检索结果-内蒙古大学图书馆

Improving Multi-task GNNs for Molecular Property Prediction via Missing Label Imputation

Machine intelligence Research 2025年第1期22卷 131-144页

作者： Fenyu Hu Dingshuo Chen Qiang Liu Shu Wu University of Chinese Academy of Sciences Beijing100190China Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence SystemsInstitute of AutomationChinese Academy of SciencesBeijing100190China

The prediction of molecular properties is a fundamental task in the field of drug ***,graph neural networks(GNNs)have been gaining prominence in this *** a molecule tends to have multiple correlated properties,there is a great need to develop the multi-task learning ability of ***,limited by expensive and time-consuming human annotations,collecting complete labels for each task is *** a result,most existing benchmarks involve many missing labels in training data,and the performance of GNNs is impaired due to the lack of sufficient supervision *** overcome this obstacle,we propose to improve multi-task molecular property prediction by missing label ***,a bipartite graph is first introduced to model the molecule-task co-occurrence ***,the imputation of missing labels is transformed into predicting missing edges on this bipartite *** predict the missing edges,a graph neural network is devised,which can learn the complex molecule-task co-occurrence *** that,we select reliable pseudo labels according to the uncertainty of the prediction *** with enough and reliable supervision information,our approach achieves state-of-the-art performance on a variety of real-world datasets.

关键词： Graph classification imbalance learning prediction bias mixture of experts multiview representations

来源：评论

学校读者我要写书评

暂无评论

Collaborative Pushing and Grasping in Complex Scenarios via a Generator-Evaluator Network with Multiple Action Primitives 17th

Collaborative Pushing and Grasping in Complex Scenarios vi...

引用

17th International Conference on intelligent Robotics and Applications, ICIRA 2024

作者： Zuo, Guoyu Wang, Zihao Luo, Yongkang Yu, Shuangyue Zhao, Min School of Information Science and Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9789819607761

As robotic technologies advance, robotic arm manipulation tasks in complex environments become increasingly important. This paper presents a new collaborative pushing and grasping strategy to address two major challenges robotic arms encounter in complex environments: invisibility and tight enclosure of target objects. We propose a generator-evaluator network architecture based on multiple action primitives, incorporating hierarchical reinforcement learning and Double DQN techniques to optimize the operational efficiency of the robotic arm. By introducing a new action primitive to prioritize pushing operations around the topmost objects in space, our approach effectively reveals and locates obscured target objects. Additionally, utilizing the Spatial Correlation Test (SCT), our method explores all possible collision-free operational positions in the action space, selecting the optimal position from among them. Experimental results demonstrate that our approach achieves high efficiency and success rates in scenarios with randomly distributed objects, objects tightly enclosed by others, and invisible objects. This strategy enhances the speed and accuracy of tasks and improves the robot’s adaptability to complex environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Enhancing rheology and mechanical properties of DLP 3D-printed Si_(3)N_(4)materials via composition optimization and gas-pressure sintering

引用

International Journal of Minerals,Metallurgy and Materials 2025年第5期32卷 1220-1233页

作者： Qing Qin Gang Xiong Lin Han Yujuan Zhang Zhen Shen Changchun Ge Institute of Powder Metallurgy and Advanced Ceramics School of Materials Science and EngineeringUniversity of Science and Technology BeijingBeijing 100083China State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing Engineering Research Center of Intelligent Systems and TechnologyInstitute of AutomationChinese Academy of SciencesBeijing 100190China

Digital light processing(DLP)is a crucial additive manufacturing(AM)technique for producing high-precision ceramic *** study aims to optimize the formulation of Si_(3)N_(4)slurry to enhance both its performance and manufacturability in the DLP process,and investigate key factors such as particle size distribution,photopolymer resin monomer ratios,and dispersant types to im-prove the slurry’s rheological *** these optimizations,a photosensitive Si_(3)N_(4)slurry with 50vol%solid content was de-veloped,exhibiting excellent stability,and low viscosity(2.48 Pa·s at a shear rate of 12.8 s^(-1)).The effects of gas-pressure sintering on the material’s phase composition,microstructure,and mechanical properties were further explored,revealing that this technique significantly increases the flexural strength of the green sample from(109±10.24)to(618±42.15)*** sintered ceramics exhibited high hard-ness((16.59±0.05)GPa)and improved fracture toughness((4.45±0.03)MPa·m^(1/2)).Crack trajectory analysis revealed that crack deflec-tion,crack bridging,and the pull-out of rod-likeβ-Si_(3)N_(4)grains,are the main toughening mechanisms,which could effectively mitigate crack *** these mechanisms,crack deflection and bridging were particularly influential,significantly enhancing the frac-ture toughness of the Si_(3)N_(4)***,this research highlights how monomer formulation and gas-pressure sintering strengthen the performance of Si_(3)N_(4)slurry in the DLP three-dimensional printing *** work is expected to provide new insights for fabricat-ing complex Si_(3)N_(4)ceramic components with superior mechanical properties.

关键词： additive manufacturing Si_(3)N_(4)slurry low viscosity pressure sintering

来源：评论

学校读者我要写书评

暂无评论

Multiscale Temporal-Convolution and Attention Improved Neural Network for Biased Mental State Recognition 17th

Multiscale Temporal-Convolution and Attention Improved Neur...

引用

17th International Conference on Brain Informatics, BI 2024

作者： Zuo, Guoyu Xiao, Erjun Zhang, Tielin Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing University of Technology Beijing100124 China Center for Excellence in Brain Science and Intelligence Technology University of Chinese Academy of Sciences Shanghai200031 China

ISBN: (纸本)9789819632930

Accurate detection of mental state is vital for sleep assessment and anesthesia monitoring. However, challenges exist, including 1) limited data sources caused by few modalities, few channels, biased sample distribution, or large individual differences;2) multiscale dynamic feature of mental state signals, containing complex and dynamic fluctuations. In this paper, we proposed a multiscale temporal convolution and attention improved neural network (MTA-NN) to handle these two challenges, including: a preprocessing method using a clustering-first and label-generation approach for data augmentation involves filtering the production samples to mitigate the impact of noise on model performance;multiscale temporal-convolution module for detecting different scales of temporal and frequency features;an attention module for decoding key features in different spatial and temporal channels, and for setting the importance of historical dependencies;a full-connection layer is designed to recognize different sleep stage. The proposed MTA-NN is then verified in three typical sleep-state recognition tasks, including SleepEDF-20, SleepEDF-78, and ISRUC3. Compared to some state-of-the-art algorithms, the proposed MTA-NN achieves higher performance. Further ablation experiments show the necessary and importance of these designed sub modules in MTA-NN. We consider the same algorithm can also be extended to further similar mental state recognition tasks such as anesthesia monitoring. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Anesthesiology

来源：评论

学校读者我要写书评

暂无评论

Enabling intelligent Connectivity: A Survey of Secure ISAC in 6G Networks

引用

IEEE Communications Surveys and Tutorials 2025年第2期27卷 748-781页

作者： Zhu, Xiaoqiang Liu, Jiqiang Lu, Lingyun Zhang, Tao Qiu, Tie Wang, Chunpeng Liu, Yuan Beijing Jiaotong University School of Software Engineering Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China Tianjin University College of Intelligence and Computing Tianjin300350 China Qilu University of Technology School of Cyber Security and the Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan250353 China

The rapid growth of intelligent sensing capabilities and super computation power in 6G mobile communication systems has facilitated their application in diverse domains such as smart health, smart factories, and the industrial Internet of Things. Integrated Sensing and Communication (ISAC), as a core technology, has merged with artificial intelligence (AI) to enable intelligent connectivity, leading to a paradigm shift in traditional communication modes. This paper presents a visionary design for an ISAC-oriented unified IoT architecture that integrates software-defined communication and super-intelligent agents. By leveraging dynamic adaptability, self-learning, and optimization, the ISAC system can intelligently and flexibly respond to evolving requirements and environments. The architecture is redefined into three layers: the hardware layer, the omniscient layer, and the application layer. Furthermore, a retrospective survey of ISAC technology development over the past decade is conducted, highlighting new design principles for AI-empowered networks and multi-modals that support "intelligent connectivity" across various application scenarios and reinforce the security of ISAC. This paper categorizes the related works according to the different layer structures of the proposed architecture, and some important physical and machine learning models are introduced. Additionally, we summarize the current technological bottlenecks associated with ISAC and propose future research directions and potential solutions that lay the foundation for the future development of secure and intelligent communication networks. © 1998-2012 IEEE.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Noncollocated Output Feedback Control for the Semilinear Parabolic PDEs Under Input and Output Quantization

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 2934-2947页

作者： Zhao, Xuena Liu, Zhijie Zhang, Shuang Liu, Yu He, Wei University of Science and Technology Beijing Institute of Artificial Intelligence Key Laboratory of Perception and Control of Intelligent Bionic Unmanned Systems Ministry of Education School of Intelligence Science and Technology Beijing100083 China School of Automation Science and Engineering Engineering Research Center of Precision Electronic Manufacturing Equipment of Ministry of Education Guangzhou510640 China Institute of Artificial Intelligence Key Laboratory of Perception and Control of Intelligent Bionic Unmanned Systems Ministry of Education School of Intelligence Science and Technology Beijing100083 China School of Automation Beijing102206 China

In the context of increasingly networked control systems, this article concentrates on the noncollocated control issue of input and output quantization for industrial processes governed by semilinear parabolic partial differential equation (PDE) systems. Both the control and measurement signals are quantized and transmitted through the network, which causes signal errors and reduces the stability and robustness of the system. A Luenberger-type PDE observer is developed to overcome the control difficulty of quantized measurement feedback signals and noncollocated pointwise sensors. Based on the observed value, a feedback controller is proposed, which undergoes quantization and operates on the distributed actuators within the domain. By employing the Lyapunov direct method, it is demonstrated that the observer can accurately track the system state with exponential precision, and the closed-loop system is exponentially converged. The well-posedness analysis of the closed-loop system is discussed via the C0-semigroup method. The performance of the developed control strategy is validated through simulation examples. © 1963-2012 IEEE.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

Recent advances in photopolymerization 3D printing of alumina-ceramic

引用

Progress in Natural Science:Materials International 2025年第1期35卷 1-30页

作者： M.Irfan Hussain Min Xia XiaoNa Ren Zhen Shen Muhammad Jamil Changchun Ge Institute of Powder Metallurgy and Advanced Ceramics School of Material Science and Engineering University of Science and Technology Beijing State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of AutomationChinese Academy of Sciences College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and Astronautics

Digital light processing(DLP) 3D printing has a huge potential for manufacturing intricate and customized ceramic parts with high precision and cost-effectiveness. Research in this field contributes to material innovation,opening the avenues for new process designs in both scientific and industrial sectors. However, the implementation of DLP 3D printing technology in ceramic research has not yet reached the maturity level as that in polymer and tissue engineering. Necessarily, a holistic in-depth literature reporting the successful integration of alumina ceramics within DLP 3D printing technology is urgently needed. This review, systematic examines recent progress in DLP technology, focusing on photopolymer resins that incorporate UV-sensitive monomers, photoinitiators, and dispersants, as well as their synergistic effects on achieving high-quality printing, desirable material properties, and enhanced performance. Further, the review discusses key factors including post-processing characteristics such as debinding and sintering, which influence microstructure, and defect formation including microcracks, porosity and voids. Finally, the challenges associated with printing and sintering are highlighted,aiming to identify focused focused development pathways and potential solution to optimize outcomes. This analysis clarifies existing challenges and also propsoes future applications for DLP technology in the aluminaceramic field.

关键词： Al2O3 ceramics Applications Digital light processing (DLP) Post-processing Resin

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Random Pretraining With Prototypes for Reinforcement Learning

引用

IEEE Transactions on systems, Man, and Cybernetics: systems 2025年第5期55卷 3601-3613页

作者： Liu, Xin Chen, Yaran Li, Haoran Li, Boyu Zhao, Dongbin Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Xi'an Jiaotong-Liverpool University Department of Intelligent Science Suzhou215000 China Beijing Academy of Artificial Intelligence Multimodal Interaction Research Center Beijing100084 China

Unsupervised cross-domain reinforcement learning (RL) pretraining shows great potential for challenging continuous visual control but poses a big challenge. In this article, we propose cross-domain random pretraining with prototypes (CRPTpro), a novel, efficient, and effective self-supervised cross-domain RL pretraining framework. CRPTpro decouples data sampling from encoder pretraining, proposing decoupled random collection to easily and quickly generate a qualified cross-domain pretraining dataset. Moreover, a novel prototypical self-supervised algorithm is proposed to pretrain an effective visual encoder that is generic across different domains. Without finetuning, the cross-domain encoder can be implemented for challenging downstream tasks defined in different domains, either seen or unseen. Compared with recent advanced methods, CRPTpro achieves better performance on downstream policy learning without extra training on exploration agents for data collection, greatly reducing the burden of pretraining. We conduct extensive experiments across multiple challenging continuous visual-control domains, including balance control, robot locomotion, and manipulation. CRPTpro significantly outperforms the next best Proto-RL(C) on 11/12 cross-domain downstream tasks with only 54.5% wall-clock pretraining time, exhibiting state-of-the-art pretraining performance with greatly improved pretraining efficiency. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Recognition and Early Warning of Ride-hailing Vehicle Aggregation Based on Multi-Source Spatiotemporal Data Fusion

Recognition and Early Warning of Ride-hailing Vehicle Aggreg...

引用

2025 Australian and New Zealand Control Conference, ANZCC 2025

作者： Wu, Yue Zhong, Yuan Yu, Haitao Wang, Jiong Yan, Huaimin Wang, Jingcheng Dai, Xingyuan Zhao, Hongxia Lv, Yisheng Beijing Intelligent Transportation Development Center China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China

ISBN: (纸本)9798331532192

This paper proposes a deep learning-based hierarchical warning method designed to detect and respond to abnormal ride-hailing vehicle clustering. By integrating previously developed traffic forecasting and anomaly detection techniques, the method can differentiate varying degrees of clustering severity and trigger appropriate actions. The proposed approach fuses multi-source traffic data, utilizing a convolution-based spatio-temporal feature extraction module to predict ride-hailing vehicle arrival times, and implements a hierarchical warning system based on predefined thresholds. Validation results show that the proposed method can assess the difference between predicted and actual arrival times to evaluate the model’s confidence. On a real historical dataset from beijing, significant deviations were used to identify abnormal ride-hailing behavior, achieving accurate graded warnings. © 2025 IEEE.

关键词： Data fusion

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：