检索结果-内蒙古大学图书馆

17th Chinese Intelligent Systems Conference, CISC 2021

作者： Yang, Guang Li, Yuqin Zhou, Wuneng Wu, You Wu, Wanpeng Gu, Xuan College of Information Sciences and Technology Donghua University Shanghai201620 China College of Automotive Engineering Guangxi City Vocational University Chongzuo532299 China Engineering Research Center of Digitized Textile and Fashion Technology Donghua University Shanghai China

ISBN: (纸本)9789811663239

In the field of transportation, accurate and real-time forecasting of traffic information is of great significance. However, Most of the existing traffic flow prediction methods lack the ability to model the dynamic spatial-temporal correlations. In order to obtain the satisfactory prediction results, We propose a new traffic prediction method based on neural network—a graph convolutional network (GCN) model based on the attention mechanism combined with gated recurrent unit (GRU). Specifically, the model uses an attention mechanism to obtain the weight information of each node at the input, and then uses GCN to learn complex topological structures to effectively capture spatial correlation, and finally uses GRU to learn the dynamics of traffic data change to capture time correlation. Applying the model to the experimental network dataset from the Traffic Performance Measurement System (PeMS) shows that our AT-GCN model can obtain spatial-temporal correlations from the traffic data, and has relatively good prediction effect. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The Low Carbon Pickup and Delivery Problem with Time Windows and its Optimization Approach

The Low Carbon Pickup and Delivery Problem with Time Windows...

引用

2021 China Automation Congress, CAC 2021

作者： Wang, Chuang Pan, Anqi Feng, Xue College of Information Sciences and Technology Donghua University Engineering Research Center of Digitized Textile and Fashion Technology Ministry of Education Shanghai201620 China

ISBN: (纸本)9781665426473

Pickup and delivery problem is commonly exist in logistics system, and its optimization considering time windows is essential in practical application. Meanwhile, with the increasing awareness of environmental protection, carbon emissions should also be considered during the routing design. In this paper, a low-carbon model is introduced for the pickup and delivery problem with time windows;a division method is proposed for the different delivery costs of logistics customers in different regions;a capacity constraint processing approach is proposed to solve the capacity of the vehicle during driving. Since the requirements for the logistic system are described by several objective formulations, the multi-objective approach is adopted to solve the optimization problem. The experiment selects two sets of Shanghai logistics data at different scales. Feasible solutions with advantages of different expectations can be obtained from the experiment result. © 2021 IEEE

关键词： Pickups

来源：评论

学校读者我要写书评

暂无评论

An improved Image Inpainting Algorithm Based on Attention Fusion Module

An improved Image Inpainting Algorithm Based on Attention Fu...

引用

Chinese Control and Decision Conference, CCDC

作者： Zhen Ding Tong Wang Kuangrong Hao Engineering Research Center of Digitized Textile & Apparel Technology Ministry of Education Shanghai College of Information Science and Technology Donghua University Shanghai P. R. China

ISBN: (纸本)9781665478977

When we try to reproduce existing inpainting algorithms, our performances are often not stable, and the results are not up to expectations. In this paper, we devise an improved image inpainting algorithm mainly constructed by an attention fusion module (AFM) and a refined inpainting module. The AFM evaluates the existing methods' results pixel-wise, similar to humans judging the quality of the inpainting results with naked eyes. The evaluations make a quantitative judgment on the inpainting quality and fused with pre-inpainted images. The refined inpainting module focuses on the areas with poor quality and improves them. This method address the shortcomings of other models like smoothness and texture sharpening. The experimental results on multiple datasets show significant improvements based on existing methods.

关键词： Feature extraction Training Testing Maintenance engineering Task analysis Kernel Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Balancing diversity and accuracy of the recommendation system based on multi-objective optimization

Balancing diversity and accuracy of the recommendation syste...

引用

2021 China Automation Congress, CAC 2021

作者： Zhang, Langlang Pan, Anqi Shi, Hongrui College of Information Sciences and Technology Donghua University Engineering Research Center of Digitized Textile and Fashion Technology Ministry of Education Shanghai201620 China

ISBN: (纸本)9781665426473

Recommendation systems are used in every aspect of people's lives in the context of today's Internet boom. However, most of the research on recommendation algorithms focus on improving the accuracy of algorithms, while the diversity and novelty of recommendation quality are more or less ignored. In addition, the accuracy and diversity of recommendation algorithms are usually contradictory. Therefore, the paper proposed a novel multi-objective framework to balance accuracy and diversity. Under the framework, similar products and diverse products are recommended by user clustering. Two objective functions are designed to represent the similarity and diversity of clustering. One objective function is to bring together users with similar preferences. Another objective function is to recommend diverse items to users. The novel multi-objective evolutionary algorithm can return a series of different trade-off solutions in one run. The proposed algorithm is applied on a real-world baseline dataset: MovieLens. Experimental results show that diversity and novelty are improved without sacrificing too much precision. © 2021 IEEE

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Fabrication of Customized, Tunable, Ultrathin, and Flexible Metamaterial Absorbers Based on Laser-Induced Graphene

SSRN

引用

SSRN 2024年

作者： Chen, Chunhui Jiang, Ziyang Bai, Yu Zhai, Menglin Jia, Fengde Hai, Wenqing Li, Minghao Jiang, Jinhua Shao, Huiqi Shao, Guangwei Chen, Nanliang Bi, Siyi Engineering Research Center of Technical Textile Ministry of Education College of Textiles Donghua University Shanghai201620 China College of Mechanical Electrification Engineering Tarim University Xinjiang843300 China Beijing Institute of Astronautical Systems Engineering Beijing100076 China College of Information Science and Technology Donghua University Shanghai201620 China Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Shanghai201620 China Innovation Center for Textile Science and Technology Donghua University Shanghai201620 China Binzhou Institute of Technology Weiqiao-UCAS Science and Technology Park Shandong256606 China

Developing various 3D graphene microwave absorbers is a hotspot strategy to address the issue of continuous electromagnetic pollution, but remains great challenges in realizing high-performance microwave absorption capability at thin thickness. Herein, a series of flexible metamaterial absorbers (MAs) composed of periodical laser-induced graphene (LIG) surface, dielectric substrate and metallic ground fabric from top to bottom are fabricated. The LIG meta-surface is customized by means of regulating parameters including laser power density (LPD), laser engraving rate (LER) and input patterns to well balance impedance matching and electromagnetic loss. LIG MAs exhibit minimum reflection loss (RL) of -39.7 dB and effective absorption bandwidth (EAB) of -13.3 GHz at thickness less than 1.1 mm, and the simulated and experimental results are highly consistent. In addition, radar cross section (RCS) simulation of LIG MA with multi-angles endows its potential for prospective applications in in-orbit satellites electromagnetic protection. © 2024, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Evolutionary for Object Detection Mobile Architectures Search

arXiv

引用

arXiv 2022年

作者： Zhang, Haichao Li, Jiashi Xia, Xin Hao, Kuangrong Xiao, Xuefeng College of Information Science and Technology Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Donghua University Shanghai201620 China ByteDance Intelligent Creation China

Recently, Neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on the image classification task. However, the architecture which is searched through the classification task is sub-optimal because of the gap between the task of image and object detection. As while work focuses on backbone network architecture search for mobile device object detection is limited, mainly because the backbone always requires expensive ImageNet pre-training. Accordingly, it is necessary to study the approach of network architecture search for mobile device object detection without expensive pretraining. In this work, we propose a mobile object detection backbone network architecture search algorithm which is a kind of evolutionary optimized method based on non-dominated sorting for NAS scenarios. It can quickly search to obtain the backbone network architecture within certain constraints. It better solves the problem of suboptimal linear combination accuracy and computational cost. The proposed approach can search the backbone networks with different depths, widths, or expansion sizes via a technique of weight mapping, making it possible to use NAS for mobile devices detection tasks a lot more efficiently. In our experiments, we verify the effectiveness of the proposed approach on YoloX-Lite, a lightweight version of the target detection framework. Under similar computational complexity, the accuracy of the backbone network architecture we search for is 2.0% mAP higher than MobileDet. Our improved backbone network can reduce the computational effort while improving the accuracy of the object detection network. To prove its effectiveness, a series of ablation studies have been carried out and the working mechanism has been analyzed in detail. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Bilateral boundary control of an input delayed 2-D reaction-diffusion equation

arXiv

引用

arXiv 2023年

作者： Guan, Dandan Chen, Yanmei Qi, Jie Du, Linglong College of Information Science and Technology Donghua University Shanghai201620 China Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Donghua University Shanghai201620 China Department of Applied Mathematics Donghua University Shanghai201620 China

In this paper, a delay compensation design method based on PDE backstepping is developed for a two-dimensional reaction-diffusion partial differential equation (PDE) with bilateral input delays. The PDE is defined in a rectangular domain, and the bilateral control is imposed on a pair of opposite sides of the rectangle. To represent the delayed bilateral inputs, we introduce two 2-D transport PDEs that form a cascade system with the original PDE. A novel set of backstepping transformations is proposed for delay compensator design, including one Volterra integral transformation and two affine Volterra integral transformations. Unlike the kernel equation for 1-D PDE systems with delayed boundary input, the resulting kernel equations for the 2-D system have singular initial conditions governed by the Dirac Delta function. Consequently, the kernel solutions are written as a double trigonometric series with singularities. To address the challenge of stability analysis posed by the singularities, we prove a set of inequalities by using the Cauchy-Schwarz inequality, the 2-D Fourier series, and the Parseval’s theorem. A numerical simulation illustrates the effectiveness of the proposed delay-compensation method. Copyright © 2023, The Authors. All rights reserved.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Chinese Influence on Fashion——The Incorporation of Chinese Folding Fans in Upcycled Fashion

Chinese Influence on Fashion——The Incorporation of Chinese...

引用

第二届时尚与可持续发展国际会议

作者： Zarwa Mughal SHA Sha School of Fashion Design Wuhan Textile University Innovation and Fiber Science Research Institute.School of Fashion Wuhan Textile University Wuhan Textile and Apparel Digital Engineering Technology Research Center

Chinese influence on fashion is becoming more and more prominent with *** national to international runways,themes inspired by Chinese culture are *** prominent source of identity in Chinese culture is the folding *** to its compelling shape,scenery,texture,and many other properties,it can be drawn as inspiration for fashion ***,developing new fashion surfaces with virgin materials has its *** fashion industry generates a substantial amount of pre-and post-consumer waste which ends up in landfills and releases harmful greenhouse *** like upcycling can combat this *** fabrics and garments can be used to create new surfaces and *** this way,mixing traditional Chinese craft elements with upcycled fashion will result in an innovative,ethical,and sustainable fashion.

关键词： Chinese folding fan Sustainable fashion Upcycling Chinese culture

来源：评论

学校读者我要写书评

暂无评论

Intelligent Greedy Perimeter Stateless Routing Scheme for Unmanned Aerial Vehicles

引用

Journal of Donghua University(English Edition) 2022年第6期39卷 603-613页

作者： BAIG Mohsin Ayub ZHANG Yihong YE Xiaoxian SULTANA Umbrin AKBAR Sunila LI Shuai AHMAD Sohail College of Information Science and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile&Fashion Technology Ministry of EducationDonghua UniversityShanghai 201620China School of Art and Design Shanghai University of Engineering ScienceShanghai 201620China Department of Electrical Engineering NED University of Engineering and TechnologyKarachi 75270Pakistan

The dynamic behavior,rapid mobility,abrupt changes in network topology,and numerous other flying constraints in unmanned aerial vehicle(UAV)networks make the design of a routing protocol a challenging *** data routing for communication between UAVs faces numerous challenges,such as low link quality,data loss,and routing path *** work proposes greedy perimeter stateless routing(GPSR)based design and implementation of a new adaptive communication routing protocol technique for UAVs,allowing multiple UAVs to communicate more effectively with each other in a *** imitation of the real environment is accomplished by considering UAVs’three-dimensional(3D)mobility in the *** performance of the proposed intelligent greedy perimeter stateless routing(IGPSR)scheme has been evaluated based on end-to-end(E2E)delay,network throughput,and data loss *** adapted scheme displayed on average 40%better *** scenario has been implemented holistically on the network simulator software NS-3.

关键词： flying ad-hoc network(FANET) vehicular ad-hoc network(VANET) unmanned aerial vehicle(UAV) greedy perimeter stateless routing(GPSR) intelligent greedy perimeter stateless routing(IGPSR)

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Programming Strategy for the dynamic spinning process optimization

Nonlinear Programming Strategy for the dynamic spinning proc...

引用

Chinese Control and Decision Conference, CCDC

作者： Junhao Qiu Tong Wang Kuangrong Hao Engineering Research Center of Digitized Textile & Apparel Technology Ministry of Education Shanghai College of Information Science and Technology Donghua University Shanghai P. R. China

ISBN: (纸本)9781665478977

The polyester fiber spinning process is extensive, and the involved dynamic models are complex and difficult to solve analytically. This paper presents the optimal control strategy of polyester fiber production. Based on a dynamic model of the spinning process, optimal objectives are determined to minimize production costs and meet production goals. We employ Radau collocation on finite elements to discretize the continuous dynamic model, which is transformed into finite-dimensional nonlinear programming (NLP) model. The developed strategy combines a multiple shot algorithm and half-score method to solve the obtained NLP model. We find the best initial values quickly and achieve the control objective under the constraints of the spinning process's mechanism equations. The objective function measures the difference between the actual production and the desired value, and the merit of the objective function directly affects the control variables. In this paper, single-objective and multi-objective control strategies are designed according to different production requirements. To make the objective function effectively reflect the product quality, its setting is inseparable from each state variable, and we explore the control effect for different objective functions. Finally, simulation results verify the feasibility and superiority of the orthogonal collocation on finite element and multiple shooting algorithms.

关键词： Process control Production Programming Linear programming Mathematical models Product design Dynamic programming

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：