检索结果-内蒙古大学图书馆

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

作者： Noreen Anwar Gang Xiong Wanze Lu Peijun Ye Hongxia Zhao Qinglai Wei The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation and with The Cloud Computing Center Chinese Academy of Sciences China School of Artificial Intelligence and Automation Beijing University of Technology Beijing China

Cyber-physical social systems (CPSS) include cyberspace, physical space, and social space. Since the introduction of CPSS, human relationships with machinery and the physical world have altered as a new paradigm. Recent estimates indicate that approximately 60 percent of the world's population will live in cities by 2030. Large, dense cities can be highly productive, innovative, and very green per capita, hence ideal for our future. However, the huge influx of new people poses enormous challenges to their administrations. Smart cities are becoming a reality, therefore, to achieve higher efficiency, optimum use of resources, management and to strengthen several features of modern towns, several elements of modern cities are automated and integrated into Information and Communications Technology (ICT). Cities and infrastructure are growing all over the world, in providing end-users with increased performance, comfort, visibility and convenience, the Smart Cities concept is critical. This paper will discuss smart cities and the CPSS concept intensively with some of its key technologies, challenges, and further development by using CPSS.

关键词： Smart cities Digital twin Sociology Information and communication technology Security Resource management Statistics

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks with Gated Recurrent Connections

arXiv

引用

arXiv 2021年

作者： Wang, Jianfeng Hu, Xiaolin the Computer Science Department University of Oxford Oxfordshire United Kingdom the Institute for Artificial Intelligence the State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing100084 China

The convolutional neural network (CNN) has become a basic model for solving many computer vision problems. In recent years, a new class of CNNs, recurrent convolution neural network (RCNN), inspired by abundant recurrent connections in the visual systems of animals, was proposed. The critical element of RCNN is the recurrent convolutional layer (RCL), which incorporates recurrent connections between neurons in the standard convolutional layer. With increasing number of recurrent computations, the receptive fields (RFs) of neurons in RCL expand unboundedly, which is inconsistent with biological facts. We propose to modulate the RFs of neurons by introducing gates to the recurrent connections. The gates control the amount of context information inputting to the neurons and the neurons’ RFs therefore become adaptive. The resulting layer is called gated recurrent convolution layer (GRCL). Multiple GRCLs constitute a deep model called gated RCNN (GRCNN). The GRCNN was evaluated on several computer vision tasks including object recognition, scene text recognition and object detection, and obtained much better results than the RCNN. In addition, when combined with other adaptive RF techniques, the GRCNN demonstrated competitive performance to the state-of-the-art models on benchmark datasets for these tasks. The codes are released at https://***/Jianf-Wang/GRCNN. © 2021, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Feature Selection and Learning-Based Model for Uav Path Planning on Rough Terrains

SSRN

引用

SSRN 2022年

作者： Ali, Hub Xiong, Gang Husnain, Haider Muhammad Tamir, Tariku Sinshaw Dong, Xisong Shen, Zhen State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China Qingdao Academy of Intelligent Industries Qingdao266109 China Chengdu610054 China

Path planning and obstacle avoidance in 3D terrain have been identified as a monumental challenge for a UAV in a variety of autonomous missions, such as disaster management and search and rescue operations. In large terrain areas, it’s a key problem for traditional approaches to search within the point-cloud maps to find a global path for a UAV considering the flight safety, maneuverability, weather constraints, and fuel cost. Hence, this paper proposes a trajectory planning technique for global and local path planning of a fixed-wing UAV above 3D terrain under static and dynamic constraints. For global path generation, a novel Feature Selection and Learning-based Model (FSLM) has been introduced to select the features of a point-cloud map and transform them into the feature set. The feature set is utilized by an improved A* planner with an extensive search area to deliver an optimal global path. The global path is assumed as the UAV's reference waypoints. The motion of the UAV on reference waypoints is simplified with two coordinates (R, d), where R is the cumulative distance covered by the UAV along the reference waypoints and d is its offset distance from the reference line segment in time t. For any local collision, offset trajectories are generated along with reference waypoints to avoid collision. Cost functions have been added so that the best global and local path can be chosen, taking into account altitude, weather, and fuel constraints. The simulation results show the performance of this approach in various complex terrains by considering weather and dynamic constraints, and the results are also compared to other 3D UAV path planning techniques. © 2022, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Auto-MatRegressor材料性能自动预测器:解放材料机器学习"调参师"

引用

Science Bulletin 2023年第12期68卷 1259-1270,M0004页

作者：刘悦王双燕杨正伟 Maxim Avdeev 施思齐 School of Computer Engineering and Science Shanghai UniversityShanghai 200444China Shanghai Engineering Research Center of Intelligent Computing System Shanghai 200444China State Key Laboratory of Advanced Special Steel School of Materials Science and EngineeringShanghai UniversityShanghai 200444China Materials Genome Institute Shanghai UniversityShanghai 200444China Zhejiang Laboratory Hangzhou 311100China Australian Nuclear Science and Technology Organisation Sydney 2232Australia School of Chemistry The University of SydneySydney 2006Australia

机器学习因其能够快速、精准拟合数据的潜在模式而被广泛应用于材料构效关系研究。然而,材料科学家往往需要进行繁琐的模型选择及参数寻优才能构建出高精度预测模型,为了解放材料机器学习"调参师",本文研发了基于元学习的材... 详细信息

机器学习因其能够快速、精准拟合数据的潜在模式而被广泛应用于材料构效关系研究。然而,材料科学家往往需要进行繁琐的模型选择及参数寻优才能构建出高精度预测模型,为了解放材料机器学习"调参师",本文研发了基于元学习的材料性能自动预测器,采集了60份文献公开数据集与60份标准数据集,基于此训练18种常用回归算法并获得其预测性能,定义与计算了27个刻画数据集特点的元特征,以此构建了一份蕴含建模经验的元数据集;同时,创建了表征数据集所属材料类型的类别树,将其嵌入基于距离的元学习算法,进一步耦合贝叶斯优化算法,实现领域知识和元数据协同驱动下的自动算法推荐和模型参数确定,实验结果表明,材料科学家仅需为新材料性能预测任务提供数据集,便可利用该预测器高效地构建具有与文献报道相当或更高预测精度的机器学习模型.

关键词：机器学习贝叶斯优化算法预测器材料科学家元数据参数寻优预测性能材料性能

来源：评论

学校读者我要写书评

暂无评论

MACK: multimodal aligned conceptual knowledge for unpaired image-text matching 22

MACK: multimodal aligned conceptual knowledge for unpaired i...

引用

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Yan Huang Yuming Wang Yunan Zeng Liang Wang Center for Research on Intelligent Perception and Computing (CRIPAC) State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences (CASIA) School of Artificial Intelligence University of Chinese Academy of Sciences (UCAS) Chinese Academy of Sciences Artificial Intelligence Research (CAS-AIR)

ISBN: (纸本)9781713871088

Recently, the accuracy of image-text matching has been greatly improved by multimodal pretrained models, all of which are trained on millions or billions of paired images and texts. Different from them, this paper studies a new scenario as unpaired image-text matching, in which paired images and texts are assumed to be unavailable during model training. To deal with this, we propose a simple yet effective method namely Multimodal Aligned Conceptual Knowledge (MACK), which is inspired by the knowledge use in human brain. It can be directly used as general knowledge to correlate images and texts even without model training, or further fine-tuned based on unpaired images and texts to better generalize to certain datasets. In addition, we extend it as a re-ranking method, which can be easily combined with existing image-text matching models to substantially improve their performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs

Cross-Modality Time-Variant Relation Learning for Generating...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jingyi Wang Jinfa Huang Can Zhang Zhidong Deng Department of Computer Science Tsinghua University Beijing China School of Electronic and Computer Engineering Peking University China Department of Computer Science Beijing National Research Center for Information Science and Technology (BNRist) THUAI State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China

Dynamic scene graphs generated from video clips could help enhance the semantic visual understanding in a wide range of challenging tasks such as environmental perception, autonomous navigation, and task planning of self-driving vehicles and mobile robots. In the process of temporal and spatial modeling during dynamic scene graph generation, it is particularly intractable to learn time-variant relations in dynamic scene graphs among frames. In this paper, we propose a Time-variant Relation-aware TRansformer (TR 2 ), which aims to model the temporal change of relations in dynamic scene graphs. Explicitly, we leverage the difference of text embeddings of prompted sentences about relation labels as the supervision signal for relations. In this way, cross-modality feature guidance is realized for the learning of time-variant relations. Implicitly, we design a relation feature fusion module with a transformer and an additional message token that describes the difference between adjacent frames. Extensive experiments on the Action Genome dataset prove that our TR2 can effectively model the time-variant relations. TR2 significantly outperforms previous state-of-the-art methods under two different settings by 2.1 % and 2.6% respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Context-specific miRNA regulation network predicts cancer prognosis

Context-specific miRNA regulation network predicts cancer pr...

引用

IEEE International Conference on systems Biology

作者： Xionghui Zhou Juan Liu Changning Liu Simon Rayner Fengji Liang Jingfang Ju Yinghui Li Shanguang Chen Jianghui Xiong School of Computer Science Wuhan University Wuhan China Bioinformatics Research Group Key Laboratory of Intelligent Information Processing Advanced Computing Research Laboratory Institute of Computing Technology Chinese Academy of Sciences (CAS) Beijing China Bioinformatics Group State Key Laboratory of Virology Wuhan Institute of Virology Chinese Academy of Sciences (CAS) Wuhan China Bioinformatics Group and Data Coordination Center State Key Laboratory of Space Medicine Fundamentals and Application China Astronaut Research and Training Center Beijing China Department of Pathology Stony Brook University Medical Center New York USA

MicroRNAs can regulate hundreds of target genes and play a pivotal role in a broad range of biological process. However, relatively little is known about how these highly connected miRNAs-target networks are remodelled in the context of various diseases. Here we examine the dynamic alteration of context-specific miRNA regulation to determine whether modified microRNAs regulation on specific biological processes is a useful information source for predicting cancer prognosis. A new concept, Context-specific miRNA activity (CoMi activity) is introduced to describe the statistical difference between the expression level of a miRNA's target genes and non-targets genes within a given gene set (context).

关键词： Breast cancer Context Correlation Biological processes Metastasis Tumors

来源：评论

学校读者我要写书评

暂无评论

Text Semantic Analysis and intelligent Interaction in Parallel Dispatching systems for Technical Station

Text Semantic Analysis and Intelligent Interaction in Parall...

引用

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

作者： Yuantao Jiao Jian Wang Runmei Li Gang Xiong Shichao Chen School of Automation and Intelligence Beijing Jiaotong University Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China State Key Laboratory for Multimodal Artificial Intelligence Systems Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

Technical station dispatching system plays an important role in cargo operation, but due to the large number of dispatching systems and complex operation, dispatchers rely on manual experience to complete the task, and many scenarios cannot be applied in the real system. Therefore, this paper utilizes the data-driven form to establish a parallel dispatching system for technical stations, semantically analyzes text data rich in dispatcher experience, completes the Computational Experiments on the textual semantic data in the artificial dispatching system, and synchronizes the Parallel Execution of data interaction with the real dispatching system.

关键词： Training Analytical models Semantics Dispatching Digital twins Synchronization Feeds

来源：评论

学校读者我要写书评

暂无评论

An Actor-Critic Framework Deep Reinforcement Learning Approach to High-speed Train Timetable Rescheduling Problem

An Actor-Critic Framework Deep Reinforcement Learning Approa...

引用

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

作者： Zhilong Tian Runmei Li Gang Xiong Fenghua Zhu School of Automation and Intelligence Beijing Jiaotong University Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China State Key Laboratory for Multimodal Artificial Intelligence Systems Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

High-speed trains are inevitably affected by emergencies in their daily operation, which may cause the trains to fail to run according to the original planned timetable. Therefore, how to adjust the timetable of subsequent trains in emergencies is crucial for railway operations. This paper introduces a deep reinforcement learning algorithm based on an actor-critic network, which minimizes the total delay time by defining the departure order as an action. Numerical experiments are performed on the timetable of Beijing-Shanghai high-speed railway line.

关键词： Optimization models Deep reinforcement learning Rail transportation Dispatching Digital twins Delays Optimization

来源：评论

学校读者我要写书评

暂无评论

Neural piecewise-constant delay differential equations

arXiv

引用

arXiv 2022年

作者： Zhu, Qunxi Shen, Yifei Li, Dongsheng Lin, Wei Research Institute of Intelligent Complex Systems Fudan University China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong Microsoft Research Asia China School of Mathematical Sciences State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Institutes of Brain Science Shanghai Center for Mathematical Sciences Center for Computational Systems Biology LCNBI and Research Institute of Intelligent Complex Systems Fudan University China

Continuous-depth neural networks, such as the Neural Ordinary Differential Equations (ODEs), have aroused a great deal of interest from the communities of machine learning and data science in recent years, which bridge the connection between deep neural networks and dynamical systems. In this article, we introduce a new sort of continuous-depth neural network, called the Neural Piecewise-Constant Delay Differential Equations (PCDDEs). Here, unlike the recently proposed framework of the Neural Delay Differential Equations (DDEs), we transform the single delay into the piecewiseconstant delay(s). The Neural PCDDEs with such a transformation, on one hand, inherit the strength of universal approximating capability in Neural DDEs. On the other hand, the Neural PCDDEs, leveraging the contributions of the information from the multiple previous time steps, further promote the modeling capability without augmenting the network dimension. With such a promotion, we show that the Neural PCDDEs do outperform the several existing continuousdepth neural frameworks on the one-dimensional piecewiseconstant delay population dynamics and real-world datasets, including MNIST, CIFAR10, and *** Codes 34Kxx, 93Cxx, 92B2 © 2022, CC BY.

关键词： Ordinary differential equations

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：