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.

As one of the promising self-powered sensors on Internet of Things (IoT) platforms, unmanned aerial vehicles (UAVs) have attracted much attention for parcel delivery. Their high flexibility and low cost facilitate last-one-mile delivery. However, the limitations of battery capacity and payloads prevent drones from delivering independently over large scales. In this case, it is available to employ vehicles to assist the drones. The vehicles can be private-own trucks and vehicles in public transportation systems (PTSs). Compared to trucks, PTSs, such as buses and trains, do not require extra operating and fuel costs. Given these advantages, this article adopts PTSs to assist UAVs in parcel delivery. Nevertheless, the fixed routes and schedules of public vehicles pose new challenges to the routing and scheduling problem for PTS-assisted multidrone parcel delivery (RSPMD). To tackle the problem, we propose a novel routing and scheduling algorithm, referred to as the PTS-assisted multidrone parcel delivery (PDD) algorithm. Considering the schedules of the public vehicles, the algorithm jointly optimizes the distance and time cost of drones by iteratively combining parts of existing routes. To the best of our knowledge, we are the first to address RSPMD in which UAVs ride public vehicles to deliver parcels in a wide area. Simulation results are finally presented to demonstrate that PDD outperforms existing solutions in terms of effectiveness and efficiency.

Edge computing technologies with container-based microservice architectures promise to provide stable and low-latency services for large-scale and complex edge applications. However, due to the limited CPU and storage resources in edge computing scenarios, the coarse-grained service deployment on edge nodes causes performance bottlenecks. In addition, the effective deployment of microservices is tightly correlated with request routing, but the current research ignores the joint optimization of multi-instance deployment and routing. In this paper, we first model the problem of jointly optimizing service deployment and routing in a dynamically changing environment with multi-edge network collaboration based on a queuing network analysis. Secondly, we design heuristic algorithms to scale microservice instances horizontally in dynamic user request states. In addition, we propose a reinforcement learning algorithm based on reward shaping (RSPPO) to minimize user waiting delay and edge network resource consumption. We also solve the microservice deployment and request routing problem for multi-edge collaboration to achieve load balancing among edge nodes. Finally, extensive experiments verify the significant and extensive effectiveness of our algorithm.

We present MVPose, a novel system designed to enable real-time multi-person pose estimation (PE) on commodity mobile devices, which consists of three novel techniques. First, MVPose takes a motion-vector-based approach to fast and accurately track the human keypoints across consecutive frames, rather than running expensive human-detection model and pose-estimation model for every frame. Second, MVPose designs a mobile-friendly PE model that uses lightweight feature extractors and multi-stage network to significantly reduce the latency of pose estimation without compromising the model accuracy. Third, MVPose leverages the heterogeneous computing resources of both CPU and GPU to execute the pose estimation model for multiple persons in parallel, which further reduces the total latency. We present extensive experiments to evaluate the effectiveness of the proposed tecniques by implemented the MVPose on five off-the-shelf commercial smartphones. Evaluation results show that MVPose achieves over30frames per second PE with4persons per frame, which significantly outperforms the state-of-the-art baseline, with a speedup of up to5.7×and3.8×in latency on CPU and GPU, respectively. Compared with baseline, MVPose achieves an improvement of10.1%in multi-person PE accuracy. Furthermore, MVPose achieves up to74.3%and57.6%energy-per-frame saving on average in comparison with the baseline on mobile CPU and GPU, respectively.

Most existing image enhancement methods require paired images, and rarely consider the aesthetic quality. This paper proposes a bi-directional normalization and color attention-guided generative adversarial network (BNCAGAN) for unsupervised image enhancement. An auxiliary attention classifier (AAC) and a bi-directional normalization residual (BNR) module are designed to assist the generator in flexibly controlling the local details with the constraint from both the low/high-quality domain. Moreover, a color attention module (CAM) is proposed to preserve the color fidelity in the discriminator. The qualitative and quantitative experimental results demonstrate that our BNCAGAN is superior to the existing methods with distinctively improved authenticity and naturalness of the enhanced images. The source code is available at https://github.com/SWU-CS-MediaLab/BNCAGAN.

Federated learning (FL) is a novel machine learning that performs distributed training locally on devices and aggregating the local models into a global one. The limited network bandwidth and the tremendous amount of model data that need to be transported bring up expensive communication cost. Meanwhile, heterogeneity in the devices’ local datasets and computation power exerts a huge influence on the performance of FL. To address these issues, we provide an empirical and mathematical analysis of device heterogeneity on the performance of model convergence and quality, then propose a holistic design to efficiently sample devices. Furthermore, we design a dynamic strategy to further speed up convergence and propose the FedAgg algorithm to alleviate the deviation caused by device heterogeneity. With extensive experiments performed in PyTorch, we show that the number of communication rounds required in FL can be reduced by up to 52% on the MNIST dataset, 32% on CIFAR-10, and 28% on FashionMNIST in comparison to the Federated Averaging algorithm.

Human pose estimation is a key technique for many vision-based mobile applications. Yet existing multi-person pose-estimation methods fail to achieve a satisfactory user experience on commodity mobile devices such as smartphones, due to their long model-inference latency. In this paper, we propose MobiPose, a system designed to enable real-time multi-person pose estimation on mobile devices through three novel techniques. First, MobiPose takes a motion-vector-based approach to fast locate the human proposals across consecutive frames by fine-grained tracking of joints of human body, rather than running the expensive human-detection model for every frame. Second, MobiPose designs a mobile-friendly model that uses lightweight multi-stage feature extractions to significantly reduce the latency of pose estimation without compromising the model accuracy. Third, MobiPose leverages the heterogeneous computing resources of both CPU and GPU to execute the pose estimation model for multiple persons in parallel, which further reduces the total latency. We have implemented the MobiPose system on off-the-shelf commercial smartphones and conducted comprehensive experiments to evaluate the effectiveness of the proposed techniques. Evaluation results show that MobiPose achieves over 20 frames per second pose estimation with 3 persons per frame, and significantly outperforms the state-of-the-art baseline, with a speedup of up to 4.5X and 2.8X in latency on CPU and GPU, respectively, and an improvement of 5.1% in pose-estimation model accuracy. Furthermore, MobiPose achieves up to 62.5% and 37.9% energy-per-frame saving on average in comparison with the baseline on mobile CPU and GPU, respectively.

As microwave spectrum becomes increasingly scarce, millimeter wave communication has gained wide attention for its sufficient bandwidth, which is also considered as one of the key technologies in the Fifth Generation (5G) communication networks. Different from microwave, millimeter communication is easy to suffer from the blockages. In order to take advantage of the wide spectrum and avoid the big loss caused by blockage in millimeter D2D communication, we propose a hybrid communication model which employs mmWave communication when there is no blockage, and switch to microwave otherwise, and design the protocol among base stations and D2D equipment to implement such a hybrid scheme. Coverage probability and area spectrum efficiency are analyzed in closed-form for the proposed hybrid mode, conventional microwave mode and millimeter mode using stochastic geometry. The numerical results show that the hybrid communication model achieves better performance comparing to the microwave alone and millimeter wave alone.