts, and reflection/path coefficients of the targets/channels. In addition, we propose a segment-based shared training pattern to facilitate the channel and target parameter estimation for the case with significant beam squint effects. Simulation results verify our theoretical analysis and the superiority of the proposed unified algorithms in terms of estimation accuracy, sensing resolution, and training overhead reduction.

We investigate the problem of direction of arrival (DOA) estimation with 1-b measurements in massive MIMO systems, as 1-b quantization offers low cost and low complexity in the implementation. We first establish the connection between 1-b DOA estimation and linear classification based on the sparsity of the incident signals. Then, we present an iterative refinement procedure based on Taylor expansion to obtain DOA estimation off the grid. This refinement procedure can be easily extended to other 1-b DOA estimation algorithms with minor changes. Finally, simulations are conducted for validation and the results illustrate the high performance of the proposed algorithm in spite of the extreme 1-b quantization.

Accurate detection of passable regions in images is important for ensuring the safe navigation of unmanned surface vehicles, especially in inland waterways with irregular waterlines and various obstacles. However, the existing methods are susceptible to environmental changes and produce high false-positive rates (FPRs) for confusable textures and complex edge details. We, therefore, propose a collision-free waterway segmentation network based on deep learning such that pixel-level classification results can be obtained. The segmentation accuracy for indistinguishable textures is improved by learning the context dependency of features through a modified context prior, and the detailed refinement of waterlines and small obstacles is achieved via an asymmetric encoder–decoder structure. To learn the features of waterways as comprehensively as possible, data integration and data augmentation are performed on three public datasets. In addition, a new annotated urban waterway dataset called the Dasha River dataset is proposed and made publicly available. The proposed model is tested and cross validated using multiple inland and maritime water segmentation datasets, the results of which show that the model achieves superior performance than the current state of the art with pixel accuracy (PA) of 97.43% and FPR of 1.37%.

Wideband spectrum sensing is an important aspect of cognitive radio systems. In current models of wide spectrum sensing, a discrete frequency denotes a continuous frequency band. This type of model is divorced from practice and cannot reflect the reality of spectrum occupation. In this study, we propose a novel wideband spectrum sensing scheme in terms of a modulated wideband converter (MWC) and sparse Bayesian learning (SBL). By exploiting MWC, a practical wideband signal denoted by a block-sparse model is sampled to acquire the compressed measurements. We then employ SBL to directly extract the relevant information from the compressed measurements for estimating the support set. The estimated support set is chosen as the test statistic to facilitate spectrum sensing and analyze the detection performance. For applications in actual situations of support sets, different matching criteria are presented according to the requirements imposed by wideband spectrum sensing. Finally, we analyze the detection performance when a frequency band’s location is given as well as when it is randomly generated by conducting simulations. These simulations show that the proposed method outperforms the MWC-based orthogonal matching pursuit (MWC-OMP) method, and the best performance can be achieved under matching criterion 3.

Federated learning (FL) enables edge nodes to collaboratively train a global model under the coordination of a server without sharing local private data. However, data heterogeneity across nodes leads to serious performance degradation or even non-convergence of the learned model. To tackle this challenge, most existing methods typically involve either local model regularization or global model adjustments. Nevertheless, these methods primarily perform model aggregation based on the dataset size proportion, while the exploration of the impact of non-independent and identically distributed (non-IID) data on aggregation weights remains insufficient. To this end, we theoretically derive an analytical expression for the aggregation weights by minimizing the convergence upper bound of standard FL on non-IID data across nodes, achieving a tighter bound and superior convergence performance. Accordingly, we propose an adaptive aggregation weight strategy, called FedAAW. It can be easily incorporated into other FL methods to improve their convergence performance with negligible additional communication overhead. Extensive experiments on four common datasets show that FedAAW can effectively mitigate the performance degradation caused by data heterogeneity in various cases. Simply applying FedAAW to other methods can significantly improve their performance, achieving a maximum improvement of 37.32% in test accuracy and outperforming other state-of-the-art aggregation weight strategies.