Existing mobile-edge computing (MEC) systems are facing the challenges of limited resources and highly dynamic network environments. How to allocate resources to maintain the efficiency and timeliness of data and tasks is still an open issue. To address this problem, we propose a novel framework for unmanned aerial vehicle-assisted MEC systems using federated multiagent reinforcement learning (RL). First, we formulate a joint optimization problem as a multiagent Markov decision process by jointly minimizing the average age of information and maximizing the number of recent tasks. Second, we design a novel scheduling algorithm for online collaborative resources by adopting multiple agents to learn and make decisions in accordance with the overall interests through federal learning. Finally, an experience replay mechanism for the internal experience pool is introduced to further improve learning efficiency. Experimental results show that our proposed algorithm is superior to the recent typical RL-based algorithms. It not only has higher efficiency in task processing and data freshness but also has more stable performance and adaptability across diverse experimental conditions.

Unmanned Aerial Vehicles (UAVs) face a significant challenge in balancing high accuracy and high efficiency when performing real-time object detection tasks, especially amidst intricate backgrounds, diverse target scales, and stringent onboard computational resource constraints. To tackle these difficulties, this study introduces YOLO-SRMX, a lightweight real-time object detection framework specifically designed for infrared imagery captured by UAVs. Firstly, the model utilizes ShuffleNetV2 as an efficient lightweight backbone and integrates the novel Multi-Scale Dilated Attention (MSDA) module. This strategy not only facilitates a substantial 46.4% reduction in parameter volume but also, through the flexible adaptation of receptive fields, boosts the model’s robustness and precision in multi-scale object recognition tasks. Secondly, within the neck network, multi-scale feature extraction is facilitated through the design of novel composite convolutions, ConvX and MConv, based on a “split–differentiate–concatenate” paradigm. Furthermore, the lightweight GhostConv is incorporated to reduce model complexity. By synthesizing these principles, a novel composite receptive field lightweight convolution, DRFAConvP, is proposed to further optimize multi-scale feature fusion efficiency and promote model lightweighting. Finally, the Wise-IoU loss function is adopted to replace the traditional bounding box loss. This is coupled with a dynamic non-monotonic focusing mechanism formulated using the concept of outlier degrees. This mechanism intelligently assigns elevated gradient weights to anchor boxes of moderate quality by assessing their relative outlier degree, while concurrently diminishing the gradient contributions from both high-quality and low-quality anchor boxes. Consequently, this approach enhances the model’s localization accuracy for small targets in complex scenes. Experimental evaluations on the HIT-UAV dataset corroborate that YOLO-SRMX achieves an ${\mathrm{mAP}}_{50}$ of 82.8%, representing a 7.81% improvement over the baseline YOLOv8s model; an F1 score of 80%, marking a 3.9% increase; and a substantial 65.3% reduction in computational cost (GFLOPs). YOLO-SRMX demonstrates an exceptional trade-off between detection accuracy and operational efficiency, thereby underscoring its considerable potential for efficient and precise object detection on resource-constrained UAV platforms.

Intelligent Connected Vehicles (ICVs) impose stringent requirements on real-time computational services. However, limited onboard resources and the high latency of remote cloud servers restrict traditional solutions. Unmanned Aerial Vehicle (UAV)-assisted Mobile Edge Computing (MEC), which deploys computing and storage resources at the network edge, offers a promising solution. In UAV-assisted vehicular networks, jointly optimizing content and service caching, computation offloading, and UAV trajectories to maximize system performance is a critical challenge. This requires balancing system energy consumption and resource allocation fairness while maximizing cache hit rate and minimizing task latency. To this end, we introduce system efficiency as a unified metric, aiming to maximize overall system performance through joint optimization. This metric comprehensively considers cache hit rate, task computation latency, system energy consumption, and resource allocation fairness. The problem involves discrete decisions (caching, offloading) and continuous variables (UAV trajectories), exhibiting high dynamism and non-convexity, making it challenging for traditional optimization methods. Concurrently, existing multi-agent deep reinforcement learning (MADRL) methods often encounter training instability and convergence issues in such dynamic and non-stationary environments. To address these challenges, this paper proposes a MADRL-based joint optimization approach. We precisely model the problem as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) and adopt the Multi-Agent Proximal Policy Optimization (MAPPO) algorithm, which follows the Centralized Training Decentralized Execution (CTDE) paradigm. Our method aims to maximize system efficiency by achieving a judicious balance among multiple performance metrics, such as cache hit rate, task delay, energy consumption, and fairness. Simulation results demonstrate that, compared to various representative baseline methods, the proposed MAPPO algorithm exhibits significant superiority in achieving higher cumulative rewards and an approximately 82% cache hit rate.

In the industrial IoT, it is vital to detect anomalies in multivariate time series, yet it faces numerous challenges, including highly imbalanced datasets, complex and high-dimensional data, and large disparities across variables. Despite the recent surge in proposals for deep learning-based methods, these approaches typically treat the multivariate data at each point in time as a unique token, weakening the personalized features and dependency relationships between variables. As a result, their performance tends to degrade under highly imbalanced conditions, and reconstruction-based models are prone to overfitting abnormal patterns, leading to excessive reconstruction of anomalous inputs. In this paper, we propose ITMMG, an inverted Transformer with a multivariate memory gate. ITMMG employs an inverted token embedding strategy and multivariate memory to capture deep dependencies among variables and the normal patterns of individual variables. The experimental results obtained demonstrate that the proposed method exhibits superior performance in terms of detection accuracy and robustness compared with existing baseline methods across a range of standard time series anomaly detection datasets. This significantly reduces the probability of misclassifying anomalous samples during reconstruction.

Multivariate time series anomaly detection holds critical application value in key domains such as industrial system monitoring, financial risk management, and medical surveillance. However, existing approaches face two major challenges: reconstruction-based or prediction-based models tend to adapt to anomalous patterns during training, thereby weakening the distinction between normal and abnormal samples; furthermore, the non-stationary nature of time series leads to distribution shifts between training and testing data, impairing model generalization. To address these issues, this paper proposes the TFCID model. The model innovatively leverages diffusion principles to effectively impute missing time series data while capturing significant frequency-domain features. In the temporal processing stream, an unconditional diffusion model combined with imputation masking is employed to achieve high-precision imputation of randomly missing values, effectively preventing anomalies from interfering with model training. In the frequency-domain processing stream, an amplitude-aware frequency-domain masked autoencoder is introduced to specifically capture periodic or trend-based pattern anomalies. The model mitigates distribution shift by constraining the discrepancy between temporal and frequency-domain representations via adversarial contrastive learning, and uses this discrepancy as a robust anomaly scoring metric. Experimental results on five public benchmark datasets show that TFCID significantly outperforms state-of-the-art methods in detection accuracy (F1-Score), validating its effectiveness in anomaly detection tasks.

Deep reinforcement learning has achieved remarkable progress in the field of computer games, but these advancements come with significant computational resource consumption. To improve computational efficiency and reduce reliance on high computational resources, we applied two ingenious methods: reparameterization and terminal batch processing operators. By employing a specially designed replay buffer and neural networks integrated with reparameterization, and directly simulating end-game operations on the GPU, these methods not only reduce the computational burden but also ensure rapid convergence during the training process. This enhanced training framework allows for more iterations in a shorter period, thereby improving computational efficiency in self-play and training processes. We applied this technique to the game of NoGo. Experimental results indicate that, compared to the traditional AlphaZero method, the proposed approach achieves a faster increase in Elo score within the same timeframe. The agent utilizing this method secured first place among 1070 agents on the BotZone platform of Peking University.