IoT intrusion detection faces critical challenges from device heterogeneity, non-iid data distributions, and malicious updates. To address these, we propose FedAligns, a robust and efficient federated learning intrusion detection framework. First, we design a Temporal Attention Autoencoder that integrates TCN, GRU, and self-attention to capture local patterns and global dependencies in complex IoT traffic, enhancing feature representation. Second, we introduce a dual-aggregation algorithm, AlignMSE, to tackle non-iid heterogeneity and malicious threats. Its first phase filters anomalous updates via temporal direction alignment and sign consistency to ensure robust aggregation. Its second phase dynamically allocates weights based on local Mean Squared Error, prioritizing high-performing clients to better adapt to non-iid data. Experiments on N-BaIoT and ToN IoT datasets show FedAligns significantly outperforms traditional methods in accuracy and robustness, demonstrating superior resilience against malicious updates in non-iid scenarios.

With increasing deployment of distributed energy resources, the energy market which aims for local generation and load profile redistribution is facing the challenge to accommodate various types of participants. To realize social welfare maximization with privacy preserving in a dynamic energy market, this article propose a multiagent reinforcement learning (MARL) method for quotation decision optimization in continuous double auction (CDA)-based peer-to-peer (P2P) energy market. To address the nonstationarity and privacy violation brought by multiagent context, we utilize mean-field approximation to abstract the unauthorized local information of other agents from the public market dynamics. An abstract Q-value function is developed for each agent to infer the neighbor agents' local observation and action through the public clearing results in the dynamic CDA market. Moreover, to avoid sparse reward so as to stabilize the learning process, we propose a dynamic potential-based reward shaping term in the reward. Without altering the learnt optimal policies, the agents can be informed with the additional energy storage state as the reward shaping in each time instants. To validate the effectiveness and economy of our proposed method, simulation studies are conducted on a real-world dataset. Simulation results show that the proposed MARL method produces up to 17% more convergent episodic reward and 67% less energy bills which indicates competitive convergence performance and significant economic benefits.

Compared with conventional wireless sensor networks (WSNs), industrial WSNs (IWSNs) have stricter requirements in real-time data transmission, energy consumption, and energy uniformity. To fulfill these requirements, a new energy-efficient clustering approach using quantum-related bioinspired optimization, i.e., quantum elite gray wolf optimization (QEGWO), is proposed to improve the performance of IWSNs. Innovatively, a new quantum operator, including quantum probability amplitude, quantum rotation gate, and quantum NOT gate, is designed in QEGWO to enhance its global search capability. This quantum operator need not query the quantum rotation angle table in updating quantum probability amplitude with the quantum rotation gate, which reduces the computational complexity of introducing quantum optimization into the clustering problem of IWSNs. Moreover, to enhance the convergence performance of the clustering algorithm, a multielite strategy is proposed to preserve the historical optimal individuals generated in the iterative process by establishing a dynamic elite pool. Compared with the state-of-the-art clustering approaches, extensive simulations in four different scenarios are carried out, and the results demonstrate that the proposed QEGWO outperforms other comparison approaches in delay, energy consumption, and energy uniformity.

Real-world systems from a variety of domains, ranging from physics to medicine, can naturally be modelled as dynamic networks. Dynamic community detection is regarded as a fundamental tool to probe into the mechanisms of networks. Here, we describe a framework for tracking the network evolution over time, where each community is characterized by a series of transition events, which is one of the most influential evolutionary patterns in dynamic networks. The framework is used to motivate a temporal smoothness strategy for efficiently identifying dynamic communities and exploring the transition behavior of networks from community-level and node-level. Evaluations on two synthetic and real-world datasets containing embedded transition events demonstrate that the framework can successfully discover dynamic communities and analyze the transition behavior of networks.

6D pose estimation from a single RGB image is a challenging and vital task in computer vision. The current mainstream deep model methods resort to 2D images annotated with real-world ground-truth 6D object poses, whose collection is fairly cumbersome and expensive, even unavailable in many cases. In this work, to get rid of the burden of 6D annotations, we formulate the 6D pose refinement as a Markov Decision Process and impose on the reinforcement learning approach with only 2D image annotations as weakly-supervised 6D pose information, via a delicate reward definition and a composite reinforced optimization method for efficient and effective policy training. Experiments on LINEMOD and T-LESS datasets demonstrate that our Pose-Free approach is able to achieve state-of-the-art performance compared with the methods without using real-world ground-truth 6D pose labels.

Accurately estimating the 6-DoF object pose from a single RGB image is a challenging task in computer vision. Though pose regression approaches have achieved great progress, the performance is still limited. In this work, we propose Pose-guided Auto-Encoder (PAE), which can distill better pose-related features from the image by utilizing a suitable pose representation, 3D Location Field (3DLF), to guide the encoding process. The features from PAE show strong robustness to pose-irrelevant factors. Compared with traditional auto-encoder, PAE can not only improve the pose estimation performance but also handle the ambiguity viewpoints problem. Further, we propose Feature-based Pose Refiner (FPR), which refines the pose from the extracted features without rendering. Combining PAE with FPR, our approach achieved state-of-the-art performance on the widely used LINEMOD dataset. Our approach not only outperforms the direct regression-based approaches with a large margin but also thrillingly surpasses current state-of-the-art indirect PnP-based approach.

Automatic and accurate segmentation of anatomical structures in chest radiographs is fundamental and essential for computer-aided diagnosis system. We introduce Mask R-CNN for instance segmentation of lung fields, heart and clavicles. This method efficiently detects different structures and generates accurate segmentation mask for each instance. To the best of our knowledge, we are the first to implement instance segmentation of these three anatomical structures in chest radiographs. We have done extensive experiments on a common benchmark dataset. Results show that the best of our models achieves the state-of-the-art segmentation performance on image resolution of 512 × 512. The Dice and Ω similarity are 0.976 and 0.953 for lung fields, 0.949 and 0.904 for heart, 0.920 and 0.852 for clavicles. And the average contour distance outperforms human observer on both lungs and heart with image resolution of 256 × 256. In addition, it takes only 0.16 and 0.12 seconds per image for the above two resolutions during inference, which is comparable to or even better than current methods.

6-DoF object pose estimation from a single RGB image is a fundamental and long-standing problem in computer vision. Current leading approaches solve it by training deep networks to either regress both rotation and translation from image directly or to construct 2D-3D correspondences and further solve them via PnP indirectly. We argue that rotation and translation should be treated differently for their significant difference. In this work, we propose a novel 6-DoF pose estimation approach: Coordinates-based Disentangled Pose Network (CDPN), which disentangles the pose to predict rotation and translation separately to achieve highly accurate and robust pose estimation. Our method is flexible, efficient, highly accurate and can deal with texture-less and occluded objects. Extensive experiments on LINEMOD and Occlusion datasets are conducted and demonstrate the superiority of our approach. Concretely, our approach significantly exceeds the state-of-the- art RGB-based methods on commonly used metrics.