检索结果-内蒙古大学图书馆

第35届中国控制与决策会议

作者： Lin Qiao Yuanqi Yu Qun Wang Yu Zhang Yueming Song Xiaosheng Yu Department Information Communication Branch of State Grid Liaoning Electric Power Co. Ltd. Department Information Communication Branch of State Grid Liaoning Electric Power Co. Ltd Faculty of Robot Science and Engineering Northeastern University

The accurate prediction of time series data in the industrial production process can provide important guidance for the scheduling and decision-making of industrial systems,and is also an important part of predictive control *** this paper,a time series prediction model which introduces the graph neural network(GCN) is *** model mainly consists of a time series feature extraction module and a relational modeling *** the time series feature extraction module,the Att-LSTM model is proposed to extract the feature information of time series *** the relational modeling module,a novel M-GCN network is proposed to model the relevance among different time series *** addition,based on the time series prediction model,a time series multiclassification model is also *** proposed model can predict the energy consumption conditions of the data center *** experimental results demonstrate that the propose model can provide a desirable performance superior to some traditional models in accuracy and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ikcs: An Effective Intelligent K-Medoids Clustering Scheme Based on Granularity Rough Entropy for Social Networks

SSRN

引用

SSRN 2024年

作者： Chen, Linshu Chen, Panyu Chen, Yuxiang Xiong, Neal Naixue Woźniak, Marcin Liang, Wei School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Department of Mathematics and Computer Science Northeastern State University OK United States Faculty of Applied Mathematics Silesian University of Technology Kaszubska 23 Gliwice44100 Poland

The k-Medoids clustering algorithm is one of the commonly used clustering methods, but it does not consider the weight of each attribute which lead to different impacts on clustering results. Granular computing characterizes given knowledge from different perspectives while considering the granularity and completeness of the given knowledge, thus determining which feature has the greatest impact on the results in clustering problems, which helps to focus on important features. Therefore, this paper proposes an effective Intelligent k-Medoids Clustering Scheme based on granularity rough entropy for social networks (IKCS). Specifically, the granularity rough entropy is firstly defined based on indistinguishable relationships and roughness. Secondly, attribute weight coefficients are introduced to define the similarity function between samples. Finally, the samples are clustered based on the similarity function mentioned above, and the original cluster centers are initialized through k remote cluster centers. The experimental results on the artificial and UCI datasets effectively prove the validity of the proposed IKCS. As a result, it achieves the average Accuracy of Clustering 5.36% higher than the PAM and 4.16% higher than the fast k-Medoids. Moreover, it exhibits excellence in both the clustering Sum of Squared Errors and Adjusted Rand Index. © 2024, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Face Liveness Detection Algorithm based on Livenesslight Network

Face Liveness Detection Algorithm based on Livenesslight Net...

引用

2020 International Conference on High Performance Big Data and Intelligent Systems, HPBD and IS 2020

作者： Zuo, Yinlong Gao, Wenlong Wang, Jintao Faculty of Robot Science and Engineering Northeastern University Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781728165110

Face liveness detection is the first stage of the whole face detection technology, and it is of great significance to the system security using face recognition technology. In this paper we use convolutional neural networks to extract facial features. Compared to ResNet, SqueezeNet and VGG Face networks, the network structure is lighter and the model training takes less time. After testing, it achieved an accuracy of 99.5% on the Nanjing university of Aeronautics and Astronautics (NUAA) face detection data set of China Southern Airlines. In order to improve the robustness of the model, we built our own dataset through collecting pictures from internet and camera shooting, and horizontally compared the accuracy of the above several models on the self-built dataset. Finally the model proposed in this paper achieved the highest 99.02% accuracy and achieved the best results in actual testing. © 2020 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Experimental and MD simulation of 3-dodecyloxypropanamine and 3-tetradecyloxypropylamine adsorbed onto quartz(101) surface

引用

International Journal of Mining science and Technology 2021年第6期31卷 1033-1042页

作者： Zhouyueyang Cheng Yimin Zhu Yanjun Li Stephen Butt a College of Resource and Civil Engineering Northeastern UniversityShenyang 110819China b National-Local Joint Engineering Research Center of Refractory Iron Ore Resources Efficient Utilization Technology Shenyang 110819China c Faculty of Engineering and Applied Science Memorial University of NewfoundlandSt.John’s A1C 5S7Canada

In this paper,two surfactants,3-dodecyloxypropanamine(DOPA) and 3-tetradecyloxypropylamine(TOPA),were synthesized and used as collectors in the quartz micro-flotation in the *** tests,FT-IR,XPS measurements,and ab initio Molecular Dynamics(MD) simulations were conducted to research DOPA,TOPA,and dodecylamine(DDA)'s adsorption mechanisms onto quartz(101)*** results of micro-flotation show that the adsorption of DOPA and TOPA onto quartz surface is more robust than that of *** zeta-potential result shows that the DOPA/TOPA was adsorbed on quartz through electrostatic ***,MD simulation adsorption models were built to compare the computational properties of the three surfactants,such as the radial distribution function,and the interaction energies between the collectors and the quartz cleavage *** interaction energies of surfactants(RNH_(3)^(+) or RNH_(2)) on the quartz surface explained why the pH range of DOPA/TOPA is wider than that of *** analyses and MD simulations confirmed that DOPA bonded with the(101) surface of quartz through three types of hydrogen bonds between the-NH_(2) of DOPA and the O atom of *** hydrogen bonds of type A and type C were the most likely type and more potent than those of type B.

关键词： Quartz(101)surface Flotation Molecular dynamics 3-Dodecyloxypropanamine Adsorption

来源：评论

学校读者我要写书评

暂无评论

Modeling and reliability characterization of micro-coil springs for ceramic grid array integrated circuits

Modeling and reliability characterization of micro-coil spri...

引用

International Conference on (ICEPT) Electronic Packaging Technology

作者： Minghua Zhang Qi An Jingming Fei Jianghao Yu Hailong Li Ping Wu Xiaomin Li Hefeng Zhang Beijing Spacecraft China Academy of Space Technology Beijing China School of Materials Science and Engineering Tianjin University Tianjin China Faculty of Science Tianjin University Tianjin China Mechanical Engineering Northeastern University at Qinhuangdao Qinhuangdao China

Micro-coil spring is a new technology for large-scale integrated circuit interconnection to replace traditional solder columns due to its ability to absorb the mechanical stress generated by external vibration and withstand the shear force caused by CTE mismatch. In this paper, the simulation platform was built to predict the thermal fatigue life, durable vibration capacity and high impact life of the solder joints of MCS interconnected structures, respectively. In the thermal cycling process, flexible micro-springs bear the lateral displacement, which effectively alleviated the thermal mismatch problem. In addition, longitudinal cracks of the solder joints of micro-springs were generated by S11. Based on the Darveaux model, the thermal cycling life of the micro-spring board-level interconnect was predicted to be 9934 cycles. The vibration fatigue simulation results showed that the RMISES were 4.969MPa and 3.629MPa for the MCS and solder, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamical Audio-Visual Navigation: Catching Unheard Moving Sound Sources in Unmapped 3D Environments

arXiv

引用

arXiv 2022年

作者： Younes, Abdelrahman Albert-Ludwigs-University Freiburg Faculty of Engineering Department of Computer Science Robot Learning Lab Germany

Recent work on audio-visual navigation targets a single static sound in noise-free audio environments and struggles to generalize to unheard sounds. We introduce the novel dynamic audio-visual navigation benchmark in which an embodied AI agent must catch a moving sound source in an unmapped environment in the presence of distractors and noisy sounds. We propose an end-to-end reinforcement learning approach that relies on a multi-modal architecture that fuses the spatial audio-visual information from a binaural audio signal and spatial occupancy maps to encode the features needed to learn a robust navigation policy for our new complex task settings. We demonstrate that our approach outperforms the current state-of-the-art with better generalization to unheard sounds and better robustness to noisy scenarios on the two challenging 3D scanned real-world datasets Replica and Matterport3D, for the static and dynamic audio-visual navigation benchmarks. Our novel benchmark will be made available at http://***. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fast Swarming of UAVs in GNSS-denied Feature-poor Environments without Explicit Communication

arXiv

引用

arXiv 2024年

作者： Horyna, Jiří Krátký, Vít Pritzl, Václav Báča, Tomáš Ferrante, Eliseo Saska, Martin Multi-Robot Systems Group Faculty of Electrical Engineering Czech Technical University in Prague Technicka 2 Prague Czech Republic Department of Computer Science Vrije Universiteit Amsterdam Amsterdam Netherlands

A decentralized swarm approach for the fast cooperative flight of Unmanned Aerial Vehicles (UAVs) in feature-poor environments without any external localization and communication is introduced in this paper. A novel model of a UAV neighborhood is proposed to achieve robust onboard mutual perception and flocking state feedback control, which is designed to decrease the inter-agent oscillations common in standard reactive swarm models employed in fast collective motion. The novel swarming methodology is supplemented with an enhanced Multi-robot State Estimation (MRSE) strategy to increase the reliability of the purely onboard localization, which may be unreliable in real environments. Although MRSE and the neighborhood model may rely on information exchange between agents, we introduce a communication-less version of the swarming framework based on estimating communicated states to decrease dependence on the often unreliable communication networks of large swarms. The proposed solution has been verified by a set of complex real-world experiments to demonstrate its overall capability in different conditions, including a UAV interception-motivated task with a group velocity reaching the physical limits of the individual hardware platforms. Copyright © 2024, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Ensemble Inequivalence and Phase Transitions in Unlabeled Networks

引用

Physical Review Letters 2025年第20期134卷 207401-207401页

作者： Oleg Evnin Dmitri Krioukov High Energy Physics Research Unit Faculty of Science Chulalongkorn University Bangkok Thailand and Theoretische Natuurkunde Vrije Universiteit Brussel and International Solvay Institutes Brussels Belgium Department of Physics and Network Science Institute and Department of Mathematics and Department of Electrical and Computer Engineering Northeastern University Boston Massachusetts USA

We discover a first-order phase transition in the canonical ensemble of random unlabeled networks with a prescribed average number of links. The transition is caused by the nonconcavity of microcanonical entropy. Above the critical point coinciding with the graph symmetry phase transition, the canonical and microcanonical ensembles are equivalent and have a well-behaved thermodynamic limit. Below the critical point, the ensemble equivalence is broken, and the canonical ensemble is a mixture of phases: empty networks and networks with average degrees diverging logarithmically with the network size. As a consequence, networks with bounded average degrees do not survive in the thermodynamic limit, decaying into the empty phase. The celebrated percolation transition in labeled networks is thus absent in unlabeled networks. In view of these differences between labeled and unlabeled ensembles, the question of which one should be used as a null model of different real-world networks cannot be ignored.

关键词： Maximum entropy methods

来源：评论

学校读者我要写书评

暂无评论

Improved signed distance function for 2D real-time SLAM and accurate localization

arXiv

引用

arXiv 2021年

作者： Fu, Xingyin Fang, Zheng Xiao, Xizhen He, Yijia Liu, Xiao Technology Inc. Beijing China Faculty of Robot Science and Engineering Northeastern University Shenyang110169 China

Accurate mapping and localization are very important for many industrial robotics applications. In this paper, we propose an improved Signed Distance Function (SDF) for both 2D SLAM and pure localization to improve the accuracy of mapping and localization. To achieve this goal, firstly we improved the back-end mapping to build a more accurate SDF map by extending the update range and building free space, etc. Secondly, to get more accurate pose estimation for the front-end, we proposed a new iterative registration method to align the current scan to the SDF submap by removing random outliers of laser scanners. Thirdly, we merged all the SDF submaps to produce an integrated SDF map for highly accurate pure localization. Experimental results show that based on the merged SDF map, a localization accuracy of a few millimeters (5mm) can be achieved globally within the map. We believe that this method is important for mobile robots working in scenarios where high localization accuracy matters. © 2021, CC BY.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Improving Referring Expression Comprehension by Suppressing Expression-unrelated Proposals 3

Improving Referring Expression Comprehension by Suppressing ...

引用

3rd International Conference on Electronic Information engineering and Computer, EIECT 2023

作者： Wang, Qun Zhu, Feng Li, Xiang Ye, Ruida Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China Northeastern University Faculty of Computer Science and Engineering Shenyang110016 China Space Engineering University Department of Aerospace Engineering and Technology Beijing101416 China

ISBN: (纸本)9798350357707

The prevailing referring expression comprehension (REC) method is based on two stages: 1) detecting multiple candidate proposals using an object detector and 2) aligning proposals with text descriptions. Existing two-stage models have achieved significant improvements with excellent alignment modules. However, their alignment modules treat each proposal equally without filtering expression-unrelated proposals. These expression-unrelated proposals may interfere with the alignment modules' ability to accurately reason about the target proposal. These proposals also increase the difficulty of training alignment modules. To solve this problem, we propose a new framework, that can suppress expression-unrelated proposals for alignment modules. Specifically, we first design a suppression module, which calculates the relevance scores between the proposals and the expression by using the semantics in the expression. Then, these scores are integrated into three basic alignment modules, including subject, location, and relationship modules, to guide each module to focus on the expression-related proposals. We conduct extensive experiments on three benchmark datasets, and the results show the effectiveness of our suppression module and performance improvement. © 2023 IEEE.

关键词： Alignment

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：