检索结果-内蒙古大学图书馆

Multi-hop reasoning over sparse knowledge graphs with deep reinforcement learning

Expert systems with Applications 2025年 290卷

作者： Liu, Yiyang Fu, Lejun Fu, Yukai Wu, Tianxing Bai, Hongfei State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China College of Information Engineering Shenyang University of Chemical Technology Shenyang110142 China School of Computer Science and Engineering Southeast University Nanjing211189 China

In recent years, knowledge reasoning has demonstrated substantial progress in inferring missing information, effectively alleviating the limitations caused by the incompleteness of knowledge graphs (KGs). Dealing with entities that have sufficient paths between them, multi-hop reasoning methods have achieved notable success and demonstrated interpretability, but they still exhibit deficiencies when dealing with sparse KGs. To overcome the insufficiency of edges in sparse KGs and the absence of effective guidance in multi-hop reasoning methods, a hybrid multi-hop collaborative Multi-Agent Sparse Knowledge Graph Reasoning model (MASKGR) is proposed. Attention-based dynamic completion (ADC) and variable rule guidance(VRG) are used to enhance the reasoning capability of deep reinforcement learning (RL) in sparse KGs. ADC focuses on high-value relations based on attention weights and combines embedding-based methods to predict the tail entities of these relations, expanding the original action space and improving the exploration capability of agents. Moreover, VRG greatly improves the ability of MASKGR to use rule-guided agent learning by utilizing the variable rule ratio and the variable loss reshaping. ADC can be applied to both single-agent and multi-agent in other models, while VRG is specifically designed for multi-agent. Comprehensive experiments have been conducted on four datasets: FB15K-237-10 %, FB15K-237-50 %, NELL23K, and WD-singer. Specifically, MASKGR achieves relative improvements of 1.3 % in Mean Reciprocal Rank (MRR) and 1.1 % in the proportion of correct tail entity rankings in the top 3 (Hit@3) on the FB15K-237-10 %, 2.4 % in MRR and 1.3 % in Hit@3 on the NELL23K, and 2.7 % in MRR and 3.6 % in Hit@3 on the WD-singer. The results indicate that MASKGR outperforms state-of-the-art multi-hop reasoning models based on reinforcement learning. © 2025

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Influence of Sintered Conditions on Electrophysical Properties of the Ceramics Based on BeO with a Dopant of a TiO2Powder

Influence of Sintered Conditions on Electrophysical Properti...

引用

2022 Ural Symposium on Biomedical engineering, Radioelectronics and Information Technology, USBEREIT 2022

作者： Malkin, Alexander Kijko, Victor Mikhaylovskaya, Zoya Korotkov, Alexey Knyazev, Sergei Malkina, Sofia Petrova, Sofia Belova, Ksenia Pavlov, Alexander Ural Federal University Named after the First President of Russia B. N. Yeltsin Engineering School of Information Technologies Telecommunications and Control Systems Yekaterinburg Russia Department of Chemical Technology of Ceramics and Refractory Materials Ural Federal University Named after the First President of Russia B. N. Yeltsin Yekaterinburg Russia Zavaritsky Institute of Geology and Geochemistry Ural Br. of Ras Yekaterinburg Russia Institute of Metallurgy Ural Br. of Ras Yekaterinburg Russia Ural Federal University Named after the First President of Russia B. N. Yeltsin Yekaterinburg Russia Siberian Federal University Krasnoyarsk Russia

ISBN: (数字)9781665460927

ISBN: (纸本)9781665460927

The BeO-based ceramics with adding micro and nano-size powders of TiO2 have a number of unique properties such as a high specific thermal conductivity, high insertion loss values for an electromagnetic wave propagating through the material under research. All of these features of BeO-based ceramics give us the possibility to use this material for a high power load realization in the RF range. The investigation of the influence of the sintering temperature of ceramics on electrophysical properties of studying materials in the frequency range from 8 to 12 GHz has been presented in this article. The vector network analyzer R&S ZVA50 with a set of measuring equipment consisting of the waveguide transmission line WR90 standard and calibration kit for performing TRL calibration procedure has been used for performing measurement of electrodynamics properties of researching materials. Structural characteristics of BeO-based ceramic samples with the addition of TiO2 micro and nanopowders were investigated using scanning electron microscopy and differential thermal analysis. The density of research samples was defined by the hydrostatic weighing method. The comparison of ceramic samples with different sintering temperatures of ceramics 1550 0C and 1660 0C was presented in the article. The frequency dependences of the complex dielectric permittivity of studied samples are given. © 2022 IEEE.

关键词： Permittivity

来源：评论

学校读者我要写书评

暂无评论

A Parallel Framework for Scene Understanding

A Parallel Framework for Scene Understanding

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Wenwen Zhang Jiangong Wang Kunfeng Wang School of Software Engineering Xi'an Jiaotong University Xi'an China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China College of Information Science and Technology Beijing University of Chemical Technology Beijing China

Different related computer vision tasks make it possible to understand and analyze the scene totally. However, there is no useful framework combining different tasks for scene understanding. In this paper, we investigate the current state of scene understanding from different aspects relying on different computer vision tasks and propose an effective framework based on the theory of parallel vision to combine different tasks for scene understanding. With the maintained artificial scene throughout time from the proposed framework, we can understand the scene in an elegant way. To explain our proposed framework, a case study is given.

关键词： Computer vision Digital twin Conferences Task analysis

来源：评论

学校读者我要写书评

暂无评论

A liquid copper strategy for wafer-scale single-crystalline hexagonal boron nitride with tunable thickness

引用

Materials Today 2025年

作者： Xin Zhang Mingjin Dai You Wu Yunxia Hu Qinghe Wang Shuai Wang Huiming Shang Biying Tan Zhen Su Yanan Ding Kaihui Liu Yongqing Fu Jinzhong Wang PingAn Hu Dechang Jia Yu Zhou Linben Ling Xiaolei Chen MOE Key Laboratory of Micro-Systems and Micro-Structures Manufacturing Harbin Institute of Technology Harbin China School of Chemistry and Chemical Engineering Harbin Institute of Technology Harbin China School of Materials Science and Engineering Harbin Institute of Technology Harbin China School of Physics Peking University Beijing China School of Mechanical Engineering Xi’an Jiaotong University Xian Shanxi China Beijing Institute of Aerospace Control Devices Beijing China

Wafer-scale single-crystalline hexagonal boron nitride (h-BN) films can act as an excellent interface dielectric, and are highly desirable as an ideal platform for electronic devices. However, those practical applications require the controllable synthesis of single-crystalline h-BN multilayers over large area. Here, we demonstrate a wafer-scale growth approach that can realize precise thickness-tunable single-crystalline h-BN multilayer by using liquid copper as the catalytic substrate. The production of wafer-scale thickness-tunable single-crystalline h-BN multilayer is clearly evidenced by Transmission Electron Microscopy (TEM) and centimetre-scale characterization techniques of Low Energy Electron Diffraction (LEED). All evidences show that the h-BN films are produced via a self-collimation of circular grains combined with the process that subsequently created circular h-BN domains can be further nucleated, grown and finally coalesced into a new single crystalline layer on the surface of the previously formed h-BN layer. This liquid metal approach provides a feasible way to grow wafer-scale single-crystal directly, which facilitate the wide application of two-dimensional (2D) devices and synthesize of other vdW materials.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An inverse machine learning application for mixture product design

An inverse machine learning application for mixture product ...

引用

2019 AIChE Annual Meeting

作者： Mao, Haitao Lu, Wang Zhang, Lei Tula, Anjan K. Gani, Rafiqul Institute of Chemical Process Systems Engineering School of Chemical Engineering Dalian University of Technology Dalian116024 China College of Control Science and Engineering Zhejiang University Hangzhou China PSE for SPEED Skyttemosen 6 AllerodDK-3450 Denmark PSE for SPEED Bangkok Thailand

来源：评论

学校读者我要写书评

暂无评论

Introducing Digital controllers to Undergraduate Students using the TCLab Arduino Kit

引用

IFAC-PapersOnLine 2020年第2期53卷 17524-17529页

作者： P.B. de Moura Oliveira John D. Hedengren J.A. Rossiter INESC-TEC Department of Engineering University of Trás-os-Montes and Alto Douro (UTAD) Vila Real Portugal Department of Chemical Engineering Brigham Young University Provo UT USA Department of Automatic Control and Systems Engineering University of Sheffield S1 3JD UK

Many undergraduate engineering students have just a single introductory feedback control course in their study list. Often the curricula found in such courses is totally based on continuous time-domain classic control techniques. However, currently most control design techniques are implemented in digital machines. Thus, digital control concepts should be covered in introductory control courses. In this paper, the issue of how to implement and test digital industrial controllers is addressed. Teaching experiments based on the APMonitor temperature control lab (TCLab) are proposed. It will be shown that TCLab as an Arduino based portable kit, provides an excellent means to test digital controllers, as it is a compact and portable lab to be used by lecturers and students. While there are many low-cost and portable hardware options for teaching dynamics and control, a novel aspect of this paper is the digital control education methods that are validated with classroom experience, particularly with Biomedical and Bioengineering students. Preliminary results are presented.

关键词： On-off control PID control control engineering Education Arduino

来源：评论

学校读者我要写书评

暂无评论

The Role of Surface Termination in Halide Perovskites for Efficient Photocatalytic Synthesis

引用

Angewandte Chemie 2020年第31期132卷 13031-13037页

作者： Dong Y. Li K. Luo W. Zhu C. Guan H. Wang H. Wang L. Deng K. Zhou H. Xie H. Bai Y. Li Y. Chen Q. Experimental Center of Advanced Materials Beijing Key Laboratory of Nanophotonics and Ultrafine Optoelectronic Systems School of Materials Science and Engineering Beijing Institute of Technology Beijing 100081 China School of Chemistry and Chemical Engineering Southwest Petroleum University Chengdu 610500 China Key Laboratory of Agro-products Quality and Safety Control in Storage and Transport Process Ministry of Agriculture and Rural Affairs/Institute of Food Science and Technology Chinese Academy of Agricultural Sciences Beijing 100193 China Department of Materials Science and Engineering College of Engineering Peking University Beijing 100871 China School of Physics and Electronics Central South University Changsha Hunan 410083 China

Halide perovskites have received attention in the field of photocatalysis owing to their excellent optoelectronic properties. However, the semiconductor properties of halide perovskite surfaces and the influence on photocatalytic performance have not been systematically clarified. Now, the conversion of triose (such as 1,3-dihydroxyacetone (DHA)) is employed as a model reaction to explore the surface termination of MAPbI3. By rational design of the surface termination for MAPbI3, the production rate of butyl lactate is substantially improved to 7719 μg g−1 cat. h−1 under visible-light illumination. The MAI-terminated MAPbI3 surface governs the photocatalytic performance. Specially, MAI-terminated surface is susceptible to iodide oxidation, which thus promotes the exposure of PbII as active sites for this photocatalysis process. Moreover, MAI-termination induces a p-doping effect near the surface for MAPbI3, which facilitates carrier transport and thus photosynthesis. © 2020 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim

关键词： halide perovskite iodide vacancies photocatalysis surface termination triose

来源：评论

学校读者我要写书评

暂无评论

Blooming of insecticides from polyethylene mesh and film

引用

Transactions of the Royal Society of South Africa 2021年第2期76卷 127-136页

作者： Mapossa, António Benjamim Sibanda, Mthoko Mayibongwe Moyo, Dennis Kruger, Taneshka Focke, Walter Wilhelm Androsch, René Boldt, Regine Wesley-Smith, James Institute of Applied Materials Department of Chemical Engineering University of Pretoria Pretoria South Africa UP Institute for Sustainable Malaria Control MRC Collaborating Centre for Malaria Research School of Health Systems and Public Health University of Pretoria Pretoria South Africa Department of Chemistry University of Pretoria Pretoria South Africa Interdisciplinary Center for Transfer-oriented Research in Natural Sciences Martin Luther University Halle-Wittenberg Halle/Saale Germany Leibniz Institute of Polymer Research Dresden (IPF) Dresden Germany Sefako Makgatho Health Sciences University Ga-Rankuwa South Africa

Malaria remains a public health concern with vector control still the vital component of disease prevention, control, and elimination strategies. Recent years has seen a “stalling” in the progress made towards the reduction in the global malaria burden, highlighting the need to develop new, innovative, and safe alternative tools and delivery systems to achieve global malaria elimination. Interventions based on the use of indoor residual spraying (IRS) and long-life insecticidal bed nets (LLINs), i.e. insecticide-containing wall linings (IWLs), can contribute towards the reduction of malaria. Both LLINs and IWLs rely on the presence of insecticides on the fibre or filament surfaces. However, materials directly incorporating the insecticides into the polymer melt during extrusion, allows for effective killing of the mosquitoes when they come into contact with the surface of the material, only if there is insecticide present there. This means that the insecticide must migrate to the surface and precipitate there (bloom). Over time the internal concentration of insecticide will decay. This investigation was done using Fourier transform infrared spectroscopy (FTIR) in both the transmission and attenuated total reflection (ATR) modes to better understand the blooming of three World Health Organization-approved contact insecticides, i.e. alphacypermethrin, fipronil and chlorfenapyr, from mesh or film to better understand the likeliness of insecticides within the materials to migrate to the surface. Film-based samples were prepared in addition to wall lining mesh, because of their easier characterisation than the irregular shaped mesh filaments. FTIR, in ATR and in transmission modes, enabled the tracking of the migration of the three insecticides, over time to the surface of polyethylene mesh or film. This made it possible to estimate the apparent solubility of the insecticides in the polymer matrix. However, scanning electron microscopy (SEM) revealed that a portion of th

关键词： blooming insecticide malaria polyethylene wall-lining

来源：评论

学校读者我要写书评

暂无评论

一种改进的纯组分物性预测机器学习模型（英文）

引用

engineering 2024年第8期 61-73页

作者：曹欣羽贡铭 Anjan Tula 陈曦 Rafiqul Gani Venkat Venkatasubramanian State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Department of Physics Bard College at Simon's Rock PSE for SPEED Company Sustainable Energy and Environment Thrust The Hong Kong University of Science and Technology (Guangzhou) Department of Applied Sustainability Széchenyi István University Complex Resilient Intelligent Systems Laboratory Department of Chemical Engineering Columbia University

Information on the physicochemical properties of chemical species is an important prerequisite when performing tasks such as process design and product design. However, the lack of extensive data and high experimental costs hinder the development of prediction techniques for these properties. Moreover,accuracy and predictive capabilities still limit the scope and applicability of most property estimation methods. This paper proposes a new Gaussian process-based modeling framework that aims to manage a discrete and high-dimensional input space related to molecular structure representation with the group-contribution approach. A warping function is used to map discrete input into a continuous domain in order to adjust the correlation between different compounds. Prior selection techniques, including prior elicitation and prior predictive checking, are also applied during the building procedure to provide the model with more information from previous research findings. The framework is assessed using datasets of varying sizes for 20 pure component properties. For 18 out of the 20 pure component properties,the new models are found to give improved accuracy and predictive power in comparison with other published models, with and without machine learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gelatin filter capture-based high-throughput sequencing analysis of microbial diversity in haze particulate matter

引用

The Journal of Biomedical Research 2019年第6期33卷 414-421页

作者： Meiqing Sun Zhanlin Ding Hong Wang Guangping Yu Zhe Feng Bingzhi Li Penghui Li Wuqing District Center for Disease Control and Prevention Tianjin 301700China Key Laboratory of Systems Bioengineering(Ministry of Education) School of Chemical Engineering and TechnologyTianjin UniversityTianjin 300072China School of Environmental Science and Safety Engineering Tianjin University of TechnologyTianjin 300384China

Airborne particulate matter(PM),especially PM2.5,can be easily adsorbed by human respiratory *** roles in carrying pathogens for spreading epidemic diseases has attracted great ***,we developed a novel gelatin filter-based and culture-independent method for investigation of the microbial diversity in PM samples during a haze episode in Tianjin,*** method involves particle capture by gelatin filters,filter dissolution for DNA extraction,and high-throughput sequencing for analysis of the microbial diversity.A total of 584 operational taxonomic units(OTUs)of bacteria and 370 OTUs of fungi at the genus level were identified during hazy *** results showed that both bacterial and fungal diversities could be evaluated by this *** study provides a convenient strategy for investigation of microbial biodiversity in haze,facilitating accurate evaluation of airborne epidemic diseases.

关键词： airborne particulate matter gelatin filter pathogen high-throughput sequencing

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：