检索结果-内蒙古大学图书馆

OSE: On-Site State of Health Estimation for Li-ion Battery using Real-Time Field data

IEEE Transactions on Transportation Electrification 2025年

作者： Chen, Yanwen Zhao, Cong Yang, Shusen Zhao, Peng Ren, Xuebin Han, Qing Yang, Yuqian Wu, Shuaijun Xi'an Jiaotong University National Engineering Laboratory for Big Data Analytics Shaanxi Xi'an710049 China Xi'an Jiaotong University National Engineering Laboratory for Big Data Analytics The Ministry of Education Key Lab for Intelligent Networks and Network Security Shaanxi Xi'an710049 China

On-site lithium-ion battery state of health (SoH) estimation is of crucial importance for reliable operations of electric vehicles (EVs). Yet, due to the low-quality of unlabeled real-time field data, diverse operating environments of in-service EVs, and limited computational capability of onboard devices, existing techniques established on data from well-controlled experimental environments are not practical for real world EVs' SoH estimation. Accurate and rapid SoH estimation based on field data of in-service EVs still remains quite challenging. To tackle this challenge, we present an on-site SoH estimation (OSE) method using in-service EV field data through a new knowledge embedded deep transfer learning (DTL) model. Initially, an universal data preprocessing approach integrating mechanism knowledge is designed to process low-quality data under diverse operating environments. Then, we develop a domain adaptive hybrid deep neural network (DAHDNN) model suitable for unlabeled field data, which can be deployed via edge cloud collaborative framework to meet actual computational capability. We demonstrate the superiority of our method across four real datasets, where, OSE's estimation error is decreased by up to 78.5% compared with the state-of-the-art methods. The results indicate that the proposed method has good generalizability and reliability for SoH estimation on real-time field data. © 2015 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

Multi-Hop Attention Diffusion Graph Neural Networks For Multimodal Fake News Detection

Multi-Hop Attention Diffusion Graph Neural Networks For Mult...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Zhongqiang Lu, Dongli Sha, Ying Key Laboratory of Smart Farming for Agricultural Animals Wuhan China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan China Hubei Engineering Technology Research Center of Agricultural Big Data Wuhan China College of Informatics Huazhong Agricultural University Wuhan China

ISBN: (纸本)9798350368741

Fake news often spreads rapidly on social media in various forms, exposing users to a large amount of misinformation and disinformation. Recently, promising results have been achieved in fake news detection. However, most of the approaches only consider one-hop neighborhood information in cross-modal mapping relationships or focus mainly on pairwise interactions of multimodal fake news. However, the fine-grained feature mapping of multimodal fake news may go beyond binary relations. To address these issues, we propose a Multi-Hop Attention Diffusion Graph Neural Networks in this work to capture and complement the multivariate mapping relationships between fine-grained features, while extracting cross-modal higher-order alignment representations for multimodal fake news detection via cross-modal contrastive learning and modal matching. Extensive experiments on three public datasets demonstrate the effectiveness of the proposed approach in the multimodal fake news detection task. © 2025 IEEE.

关键词： attention diffusion fake news graph neural networks multivariate mapping relationships

来源：评论

学校读者我要写书评

暂无评论

Structure-Based Uncertainty Estimation for Source-Free Active Domain Adaptation

引用

IET Computer Vision 2025年第1期19卷

作者： Ouyang, Jihong Zhang, Zhengjie Meng, Qingyi Chi, Jinjin College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

Active domain adaptation (active DA) provides an effective solution by selectively labelling a limited number of target samples to significantly enhance adaptation performance. However, existing active DA methods often struggle in real-world scenarios where, due to data privacy concerns, only a pre-trained source model is available, rather than the source samples. To address this issue, we propose a novel method called the structure-based uncertainty estimation model (SUEM) for source-free active domain adaptation (SFADA). To be specific, we introduce an innovative active sample selection strategy that combines both uncertainty and diversity sampling to identify the most informative samples. We assess the uncertainty in target samples using structure-wise probabilities and implement a diversity selection method to minimise redundancy. For the selected samples, we not only apply standard-supervised loss but also conduct interpolation consistency training to further explore the structural information of the target domain. Extensive experiments across four widely used datasets demonstrate that our method is comparable to or outperforms current UDA and active DA methods. © 2025 The Author(s). IET Computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： computer vision convolutional neural nets image classification

来源：评论

学校读者我要写书评

暂无评论

Optimal torque of cantilever boring robots in the footage process under complex terrains

Robotic Intelligence and Automation

引用

Robotic Intelligence and Automation 2025年

作者： Liu, Yang Li, Fenghe Hu, Yanpeng Guo, Jin School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education Beijing China

Purpose: This paper aims to propose an optimal control strategy based on the slip rate during the tunnel footage process for cantilever boring robots. Design/methodology/approach: A method combining adaptive dynamic programming and linear quadratic regulator is used to solve for the optimal torque, aiming to achieve precise and stable control strategies. Findings: The feasibility of the proposed method is demonstrated through an actual footage process. Comparative analysis with other methods further illustrates the superiority of this approach. Originality/value: Combining the slip rate to calculate the optimal torque of the cantilever boring robots under complex road conditions is essential to overcoming the slip phenomenon during the footage process. The method proposed in this paper is very useful for current systems and intuitive for similar robots. © 2025, Emerald Publishing Limited.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on Adaptive Perturbation on Federated Graph Learning 25

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on ...

引用

Proceedings of the ACM on Web Conference 2025

作者： Ken Li Bin Shi Jiazhe Wei Bo Dong School of Computer Science and Technology Xi'an Jiaotong University Xi'an China and Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an China School of Computer Science and Technology Xi'an Jiaotong University Xi'an China and Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China School of Distance Education Xi'an Jiaotong University Xi'an China and Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China

ISBN: (纸本)9798400712746

Federated Graph Learning (FedGL) is an emerging Federated Learning (FL) framework that learns the graph data from various clients to train better Graph Neural Networks(GNNs) model. Owing to concerns regarding the security of such framework, numerous studies have attempted to execute backdoor attacks on FedGL, with a particular focus on distributed backdoor attacks. However, all existing methods posting distributed backdoor attack on FedGL only focus on injecting distributed backdoor triggers into the training data of each malicious client, which will cause model performance degradation on original task and is not always effective when confronted with robust federated learning defense algorithms, leading to low success rate of attack. What's more, the backdoor signals introduced by the malicious clients may be smoothed out by other clean signals from the honest clients, which potentially undermining the performance of the *** address the above significant shortcomings, we propose a non-intrusive graph distributed backdoor attack(NI-GDBA) that does not require backdoor triggers to be injected in the training data. Our attack trains an adaptive perturbation trigger generator model for each malicious client to learn the natural backdoor from the GNN model downloading from the server with the malicious client's local data. In contrast to traditional distributed backdoor attacks on FedGL via trigger injection in training data, our attack on different datasets such as Molecules and Bioinformatics have higher attack success rate, stronger persistence and stealth, and has no negative impact on the performance of the global GNN model. We also explore the robustness of NI-GDBA under different defense strategies, and based on our extensive experimental studies, we show that our attack method is robust to current federated learning defense methods, thus it is necessary to consider non-intrusive distributed backdoor attacks on FedGL as a novel threat that requires custom de

关键词： backdoor attacks

来源：评论

学校读者我要写书评

暂无评论

A novel color-tunable β-Ca3(PO4)2-type phosphor with applications in WLEDs and anti-counterfeiting

引用

Ceramics International 2025年

作者： Xu, He-Yun Long, Fei Wei, Tao He, Duan-Duan Xu, Lei Deng, Chao-Yong Li, Xu-Cheng Key Laboratory of Functional Composite Materials of Guizhou Province College of Big Data and Information Engineering Guizhou University Guizhou Guiyang550025 China College of Data Science and Information Engineering Guizhou Minzu University Guizhou Guiyang550025 China

Ca9-xNaLu2/3(PO4)7:xEu2+(0.005 ≤ x ≤ 0.04) phosphors were synthesized via a high-temperature solid-state method. Eu2+ ions were found to occupy the Ca3, Ca1/Ca2, and Na sites, corresponding to emission peaks at 422 nm, 485 nm, and 530 nm, respectively. At a low doping concentration (x = 0.005), Eu2+ ions were evenly distributed between the Ca3 and Ca1/Ca2 sites. As the doping concentration increased, the emission intensity at 422 nm decreased and eventually disappeared, while the emission at 485 nm gradually intensified until concentration quenching occurred. This behavior was primarily attributed to the preferential occupancy of Eu2+ ions and the associated energy transfer. By partially substituting Lu3+ with Ca2+, Ca9+yNaLu2(1-y)/3(PO4)7:0.02Eu2+ phosphors (0 ≤ y ≤ 1) were synthesized, resulting in enhanced emission intensity at 422 nm with a redshift, while the 485 nm emission showed reduced intensity and a blueshift. This adjustment shifted the emission color gradually from cyan to blue. Building on this, Ca9.6-zNaLu2∗0.4/3(PO4)7:0.02Eu2+,zMn2+(0.1 ≤ z ≤ 0.55) phosphors were prepared, enabling color tunability from blue to white and ultimately red with increasing Mn2+ concentration. Detailed analysis of the Eu2+→Mn2+ energy transfer (ET) process revealed a transfer efficiency of up to 96.45 % at 422 nm. White-light-emitting diode (WLED) devices fabricated using Ca9.6-zNaLu2∗0.4/3(PO4)7:0.02Eu2+,zMn2+(z = 0.1, 0.15) phosphors combined with 365 nm chips exhibited excellent performance, with a high color rendering index (CRI = 93.5) and low correlated color temperature (CCT = 4756 K). Additionally, anti-counterfeiting inks were prepared by mixing Ca9.6NaLu2∗0.4/3(PO4)7:0.025Eu2+ phosphors with polyvinyl alcohol (PVA) solutions and filling them into floral stamps. These inks exhibited distinct color changes under UV excitation at 302 nm and 365 nm, demonstrating the phosphor's strong potential for anti-counterfeiting applications. © 2025 Elsevier Ltd and Techna Grou

关键词： Phosphors

来源：评论

学校读者我要写书评

暂无评论

Distributed observer-based formation control and obstacle avoidance of nonholonomic mobile robots with input saturation

引用

knowledge-Based Systems 2025年 319卷

作者： Wang, Siqi Wang, Heng Wang, Yulong Li, Qing Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Shanghai Key Laboratory of Power Station Automation Technology School of Mechatronic Engineering and Automation Shanghai University Shanghai200072 China

This paper studies the problem of distributed observer-based formation control and collision avoidance for multi-robot systems with input saturation. Different from existing approaches where accurate robot poses are assumed to be available, a novel distributed observer-based control framework is developed, which can deal with the failure to fulfill safety constraints caused by pose estimation errors, ensuring both formation maintenance and collision avoidance. The proposed method can be applied to any kind of pose observer satisfying a mild requirement, and at the same time, it can adaptively deal with estimation inaccuracies using function approximation and does not need prior knowledge of the weight upper bounds in approximation. Additionally, in contrast to common position-only CBF-based methods, both position and orientation are considered simultaneously, which offers more control flexibility to ensure coordination and safety in environments with static and dynamic obstacles. Furthermore, the framework decentralizes traditional safety conditions into distributed constraints, which allows independent computation for each robot. Particularly, to address infeasibility issues caused by multiple CBF constraints, relaxation parameters are introduced in safety barrier certificates, broadening the feasible solution space in the quadratic program. Finally, the effectiveness and advantage of the proposed framework are validated by numerical simulation and comparison studies. © 2025 Elsevier B.V.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

ApriDS: An evidence linkage network construction model for judgment documents

引用

Journal of King Saud University - Computer and Information Sciences 2025年第1期37卷 1-13页

作者： Zhou, Yulin Qin, Yongbin Lin, Chuan Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou University Guiyang 550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang 550025 China College of Computer Science & Technology Guizhou University Guiyang 550025 China

Evidence serves as the basis for determining facts in the judicial trial process, and exploring the correlation between evidence has become an essential task. However, there is uncertainty and unreliability of evidence. In this paper, we propose an ApriDS model that can mine correlations between evidence and construct evidence linkage networks. Specifically, we use the association rule algorithm to mining for the correlations between evidence in order to initially construct an evidence linkage network. Moreover, we also combine the imprecise reasoning theory to alleviate unreliability among evidence. Finally, combining the above effectively mitigates uncertainty and unreliability in the evidence linkage network. We conduct extensive experiments and present analyses on five case datasets, including marriages, thefts, homicides, contract disputes and unlawful detention. Compared to the baseline model, our method’s accuracy improves by 12.75%, 14.16%, 14.80%, 21.64% and 26.15% on the five datasets, respectively. © The Author(s) 2025.

关键词： Apriori algorithm D-S evidence theory Evidence linkage network Judgment document

来源：评论

学校读者我要写书评

暂无评论

Development and validation of a nomogram prediction model for overall survival in patients with rectal cancer

引用

World Journal of Gastrointestinal Oncology 2025年第2期17卷 93-104页

作者： Ling Liang Xiao-Sheng Li Ze-Jun Huang Zu-Hai Hu Qian-Jie Xu Yu-Liang Yuan Wei Zhang Hai-Ke Lei Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment Chongqing University Cancer HospitalChongqing 400030China Chongqing Cancer Multiomics Big Data Application Engineering Research Center Chongqing University Cancer HospitalChongqing 400030China Department of Health Statistics School of Public HealthChongqing Medical UniversityChongqing 400016China

BACKGROUND Rectal cancer is prevalent and associated with substantial morbidity and *** To develop a nomogram prediction model for overall survival(OS)in patients with rectal cancer by leveraging a comprehensive analysis of demographic,clinicopathological,haematological,and follow-up data to identify independent prognostic *** We conducted a prospective cohort study in China involving rectal cancer patients and applied Cox regression and least absolute shrinkage and selection operator regression to assess the significance of various variables as independent prognostic factors for *** identified factors were integrated into a nomogram model,which was evaluated for predictive accuracy via the C-index,area under the curve(AUC),calibration curve,and decision curve analysis(DCA).RESULTS Multivariate analysis revealed independent predictors of OS,including the Karnofsky performance status,age,sex,TNM stage,chemotherapy,surgery,targeted therapy,β2-microglobulin,lactate dehydrogenase,and the neutrophil-to-lymphocyte *** nomogram demonstrated a C-index of 0.80 for the training and validation cohorts,with AUC values indicating high predictive accuracy for 1-year,3-year,and 5-year *** calibration curves confirmed the model's excellent agreement with the observed survival rates,and DCA revealed the superior clinical utility of the nomogram over the TNM staging *** In this study,a novel prognostic model that accurately predicts the OS of rectal cancer patients was *** model exhibited excellent discriminatory and calibration capabilities,thus offering a reliable tool for health care professionals to estimate patient survival.

关键词： Rectal cancer Overall survival Nomogram Prognosis

来源：评论

学校读者我要写书评

暂无评论

Priority-Based Blockchain Packing for Dependent Industrial IoT Transactions

引用

IEEE Transactions on Network and Service Management 2025年第2期22卷 1618-1628页

作者： Lin, Chaofeng Tang, Jinchuan Dang, Shuping Chen, Gaojie Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China University of Bristol Department of Electrical and Electronic Engineering BristolBS8 1UB United Kingdom Guangdong Shenzhen518107 China 5GIC and 6GIC The University of Surrey United Kingdom

Blockchain plays a key role in establishing secure and decentralized Industrial Internet of Things (IIoT) systems. Currently, the dependent transactions generated by IIoT devices require a packing process to select a set of non-conflicted transactions, which results in significant delay and deviation of the transaction response time. In this paper, we propose a novel transaction packing algorithm named Priority-Pack to address the above issue. Firstly, we use directed acyclic graphs to model the dependent transactions in IIoT systems to establish the mathematical relationships between transaction priority and waiting time as well as dependencies. Secondly, we propose an algorithm to specify a higher priority to a transaction with longer waiting time without violating transaction dependencies. It eliminates the time required to traverse the subsets of transactions in other algorithms. Thirdly, to further reduce the response delay for transactions with the same priority level, we choose to first pack transactions with smaller sizes. We prove that this selection can achieve the lowest average response time. Finally, simulations are conducted to benchmark the Priority-Pack against the state-of-the-art algorithms including Fair-Pack and Random-Pack. The results demonstrate that Priority-Pack outperforms the others in terms of average response time and deviations. © 2004-2012 IEEE.

关键词： Industrial internet of things (IIoT)

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：