Traffic signal control systems (TSCSs) are integral to intelligent traffic management, fostering efficient vehicle flow. Traditional approaches often simplify road networks into standard graphs, which results in a failure to consider the dynamic nature of traffic data at neighboring intersections, thereby neglecting higher-order interconnections necessary for real-time control. To address this, we propose a novel TSCS framework to realize intelligent traffic control. This framework collaborates with multiple neighboring edge computing servers to collect traffic information across the road network. To elevate the efficiency of traffic signal control, we have crafted a multi-agent soft actor-critic (MA-SAC) reinforcement learning algorithm. Within this algorithm, individual agents are deployed at each intersection with a mandate to optimize traffic flow across the road network collectively. Furthermore, we introduce hypergraph learning into the critic network of MA-SAC to enable the spatio-temporal interactions from multiple intersections in the road network. This method fuses hypergraph and spatio-temporal graph structures to encode traffic data and capture the complex spatio-temporal correlations between multiple intersections. Our empirical evaluation, tested on varied datasets, demonstrates the superiority of our framework in minimizing average vehicle travel times and sustaining high-throughput performance. This work facilitates the development of more intelligent urban traffic management solutions.
As a key enabler of Industry 4.0, the Industrial Internet of Things (IIoT) has been rapidly advancing, driving the increasingly widespread adoption of artificial intelligence (AI) in industrial production. However, the high computational demands of AI tasks contrast sharply with the limited computing resources available in industrial environments, highlighting the need for efficient task offloading strategies. This article addresses AI task offloading under resource-constrained IIoT scenarios by proposing LSTM-enhanced hierarchical-classification offloading with DQN (LHC-DQN). The proposed framework adopts a two-layer offloading architecture: the first layer performs global scheduling by assigning tasks to cloud, edge, or device resources, while the second layer refines the allocation. Cloud and edge nodes apply mathematical optimization, whereas device nodes leverage DRL agents for autonomous decision-making. To handle AI task heterogeneity, a classification-aware mechanism is introduced in the first layer, deploying separate DQN agents for inference and training tasks to improve adaptability and efficiency. Furthermore, an LSTM module is integrated into the DQN backbone to capture temporal dependencies in task states. Experimental results in a simulated environment demonstrate that LHC-DQN significantly outperforms traditional methods, increasing task completion rates approximately from 47% to 68%. Ablation and generalization tests further confirm the robustness and effectiveness of the proposed method. Overall, LHC-DQN offers a practical and efficient solution for intelligent task offloading and resource scheduling in IIoT environments.
10 May 2024 in ACM Transactions on Asian and Low-Resource Language Information Processing
Named Entity Recognition (NER) in low-resource settings aims to identify and categorize entities in a sentence with limited labeled data. Although prompt-based methods have succeeded in low-resource perspectives, challenges persist in effectively harnessing information and optimizing computational efficiency. In this work, we present a novel prompt-based method to enhance low-resource NER without exhaustive template tuning. First, we construct knowledge-enriched prompts by integrating representative entities and background information to provide informative supervision tailored to each entity type. Then, we introduce an efficient reverse generative framework inspired by question answering (QA), which avoids redundant computations. Finally, we reduce costs by generating entities from their types while retaining model reasoning capacity. Experiment results demonstrate that our method outperforms other baselines on three datasets under few-shot settings.
Due to the strong uncertainty in the retrieval order of containers and the complex coupling relationship between container yard production equipment, it is challenging for yards to formulate an appropriate slot allocation strategy to control the proportion of rehandling containers. Meanwhile, the unpredictable performance of the slot allocation strategy results in the yard lacking the means to adjust the allocation strategy. To address these issues, an efficient container rehandling probability prediction model based on deep learning has been proposed to assist yards in formulating and adjusting slot allocation strategy. Moreover, we design a container slot allocation strategy driven by the predictive container rehandling probability for reducing the proportion of rehandling container at yards. Extensive experiments on the container storage dataset demonstrate that: 1) the prediction model based on deep learning enables to efficiently and precisely predict the container rehandling, 2) taking Seq2Seq network as the prediction layer of model outperforms other deep sequence models on MSE, MAE, and accuracy, and 3) the slot allocation strategy based on the predictive container rehandling probability can effectively reduce the probability of the rehandling container.
21 August 2025 in Robotics and Computer-Integrated Manufacturing