检索结果-内蒙古大学图书馆

SpaGRA:Graph augmentation facilitates domain identification for spatially resolved transcriptomics

Journal of Genetics and Genomics 2025年第1期52卷 93-104页

作者： Xue Sun Wei Zhang Wenrui Li Na Yu Daoliang Zhang Qi Zou Qiongye Dong Xianglin Zhang Zhiping Liu Zhiyuan Yuan Rui Gao Center of Intelligent Medicine School of Control Science and EngineeringShandong UniversityJinanShandong 250061China MOE Key Lab of Bioinformatics and Bioinformatics Division of BNRIST Department of AutomationTsinghua UniversityBeijing 100084China Institute of Precision Medicine Peking University Shenzhen HospitalShenzhenGuangdong 518036China Department of Clinical Laboratory The Second HospitalCheeloo College of MedicineShandong UniversityJinanShandong 250033China Institute of Science and Technology for Brain-Inspired Intelligence Center for Medical Research and InnovationShanghai Pudong HospitalFudan University Pudong Medical CenterFudan UniversityShanghai 200433China

Recent advances in spatially resolved transcriptomics(SRT)have provided new opportunities for characterizing spatial structures of various ***-based geometric deep learning has gained widespread adoption for spatial domain identification ***,most methods define adjacency relation between cells or spots by their spatial distance in SRT data,which overlooks key biological interactions like gene expression similarities,and leads to inaccuracies in spatial domain *** tackle this challenge,we propose a novel method,SpaGRA(https://***/sunxue-yy/SpaGRA),for automatic multi-relationship construction based on graph *** uses spatial distance as prior knowledge and dynamically adjusts edge weights with multi-head graph attention networks(GATs).This helps SpaGRA to uncover diverse node relationships and enhance message passing in geometric contrastive ***,SpaGRA uses these multi-view relationships to construct negative samples,addressing sampling bias posed by random *** results show that SpaGRA presents superior domain identification performance on multiple datasets generated from different *** SpaGRA,we analyze the functional regions in the mouse hypothalamus,identify key genes related to heart development in mouse embryos,and observe cancer-associated fibroblasts enveloping cancer cells in the latest Visium HD ***,SpaGRA can effectively characterize spatial structures across diverse SRT datasets.

关键词： Spatial domain identification Spatially resolved transcriptomics Multi-head graph attention networks Graph augmentation Geometric contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Combined Nonlinear control of Non-Affine MIMO system with Input and State Delays 5

Combined Nonlinear Control of Non-Affine MIMO System with In...

引用

5th International Scientific and Technical Conference on Mechanical Science and Technology Update, MSTU 2021

作者： Eremin, E.L. Nikiforova, L.V. Shelenok, E.A. Information and Control Systems Department Amur State University Blagoveshchensk Russia Automation and System Engineering Department Pacific National University Khabarovsk Russia

The article studies algorithms synthesis of a multiply connected system for controlling non-affine plants, the state variables of which are not available for direct measurement. It is shown that the decentralized control law constructed on the basis of the hyperstability criterion eliminates the influence of non-linearities and compensates external and parametric perturbations in the tracking multiply connected system with the required accuracy. © Published under licence by IOP Publishing Ltd.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Combined Nonlinear control Algorithm for Structural Undefined Non-Affine Input Delayed Plant

Combined Nonlinear Control Algorithm for Structural Undefine...

引用

2021 International Russian automation Conference, RusAutoCon 2021

作者： Eremin, E.L. Nikiforova, L.V. Shelenok, E.A. Amur State University Information and Control Systems Department Blagoveshchensk Russia Pacific National University Automation and System Engineering Department Khabarovsk Russia

ISBN: (纸本)9780738131566

The article is devoted to solving the problem of the combined control law synthesis for one class of non-affine plants with a delay in the input variable. The considered plant operates under conditions of a priori parametric and structural uncertainties in the presence of permanent external noise. Only the scalar plant output is available for direct measurement. The structure of the control system includes a reference predictor and dynamic filter-corrector. The synthesis of the combined regulator is based on the use of the hyperstability criterion, and the required operation quality of the obtained system is ensured at the stage of simulation. © 2021 IEEE.

关键词： Uncertainty Regulators automation Input variables Heuristic algorithms Filtering algorithms control systems

来源：评论

学校读者我要写书评

暂无评论

Virtually coupled train set control subject to space-time separation:A distributed economic MPC approach with emergency braking configuration

引用

High-Speed Railway 2024年第3期2卷 143-152页

作者： Xiaolin Luo Tao Tang Le Wang Hongjie Liu State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong UniversityBeijing 100044China Department of Electrical and Computer Engineering University of CaliforniaRiversideCA 92521USA Beijing Zongheng Electro-Mechanical Technology Development Co. Ltd.Beijing 100081China School of Automation and Intelligence Beijing Jiaotong UniversityBeijing 100044China National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong UniversityBeijing 100044China

The emerging virtual coupling technology aims to operate multiple train units in a Virtually Coupled Train Set(VCTS)at a minimal but safe *** guarantee collision avoidance,the safety distance should be calculated using the state-of-the-art space-time separation principle that separates the Emergency Braking(EB)trajectories of two successive units during the whole EB *** this case,the minimal safety distance is usually numerically calculated without an analytic ***,the constrained VCTS control problem is hard to address with space-time separation,which is still a gap in the existing *** solve this problem,we propose a Distributed Economic Model Predictive control(DEMPC)approach with computation efficiency and theoretical ***,to alleviate the computation burden,we transform implicit safety constraints into explicitly linear ones,such that the optimal control problem in DEMPC is a quadratic programming problem that can be solved *** theoretical analysis,sufficient conditions are derived to guarantee the recursive feasibility and stability of DEMPC,employing compatibility constraints,tube techniques and terminal ingredient ***,we extend our approach with globally optimal and distributed online EB configuration methods to shorten the minimal distance among ***,experimental results demonstrate the performance and advantages of the proposed approaches.

关键词： Virtually coupled train set Space-time separation Economic model predictive control Distributed model predictive control Emergency braking configuration

来源：评论

学校读者我要写书评

暂无评论

ReFlow6D: Refraction-Guided Transparent Object 6D Pose Estimation via Intermediate Representation Learning

arXiv

引用

arXiv 2024年

作者： Gupta, Hrishikesh Thalhammer, Stefan Weibel, Jean-Baptiste Haberl, Alexander Vincze, Markus Vision for Robotics Laboratory Automation and Control Institute TU Wien Austria Industrial Engineering Department UAS Technikum Vienna TU Wien Austria

Transparent objects are ubiquitous in daily life, making their perception and robotics manipulation important. However, they present a major challenge due to their distinct refractive and reflective properties when it comes to accurately estimating the 6D pose. To solve this, we present ReFlow6D, a novel method for transparent object 6D pose estimation that harnesses the refractive-intermediate representation. Unlike conventional approaches, our method leverages a feature space impervious to changes in RGB image space and independent of depth information. Drawing inspiration from image matting, we model the deformation of the light path through transparent objects, yielding a unique object-specific intermediate representation guided by light refraction that is independent of the environment in which objects are observed. By integrating these intermediate features into the pose estimation network, we show that ReFlow6D achieves precise 6D pose estimation of transparent objects, using only RGB images as input. Our method further introduces a novel transparent object compositing loss, fostering the generation of superior refractive-intermediate features. Empirical evaluations show that our approach significantly outperforms state-of-the-art methods on TOD and Trans32K-6D datasets. Robot grasping experiments further demonstrate that ReFlow6D’s pose estimation accuracy effectively translates to real-world robotics task. The source code is available at: https://***/StoicGilgamesh/ReFlow6D and https://***/StoicGilgamesh/matting *** Codes 68T45 © 2024, CC BY-NC-SA.

关键词： Light refraction

来源：评论

学校读者我要写书评

暂无评论

Consistency Evaluation of IoT Smart Meter’s Metering Accuracy considering Ambient Temperature and Load Current

Consistency Evaluation of IoT Smart Meter’s Metering Accura...

引用

system Reliability and Safety engineering (SRSE), International Conference on

作者： Weiming Liu Cen Chen Zhifei Wang Xiaosheng Zhang Guofu Zhai Wei Zheng Department of Electrical Engineering & Automation Harbin Institute of Technology Harbin China Beijing Aerospace Automatic Control Institute Beijing China

The energy meter is a widely used digital-analog electronic system. However, metering accuracy is inevitably influenced by factors such as ambient temperature, load current, and component tolerance. This paper introduces a method utilizing digital twin models to analyze the consistency of metering accuracy in a new single-phase smart meter prototype. An electro-thermal coupling model incorporating a temperature compensation algorithm is established, and the metering accuracy is solved using a surrogate model. By employing the Monte Carlo method, a batch of product samples is generated to determine the impact of varying ambient temperature and load current conditions on the metering accuracy’s consistency within the maximum operating range. The results of this study provides a valuable foundation for robust design and reliability optimization of the energy meter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Developing a Window control Algorithm Based on Reinforcement Learning for Indoor PM2.5 Mitigation 5th

Developing a Window Control Algorithm Based on Reinforcement...

引用

5th International Conference on Building Energy and Environment, COBEE 2022

作者： An, Yuting Xia, Tongling You, Ruoyu Lai, Dayi Liu, Junjie Chen, Chun Department of Mechanical and Automation Engineering The Chinese University of Hong Kong China Department of Building Services Engineering The Hong Kong Polytechnic University China School of Design Shanghai Jiao Tong University Shanghai China Tianjin Key Lab of Indoor Air Environmental Quality Control School of Environmental Science and Engineering Tianjin University Tianjin China Shenzhen Research Institute The Chinese University of Hong Kong Shenzhen China

ISBN: (纸本)9789811998218

Smart control of window is a means of effectively reducing concentrations of indoor PM2.5 (particulate matter with aerodynamic diameter less than 2.5 μm) in naturally ventilated residential buildings without air cleaning devices. This study aimed to develop a reinforcement learning (RL) approach to automatically control window behavior in real time for mitigation of indoor PM2.5 pollution. The method trains the window controller using deep Q-network (DQN) in a specific apartment for a month. The trained controller can be employed to control window behavior to mitigate indoor PM2.5 in that apartment. The input data for the controller are the real-time indoor and outdoor PM2.5 concentrations with 1-min resolution. Simulation was conducted in a real apartment in Tianjin. The results show that, the RL algorithm reduced the average indoor PM2.5 concentration by 9.11% when compared with the I/O ratio algorithm and by 7.40% when compared with real window behavior. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

High-Entropy Oxide of (BiZrMoWCeLa)O2 as a Novel Catalyst for Vanadium Redox Flow Batteries

引用

ACS Applied Materials and Interfaces 2024年第8期16卷 10019-10032页

作者： Demeku, Aknachew Mebreku Kabtamu, Daniel Manaye Chen, Guan-Cheng Ou, Yun-Ting Huang, Zih-Jhong Hsu, Ning-Yih Ku, Hung-Hsien Wang, Yao-Ming Wang, Chen-Hao Department of Materials Science and Engineering National Taiwan University of Science and Technology Taipei106335 Taiwan Department of Chemistry Debre Berhan University Debre Berhan000000 Ethiopia Chemistry Division National Atomic Research Institute Taoyuan325207 Taiwan Maritime Innovation & Industry Promotion Department Metal Industries Research & Development Centre Kaohsiung811160 Taiwan Research Center National Cheng Kung University Tainan701401 Taiwan Center of Automation and Control National Taiwan University of Science and Technology Taipei106335 Taiwan

In this study, new fluorite high-entropy oxide (HEO), (BiZrMoWCeLa)O2, nanoparticles were produced using a surfactant-assisted hydrothermal technique followed by calcination and were used as novel catalytic materials for vanadium redox flow batteries (VRFBs). The HEO calcined at 750 °C (HEO-750) demonstrates superior electrocatalytic activity toward V3+/V2+ and VO2+/VO2+ redox couples compared to those of cells assembled with other samples. The charge-discharge tests further confirm that VRFBs using the HEO-750 catalyst demonstrate excellent Coulombic efficiency, voltage efficiency, and energy efficiency of 97.22, 87.47, and 85.04% at a current density of 80 mA cm-2 and 98.10, 74.76, and 73.34% at a higher current density of 160 mA cm-2, respectively. Moreover, with 500 charge-discharge cycles, there is no discernible degradation. These results are attributed to the calcination heat treatment, which induces the formation of a new single-phase fluorite structure, which facilitates the redox reactions of the vanadium redox couples. Furthermore, a high surface area, wettability, and plenty of oxygen vacancies can give more surface electroactive sites, improving the electrochemical performance, the charge transfer of the redox processes, and the stability of the VRFBs’ electrode. This is the first report on the development of fluorite structure HEO nanoparticles in VRFBs, and it opens the door to further research into other HEOs. © 2024 The Authors. Published by American Chemical Society.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers

ZS6D: Zero-shot 6D Object Pose Estimation using Vision Trans...

引用

IEEE International Conference on Robotics and automation (ICRA)

作者： Philipp Ausserlechner David Haberger Stefan Thalhammer Jean-Baptiste Weibel Markus Vincze Vision for Robotics Laboratory Automation and Control Institute TU Wien Austria Industrial Engineering Department University of Applied Sciences Technikum Vienna Austria

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

As robotic systems increasingly encounter complex and unconstrained real-world scenarios, there is a demand to recognize diverse objects. The state-of-the-art 6D object pose estimation methods rely on object-specific training and therefore do not generalize to unseen objects. Recent novel object pose estimation methods are solving this issue using task-specific fine-tuned CNNs for deep template matching. This adaptation for pose estimation still requires expensive data rendering and training procedures. MegaPose for example is trained on a dataset consisting of two million images showing 20,000 different objects to reach such generalization capabilities. To overcome this shortcoming we introduce ZS6D, for zero-shot novel object 6D pose estimation. Visual descriptors, extracted using pre-trained Vision Transformers (ViT), are used for matching rendered templates against query images of objects and for establishing local correspondences. These local correspondences enable deriving geometric correspondences and are used for estimating the object's 6D pose with RANSAC- based PnP. This approach showcases that the image descriptors extracted by pre-trained ViTs are well-suited to achieve a notable improvement over two state-of-the-art novel object 6D pose estimation methods, without the need for task-specific fine-tuning. Experiments are performed on LMO, YCBV, and TLESS. In comparison to MegaPose, we improve the Average Recall on all three datasets and compared to OSOP we improve on two datasets. The code is available at https://***/PhilippAuss/ZS6D.

关键词： Training Computer vision Visualization Codes Computational modeling Pose estimation Transformers

来源：评论

学校读者我要写书评

暂无评论

Light-Weight Low-Cost Drive control Modules Design and Mass Production Research in SAR Satellites

Light-Weight Low-Cost Drive Control Modules Design and Mass ...

引用

China International SAR Symposium (CISS)

作者： Pengfei Liu Xiaoyan Ma Jun Wang Weixin Qian Zhengkang Feng Department of Electrical Control Aerospace System Engineering Shanghai Shanghai China Department of Radar System Shanghai Aerospace Electronic Technology Institute Shanghai China

In order to adapt to the development trend of light-weight and low-cost SAR (Synthetic Aperture Radar) satellites, products of drive control modules, especially drive control modules of SAR antenna deployment mechanism and solar array, are required to be light-weight and low-cost. At the level of product design, the mechanical structure of light-weight drive control module and low-cost hardware circuit design are given. The design scheme mainly involves the electromechanical integration interface of the drive control module and the drive mechanism, and the protection and reinforcement of the industrial components of the hardware circuit. At the level of product production, firstly, the product is designed according to modularization. Secondly, a series of standard systems from production to test are established. Finally, automatic production lines and automatic testing equipment are used for mass production and testing of products. The above design and production optimization measures reduce the weight and cost of drive control module products. The light-weight and low-cost drive control modules is conducive to carrying more payloads on SAR satellites and networking between satellites.

关键词：

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：