检索结果-内蒙古大学图书馆

Physical-aware uncertainty prompt learning for real-world blind image restoration

Applied Soft Computing 2025年 177卷

作者： Qiao, Yuanjian Shao, Mingwen Meng, Lingzhuang Zuo, Wangmeng Qingdao266580 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518107 China School of Computer Science Harbin Institute of Technology Harbin150001 China

Recent years have witnessed notable progress in universal image restoration, which tackles multiple image degradations using a single model. However, these methods struggle to handle complex real-world scenarios due to the lack of paired real data and limited adaptability to unknown corruptions. To address these challenges, we propose a novel Physical-aware Uncertainty Prompt (PUP) paradigm for real-world blind image restoration. Specifically, instead of simply employing pre-synthesized degraded images, we develop a Physical-aware Degradation Modeling scheme (PDM) that considers multiple distortion factors to generate more authentic degraded data online during training. To adaptively handle unknown corruptions, we propose an Uncertainty-Prompted Fourier Transformer (UPFomer) for unified image restoration, which comprises two collaborative designs: Spatial-Frequency Selective Interaction (SSI) and Uncertainty Prompt Alignment (UPA). The former aggregates global frequency information and local spatial context for robust feature representation, while the latter interacts learnable prompts with SSI features via uncertainty weights to compute degradation-aware knowledge. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods on real-world images while ensuring favorable model efficiency. © 2025

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Job Scheduling and Resource Management in Cloud Computing: An Algorithm-Level Review

arXiv

引用

arXiv 2025年

作者： Gu, Yan Liu, Zhaoze Dai, Shuhong Liu, Cong Wang, Ying Wang, Shen Theodoropoulos, Georgios Cheng, Long The School of Control and Computer Engineering North China Electric Power University Beijing China The School of Computer Science and Technology Shandong University of Technology China The Institute of Computing Technology Chinese Academy of Sciences Beijing China The School of Computer Science University College Dublin Ireland Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

Cloud computing has revolutionized the provisioning of computing resources, offering scalable, flexible, and on-demand services to meet the diverse requirements of modern applications. At the heart of efficient cloud operations are job scheduling and resource management, which are critical for optimizing system performance and ensuring timely and cost-effective service delivery. However, the dynamic and heterogeneous nature of cloud environments presents significant challenges for these tasks, as workloads and resource availability can fluctuate unpredictably. Traditional approaches, including heuristic and meta-heuristic algorithms, often struggle to adapt to these real-time changes due to their reliance on static models or predefined rules. Deep Reinforcement Learning (DRL) has emerged as a promising solution to these challenges by enabling systems to learn and adapt policies based on continuous observations of the environment, facilitating intelligent and responsive decision-making. This survey provides a comprehensive review of DRL-based algorithms for job scheduling and resource management in cloud computing, analyzing their methodologies, performance metrics, and practical applications. We also highlight emerging trends and future research directions, offering valuable insights into leveraging DRL to advance both job scheduling and resource management in cloud computing. © 2025, CC BY.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Dual-Mode Disturbance Observer-based Predictive control with Harmonic Current Suppression for Dual Three-Phase Permanent Magnet Synchronous Motor Drives

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Liu, Huanli Lin, Weiyang Liu, Zhitai Yu, Xinghu Buccella, Concettina Cecati, Carlo Harbin Institute of Technology Research Institute of Intelligent Control and Systems Harbin150001 China Ningbo Institute of Intelligent Equipment Technology Company Ltd Ningbo315200 China University of L'Aquila DigiPower srl Department of Information Engineering Computer Science and Mathematics L'Aquila67100 Italy

Dual three-phase permanent magnet synchronous motor drives have gained considerable interest in those applications requiring high levels of reliability. However, they often suffer from high-order harmonic currents and mismatch of motor parameters, resulting in degraded performance and reduced efficiency. Therefore, this paper proposes a dual-mode disturbance observer based model predictive current controller. Not only direct current disturbances caused by motor parameters, but also alternating current disturbances caused by high-order harmonic currents are explicitly modeled and estimated to achieve improved model accuracy. In addition, the observer parameter design is given in detail. Furthermore, a generalized predictive current controller with the integration of the proposed observer is developed to provide satisfactory harmonic current suppression capability and parameter robustness simultaneously. Proof of the stability with the proposed controller is given and several experiments and comparisons demonstrate the effectiveness of the proposed method. © 2013 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

On Word-of-Mouth and Private-Prior Sequential Social Learning

arXiv

引用

arXiv 2025年

作者： Da Col, Andrea Rojas, Cristian R. Krishnamurthy, Vikram The Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm100 44 Sweden The School of Electrical and Computer Engineering Cornell University IthacaNY14853 United States

— Social learning provides a fundamental framework in economics and social sciences for studying interactions among rational agents who observe each other’s actions but lack direct access to individual beliefs. This paper investigates a specific social learning paradigm known as Word-of-Mouth (WoM), where a series of agents seeks to estimate the state of a dynamical system. The first agent receives noisy measurements of the state, while each subsequent agent relies solely on a degraded version of her predecessor’s estimate. A defining feature of WoM is that the final agent’s belief is publicly broadcast and adopted by all agents, in place of their own. We analyze this setting both theoretically and through numerical simulations, showing that some agents benefit from using the public belief broadcast by the last agent, while others suffer from performance deterioration. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Calibration-free method of recovering the time-varying absorbance profile in TDLAS by the Fourier reconstructed spectroscopy

引用

Measurement: Journal of the International Measurement Confederation 2025年 253卷

作者： Yang, Youquan Peng, Zhimin Zheng, Dao Ding, Yanjun Du, Yanjun School of Control and Computer Engineering North China Electric University Beijing102206 China State Key Laboratory of Power Systems Department of Energy and Power Engineering Tsinghua University Beijing100084 China Shanxi Research Institute of Huairou Laboratory Taiyuan030032 China

Traditional scan-direct absorption spectroscopy (scan-DAS) is susceptible to 1/f noise, limiting its ability to realize high signal-to-noise ratio (SNR) measurements. This study proposes a calibration-free and noise-immune method, named fast scan–Fourier reconstructed spectroscopy (FC-FRS), capable of improving the SNR of the single-shot absorbance spectrum and reconstructing the time-varying absorbance without decreasing the time resolution. Two validation experiments with CO2 absorbance varying over time were designed using a shock tube device within the millisecond time duration. In the first validation experiment, CO2 was gradually released during the combustion of hydrocarbons, resulting in the slowly increased CO2 absorbance. The average spectral SNR of FC-FRS reconstructed absorbance at 2100 K reached 73.51, which increased by 22.83 % compared to the original scan-DAS spectrum. The CO2 generation profile extracted from the recovered absorbance agreed well with the prediction of kinetic mechanisms. In the second experiment where the CO2 absorbance was stable behind the reflected shock at 1312 K, the average spectral SNR of the recovered absorbance line behind the reflected shock was 433.81, which is 44 % higher than that of the scan-DAS spectrum. The averaged fitted line strength from the recovered absorbance curve had a relative error of only 1.07 % compared to the HITAN2020 database. Finally, the proposed method was compared with the 2f/1f method of scan-WMS in a static CO measurement experiment, the FC-FRS showed the similar SNR but better stability over time. © 2025 Elsevier Ltd

关键词： Absorption spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Hybrid Model Based on Deep Learning for Myocardial Infarction Detection 25

Hierarchical Hybrid Model Based on Deep Learning for Myocard...

引用

Proceedings of the 2025 4th International Conference on Big Data, Information and computer Network

作者： Mingxi Han Chi Ma Siyuan Li Baoming Pu School of Software Liaoning Technical University Huludao Liaoning China School of Computer Science and Engineering Northeastern University Shenyang Liaoning China School of Electrical and Intelligent Control Liaoning Institute of Science and Engineering Jinzhou Liaoning China

ISBN: (纸本)9798400712425

Myocardial Infarction (MI) is a major global health threat, where rapid and accurate diagnosis is essential for improving treatment outcomes. This study proposes MSRC-TransBLSTM, a deep learning-based hierarchical hybrid model for the automatic detection of MI. The model combines spatial and temporal features through a hierarchical modeling strategy: multi-layer convolutional blocks and improved MSRC modules extract and optimize spatial features, strengthening the representation of both local and global features. For temporal modeling, the Transformer Encoder captures global dependencies, while the BLSTM focuses on refining local dynamics features. Experiments on the PTB-XL dataset demonstrated the model's strong performance across key metrics (Acc = 98.68%, Sen = 97.33%, F1 = 97.43%). Compared to other models, it achieves notable improvements in accuracy and feature representation, confirming its effectiveness in MI detection.

关键词： Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Energy-Based Trajectory Tracking for Underactuated Mechanical Systems: Velocity-Free and Disturbance Rejection Methods

引用

International Journal of Robust and Nonlinear control 2025年

作者： Javanmardi, N. Borja, P. van der Schaft, A.J. Yazdanpanah, M.J. Scherpen, J.M.A. Jan C. Willems Center for Systems and Control ENTEG Faculty of Science and Engineering University of Groningen Groningen Netherlands Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran School of Engineering Computing and Mathematics University of Plymouth Plymouth United Kingdom Jan C. Willems Center for Systems and Control Bernoulli Institute Faculty of Science and Engineering University of Groningen Groningen Netherlands

This work investigates three energy-shaping control approaches to address the trajectory-tracking problem for specific classes of underactuated mechanical systems. In particular, the notions of contractive systems and dynamic extensions are utilized to solve the trajectory-tracking problem while addressing implementation issues such as the lack of velocity sensors and the presence of constant disturbances. To this end, a first tracking controller is developed without the need for velocity measurements. A second controller is introduced, solving the trajectory-tracking problem while rejecting matched constant disturbances. Then, a third approach establishes conditions to combine both mentioned controllers. It is shown that the proposed design methods guarantee exponential convergence of closed-loop systems for specific classes of underactuated mechanical systems. The third method is illustrated with an example. © 2025 The Author(s). International Journal of Robust and Nonlinear control published by John Wiley & Sons Ltd.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Text-to-Decision Agent: Learning Generalist Policies from Natural Language Supervision

arXiv

引用

arXiv 2025年

作者： Zhang, Shilin Hu, Zican Wu, Wenhao Xie, Xinyi Tang, Jianxiang Chen, Chunlin Dong, Daoyi Cheng, Yu Sun, Zhenhong Wang, Zhi Department of Control Science and Intelligent Engineering Nanjing University China School of Engineering Australian National University Australia Australian Artificial Intelligence Institute University of Technology Sydney Australia Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

RL systems usually tackle generalization by inferring task beliefs from high-quality samples or warmup explorations. The restricted form limits their generality and usability since these supervision signals are expensive and even infeasible to acquire in advance for unseen tasks. Learning directly from the raw text about decision tasks is a promising alternative to leverage a much broader source of supervision. In the paper, we propose Text-to-Decision Agent (T2DA), a simple and scalable framework that supervises generalist policy learning with natural language. We first introduce a generalized world model to encode multi-task decision data into a dynamics-aware embedding space. Then, inspired by CLIP, we predict which textual description goes with which decision embedding, effectively bridging their semantic gap via contrastive language-decision pre-training and aligning the text embeddings to comprehend the environment dynamics. After training the text-conditioned generalist policy, the agent can directly realize zero-shot text-to-decision generation in response to language instructions. Comprehensive experiments on MuJoCo and Meta-World benchmarks show that T2DA facilitates high-capacity zero-shot generalization and outperforms various types of baselines. Copyright © 2025, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning With Adaptive Distribution Transformation for Fault Detection and Isolation Using Limited Labeled Faults

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Jia, Mingwei Shen, Bingbing Liu, Yi Zhejiang University of Technology Institute of Process Equipment and Control Engineering Hangzhou310023 China Hangzhou Normal University School of Mathematics Hangzhou311121 China McGill University Department of Electrical and Computer Engineering MontrealH3A 0E9 Canada

Fault detection and isolation (FDI) in process industries remain challenging due to misdiagnosed dynamic variations, limited fault labels, and complex variable interactions. To address these challenges, an adaptive distribution transformation-graph contrastive learning (ADT-GCL) is proposed to differentiate between global dynamics and local faults, even when labeled faults are limited. To capture variable interactions at both global and local levels, global and local graphs are established, and a local-global learning strategy is introduced. To prevent the few available fault labels from being misidentified as normal, contrastive tasks first cluster data embeddings before mapping them to labels. For fault isolation, an adaptive distribution transformation loss reconstructs fault embeddings as normal data, thereby increasing reconstruction errors. The T2 statistic is then used to identify fault variables based on these errors. Lastly, case studies on a sugar production process and a multiphase flow process (MFP) demonstrate ADT-GCL’s superiority in distinguishing global dynamics from local faults. © 1963-2012 IEEE.

关键词： Sugar manufacture

来源：评论

学校读者我要写书评

暂无评论

Boolean matrix compressed sensing

Boolean matrix compressed sensing

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qiang Liu Mahdi Soleymani Hessam Mahdavifar National Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Halıcıoğlu Data Science Institute University of California San Diego La Jolla CA USA Department of Electrical and Computer Engineering Northeastern University Boston MA USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In real-world datasets, leveraging the low-rank and sparsity properties enables developing efficient algorithms across a diverse array of data-related tasks, including compression, compressed sensing, matrix completion, etc. Notably, these two properties often coexist in certain real-world datasets, especially in Boolean datasets and quantized real-valued datasets. To harness the advantages of low-rank and sparsity simultaneously, we adopt a technique inspired by compressed sensing and Boolean matrix completion. Our approach entails compressing a low-rank sparse Boolean matrix by performing inner product operations with a randomly generated Boolean matrix. We then propose a decoding algorithms based on message-passing techniques to recover the original matrix. Our experiments demonstrate superior recovery performance of our proposed algorithms compared to Boolean matrix completion, with equal measurement requirements.

关键词： Image coding Signal processing algorithms Signal processing Acoustics Sensors Decoding Sparse matrices Speech processing Compressed sensing

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：