检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Lu, Dening Gao, Kyle Xie, Qian Xu, Linlin Li, Jonathan The Department of Systems Design Engineering University of Waterloo WaterlooONN2L 3G1 Canada The Departmemt of Geography and Environmental Management University of Waterloo WaterlooONN2L 3G1 Canada The Department of Computer Science University of Oxford OxfordOX1 3QD United Kingdom

Although the application of Transformers in 3D point cloud processing has achieved significant progress and success, it is still challenging for existing 3D Transformer methods to efficiently and accurately learn both valuable global features and valuable local features for improved applications. This paper presents a novel point cloud representational learning network, called 3D Dual Self-attention Global Local (GLocal) Transformer Network (3DGTN), for improved feature learning in both classification and segmentation tasks, with the following key contributions. First, a GLocal Feature Learning (GFL) block with the dual self-attention mechanism (i.e., a novel Point-Patch Self-Attention, called PPSA, and a channel-wise self-attention) is designed to efficiently learn the GLocal context information. Second, the GFL block is integrated with a multi-scale Graph Convolution-based Local Feature Aggregation (LFA) block, leading to a Global-Local (GLocal) information extraction module that can efficiently capture critical information. Third, a series of GLocal modules are used to construct a new hierarchical encoder-decoder structure to enable the learning of"GLocal" information in different scales in a hierarchical manner. The proposed framework is evaluated on both classification and segmentation datasets, demonstrating that the proposed method is capable of outperforming many state-of-the-art methods on both classification and segmentation tasks. Our code will be made publicly available. © 2022, CC BY-NC-ND.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Panel on Simulation Modeling for Covid-19

Panel on Simulation Modeling for Covid-19

引用

2021 Winter Simulation Conference, WSC 2021

作者： Aleman, DIonne M. Anagnostou, Anastasia Currie, Christine S.M. Fowler, John W. Gel, Esma S. Rutherford, Alexander R. University of Toronto Department of Mechanical Industrial and Systems Engineering TorontoONM5S 3G8 Canada Modelling Simulation Group Brunel University London Department of Computer Science UxbridgeUB8 3PH United Kingdom University of Southampton Mathematical Sciences SouthamptonSO17 1BJ United Kingdom Arizona State University Department of Supply Chain Management TempeAZ85287 United States Arizona State University Industrial Engineering TempeAZ85281 United States Simon Fraser University Department of Mathematics BurnabyBCV5A 1S6 Canada

ISBN: (纸本)9781665433112

This is a panel paper which discusses the use of simulation modeling in mitigating the effects of the Covid-19 pandemic. We have gathered a group of expert modelers from around the world who have worked on healthcare simulation projects associated with the pandemic and the paper provides their answers to an initial set of questions. These serve to provide a description of the modeling work that has taken place already and to make suggestions for future directions both in modeling Covid-19 and preparing the world for future healthcare emergencies. © 2021 IEEE.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem

arXiv

引用

arXiv 2021年

作者： Li, Jingwen Ma, Yining Gao, Ruize Cao, Zhiguang Lim, Andrew Song, Wen Zhang, Jie The Department of Industrial Systems Engineering and Management National University of Singapore Singapore Singapore The Departmant of Computer Science and Engineering Chinese Universiry of Hong Kong China The Singapore Institute of Manufacturing Technology Singapore Singapore The School of Computing and Artificial Intelligence Southwest Jiaotong University China The Institute of Marine Science and Technology Shandong University China The School of Computer Science and Engineering Nanyang Technological University Singapore

Existing deep reinforcement learning (DRL) based methods for solving the capacitated vehicle routing problem (CVRP) intrinsically cope with homogeneous vehicle fleet, in which the fleet is assumed as repetitions of a single vehicle. Hence, their key to construct a solution solely lies in the selection of the next node (customer) to visit excluding the selection of vehicle. However, vehicles in real-world scenarios are likely to be heterogeneous with different characteristics that affect their capacity (or travel speed), rendering existing DRL methods less effective. In this paper, we tackle heterogeneous CVRP (HCVRP), where vehicles are mainly characterized by different capacities. We consider both min-max and min-sum objectives for HCVRP, which aim to minimize the longest or total travel time of the vehicle(s) in the fleet. To solve those problems, we propose a DRL method based on the attention mechanism with a vehicle selection decoder accounting for the heterogeneous fleet constraint and a node selection decoder accounting for the route construction, which learns to construct a solution by automatically selecting both a vehicle and a node for this vehicle at each step. Experimental results based on randomly generated instances show that, with desirable generalization to various problem sizes, our method outperforms the state-of-theart DRL method and most of the conventional heuristics, and also delivers competitive performance against the state-of-the-art heuristic method, i.e., SISR. Additionally, the results of extended experiments demonstrate that our method is also able to solve CVRPLib instances with satisfactory performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating Mixed Reality and Tablet Technologies in Military Planning

Evaluating Mixed Reality and Tablet Technologies in Military...

引用

IEEE Symposium on systems and Information engineering Design, SIEDS

作者： Betsy Guzmá n Sarah Deresky Sabrina Taylor Hawk Wimmer Ali Momen Chad Tossell Michael Boyce Joel Cartwright Charles Amburn Ben Sawyer Department of Industrial Engineering and Management Systems Univ. of Central Florida Orlando FL Warfighter Effectiveness Research Center U.S Air Force Academy Usafa CO Department of Behavioral Sciences and Leadership U.S Military Academy West PointNY U.S. Army DEVCOM Simulation &#x0026 Training Technology Center Orlando FL

Increasingly advanced technologies are penetrating military domains (e.g., air, land, sea, cyber, space) requiring more complex decision-making to support activities that apply across these domains (multi-domain planning & operations). These decisions often require humans to perceive, comprehend, project, and then communicate information in a timely and accurate manner, oftentimes with life-or-death consequences. To support these decisions, department of Defense leaders are calling for more effective representations and displays of joint warfighting environments. This project addresses this requirement by examining novel technologies for integrating and displaying complex MDO plans for human decision-making. Using a mission planning scenario, we assessed situation awareness (SA), usability, cost, and overall effectiveness of a two-dimensional (2D) representation of a common joint warfighting display on a Samsung tablet against a three-dimensional (3D) display of the same information designed for use in a Microsoft HoloLens mixed reality system. A total of 22 U.S. Air Force Academy cadets were randomly assigned to either use the tablet or the HoloLens to develop and analyze a mission plan and assessed for situation awareness across two scenarios. Interestingly, the HoloLens did not provide any additional SA relative to the tablet. The tablet was also perceived as more usable and effective in terms of cost and overall performance. These results suggest more traditional technologies, such as a tablet, can provide SA at similar levels as more advanced technology with increased usability and affordability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new validity index for fuzzy-possibilistic c-means clustering

arXiv

引用

arXiv 2020年

作者： Zarandi, Mohammad Hossein Fazel Sotudian, Shahabeddin Castillo, Oscar Department of Industrial Engineering and Management Systems Amirkabir University of Technology Tehran Iran Tijuan Institute of Technology Tijuan Mexico

In some complicated datasets, due to the presence of noisy data points and outliers, cluster validity indices can give conflicting results in determining the optimal number of clusters. This paper presents a new validity index for fuzzy-possibilistic c-means clustering called Fuzzy-Possibilistic)FP(index, which works well in the presence of clusters that vary in shape and density. Moreover, FPCM like most of the clustering algorithms is susceptible to some initial parameters. In this regard, in addition to the number of clusters, FPCM requires a priori selection of the degree of fuzziness (m) and the degree of typicality (η). Therefore, we presented an efficient procedure for determining an optimal value for m and η. The proposed approach has been evaluated using several synthetic and real-world datasets. Final computational results demonstrate the capabilities and reliability of the proposed approach compared with several well-known fuzzy validity indices in the literature. Furthermore, to clarify the ability of the proposed method in real applications, the proposed method is implemented in microarray gene expression data clustering and medical image segmentation. Copyright © 2020, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Digital transformation and organizational resilience: Unveiling the path to sustainable performance in adversity and crisis

引用

International Journal of Information management 2025年 84卷

作者： Gaoyong Li Kui Du Lu Liu Fang Su School of Management Science and Engineering Shandong University of Finance and Economics Jinan 250014 China Department of Management Science and Information Systems College of Management University of Massachusetts Boston Boston MA 02125 USA School of Business Renmin University of China Beijing 100872 China School of Management Jinan University Guangzhou Guangdong 510632 China

Bridging the literature on digital transformation (DT) and organizational resilience, we discuss the mechanisms whereby DT can contribute to the development and enactment of organizational resilience, which lead to the persistence of superior performance through times of adversity and crisis. We developed and validated brand new measurement scales for DT as a multidimensional construct. Then, we conducted two waves of surveys to collect data from 238 firms. The COVID-19 pandemic serves as the empirical context of aversity and crisis for our sampled firms. The results of PLS-SEM analyses supported our hypotheses. We then articulated our contributions to the studies of DT and organizational resilience.

关键词： Adversity and crisis Digital transformation Firm performance Organizational resilience

来源：评论

学校读者我要写书评

暂无评论

FaNDOM: Fast Nested Distance-Based Seeding of Optical Maps

SSRN

引用

SSRN 2021年

作者： Dehkordi, Siavash Raeisi Luebeck, Jens Bafna, Vineet Department of Computer Science & Engineering University of California San Diego San diegoCA92093 United States Bioinformatics & Systems Biology Graduate Program University of California San Diego San diegoCA92093 United States

Optical mapping provides single-molecule readouts of the locations of fluorescently labeled sequence motifs on long fragments of DNA, resolved to nucleotide-level coordinates. With the advent of microfluidic technologies for manipulating large numbers of individual molecules, and advances in the imaging of fluorescent DNA tags, it is possible to inexpensively generate high coverage and long OM molecules (>150Kbp). In addition to its use in scaffolding for de novo assembly, optical map data can also be mapped to a reference for identifying genetic structural variants implicated in Mendelian diseases and cancer. To address the computational challenge, we introduce FaNDOM (Fast Nested Distance seeding of Optical Maps) - an optical map alignment tool which greatly reduces the search space of the alignment process. On 4 benchmark human data-sets, FaNDOM was significantly (4-14X) faster than competing tools while maintaining comparable sensitivity and specificity. We used FaNDOM to map variants in 3 cancer cell-lines and identified many structural variations, including deletion of tumor-suppressor genes, duplications, gene fusions and gene-disrupting rearrangements. FaNDOM is publicly available at (https://***/jluebeck/FaNDOM). © 2021, The Authors. All rights reserved.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Feasibility study of novel magnetic compaction force assisted additive manufacturing (MCFA-AM) methodology for continuous carbon fiber reinforced polymer (C-CFRP) composites

Feasibility study of novel magnetic compaction force assiste...

引用

SAMPE 2019 Conference and Exhibition

作者： Ranabhat, Bikash Kirmse, Sebastian Hsiao, Kaung-Ting University of South Alabama Department of Mechanical Engineering 150 Jaguar Drive Shelby Hall Suite 3130 MobileAL36608 United States Department of Mechanical Engineering United States Systems Engineering Program United States

ISBN: (纸本)9781934551301

Composite parts manufactured by the current additive manufacturing (AM) methods are inferior in strength and stiffness compared to traditional composite manufacturing. Major issues include voids, physical gaps at layer/layer interface, and low reinforcing fiber content. This paper experimentally examined the feasibility of a patent-pending novel method, Magnetic Compaction Force Assisted-Additive Manufacturing (MCFA-AM), that utilized a magnetic compaction force to print and support curve-shaped continuous carbon fiber reinforced polymer (C-CFRP) composites in free space without any mold. C-CFRP prepreg tapes were fed through a magnet-assisted roller-like-setting, which was a part of the 3D printing head, and consolidated with a magnetic compaction pressure of 0.21 MPa in this feasibility trial. Short beam shear tests (ASTM D2344) showed that the 0.21 MPa MCFA-AM samples’ interlaminar shear strength (ILSS) was 8 % and 9 % stronger and 7% weaker compared with the C-CFRP samples manufactured by the hand layup, the Tension-Tape-Placement-Without Compaction-AM, and the Out-Of-Autoclave Vacuum-Bag-Only (OOA-VBO) methods, respectively. Microscopic observations showed the size and number of voids were significantly reduced by the magnetic compaction. Finally, it demonstrated that printing stiff, strong, and complex shaped C-CFRP parts with great freedom can be done within a few minutes with this exciting AM-Composites technology advance. Copyright 2019 by Bikash Ranabhat et al. Published by Society for the Advancement of Material and Process engineering with permission.

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

Innoframe: A project and portfolio management multilayer framework to support innovation-driven SMEs 4

Innoframe: A project and portfolio management multilayer fra...

引用

4th International Conference on Quality engineering and management, ICQEM 2020

作者： Tereso, A.P. Mishly, M.A. Production and Systems Department Centre ALGORITMI University of Minho Campus of Azurém Guimarães4804-533 Portugal Doctoral Program in Industrial and Systems Engineering University of Minho Campus of Azurém Guimarães4804-533 Portugal SchemaZone 18 Yonge Street TorontoONM5E 1Z8 Canada

ISBN: (纸本)9789895491100

Purpose - The purpose of this research was to discover what frameworks for project, portfolio, and innovation management there are and if necessary to propose a new framework useful for SMEs of the construction and building materials industry. Design/methodology/approach - The methodology used in this research was the case study, in which the Canadian construction and building materials industry was selected. The research was based on literature review, interviews, group discussion and survey. Findings - Although there are currently many frameworks available for the three management areas (project, portfolio and innovation), research has shown that a framework that helps companies to follow an approach that supports their business at these three levels is lacking. Originality/value - Innoframe is a new framework for project, portfolio, and innovation management that incorporates a pipeline and two phases as well as a performance management matrix, that can be used for project and portfolio management, to support innovation-driven SMEs. © 2020 Universidade do Minho. All rights reserved.

关键词： Framework Innovation Portfolio management Project management

来源：评论

学校读者我要写书评

暂无评论

Reducing the defects of a-pillar stamping part in the automotive assembly process 6

Reducing the defects of a-pillar stamping part in the automo...

引用

6th International Conference on Frontiers of Industrial engineering, ICFIE 2019

作者： Rojpitinithikorn, Hassakorn Tang, Jing Leelawat, Natt Chulalongkorn University Department of Industrial Engineering Disaster and Risk Management Information Systems Research Group Bangkok Thailand Chulalongkorn University International School of Engineering Bangkok Thailand

ISBN: (纸本)9781728145594

This research aims to reduce defect in the automotive assembly process. Considering the defect and cost that occurred during one year;the highest defect cost came from the A-Pillar stamping part. Therefore, we analyzed production process as well as finding out the cause of the problems that occur in the stamping process by using Failure Mode and Effect Analysis (FMEA) to analyze it and conduct experiments by Design of Experiment (DOE) method. The results found that the problem came from the design of metal stamping die are not good enough to produce large parts, which are the risk of spring back problems of parts. After improving the stamping process by adding re-strike die;it is expected to reduce the number of defect from 492 cases to be zero and save the defect cost amount of 27 million Thai Baht per year. © 2019 IEEE.

关键词： Design of experiments

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

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

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：