检索结果-内蒙古大学图书馆

A survey on computationally efficient neural architecture search

Journal of Automation and Intelligence 2022年第1期1卷 8-22页

作者： Shiqing Liu Haoyu Zhang Yaochu Jin Chair of Nature Inspired Computing and Engineering Faculty of TechnologyBielefeld University33619 BielefeldGermany Department of Computer Science University of SurreyGuildfordGU27XHUnited Kingdom Engineering Research Center of Digitized Textile&Apparel Technology Ministry of EducationCollege of Information Science and TechnologyDonghua UniversityShanghai 201620China

Neural architecture search(NAS)has become increasingly popular in the deep learning community recently,mainly because it can provide an opportunity to allow interested users without rich expertise to benefit from the success of deep neural networks(DNNs).However,NAS is still laborious and time-consuming because a large number of performance estimations are required during the search process of NAS,and training DNNs is computationally *** solve this major limitation of NAS,improving the computational efficiency is essential in the design of ***,a systematic overview of computationally efficient NAS(CE-NAS)methods still *** fill this gap,we provide a comprehensive survey of the state-of-the-art on CE-NAS by categorizing the existing work into proxy-based and surrogate-assisted NAS methods,together with a thorough discussion of their design principles and a quantitative comparison of their performances and computational *** remaining challenges and open research questions are also discussed,and promising research topics in this emerging field are suggested.

关键词： Neural architecture search(NAS) One-shot NAS Surrogate model Bayesian optimization Performance predictor

来源：评论

学校读者我要写书评

暂无评论

Smart Clothing Fabric Color Matching with Reference to Popular Colors

引用

Journal of Donghua University(English Edition) 2022年第4期39卷 317-324页

作者： ZHANG Yani ZHUANG Jianqiang HUANG Rong DONG Aihua YUAN Haodong College of Information Science and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile&Fashion Technology Ministry of EducationDonghua UniversityShanghai 201620China

Color economy and market fashion trend have an increasing impact on clothing fabric color ***,a smart clothing fabric color matching system with reference to popular colors is designed to realize the diversification of clothing color matching,which includes a palette generation module and a clothing fabrics-palette color matching network(CF-PCN).Firstly,palette generation module generates palettes referring popular colors while maintains color styles of clothing ***,CF-PCN generates color matching images containing color information of *** experimental results show that the color matching system has a higher average pixel ratio of palette colors and contains more palette color *** demonstrates that the system achieves color matching innovation referring popular colors while retaining color style of clothing brands and provides designers with appropriate color matching solutions.

来源：评论

学校读者我要写书评

暂无评论

Robotic motion planning with obstacle avoidance based on hierarchical deep reinforcement learning 23

Robotic motion planning with obstacle avoidance based on hie...

引用

3rd International Conference on Robotics and Control engineering, RobCE 2023

作者： Zhao, Guoquan Ying, Fengkang Pang, Zuowei Liu, Huashan College of Information Science and Technology Donghua University Shanghai201620 China Engineering Research Center of Digitized Textile & Fashion Technology Ministry of Education Shanghai201620 China Huzhou Institute of Zhejiang University Zhejiang Huzhou313002 China

ISBN: (纸本)9781450398107

When the task environment becomes complex, deep reinforcement learning (DRL) is easy to encounter the problems of gradient disappearance or explosion. To solve this problem, this paper proposes a hierarchical DRL framework consisting of task and action layers. The task layer learns interpretable representations of tasks and decision processes, and drives the action layer. The action layer learns to collaboratively accomplish complex tasks in different roles. The DRL algorithm based on this framework is tested on a redundant degree of freedom robot in obstacle avoidance motion planning tasks, and comparative experimental results prove the effectiveness and feasibility of the proposed method. © 2023 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning an End-to-End Spatial Grasp Generation Algorithm from Incomplete Point Clouds 18th

Learning an End-to-End Spatial Grasp Generation Algorithm f...

引用

18th Chinese Intelligent Systems Conference, CISC 2022

作者： Huang, Kunrong Zhou, Wuneng Zhang, Yiyu Zhang, Ming Huang, Jinbo Tang, Xinxin College of Information Sciences and Technology Donghua University Shanghai201620 China Engineering Research Center of Digitized Textile and Fashion Technology Donghua University Shanghai201620 China

ISBN: (纸本)9789811962028

In this paper, in order to solve the problem of reducing the accuracy of 3D target detection due to the loss of geometric and semantic information of point cloud caused by obstacle occlusion, ambient light reflection, transparency of object surface materials and limited shooting angle, a network combining point cloud completion and feature extraction is proposed. Firstly, according to the spatial structure of incomplete point cloud, multi resolution encode and point pyramid decode are used to complete the point cloud. Then, multi-scale and multi-resolution point cloud feature learning network is used to learn the features of the completed point cloud. Finally, the local and global features of the extracted point cloud are used for point cloud classification experiments. The experimental results show that after completing the point cloud, the accuracy of 3D target detection is significantly improved, and a better classification effect can be achieved. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Improved Spectral Clustering Clothing Image Segmentation Algorithm Based on Sparrow Search Algorithm

引用

Journal of Donghua University(English Edition) 2022年第4期39卷 340-344页

作者： HUANG Wenan QIAN Suqin College of Information Science and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile&Fashion Technology Ministry of EducationDonghua UniversityShanghai 201620China

In the process of clothing image researching,how to segment the clothing quickly and accurately and retain the clothing style details as much as possible is the basis of subsequent image *** clustering clothing image segmentation algorithm is a common method in the process of clothing image ***,the traditional model requires high computing power and is easily affected by the initial center of *** often falls into local *** at the above two points,an improved spectral clustering clothing image segmentation algorithm is proposed in this *** Nystrom approximation strategy is introduced into the spectral mapping process to reduce the computational *** the clustering stage,this algorithm uses the global optimization advantage of the particle swarm optimization algorithm and selects the sparrow search algorithm to search the optimal initial clustering point,to effectively avoid the occurrence of local *** the end,the effectiveness of this algorithm is verified on clothing images in each environment.

关键词： clothing segmentation spectral clustering particle swarm optimization algorithm intelligent fashion design

来源：评论

学校读者我要写书评

暂无评论

Deep transfer model with source domain segmentation for polyester esterification processes

Deep transfer model with source domain segmentation for poly...

引用

第34届中国控制与决策会议

作者： Huiyuan Peng Lei Chen Kuangrong Hao Engineering Research Center of Digitized Textile & Apparel Technology Ministry of EducationCollege of Information Science and TechnologyDonghua University

ISBN: (纸本)9781665478977

In the polyester fiber industry,newly-built production lines or newly-installed production equipment cannot collect large enough historical data,resulting in the inability to construct accurate time series prediction models for key *** paper proposed a deep transfer model with source domain segmentation(SDS-DTM),which transfers knowledge of another production line with sufficient time series data,and the proposed model is used for multivariate time series forecasting modeling in target production line with insufficient ***-DTM adds a domain adaptation layer to the deep recurrent neural network,which transfers knowledge by minimizing distribution mismatch in the feature sharing *** long time span of the source time series will cause the problem of temporal covariate shift(TCS).SDS-DTM minimizes the influence of TCS by splitting the source domain and constructing an integrated *** effectiveness of the proposed model is verified by polyester esterification process data.

关键词： transfer learning time series forecasting domain adaption source domain segmentation polyester esterification process

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

第34届中国控制与决策会议

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

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

关键词： Image Inpainting Feature Learning Attention Mechanism Deep Learning

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

第34届中国控制与决策会议

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

The polyester fiber spinning process is extensive,and the involved dynamic models are complex and difficult to solve *** paper presents the optimal control strategy of polyester fiber *** on a dynamic model of the spinning process,optimal objectives are determined to minimize production costs and meet production *** employ Radau collocation on finite elements to discretize the continuous dynamic model,which is transformed into finite-dimensional nonlinear programming(NLP) *** developed strategy combines a multiple shot algorithm and half-score method to solve the obtained NLP *** find the best initial values quickly and achieve the control objective under the constraints of the spinning process' s mechanism *** objective function measures the difference between the actual production and the desired value,and the merit of the objective function directly affects the control *** this paper,single-objective and multi-objective control strategies are designed according to different production *** 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 ***,simulation results verify the feasibility and superiority of the orthogonal collocation on finite element and multiple shooting algorithms.

关键词： polyester fibers dynamic optimization nonlinear programming Radau orthogonal collocation

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Load Flow Algorithm with the Power Performance of Double-Fed Induction Generators

引用

Journal of Donghua University(English Edition) 2021年第3期38卷 206-213页

作者： CAO Ruilin XING Jie HOU Meiqian College of Information Science and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile&Apparel Technology Ministry of EducationDonghua UniversityShanghai 201620China

Probabilistic load flow(PLF)algorithm has been regained attention,because the large-scale wind power integration into the grid has increased the uncertainty of the stable and safe operation of the power *** PLF algorithm is improved with introducing the power performance of double-fed induction generators(DFIGs)for wind turbines(WTs)under the constant power factor control and the constant voltage control in this ***,the conventional Jacobian matrix of the alternating current(AC)load flow model is modified,and the probability distributions of the active and reactive powers of the DFIGs are derived by combining the power performance of the DFIGs and the Weibull distribution of wind ***,the cumulants of the state variables in power grid are obtained by improved PLF model and more accurate power probability *** order to generate the probability density function(PDF)of the nodal voltage,Gram-Charlier,Edgeworth and Cornish-Fisher expansions based on the cumulants are ***,the effectiveness and accuracy of the improved PLF algorithm is demonstrated in the IEEE 14-RTS system with wind power integration,compared with the results of Monte Carlo(MC)simulation using deterministic load flow calculation.

关键词： probabilistic load flow(PLF) cumulant method double-fed induction generator(DFIG) power performance series expansion

来源：评论

学校读者我要写书评

暂无评论

PSegNet: Simultaneous Semantic and Instance Segmentation for Point Clouds of Plants

引用

Plant Phenomics 2022年第1期4卷 261-280页

作者： Dawei Li Jinsheng Li Shiyu Xiang Anqi Pan State Key Laboratory for Modification of Chemical Fibers and Polymer Materials College of Information Sciences and TechnologyDonghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile&Fashion Technology Ministry of EducationDonghua UniversityShanghai 201620China College of Information Sciences and Technology Donghua UniversityShanghai 201620China

Phenotyping of plant growth improves the understanding of complex genetic traits and eventually expedites the development of modern breeding and intelligent *** phenotyping,segmentation of 3D point clouds of plant organs such as leaves and stems contributes to automatic growth monitoring and reflects the extent of stress received by the *** this work,we first proposed the Voxelized Farthest Point Sampling(VFPS),a novel point cloud downsampling strategy,to prepare our plant dataset for training of deep neural networks.

关键词： breeding eventually organs

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：