检索结果-内蒙古大学图书馆

IEEE International Conference on e-Business engineering (ICEBE)

作者： Zhuorui Qin Xiaoqian Wu Yimin Zheng Qingyao Wu School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Shenzhen Bangqi Technology Intelligent Development Co. Ltd Shenzhen China Pazhou Lab Guangzhou China

Driven by the latest advances in industrial artificial intelligence, automatic guided vehicles (AGVs) have been widely used for material handling in flexible workshops. In the pursuit of agile and flexible production transportation planning, the ability to handle unpredictable and dynamic events is becoming increasingly important. In order to achieve this real-time dynamic control, this study proposes a distributed multi-agent architecture to solve the dynamic Multi-AGVs scheduling problem. Double Deep Q-Network algorithm is used to train the scheduling agent, capture the relationship between production transportation operation information and scheduling goals, and make real-time scheduling decisions for flexible jobs with constant arrival intervals. Specialized state, action, and reward representations are proposed to handle variable specifications of dynamic scheduling problems. The performance of this method under different scene scales was verified through simulation studies. Numerical results show that compared with existing traditional heuristic scheduling strategies, this method not only has superior performance, but also its advantages persist even if the manufacturing system job scale changes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

In-situ synthesized SiC/TiC/SiTiOC hybrid nanofiber mats for broad-range temperature microwave absorption

引用

Science China Technological Sciences 2025年第6期 183-196页

作者： Yashan HUO Yuetong QIAN Minshan ZHAO Lei ZHANG Yujia TAN Zhihui HE Peng MIAO Fuchun ZHANG Wei CUI Renchao CHE School of Physics and Electronic Information Yan'an University Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Laboratory of Advanced Materials Shanghai Key Lab of Molecular Catalysis and Innovative Materials Academy for Engineering &Technology Advanced Coatings Research Center of Ministry of Education of China Fudan University School of Materials and Chemical Engineering Xi'an Technological University School of Materials Science & Engineering Tongji University College of Physics Donghua University

Efficient, temperature-insensitive electromagnetic attenuation materials are critical for high microwave absorption at high temperatures. This study presents SiC/TiC/SiTiOC hybrid nanofiber mats constructed using an in-situ synthesis method;these mats incorporate SiC/TiC as the microwave loss unit and SiTiOC as the antioxidant unit, offering an innovative approach to high-temperature microwave absorption. The introduction of high-conductivity TiC not only optimizes the dielectric constant and impedance matching of the material but also enhances its thermal cycling stability. This design ensures steady electromagnetic attenuation, enabling the hybrid nanofiber mats to maintain robust absorption performance in the X-band, even at high temperatures. At 873 K, the material demonstrates an effective absorption bandwidth of 3.6 GHz and a minimum reflection loss of-45.55 dB. Compared to single-system absorbers, such as SiC/C nanofiber materials, with a single system, the multicomponent SiC/TiC/SiTiOC hybrid nanofiber mats deliver reliable absorption performance in the temperature range of 293–873 K. This study confirms that highly conductive titanium-based ceramic materials used for dielectric property regulation effectively address the challenges of poor temperature stability and limited reusability in high-temperature carbon-ceramic absorbing materials, providing valuable insights and guidance for designing efficient microwave absorbers that can operate across a wide temperature range.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video

arXiv

引用

arXiv 2023年

作者： Xu, Zenan Meng, Xiaojun Wang, Yasheng Su, Qinliang Qiu, Zexuan Jiang, Xin Liu, Qun School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Noah’s Ark Lab Huawei Technologie The Chinese University of Hong Kong Hong Kong Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Multimodal abstractive summarization for videos (MAS) requires generating a concise textual summary to describe the highlights of a video according to multimodal resources, in our case, the video content and its transcript. Inspired by the success of the large-scale generative pre-trained language model (GPLM) in generating high-quality textual content (e.g., summary), recent MAS methods have proposed to adapt the GPLM to this task by equipping it with the visual information, which is often obtained through a general-purpose visual feature extractor. However, the generally extracted visual features may overlook some summary-worthy visual information, which impedes model performance. In this work, we propose a novel approach to learning the summary-worthy visual representation that facilitates abstractive summarization. Our method exploits the summary-worthy information from both the cross-modal transcript data and the knowledge that distills from the pseudo summary. Extensive experiments on three public multimodal datasets show that our method outperforms all competing baselines. Furthermore, with the advantages of summary-worthy visual information, our model can have a significant improvement on small datasets or even datasets with limited training data. Copyright © 2023, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Environment-aware dynamic graph learning for out-of-distribution generalization 23

Environment-aware dynamic graph learning for out-of-distribu...

引用

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

作者： Haonan Yuan Qingyun Sun Xingcheng Fu Ziwei Zhang Cheng Ji Hao Peng Jianxin Li Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University and School of Computer Science and Engineering Beihang University Key Lab of Education Blockchain and Intelligent Technology Guangxi Normal University Department of Computer Science and Technology Tsinghua University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribution shifts, which are common in real-world scenarios. As the generation of dynamic graphs is heavily influenced by latent environments, investigating their impacts on the out-of-distribution (OOD) generalization is critical. However, it remains unexplored with the following two major challenges: (1) How to properly model and infer the complex environments on dynamic graphs with distribution shifts? (2) How to discover invariant patterns given inferred spatio-temporal environments? To solve these challenges, we propose a novel Environment-Aware dynamic Graph LEarning (EAGLE) framework for OOD generalization by modeling complex coupled environments and exploiting spatiotemporal invariant patterns. Specifically, we first design the environment-aware EADGNN to model environments by multi-channel environments disentangling. Then, we propose an environment instantiation mechanism for environment diversification with inferred distributions. Finally, we discriminate spatio-temporal invariant patterns for out-of-distribution prediction by the invariant pattern recognition mechanism and perform fine-grained causal interventions node-wisely with a mixture of instantiated environment samples. Experiments on real-world and synthetic dynamic graph datasets demonstrate the superiority of our method against state-of-the-art baselines under distribution shifts. To the best of our knowledge, we are the first to study OOD generalization on dynamic graphs from the environment learning perspective.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Band Compatible Camouflage Enabled by Phase Transition Modulation of Flexible Gst Films

SSRN

引用

SSRN 2024年

作者： Wang, Jian Wu, Zuoxu Sun, Xiaoyu Tang, Zunqian Wang, Chong Yu, Fangyuan Zhao, Zirui Mao, Jun Zhang, Qian Cao, Feng School of Science Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information System Harbin Institute of Technology Shenzhen518055 China School of Materials Science and Engineering Institute of Materials Genome & Big Data Harbin Institute of Technology Shenzhen518055 China State Key Laboratory of Advanced Welding and Joining China Fuzhou University China

With the rapid development of detection technology, there is an urgent need for multi-band compatible camouflage technology, particularly in the visible-infrared band. However, the conflicting requirements between camouflage across different bands and surface thermal management pose significant challenges in achieving synchronized control for multiple bands in diverse application environments and targets. Herein, we propose a spectrally selective emitter leveraging phase-change modulation of Ge2Sb2Te5, capable of achieving effective camouflage in both the visible band and two atmospheric windows over a wide temperature range. The designed emitters exhibit colorful appearances, compatible with various background environments, thereby ensuring the visible camouflage. Meanwhile, the emitters demonstrate low emissivity values of 0.1 in the MWIR band and 0.08 in the LWIR band, effectively reducing the infrared emission through atmospheric *** radiative temperatures of the optimized emitters in the MWIR and LWIR bands are reduced by 105 °C and 140 °C relative to the target surface (200 °C), respectively, providing excellent radiative suppression compared to similar studies. Remarkably, the designed emitter still demonstrates robust flexibility, making it suitable for a variety of targets with complex curved surfaces. This work paves the way for designing the flexible visible-infrared compatible camouflage coatings with integrated thermal management functionality. © 2024, The Authors. All rights reserved.

关键词： Germanium alloys

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Multi-kernel Graph Learning for Autism Prediction and Biomarker Discovery

arXiv

引用

arXiv 2023年

作者： Liu, Jin Mao, Junbin Lin, Hanhe Kuang, Hulin Pan, Shirui Wu, Xusheng Xie, Shan Liu, Fei Pan, Yi Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi830000 China Hunan Province Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Science and Engineering University of Dundee DundeeDD1 4HN United Kingdom School of Information and Communication Technology Griffith University Gold CoastQLD4215 Australia Shenzhen Health Development Research and Data Management Center Shenzhen518109 China

Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal integration and heterogeneous information extractions from graphs, we propose a novel method called Multi-modal Multi-Kernel Graph Learning (MMKGL). To solve the problem of negative impact among modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology. The source code will be available at https://***/yutian0315/MMKGL. © 2023, CC BY-NC-ND.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Search, Estimate, and Predict: Efficient Weakly-Supervised Learning

Search, Estimate, and Predict: Efficient Weakly-Supervised L...

引用

IEEE International Conference on Electrical engineering and Photonics (EExPolytech)

作者： Bokuan Yang Jinghai Cao Jessie Wu Yuanqi Wu Jie Zhang Changyong Pan Beijing Smart-Chip Microelectronics Technology Co. Ltd Beijing China Department of Electronic Engineering Tsinghua University Beijing China Physics and Data Science University of Toronto Toronto Canada National Key Lab Adv Vehicle Control FAW Grp Co. Ltd Changchun China

ISBN: (数字)9798350388879

ISBN: (纸本)9798350388886

Most of state-of-the-arts region-based detectors are suffered from the requirement of training for a large volume of bounding box annotated data. In this paper, we propose an innovative weakly-supervised architecture, namely SEP-Net, that employs an efficient proposal searching method on feature maps to generate region proposals via transforming CNN classifiers to object detectors without bounding box annotations. We further show the proposed framework can be used for real-time detection, in which high computation efficiency is a prerequisite. Moreover, the training procedure is exactly the same as what’s for CNN classifiers, so is easy to transfer a pre-trained CNN to our weakly-supervised detector as well. Experimental validation on ImageNet 2012 dataset show that the novel model outperforms classical and most recent state-of-the-art weakly-supervised method by a wide margin in terms of both accuracy and efficiency.

关键词： Training Location awareness Learning systems Accuracy Training data Detectors Search problems Real-time systems Proposals Photonics

来源：评论

学校读者我要写书评

暂无评论

Learning Target-aware Representation for Visual Tracking via Informative Interactions

arXiv

引用

arXiv 2022年

作者： Guo, Mingzhe Zhang, Zhipeng Fan, Heng Jing, Liping Lyu, Yilin Li, Bing Hu, Weiming Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China China Department of Computer Science and Engineering University of North Texas DentonTX United States

We introduce a novel backbone architecture to improve target-perception ability of feature representation for tracking. Specifically, having observed that de facto frameworks perform feature matching simply using the outputs from backbone for target localization, there is no direct feedback from the matching module to the backbone network, especially the shallow layers. More concretely, only the matching module can directly access the target information (in the reference frame), while the representation learning of candidate frame is blind to the reference target. As a consequence, the accumulation effect of target-irrelevant interference in the shallow stages may degrade the feature quality of deeper layers. In this paper, we approach the problem from a different angle by conducting multiple branch-wise interactions inside the Siamese-like backbone networks (InBN). At the core of InBN is a general interaction modeler (GIM) that injects the prior knowledge of reference image to different stages of the backbone network, leading to better target-perception and robust distractor-resistance of candidate feature representation with negligible computation cost. The proposed GIM module and InBN mechanism are general and applicable to different backbone types including CNN and Transformer for improvements, as evidenced by our extensive experiments on multiple benchmarks. In particular, the CNN version (based on SiamCAR) improves the baseline with 3.2/6.9 absolute gains of SUC on LaSOT/TNL2K, respectively. The Transformer version obtains SUC scores of 65.7/52.0 on LaSOT/TNL2K, which are on par with recent state of the arts. Code and models will be released. Copyright © 2022, The Authors. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A Causality Network Construction Method for High Dimensional Time Series Big data 5

A Causality Network Construction Method for High Dimensional...

引用

5th International Conference on data Science and Information Technology, DSIT 2022

作者： Jing, Yi Liu, Zhenyu Gao, Jing Li, Tao Inner Mongolia Agricultural University Inner Mongolia Autonomous Reg. Key Lab. of Big Data Res. and Applic. for Agric. and Animal Husbandry Hohhot China The University of New Sales Wales The Faculty of Science Sydney Australia College of Computer and Information Engineering College of Life Sciences Inner Mongolia Agricultural University Hohhot China

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

How to infer the causal relationship between variables in high-dimensional time series data and construct the causal network have always been a difficulty of research. The two major challenges are dimension reduction and causal inference. This paper proposes a causality network construction method for high-dimensional sequential big data. In this method, the dimensionality of feature variables is reduced by fuzzy C-means clustering twice and feature variables with similar and specific patterns are screened out. Then transfer entropy is used to infer causal relationships among variables and construct the time-series data network of causal relationships among variables. The proposed method was applied to a high-dimensional time-series data set which contains 32884 rats' gene expression values at 480 time points to infer the causal regulatory relationships among the genes, and efficiently construct the regulatory network of rats' rhythm genes. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

data Governance: Status, Technologies, Applications and Development Trends 8

Data Governance: Status, Technologies, Applications and Deve...

引用

8th International Conference on data Science in Cyberspace, DSC 2023

作者： Zhu, Haiyang Chen, Xiaofeng Li, Suyan Wang, Yejin Fang, Xinwei Zhu, Minfeng Zhejiang University Wuchan Zhongda Digital Technology Co. Ltd. The State Key Lab of Cad&cg Hangzhou China Zhejiang University Hangzhou Qulian Technology Co. Ltd. The State Key Laboratory of Blockchain and Data Security Hangzhou China Zhejiang Institute of Mechanical & Electrical Engineering Hangzhou China Wuchan Zhongda Digital Technology Co. Ltd. Hangzhou China School of Medicine Zhejiang University Sir Run Run Shaw Hospital Department of Internet and Artificial Intelligence Hangzhou China Zhejiang University Hangzhou China

ISBN: (纸本)9798350331035

data governance involves legal, policy, technologies, and standards measures to ensure security, accuracy, integrity, consistency, and accessibility of data, with the primary objective of unlocking its latent value. In this context, the study initiates by scrutinizing the present status of data governance, subsequently identifying pivotal challenges through the lens of computer sciences. Moreover, to effectively grapple with the intricacies of high-dimensional data, data incompletion, and data redundancy within the realm of data governance, we present a compendium of data governance technology methodologies, encompassing data dimensionality reduction, data imputation, data deduplication, and data visualization. Further enhancing our discourse, we shed light on the typical scenarios of large-scale supply chain enterprises, elucidating data analysis and data intelligence applications. The convergence of these insights seeks to provide a comprehensive overview both data governance technology research and real-world application. © 2023 IEEE.

关键词： Blockchain data Deduplication data Dimensionality Reduction data Governance data imputation data Intelligence

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：