检索结果-内蒙古大学图书馆

Leaders and Collaborators: Addressing Sparse Reward Challenges in Multi-Agent Reinforcement Learning

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年第2期9卷 1976-1989页

作者： Sun, Shaoqi Liu, Hui Xu, Kele Ding, Bo Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha 410003 Peoples R China

Cooperative multi-agent reinforcement learning (MARL) has emerged as an effective tool for addressing complex control tasks. However, sparse team rewards present significant challenges for MARL, leading to low exploration efficiency, slow learning speed, and homogenized behaviors among agents. To address these issues, we propose a novel Leader-Collaborator (LC) MARL framework inspired by human social collaboration. The LC framework introduces parallel online knowledge distillation for policy networks (KDPN). KDPN extracts knowledge from two policy networks with different training objectives: one aims to maximize individual rewards, while the other aims to maximize team rewards. The extracted knowledge is utilized to construct team leaders and collaborators. By effectively balancing individual and team rewards, our approach enhances exploration efficiency and promotes behavioral diversity among agents. This addresses the issue of low learning efficiency caused by the lack of objectives early in the agent's learning process and facilitates the development of more effective and differentiated team interaction policies. Additionally, we present the Self-Repairing Strategy (SRS) and Self-Augmenting Strategy (SAS) to facilitate team policies learning while preserving the initial team goal. We evaluate the effectiveness of the LC framework by conducting extensive experiments on the Multi-Agent Particle Environment (MPE), the Google Research Football (GRF), and StarCraft Multi-Agent Challenge (SMAC) with varying levels of difficulty. Our experimental results demonstrate that LC significantly improves the efficiency of the agent's exploration, achieves state-of-the-art performance, and accelerates the learning of the optimal policy. Specifically, in the SMAC scenarios, our method increases the winning rate by 21.9%, increases the average cumulative reward by 12%, and reduces the training time by 57% to achieve optimal performance.

关键词： Computational modeling Training Reinforcement learning Sports Knowledge engineering Computational intelligence Teamwork Sun Standards Predictive models Multi-agent reinforcement learning sparse rewards online knowledge distillation exploration efficiency

来源：评论

学校读者我要写书评

暂无评论

An adaptive gradient correction method based on mesh skewness for finite volume fluid dynamics simulations

引用

PHYSICS OF FLUIDS 2025年第1期37卷

作者： Song, Min Li, Chao Guo, Xiaowei Liu, Jie Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Lab Digitizing Software Frontier Equipment Changsha 410073 Hunan Peoples R China

In unstructured mesh solvers based on the finite volume method, accurate gradient calculation is crucial for determining the accuracy of equations. However, most mainstream computational fluid dynamics (CFD) software offer only uncorrected or globally corrected gradient options, which do not take into account local geometric characteristics. This limitation hampers computational efficiency and accuracy, especially in complex geometries, leading to poor convergence or even divergence, thus constraining its practical application in real-world engineering problems. To address these issues, this paper presents an adaptive gradient correction algorithm based on mesh skewness. By analyzing the geometric characteristics of mesh cells and dynamically applying a correction value, the algorithm modifies the gradient calculation formula adaptively to reduce numerical errors and improve accuracy, while ensuring stability. The algorithm has been successfully implemented in a general-purpose CFD software and validated through complex engineering cases such as sub-channel analysis, demonstrating its practical engineering value. Results indicate that for turbulent flow through a pipe, the proposed adaptive correction algorithm achieves an improved accuracy, demonstrating high precision and superiority in capturing intricate details of turbulence. In more complex scenarios like sub-channel analysis, the adaptive correction algorithm yields an error of 2.54% compared to 4.03% for the uncorrected approach. Unlike global correction methods that may lead to computational divergence within a few iterations, the adaptive correction method consistently maintains stability, accelerates convergence, and improves accuracy, offering significant theoretical and practical value.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Large Pretrained Foundation Model for Key Performance Indicator Multivariate Time Series Anomaly Detection

IEEE OPEN JOURNAL OF THE COMPUTER SOCIETY

引用

IEEE OPEN JOURNAL OF THE COMPUTER SOCIETY 2025年第1期6卷 176-187页

作者： Wang, Xu Xu, Qisheng Xu, Kele Yu, Ting Ding, Bo Feng, Dawei Dou, Yong Natl Univ Def Technol Coll Comp Sci & Technol Changsha 410073 Peoples R China Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha 410073 Peoples R China

In the realm of Key Performance Indicator (KPI) anomaly detection, deep learning has emerged as a pivotal technology. Yet, the development of effective deep learning models is hindered by several challenges: scarce and complex labeled data, noise interference from data handling, the necessity to capture temporal dependencies in time series KPI data, and the complexity of multivariate data analysis. Despite recent progress in large models that show potential for handling complex, multidimensional tasks, the lack of extensive, high-quality datasets presents a significant barrier for directly training these models in KPI anomaly detection. This scarcity limits the models' ability to learn and generalize effectively within this specific domain. To overcome this, we propose an innovative approach to adapt fully pretrained large models from other domains to KPI anomaly detection, thereby mitigating data constraints and enhancing detection precision. Our approach involves adapting large models to anomaly detection tasks using patch operations and fine-tuning techniques, which significantly enhances the model's temporal dependency capture capabilities. Furthermore, to address the multivariate challenge, we introduce a novel feature extraction method based on channel independence to optimize information processing across multidimensional features. Additionally, we leverage frequency domain information to design a feature enhancement method, further boosting the model's detection accuracy. By integrating these innovative techniques, we have developed a large-scale KPI anomaly detection model named ViTSD. Empirical evidence from experiments on five benchmark datasets and two additional datasets demonstrates ViTSD's superior performance, outperforming existing models across various evaluation metrics.

关键词： Feature extraction Anomaly detection Time series analysis Key performance indicator Adaptation models Data models Analytical models Time-frequency analysis Transformers Computational modeling large foundation model patch operation Key Performance Indicator (KPI) anomaly detection

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Linear Extended State Observer-Based Sensorless IPMSM Drives With Robustness Against Current Measurement Offset Error

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2025年第1期11卷 3558-3567页

作者： Xia, Zhen Yu, Xu Wu, Xuan Dou, Yong Natl Univ Def Technol Sch Comp Natl Lab Parallel & Distributed Proc Changsha 410003 Hunan Peoples R China Hunan Univ Coll Elect & Informat Engn Changsha 410006 Hunan Peoples R China

Back-electromotive force (EMF) estimation has attracted a lot of attention in sensorless interior permanent magnet synchronous motor (IPMSM) control. However, the conventional linear extended state observer (LESO) method will obtain back EMF estimations with phase lag and is vulnerable to dc errors caused by current measurement offset error due to its low-pass characteristic. To deal with the phase lagging and dc errors problem, an enhanced LESO (ELESO) with the super-twisting sliding mode observer (STASMO)-based current measurement offset error compensation is proposed in this article. The sinusoidal tracking unit is added to the disturbance loop in LESO to obtain the rapid-varying back EMF estimation accurately. Besides, the current measurement offset errors can be compensated by the STASMO-based method after analyzing the dynamic equation of offset error. Therefore, the proposed sensorless method is able to observe back EMF accurately and compensate an offset error for position estimation improvement. Finally, the comparative experiments based on 1.5-kW IPMSM are given to certify the advantages of the proposed sensorless method, which shows the effectiveness and superior control performance of the proposed sensorless method in back EMF estimation and current measurement offset error compensation under different conditions.

关键词： Interior permanent magnet synchronous motor (IPMSM) linear extended state observer (LESO) offset error sensorless Interior permanent magnet synchronous motor (IPMSM) linear extended state observer (LESO) offset error sensorless

来源：评论

学校读者我要写书评

暂无评论

HyperPart: A Hypergraph-Based Abstraction for Deduplicated Storage Systems

引用

IEEE TRANSACTIONS ON CLOUD COMPUTING 2025年第1期13卷 46-60页

作者： Cheng, Geyao Xia, Junxu Luo, Lailong Mi, Haibo Guo, Deke Ma, Richard T. B. Natl Univ Def Technol Coll Informat & Commun State Key Lab Complex & Crit Software Environm Wuhan 430019 Peoples R China Natl Univ Def Technol Natl Key Lab Informat Syst Engn Changsha 410073 Peoples R China Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Changsha 410073 Peoples R China Natl Univ Singapore Sch Comp Singapore 119077 Singapore

Currently, deduplication techniques are utilized to minimize the space overhead by deleting redundant data blocks across large-scale servers in data centers. However, such a process exacerbates the fragmentation of data blocks, causing more cross-server file retrievals with plummeting retrieval throughput. Some attempts prefer better file retrieval performance by confining all blocks of a file to one single server, resulting in non-trivial space consumption for more replicated blocks across servers. An ideal network storage system, in effect, should take both the deduplication and retrieval performance into account by implementing reasonable assignment of the detected unique blocks. Such a fine-grained assignment requires an accurate and comprehensive abstraction of the files, blocks, and the file-block affiliation relationships. To achieve this, we innovatively design the weighted hypergraph to profile the multivariate data correlations. With this delicate abstraction in place, we propose HyperPart, which elegantly transforms this complex block allocation problem into a hypergraph partition problem. For more general scenarios with dynamic file updates, we further propose a two-phase incremental hypergraph repartition scheme, which mitigates the performance degradation with minimal migration volume. We implement a prototype system of HyperPart, and the experiment results validate that it saves around 50% of the storage space and improves the retrieval throughput by approximately 30% of state-of-the-art methods under the balance constraints.

关键词： Servers Fingerprint recognition Throughput Metadata Resource management Switches Data centers Indexing Ethernet Correlation Network storage systems data deduplication hypergraph partition

来源：评论

学校读者我要写书评

暂无评论

FE-PIRBN: Feature-enhanced physics-informed radial basis neural networks for solving high-frequency electromagnetic scattering problems

引用

JOURNAL OF COMPUTATIONAL PHYSICS 2025年 527卷

作者： Zhang, Huajian Li, Chao Xia, Rui Chen, Xinhai Xiao, Tiaojie Guo, Xiao-Wei Liu, Jie Natl Univ Def Technol Coll Comp Sci & Technol Changsha 410000 Hunan Peoples R China Natl Univ Def Technol Lab Digitizing Software Frontier Equipment Changsha 410000 Hunan Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410000 Hunan Peoples R China

The solution of electromagnetic scattering problems holds significant application prospects in fields such as target detection and electromagnetic metamaterial design. However, efficient prediction of electromagnetic fields under high-frequency and intricate geometric conditions remains one of the most challenging problems. In this study, we proposed a feature-enhanced physics-informed radial basis neural network (FE-PIRBN) for solving high-frequency electromagnetic scattering problems. As a physics-driven neural network model, FE-PIRBN incorporates a PIRBN core network to preserve the local approximating property during the electromagnetic wave propagation process. It combines multi-resolution hash encoding techniques to optimize the capture of high-frequency electromagnetic field features. Under data-free training, the FE-PIRBN enables the accurate prediction of high-frequency electromagnetic scattering at sub-wavelength scales. Based on the testing results of typical cases including the electromagnetic scattering from single and double cylinder, it is evident that FE-PIRBN achieves computational accuracy within a 1.40%-5.82% relative error compared to numerical simulation results and the reference solutions. In increasing frequency scenarios, FE-PIRBN shows excellent generalization capabilities, achieving significant accuracy improvements and more robust convergence in high- frequency electromagnetic scattering tasks, ensuring future reliability and accuracy in wider band applications. Of particular importance is that as the electromagnetic frequency increases, the computational time for numerical methods grows exponentially. In contrast, FE-PIRBN, as a neural network model, maintains a relatively stable parameter size, resulting in significantly faster computation. This presents a promising and potential solution for addressing large-scale electromagnetic problems in the field.

关键词： High-frequency electromagnetic scattering Physics-informed neural network Hash encoding Radial basis neural network

来源：评论

学校读者我要写书评

暂无评论

Cross-scale hierarchical spatio-temporal transformer for video enhancement

引用

KNOWLEDGE-BASED SYSTEMS 2025年 309卷

作者： Jiang, Qin Wang, Qinglin Chi, Lihua Liu, Jie Natl Univ Def Technol Changsha Peoples R China Lab Digitizing Software Frontier Equipment Changsha Peoples R China Sci & Technol Parallel & Distributed Proc Lab Changsha Peoples R China Hunan GuoKe Computil Technol Co Ltd Changsha Peoples R China

The diversity and complexity of degradations in low-quality videos pose non-trivial challenges on video enhancement to reconstruct the high-quality counterparts. Prevailing sliding window based methods represent poor performance due to the limitation of window size. Recurrent networks take advantage of long-term modeling to aggregate more information, resulting insignificant performance improvements. However, most of them are trained on simple degraded data and can only tackle specific degradation. To break through the limitation, we propose a progressive alignment network, namely Cross-scale Hierarchical Spatio-Temporal Transformer (CHSTT), which leverages cross-scale tokenization to generate multi-scale visual tokens in the entire sequence to capture extensive long-range temporal dependencies. To enhance the spatial and temporal interactions, we introduce an innovative hierarchical Transformer, facilitating the computation of mutual multi-head attention across both spatial and temporal dimensions. Quantitative and qualitative assessments substantiate the superior performance of CHSTT compared to several state-of-the-art benchmarks across three distinct video enhancement tasks, including video super-resolution, video denoising, and video deblurring.

关键词： Video super-resolution Denoising Deblurring Transformer Temporal

来源：评论

学校读者我要写书评

暂无评论

Slicing execution for model checking C programs

引用

INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING 2006年第5期16卷 747-768页

作者： Yi, Xiaodong Wang, Ji Yang, Xuejun Natl Lab Parallel & Distributed Proc Changsha Peoples R China

This paper presents a novel method, namely slicing execution, for model checking C programs with respect to temporal safety properties. The distinguished feature is that it shows a nice approach to the efficient reduction of state space by abstraction and symbolic representation. Slicing execution is founded on an over-approximated semantics of C programs by variable abstraction, and executes symbolically only the relevant statements under abstraction criteria to construct over-approximated finite models of programs, which may be model checked. The variable abstraction criterion begins with a proper initial set of program variables and may be iteratively refined according to spurious counterexamples generated during model checking. In general, the properties to be verified often involve only a few variables in practical programs. In these cases, significant state space reduction, as well as considerable improvement of the scalability, may be achieved. The presented method has been used to verify the initial handshake process of SSL protocol based on the C source code of openssl-0.9.6c. The experiment results confirm that slicing execution is not only practical but also effective.

关键词： slicing execution variable abstraction paxtial strongest post-condition

来源：评论

学校读者我要写书评

暂无评论

Slicing Execution with Partial Weakest Precondition for Model Abstraction of C Programs

引用

COMPUTER JOURNAL 2010年第1期53卷 37-49页

作者： Yang, Xuejun Wang, Ji Yi, Xiaodong Natl Lab Parallel & Distributed Proc Changsha Hunan Peoples R China

Model abstraction plays an important role in model checking of source codes of programs. Slicing execution is a lightweight symbolic execution procedure to extract the models of C programs in an over-approximated way. In this paper, we present an approach to improving slicing execution with a novel concept called partial weakest precondition (PWP) to alleviate the space explosion problem. PWPs specify the corresponding weakest precondition conservatively by only considering part of program variables. We present how to integrate PWP with slicing execution, which leads to a compact model with much smaller state space compared with the one obtained by the original slicing execution. A new PWP implementation is also presented to avoid possible exponential PWP formula size and support pointers and aliases as well. The distinguished features of the implementation are that it does not need to translate the program to the passive form beforehand, and it supports loops very well. Comparing with slicing execution without PWP, the experimentation on SSL protocol based on the C source code openssl-0.9.6c shows that the state space may be reduced to only 1/10 after applying PWP.

关键词： partial weakest precondition model abstraction slicing execution

来源：评论

学校读者我要写书评

暂无评论

VoiceStyle: Voice-Based Face Generation via Cross-Modal Prototype Contrastive Learning

引用

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2024年第9期20卷 1-23页

作者： Chen, Wuyang Zhu, Boqing Xu, Kele Dou, Yong Feng, Dawei Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

Can we predict a person's appearance solely based on their voice? This article explores this question by focusing on generating a face from an unheard voice segment. Our proposed method, VoiceStyle, combines cross-modal representation learning with generation modeling, enabling us to incorporate voice semantic cues into the generated face. In the first stage, we introduce cross-modal prototype contrastive (CMPC) learning to establish the association between voice and face. Recognizing the presence of false negative and deviate positive instances in real-world unlabeled data, we not only use voice-face pairs in the same video but also construct additional semantic positive pairs through unsupervised clustering, enhancing the learning process. Moreover, we recalibrate instances based on their similarity to cluster centers in the other modality. In the second stage, we harness the powerful generative capabilities of StyleGAN to produce faces. We optimize the latent code in StyleGAN's latent space, guided by the learned voice-face alignment. To address the importance of selecting an appropriate starting point for optimization, we aim to automatically find an optimal starting point by utilizing the face prototype derived from the voice input. The entire pipeline can be implemented in a self-supervised manner, eliminating the need for manually labeled annotations. Through extensive experiments, we demonstrate the effectiveness and performance of our VoiceStyle method in both cross-modal representation learning and voice-based face generation.

关键词： Cross-modal representation learning contrastive learning StyleGAN face generation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：