The rapid expansion of the Internet of Things (IoT) has led to unprecedented growth in multivariate time-series (MVTS) data, which are vital for real-world applications such as industrial monitoring, cyber-physical security, and smart city operations. These data streams are susceptible to anomalies that may indicate system malfunctions, security breaches, or environmental hazards. However, existing MVTS anomaly detection (MTAD) approaches, typically trained in centralized settings, struggle in IoT deployments due to data heterogeneity, resource constraints, and privacy concerns. We propose FEDKO, a novel federated learning (FL) framework that couples Reservoir Computing with Koopman operator theory for efficient, privacy-preserving MTAD in distributed IoT networks. At its core, ReKO, a lightweight spatio-temporal Reservoir-Koopman model, lifts nonlinear MVTS dynamics into a linear space for stable prediction and reconstruction. We formulate the FL training as a bi-level optimization procedure where the inner level learns locally stable Koopman dynamics, and the outer level refines lifted feature representations and reconstruction mappings. We further provide theoretical convergence guarantees, anomaly discriminability analysis, and a structural privacy characterization of the framework. Experiments on four IoT MVTS datasets and deployment on an NVIDIA Jetson edge device show that FEDKO achieves a balanced precision–recall profile with competitive F1-scores under heterogeneous federated settings, while substantially reducing communication and memory footprints compared with MTAD baselines.

Robust Federated Learning (RoFL) extends traditional federated learning, not only by enabling multiple clients to collaboratively train a shared model under the coordination of an edge server, but also by incorporating client-side defense mechanisms (e.g., adversarial training) to defend against adversarial attacks while preserving data privacy. However, recent studies have shown that RoFL also remains vulnerable to the challenges posed by non-independent and identically distributed (non-IID) data distributions across heterogeneous clients, which can degrade overall model generalization and robustness. To mitigate this challenge, in this paper, we propose a novel RoFL framework, called RoFLCCA, to address non-IID challenges while defending against adversarial attacks. In particular, we first introduce a local classifier calibration mechanism that utilizes feature-level augmentation to mitigate the effects of non-IID data. By incorporating global class-wise feature statistics, each client can adjust its classifier using synthetic features derived from these shared representations. Second, we propose a calibrated classifier-guided global adversarial alignment strategy, which enforces consistency between augmented and adversarial predictions to improve robustness. Simulation results demonstrate the effectiveness of the proposed RoFLCCA, which consistently outperforms existing robust federated baselines across different datasets and settings. On average, it achieves a 7.07% improvement in clean accuracy and a 4.71% gain in adversarial robustness, highlighting its ability to enhance both generalization and defense against adversarial threats.

The rapid expansion of mobile communication networks has led to a surge in cellular traffic, highlighting the need for advanced prediction models to improve network performance. Federated learning (FL) offers a promising solution by enabling distributed model training across multiple nodes, aligning well with the decentralized nature of modern networks. However, applying FL to spatiotemporal cellular traffic prediction is challenging due to the substantial communication overhead in distributed learning. To address this, we propose LFedSG, a lightweight FL framework incorporating subgraph partitioning for spatiotemporal traffic prediction. LFedSG supports collaborative training while preserving inter-client dependencies critical for accurate prediction. Communication efficiency is achieved by focusing on essential model parameters, while subgraph partitioning and spatiotemporal graph convolutional networks (STGCN) enhance spatial and temporal correlation modeling. An adaptive transmission weight pruning strategy further reduces communication and computation costs. Extensive experiments on the Telecom Italia and Pems07 datasets demonstrate that LFedSG achieves higher predictive accuracy than traditional methods, with significant reductions in communication overhead and training time, validating its effectiveness and scalability for large-scale mobile network environments.

Accurate semantic segmentation of both tactile paving and the obstacle is crucial for the safe mobility of visually impaired individuals. However, existing methods face two major challenges: (i) discontinuous segmentation fragments; (ii) Inaccurate obstacle recognition. To address challenge (i), we propose incorporating appearance priors of complete tactile pavings to prevent the model from directly learning irregular ground truth masks. To tackle challenge (ii), we propose introducing cross-modal semantic priors to complement the semantic information of obstacles. We implemented these strategies in proposed Dual Prior knowledge induced tactile paving and obstacle joint Segmentation Network (DPSN). Based on bilateral network architecture, DPSN merges obstacle category masks into tactile paving categories, constructing a complete tactile paving mask. Utilizing the complete mask, DPSN transfer appearance prior knowledge to detail features from boundary and structural perspectives. Concurrently, DPSN leverages the CLIP Text Encoder to guide visual feature decoding by attention mechanisms, transferring rich cross-modal semantic prior knowledge to the visual feature maps. Furthermore, we propose the TPO-Dataset, the first dataset for joint tactile paving and obstacle segmentation acquired from actual scenes. Experiments demonstrate that DPSN achieves state-of-the-art results on the TPO-Dataset, with relative gains of 27.16% in obstacle IoU and 30.53% in accuracy metrics compared to baseline methods. Notably, DPSN achieves real-time performance at 88.25 FPS on the maximum scale of 2048×512 resolution.

SUMMARY: Current pharmacophore-based virtual screening (VS) software has limited interactive capabilities and less intuitive screening processes. In this study, a novel tool named VRPharmer is proposed to perform the entire VS workflow in VR environments. VRPharmer enables users to interactively perceive computation processes and immersively observe molecular structures. Besides a typical screening mode (OPT mode), VRPharmer provides a unique interactive screening mode (SCORE mode) for freely exploring the optimal binding poses. Pharmacophore models are editable to study the impact of each feature and further refine the screening results. Moreover, molecular rendering algorithms are improved for precise representations. AVAILABILITY AND IMPLEMENTATION: VRPharmer is open-source software under the MIT license. The released version is available at https://github.com/VRPharmer/VRPharmer. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Attributable to the emergence of mobile edge computing (MEC), the hardware-constrained industrial devices have further computational and service capability in industrial Internet of Things (IIoT) systems. Nevertheless, unreliable network environments and unpredictable processing delays are intolerable factors for any service application. Therefore, this article studies the associated constraint problem of how to optimize the offloading decision and resource allocation in collaborative edge computing networks with multiple IIoT devices and MEC servers. In order to attain this purpose, the optimization problem is mathematically derived as a mixed-integer nonlinear programming problem which is a large-scale NP-hard problem. Then, an improved differential evolution algorithm (IDE) is proposed to obtain the optimal solutions in an accessible time complexity. Finally, the performance of the IDE-based resource allocation scheme has been compared with other baseline schemes. Simulation results demonstrate that the IDE-based optimization scheme could significantly reduce the system delay and energy consumption.

The traditional covert communication that relies on a central node is vulnerable to detection and attack. Applying blockchain to covert communication can improve the channel's anti-interference and antitampering. Whisper is the communication protocol of Ethereum, which mainly relies on payload to store information and padding to expand. These two fields can store a large amount of information, creating conditions for the realization of covert communication. In this paper, we propose a covert communication method based on the whisper protocol to covertly transfer information in the blockchain. To implement this method, we use payload to store the carrier information, matching it with the secret message. The generated index is recorded in the padding field. To improve the concealment of communication, we simulate the default filling rules of the protocol to maintain the message size. A new topic–key pair interaction method is also proposed to improve the security of the model. Moreover, the anti-interference, antitampering and antidetection of the newly proposed model are verified through theoretical analysis and experiment. The experimental findings show that the amount of information in the proposed method is 4.7 times that of the traditional time-based covert communication. The time consumption of information transmission is reduced to 52.25% under the same settings and even less in actual use. The cost of the new topic–key pair interaction is reduced by nearly 50% compared with the original method.

In cognitive radio sensor networks (CRSNs), the sensor devices which are enabled to perform dynamic spectrum access have to frequently sense the licensed channel to find idle channels. The behavior of spectrum sensing will consume a lot of battery power of sensor devices and reduce the network lifetime. In this paper, we aim to answer the question of how many spectrum sensing nodes (SSNs) are required. In order to achieve this, SSN ratio effects on the accuracy of spectrum sensing from the perspective of network energy efficiency are analyzed first. Based on these analyses, the optimal SSN ratio is derived for maximizing the network lifetime by optimizing the cooperative detection probability (CDP). Simulation results show that the optimal SSN ratio can guarantee the spectrum sensing performance in terms of detection and false alarm probabilities and effectively extend the network lifetime.