In this paper, we develop a novel visual-inertial navigation system with motion constraint (VINS-Motion), which extends the visual-inertial navigation system (VINS) to incorporate vehicle motion information for improving the autonomous vehicles localization accuracy. We introduce the vehicle stop detection module in the pre-processing measurement procedure. During the back-end processing, if the vehicle is detected to be in a stopping state, we perform optimization based on the stop constraint to help eliminate the abnormal jitter of the estimated pose, thus ensuring the reasonability of the trajectory. Otherwise, besides the prior information, IMU measurement residual, and visual measurement residual utilized in VINS, vehicle orientation/velocity constraint built by Ackerman steering model is first exploited to constitute residuals. We minimize the sum of priors and Mahalanobis norms of three kinds of residuals to obtain a maximum posterior estimation, thus increasing system consistency and accuracy. The proposed approach is validated on public datasets and compared with state-of-the-art algorithms, which demonstrates that the motion constraint proposed in this paper improves the standard VINS performance and achieves significantly higher positioning accuracy.

Cloud–edge–end computing architecture is crucial for large-scale edge data processing and analysis. However, the diversity of terminal nodes and task complexity in this architecture often result in non-independent and identically distributed (non-IID) data, making it challenging to balance data heterogeneity and privacy protection. To address this, we propose a privacy-preserving federated learning method based on cloud–edge–end collaboration. Our method fully considers the three-tier architecture of cloud–edge–end systems and the non-IID nature of terminal node data. It enhances model accuracy while protecting the privacy of terminal node data. The proposed method groups terminal nodes based on the similarity of their data distributions and constructs edge subnetworks for training in collaboration with edge nodes, thereby mitigating the negative impact of non-IID data. Furthermore, we enhance WGAN-GP with attention mechanism to generate balanced synthetic data while preserving key patterns from original datasets, reducing the adverse effects of non-IID data on global model accuracy while preserving data privacy. In addition, we introduce data resampling and loss function weighting strategies to mitigate model bias caused by imbalanced data distribution. Experimental results on real-world datasets demonstrate that our proposed method significantly outperforms existing approaches in terms of model accuracy, F1-score, and other metrics.

Increasing the hopping frequency speed and integrating artificial intelligence (AI) technologies are currently two of the most effective strategies for enhancing the anti-jamming performance of frequency hopping (FH) systems. However, due to the complexity of the decision-making process in intelligent agents, the system cannot complete decisions within the intervals between hops in fast frequency hopping (FFH) systems. As a result, there is no existing strategy for directly applying AI technologies to FFH systems. In this work, we introduce the concept of the available frequency set (AFS) and apply deep reinforcement learning (DRL) methods to FFH systems, enabling them to retain their inherent advantages while also gaining adaptability to dynamic environments. Building on this, we propose an improved multi-action deep recurrent Q-network (MA-DRQN) algorithm to determine the AFS for hopping sequence generation. Finally, the proposed method is shown to outperform both traditional FFH systems and advanced intelligent FH systems in handling blind and active jammers. Moreover, the hopping sequences generated based on AFS exhibit strong unpredictability.

Automatic modulation recognition is a critical step between signal detection and signal demodulation, and it is a critical technology for ensuring proper communication. Since the introduction of 5G technology, wireless communication systems have had massive data throughput, so combining deep learning technology with modulation recognition technology is now one of the most mainstream development directions in the field of communication. In order to effectively improve the robust recognition accuracy of modulation signals in low SNR condition, this paper proposes an end-to-end AMR model based on deep learning, called residual convolution long short memory Improved Transformer-Encoder deep neural network model (RLITNN). First, convolutional network and LSTM network extract the initial features from the communication signals of different modes. Second, the proposed Improved Transformer-Encoder module is used to capture the global and local focus of the extracted features. Then, these features are fused. Finally, the high quality features are further captured from the fused feature vector to enhance the feature representation ability of the model. Experiments on RML2016.10A and RML2016.10B datasets show that the proposed RLITNN has better feature learning ability and better recognition accuracy than other advanced (SOTA) techniques.

The Space-Air-Ground Integrated Network (SAGIN) has emerged as a core architecture for future intelligent communication due to its wide-area coverage and dynamic heterogeneous characteristics. However, its high latency, dynamic topology, and privacy–security challenges severely constrain the application of Federated Learning (FL). This paper proposes a Privacy-Preserving Federated Learning framework for SAGIN (PPFL-SAGIN), which for the first time integrates differential privacy, adaptive transfer learning, and bi-level reinforcement learning to systematically address data heterogeneity, device dynamics, and privacy leakage in SAGINs. Specifically, (1) an adaptive knowledge-sharing mechanism based on transfer learning is designed to balance device heterogeneity and data distribution divergence through dynamic weighting factors; (2) a bi-level reinforcement learning device selection strategy is proposed, combining meta-learning and hierarchical attention mechanisms to optimize global–local decision-making and enhance model convergence efficiency; (3) dynamic privacy budget allocation and robust aggregation algorithms are introduced to reduce communication overhead while ensuring privacy. Finally, experimental evaluations validate the proposed method. Results demonstrate that PPFL-SAGIN significantly outperforms baseline solutions such as FedAvg, FedAsync, and FedAsyncISL in terms of model accuracy, convergence speed, and privacy protection strength, verifying its effectiveness in addressing privacy preservation, device selection, and global aggregation in SAGINs.

In this paper, a blind adaptive detector is proposed for blind separation of user signals and blind estimation of spreading sequences in DS-CDMA systems. The blind separation scheme exploits a charrelation matrix for simple computation and effective extraction of information from observation signal samples. The system model of DS-CDMA signals is modeled as a blind separation framework. The unknown user information and spreading sequence of DS-CDMA systems can be estimated only from the sampled observation signals. Theoretical analysis and simulation results show that the improved performance of the proposed algorithm in comparison with the existing conventional algorithms used in DS-CDMA systems. Especially, the proposed scheme is suitable for when the number of observation samples is less and the signal to noise ratio (SNR) is low.