检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zhao, Xinwei Liu, Yonggui Xiao, Bin Key Laboratory of Autonomous Systems and Network Control Ministry of Education School of Automation Science and Engineering South China University of Technology Guangzhou510641 China School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China Information Engineering School Guangzhou Vocational College of Technology & Business Guangzhou511442 China

Lithium-ion batteries are valuable as the primary power source for electric vehicles (EVs). However, their capacity degradation and reliability directly affect driving of on-service EVs, accurately forecasting battery capacity is still a tricky challenge due to complex battery systems and limitations of computing power. To overcome such barriers, a concise battery capacity prediction method is proposed based on charging data and decomposition framework in this paper. First, charging hot-spot intervals are counted to provide a reliable foundation for screening high-quality and low-quantity data. Then, the seasonal-trend decomposition method with independent analysis is designed and applied to extract significant correlation features associated with capacity degradation. Subsequently, a temporal convolution network with the decomposed mode is developed to forecast battery capacity, in conjunction with the use of decoupling mechanism to rectify the analytical interference and misinformation caused by data mixing. Finally, experiment results demonstrate that the proposed method can accurately predict capacity of on-service EVs. Furthermore, this approach alleviates the computational burden without compromising prediction accuracy. © 2024, The Authors. All rights reserved.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Navigating the future:Embracing resilience and interoperability in the industrial internet

引用

Fundamental Research 2024年第1期4卷 1-2页

作者： Chaojie Gu Chunxiao Jiang Jiming Chen Yang Cong Bin Xiao College of Control Science and Engineering Zhejiang UniversityHangzhou 310027China Beijing National Research Center for Information Science and Technology Tsinghua UniversityBeijing 100084China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510641China Division II Department of Information SciencesNational Natural Science Foundation of ChinaBeijing 100085China Chongqing Key Laboratory of Image Cognition School of Computer Science and TechnologyChongqing University of Posts and TelecommunicationsChongqing 400065China

In the midst of the fourth industrial revolution,the convergence of the digital,physical,and biological realms is propelling industrial innovation to new *** the heart of this transformative era lies the Industrial In... 详细信息

关键词： internet network shaping

来源：评论

学校读者我要写书评

暂无评论

MIHCGENER: A Framework for Multiple Immunohistochemical Image Generation Based on the Combination of Pathological Foundation Model and Generative Model 22

MIHCGENER: A Framework for Multiple Immunohistochemical Imag...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Xun, Tianwang Li, Ruiyu Su, Lei Wu, Junxian Dong, Di Shang, Wenting Shao, Lizhi Institute of Automation Chinese Academy of Sciences Cas Key Laboratory of Molecular Imaging Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Peking Union Medical College Hospital Molecular Pathology Research Center Beijing China School of Computer Science and Engineering Southeast University Nanjing China School of Internet Anhui University Anhui China

ISBN: (纸本)9798331520526

The tumor microenvironment (TME) is important to the treatment and prognosis of cancer. Multiplex Immunohistochemical (mIHC) images can display the expression of multiple biomolecular markers while maintaining spatial location, making it an effective tool for TME analysis. However, acquiring mlHC images demands stringent laboratory conditions, extensive time and resources. In this study, we proposed an end-to-end generative framework to transform hematoxylin and eosin (H&E) images into mIHC images. In addition, we introduced a pathological foundation model into the feature encoding of pathological image generation to enhance the performance of our framework and proved the superiority and necessity of the foundation model. Our method successfully generated mIHC images, achieved state-of-the-art (SOTA) performance against popular methods and maintained robustness on cross-cancer. The framework we proposed is expected to provide a more efficient and cheaper tool for the observation and evaluation of TME in pathology. © 2025 IEEE.

关键词： Foundation model Generative model Multiplex Immunohistochemical image Pathology

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Empowered AI-Generated Content in Wireless Networks

arXiv

引用

arXiv 2023年

作者： Huang, Xumin Li, Peichun Du, Hongyang Kang, Jiawen Niyato, Dusit Kim, Dong In Wu, Yuan State Key Laboratory of Internet of Things for Smart City University of Macau Taipa China The School of Computer Science and Engineering Nanyang Technological University Singapore School of Automation Guangdong University of Technology Guangzhou510006 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Computer and Information Science University of Macau Taipa China

Artificial intelligence generated content (AIGC) has emerged as a promising technology to improve the efficiency, quality, diversity and flexibility of the content creation process by adopting a variety of generative AI models. Deploying AIGC services in wireless networks has been expected to enhance the user experience. However, the existing AIGC service provision suffers from several limitations, e.g., the centralized training in the pre-training, fine-tuning and inference processes, especially their implementations in wireless networks with privacy preservation. Federated learning (FL), as a collaborative learning framework where the model training is distributed to cooperative data owners without the need for data sharing, can be leveraged to simultaneously improve learning efficiency and achieve privacy protection for AIGC. To this end, we present FL-based techniques for empowering AIGC, and aim to enable users to generate diverse, personalized, and high-quality content. Furthermore, we conduct a case study of FL-aided AIGC fine-tuning by using the state-of-the-art AIGC model, i.e., stable diffusion model. Numerical results show that our scheme achieves advantages in effectively reducing the communication cost and training latency and privacy protection. Finally, we highlight several major research directions and open issues for the convergence of FL and AIGC. © 2023, CC BY.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing

DeepRicci: Self-supervised Graph Structure-Feature Co-Refine...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Li Sun Zhenhao Huang Hua Wu Junda Ye Hao Peng Zhengtao Yu Philip S. Yu School of Control and Computer Engineering North China Electric Power University Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Department of Computer Science University of Illinois at Chicago IL USA

Graph Neural Networks (GNNs) have shown great power for learning and mining on graphs, and Graph Structure Learning (GSL) plays an important role in boosting GNNs with a refined graph. In the literature, most GSL solutions either primarily focus on structure refinement with task-specific supervision (i.e., node classification), or overlook the inherent weakness of GNNs themselves (e.g., over-squashing), resulting in suboptimal performance despite sophisticated designs. In light of these limitations, we propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs. In this paper, we take a fundamentally different perspective of the Ricci curvature in Riemannian geometry, in which we encounter the challenges of modeling, utilizing and computing Ricci curvature. To tackle these challenges, we present a self-supervised Riemannian model, DeepRicci. Specifically, we introduce a latent Riemannian space of heterogeneous curvatures to model various Ricci curvatures, and propose a gyrovector feature mapping to utilize Ricci curvature for typical GNNs. Thereafter, we refine node features by geometric contrastive learning among different geometric views, and simultaneously refine graph structure by backward Ricci flow based on a novel formulation of differentiable Ricci curvature. Finally, extensive experiments on public datasets show the superiority of DeepRicci, and the connection between backward Ricci flow and over-squashing. Codes of our work are given in https://***/RiemanGraph/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Create Your World: Lifelong Text-to-Image Diffusion

arXiv

引用

arXiv 2023年

作者： Sun, Gan Liang, Wenqi Dong, Jiahua Li, Jun Ding, Zhengming Cong, Yang State Key Laboratory of Robotics Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China The School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu210094 China The Department of Computer Science Tulane University New OrleansLA70118 United States The College of Automation Science and Engineering South China University of Technology Guangzhou510640 China University of Chinese Academy of Sciences Beijing100049 China

Text-to-image generative models can produce diverse high-quality images of concepts with a text prompt, which have demonstrated excellent ability in image generation, image translation, etc. We in this work study the problem of synthesizing instantiations of a user's own concepts in a never-ending manner, i.e., create your world, where the new concepts from user are quickly learned with a few examples. To achieve this goal, we propose a Lifelong text-to-image Diffusion Model (L2DM), which intends to overcome knowledge "catastrophic forgetting" for the past encountered concepts, and semantic "catastrophic neglecting" for one or more concepts in the text prompt. In respect of knowledge "catastrophic forgetting", our L2DM framework devises a task-aware memory enhancement module and a elastic-concept distillation module, which could respectively safeguard the knowledge of both prior concepts and each past personalized concept. When generating images with a user text prompt, the solution to semantic "catastrophic neglecting" is that a concept attention artist module can alleviate the semantic neglecting from concept aspect, and an orthogonal attention module can reduce the semantic binding from attribute aspect. To the end, our model can generate more faithful image across a range of continual text prompts in terms of both qualitative and quantitative metrics, when comparing with the related state-of-the-art models. The code will be released at https://***/. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ALIM: adjusting label importance mechanism for noisy partial label learning 23

ALIM: adjusting label importance mechanism for noisy partial...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Mingyu Xu Zheng Lian Lei Feng Bin Liu Jianhua Tao The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Computer Science and Engineering Nanyang Technological University Department of Automation Tsinghua University and Beijing National Research Center for Information Science and Technology Tsinghua University

Noisy partial label learning (noisy PLL) is an important branch of weakly supervised learning. Unlike PLL where the ground-truth label must conceal in the candidate label set, noisy PLL relaxes this constraint and allows the ground-truth label may not be in the candidate label set. To address this challenging problem, most of the existing works attempt to detect noisy samples and estimate the ground-truth label for each noisy sample. However, detection errors are unavoidable. These errors can accumulate during training and continuously affect model optimization. To this end, we propose a novel framework for noisy PLL with theoretical interpretations, called "Adjusting Label Importance Mechanism (ALIM)". It aims to reduce the negative impact of detection errors by trading off the initial candidate set and model outputs. ALIM is a plug-in strategy that can be integrated with existing PLL approaches. Experimental results on multiple benchmark datasets demonstrate that our method can achieve state-of-the-art performance on noisy PLL. Our code is available at: https://***/zeroQiaoba/ALIM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Output Containment Control of Heterogeneous Multiagent Systems: A Hierarchical Scheme

Data-Driven Output Containment Control of Heterogeneous Mult...

引用

IEEE Conference on Decision and Control

作者： Malika Sader Wenyu Li Yanhui Yin Zhongmei Li Dexian Huang Zhongxin Liu Xiao He Chao Shang Department of Automation Tsinghua University Beijing China College of Artificial Intelligence Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University Tianjin China School of Automation Engineering North-East Electric Power University Jilin China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai China Department of Automation Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In this article, we propose a data-driven solution to the output containment control problem of multiagent systems characterized by heterogeneous and unknown dynamics. The proposed data-driven scheme is hierarchical, which includes a network layer and a physical layer, bypassing the traditional modeling exercise and eliminating the need for explicit state-space models. In the network layer, a fully distributed observer without knowing the dynamics of leaders is designed to generate a containment trajectory. A data-driven approach based on data sampled from an auxiliary system is developed to overcome the dependence on the explicit state-space models for design of control gains. This paves the way for deriving a datadriven solution to the regulator equation, which is derived by employing the data informativity condition and relevant data in the physical layer. The results demonstrate that the closedloop system is asymptotically stable, and the regulated output containment converges to zero. Compared to generic modelbased hierarchical schemes, the assumptions that the system matrices are completely known and homogeneous on system dynamics can be relaxed.

关键词： Regulators Protocols System dynamics Distributed feedback devices Observers Physical layer Mathematical models State-space methods Trajectory Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Based Dimensionality Reduction for Large-Scale Binary Optimization With Millions of Variables

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Tian, Ye Wang, Luchen Yang, Shangshang Ding, Jinliang Jin, Yaochu Zhang, Xingyi School of Computer Science and Technology Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Institutes of Physical Science and Information Technology Anhui University Hefei China School of Artificial Intelligence Anhui University Hefei China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China School of Engineering Westlake University Hangzhou China

Binary optimization assumes a pervasive significance in the context of practical applications, such as knapsack problems, maximum cut problems, and critical node detection problems. Existing techniques including mathematical programming, heuristics, evolutionary computation, and neural networks have been employed to tackle binary optimization problems (BOPs), however, they grapple with the challenge of optimizing a large number of binary variables. In this paper, we propose a dimensionality reduction method to assist evolutionary algorithms in solving large-scale BOPs, which is achieved based on neural networks. The proposed method converts the optimization of a large number of binary variables into the optimization of a small number of network weights, resulting in a significant reduction in search space dimensionality. Crucially, the proposed method obviates the necessity for a training process, which eliminates the requirement for a priori knowledge and enhances the search efficiency. On six types of single-and multi-objective BOPs with up to 10 000 000 variables, the proposed method demonstrates superiority over top-tier evolutionary algorithms and neural network-based methods. IEEE

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

DUSA-UNet: Dual Sparse Attentive U-Net for Multiscale Road Network Extraction

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Song, Jie Sun, Yue Cai, Ziyun Xiao, Liang Huang, Yawen Zheng, Yefeng Nanjing University of Posts and Telecommunications College of Automation College of Artificial Intelligence Nanjing210023 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Spectral Imaging & Intelligent Sense Nanjing210094 China Tencent YouTu Lab Jarvis Research Center Shenzhen518057 China

The challenges of road network segmentation demand an algorithm capable of adapting to the sparse and irregular shapes, as well as the diverse context, which often leads traditional encoding-decoding methods and simple Transformer embeddings to failure. We introduce a computationally efficient and powerful framework for elegant road-aware segmentation. Our method, called DUSA-UNet, effectively encodes fine-grained local road connectivity and holistic global topological semantics while decoding multiscale road network information. DUSA-UNet offers a novel alternative to the U-Net architecture by integrating connectivity attention, which can exploit intra-road interactions across multi-level sampling features with reduced computational complexity. This local interaction serves as valuable prior information for learning global interactions between road networks and the background through another integrality attention mechanism. The two forms of sparse attention are arranged alternatively and complementarily, and trained jointly, resulting in performance improvements without significant increases in computational complexity. Extensive experiments on various datasets with different resolutions, including Massachusetts, DeepGlobe, SpaceNet, and Large-Scale remote sensing images, demonstrate that DUSA-UNet outperforms state-of-the-art techniques. Our approach represents a significant advancement in the field of road network extraction, providing a computationally feasible solution that achieves high-quality segmentation results. © 1980-2012 IEEE.

关键词： NP-hard

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：