Remote sensing change detection (RSCD) is crucial for ur- ban monitoring, environmental protection, and disaster as- sessment, but small-sample scenarios often lead to overfitting and inaccurate predictions on unseen data. To address this, we propose GSAG-CDGAN, an end-to-end framework integrat- ing Selective Noise Augmentation (SNA) to mitigate overfit- ting, an Attention-Guided Adversarial Network (AGAN) to enhance structural consistency, and a Perceptual Loss Mod- ule (PLM) to preserve semantic consistency. Experiments on CDData-50 show that GSAG-CDGAN improves F1-Score from 0.6954 to 0.8851, with notable gains in Recall and IoU, demonstrating enhanced robustness under small-sample con- ditions. Further evaluation on the WHU-CD dataset yields an F1-Score of 0.9502, confirming strong cross-dataset general- ization and the method’s effectiveness in diverse scenarios.

In the Internet of Things (IoT) domain, end-to-end (E2E) planning tasks require distributed devices to collaboratively train deep models under highly dynamic environments. However, existing federated learning (FL) methods often assume homogeneous communication conditions and static node reliability, leading to suboptimal aggregation performance when confronted with heterogeneous uncertainty sources such as sensing noise, prediction bias, and communication instability. To address this challenge, we propose FedUAP (Federated Uncertainty-Aware End-to-End Planning), a novel framework that dynamically adjusts client contributions based on multi-source uncertainty and network topology information. Specifically, each IoV vehicle node within the broader IoT system estimates three uncertainty factors—prediction uncertainty, sensing uncertainty, and communication uncertainty—to represent its model reliability and transmission stability. A topology-aware weighting module further refines the aggregation by incorporating node connectivity and link quality. In addition, a temporal smoothing strategy is introduced to stabilize weight evolution over successive communication rounds. Extensive experiments on various E2E IoV-centric IoT planning scenarios demonstrate that FedUAP achieves superior convergence stability, communication efficiency, and planning accuracy compared with existing adaptive aggregation and uncertainty-based FL baselines. The proposed approach provides a promising direction toward uncertainty-robust and topology-adaptive federated optimization in large-scale IoT and IoV networks.

To diminish the substantial communication costs incurred by federated learning during the training of the global model and enhance the model update efficiency across both clients and server domains, we have integrated knowledge distillation into the federated learning framework. This integration has led to the development of a novel approach termed ClientsToServerKDFL, which streamlines the distillation process by directly transferring model insights from clients to the server for computational learning without the need for extensive computations across numerous clients. This iterative process ensures model accuracy and curtails communication expenses. Experimental data analysis has validated the efficacy of this algorithm.

In federated learning, frequent parameter transmission between clients and the server results in significant communication overhead, particularly due to redundancy within the parameters. To address this issue, we propose a Complementary Pruning for Device-to-Device Communication (FedCPD) method. This approach effectively reduces the amount of transmitted parameters by applying complementary pruning techniques on both the server and clients. Additionally, we decrease the communication frequency between clients and the server by employing chain updates among clients (i.e., device-to-device communication). We conducted experiments on the MNIST, FMNIST, CIFAR-10, and CIFAR-100 datasets, and the results demonstrate that our method significantly reduces communication costs while improving model accuracy.

Remote sensing image change detection is crucial for urban construction and environmental monitoring. Recent advancements have seen convolutional neural networks (CNNs) and transformer structures increasingly applied in this domain. However, CNNs struggle with long-distance feature capture, while transformers suffer from high computational demands. Moreover, the inherently high resolution of remote sensing images and their susceptibility to natural conditions complicate feature extraction and processing, thereby hindering accurate change detection. The introduction of the mamba structure has significantly mitigated the issue of long-distance feature extraction. This letter introduces a model that integrates CNN and Mamba, named CWmamba, which employs a novel architecture combining mamba blocks and a CNN-based feature extraction block (BCGF) to process dual-temporal images. In the encoding phase, CWmamba utilizes the mamba blocks for global feature integration and the BCGF module for local feature enhancement. The decoding phase involves the fusion of multilevel features to augment the model’s expressive capability. The results of CWmamba on three datasets, SYSU-CD, LEVIR-CD+, and S2Looking, demonstrate its effectiveness, with F1 scores of 84.33%, 87.21%, and 67.93%, respectively.

Face video stylization aims to convert real face videos into specified reference styles. While one-shot methods perform well in single-image stylization, ensuring continuity between frames and retaining the original facial expressions present challenges in video stylization. To address these issues, our approach employs a personalized diffusion model with pixel-level control. We propose Local Consistency Guidance(LCG) strategy, composed of local-cross attention and local style transfer, to ensure temporal consistency. This framework enables the synthesis of high-quality stylized face videos with excellent temporal continuity.

Communication overhead remains a significant challenge in federated learning due to frequent global model updates. Essentially, the update of the global model can be viewed as knowledge transfer. We aim to transfer more knowledge through a compact model while reducing communication overhead. In our study, we introduce a federated learning framework where clients pre-train large models locally and the server initializes a compact model to communicate. This compact model should be light in size but still have enough knowledge to refine the global model effectively. We facilitate the knowledge transfer from local to global models based on pre-training outcomes. Our experiments show that our approach significantly reduce communication overhead without sacrificing accuracy.

Nowadays, sign language is becoming increasingly important in people’s daily life. Existing solutions are often based on wireless signals (e.g., acoustic, visible, and WiFi) or wearable sensors to recognize gestures, but they suffer from vulnerability to environmental influences, poor security, and high energy consumption, which prevent them from accurately capturing finger micromovements. In this article, we propose RF-Sign, which uses passive radio-frequency identification (RFID) tags to capture multiple finger micromovements simultaneously to enable sign language support. In particular, two main issues are studied. One is the problem of positional differences when users make the same gesture, and the other is the problem of segmenting consecutive gestures using only empirical thresholding methods and ignoring the existence of differences in thresholds for different gestures. For position differences, we propose position models to normalize the hand’s horizontal rotation angle and radial distance. For segmenting consecutive gestures, we use the received signal strength (RSS) trend of the reference tag to represent the finger micromovements state. The experimental results show that the average accuracy reaches 92.81% under different angles, distances, and other conditions.

Digital Twins (DTs) can generate digital replicas for mobile networks (MNs) that accurately reflect the state of MN. Machine learning (ML) models trained in DT for MN (DTMN) virtual environments can be more robustly implemented in MN. This can avoid the training difficulties and runtime errors caused by MN instability and multiple failures. However, when using data from various devices in the MN system, DTs must prioritize data privacy. Federated learning (FL) enables the construction of models without data leaving devices to protect DTMN data privacy. Nevertheless, FL’s privacy protection needs further improvement for it only guarantees device-level data ownership but ignores that models may retain private information from data. Therefore, this paper focuses on data forgetting in privacy protection, and proposes a novel FL-based unlearning framework (FedME2), which contains MEval and MErase modules. Guided by memory evaluation information from MEval and employing MErase’s multi-loss training approach, FedME2 gets accurate data forgetting in DTMN. In four DTMN virtual environments, FedME2 achieves an average data forgetting rate of approximately 75% for global models under FL and kept the influence on global models’ accuracy below 4%. FedME2 has better data forgetting and improves DTMN data privacy protection while guaranteeing model accuracy.

With the rapid development of information technology, image and text data have increased dramatically. Image and text matching techniques enable computers to understand information from both visual and text modalities and match them based on semantic content. Existing methods focus on visual and textual object co-occurrence statistics and learning coarse-level associations. However, the lack of intramodal semantic inference leads to the failure of fine-level association between modalities. Scene graphs can capture the interactions between visual and textual objects and model intramodal semantic associations, which are crucial for the understanding of scenes contained in images and text. In this article, we propose a novel scene graph semantic inference network (SGSIN) for image and text matching that effectively learns fine-level semantic information in vision and text to facilitate bridging cross-modal discrepancies. Specifically, we design two matching modules and construct scene graphs within each matching module for aggregating neighborhood information to refine the semantic representation of each object and achieve fine-level alignment of visual and textual modalities. We perform extended experiments in Flickr30K and MSCOCO and achieve state-of-the-art results, which validate the advantages of our proposed approach.

When the electromagnetic suspension (EMS) type maglev vehicle is traveling over a track, the airgap must be maintained between the electromagnet and the track to prevent contact with that track. Because of the open-loop instability of the EMS system, the current must be actively controlled to maintain the target airgap. However, the maglev system suffers from the strong nonlinearity, force saturation, track flexibility, and feedback signals with network time-delay, hence making the controller design even more difficult. In this article, the minimum levitation unit of the maglev vehicle system has been established. An amplitude saturation controller (ASC), which can ensure the generation of only saturated unidirectional attractive force, is thus proposed. The stability and convergence of the closed-loop signals are proven based on the Lyapunov method. Subsequently, ASC is improved based on the radial basis function neural networks, and a neural network-based supervisor controller (NNBSC) is thus designed. The ASC plays the main role in the initial stage. As the neural network learns the control trend, it will gradually transition to the neural network controller. Simulation results are provided to illustrate the specific merit of the NNBSC. The hardware experimental results of a full-scale IoT EMS maglev train are included to validate the effectiveness and robustness of the presented control method as regards to time delay.

With the rapid development of in-vehicle communication technology and the integration of big data intelligent technology, intelligent algorithms for vehicle communication used to predict traffic flow and location information have been widely used. Aiming at the problem that the gravitational algorithm is difficult to minimize the complex function and easily fall into the local optimum, this paper proposes an improved IGSA algorithm. First, a gridding algorithm is introduced to initialize the population, and under the premise of ensuring the randomness of the initial individuals, improving the ergodicity of the population is conducive to improving the quality of the solution; then, an adaptive location-based update strategy of decreasing inertia weights is proposed. this strategy inherits the advantages of linearly decreasing weights, and adaptively adjusts the weights according to the fitness value to further improve the optimization performance. The optimization simulation of 8 classic test functions shows that the IGSA algorithm is an effective algorithm for solving complex optimization problems. Finally, the IGSA algorithm is used to predict the geographic location problem in the vehicle GPS data. The IGSA algorithm is used to optimize the extreme learning method to optimize the hyperparameters and establish a vehicle GPS data prediction model. Simulation results verify the feasibility of the method.

In large‐scale Internet of Things (IoT) applications, tags are attached to items, and users use a radiofrequency identification (RFID) reader to quickly identify tags and obtain the corresponding item information. Since multiple tags share the same channel to communicate with the reader, when they respond simultaneously, tag collision will occur, and the reader cannot successfully obtain the information from the tag. To cope with the tag collision problem, ultrahigh frequency (UHF) RFID standard EPC G1 Gen2 specifies an anticollision protocol to identify a large number of RFID tags in an efficient way. The Q‐algorithm has attracted much more attention as the efficiency of an EPC C1 Gen2‐based RFID system can be significantly improved by only a slight adjustment to the algorithm. In this paper, we propose a novel Q‐algorithm for RFID tag identification, namely, HTEQ, which optimizes the time efficiency of an EPC C1 Gen2‐based RFID system to the utmost limit. Extensive simulations verify that our proposed HTEQ is exceptionally expeditious compared to other algorithms, which promises it to be competitive in large‐scale IoT environments.

The academic society is stepping into the age of scholarly big data, where finding suitable scholars for collaboration has become ever difficult. Scholarly recommendation approaches are designed to overcome the information overload problems. However, previous methods mainly consider network topology without considering scholars' academic information and the manually designed similarity measurements may not have a good performance when applying to large-scale sparse networks. To this end, this article proposes to design a scholarly friend recommendation system by taking advantages of network embedding and scholar attributes. It is worth mentioning that different from traditional scientific collaborator recommendations, our goal is to recommend potential friends for scholars using academic social networks. We first construct an attributed social network by extracting scholars' academic attributes from digital libraries. Then, we perform an attributed random walk which can jointly model network structure and scholar attributes. Finally, a novel graph recurrent neural framework is adopted to embed attributed scholar interactions within the model for recommendations. Experimental results on two real-world scholarly datasets demonstrate the effectiveness of our proposed method.