检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Damseh, Rafat Delafontaine-Martel, Patrick Pouliot, Philippe Cheriet, Farida Lesage, Frederic Institute of Biomedical Engineering École Polytechnique de Montréal MontrealQC Canada Department of Electrical Engineering École Polytechnique de Montréal MontrealQC Canada Research Centre Montreal Hearth Institute MontrealQC Canada Department of Computer and Software Engineering École Polytechnique de Montréal MontrealQC Canada

—Generating computational anatomical models of cerebrovascular networks is vital for improving clinical practice and understanding brain oxygen transport. This is achieved by extracting graph-based representations based on pre-mapping of vascular structures. Recent graphing methods can provide smooth vessels trajectories and well-connected vascular topology. However, they require water-tight surface meshes as inputs. Furthermore, adding vessels radii information on their graph compartments restricts their alignment along vascular centerlines. Here, we propose a novel graphing scheme that works with relaxed input requirements and intrinsically captures vessel radii information. The proposed approach is based on deforming geometric graphs constructed within vascular boundaries. Under a laplacian optimization framework, we assign affinity weights on the initial geometry that drives its iterative contraction toward vessels centerlines. We present a mechanism to decimate graph structure at each run and a convergence criterion to stop the process. A refinement technique is then introduced to obtain final vascular models. Our implementation is available on https://***/Damseh/VascularGraph. We benchmarked our results with that obtained using other efficient and state-of-the-art graphing schemes, validating on both synthetic and real angiograms acquired with different imaging modalities. The experiments indicate that the proposed scheme produces the lowest geometric and topological error rates on various angiograms. Furthermore, it surpasses other techniques in providing representative models that capture all anatomical aspects of vascular structures. Copyright © 2019, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

DOOR-SLAM: Distributed, online, and outlier resilient SLAM for robotic teams

arXiv

引用

arXiv 2019年

作者： Lajoie, Pierre-Yves Ramtoula, Benjamin Chang, Yun Carlone, Luca Beltrame, Giovanni Department of Computer and Software Engineering Polytechnique Montréal Montreal Canada Massachusetts Institute of Technology Cambridge United States School of Engineering École Polytechnique Fédérale de Lausanne Switzerland

To achieve collaborative tasks, robots in a team need to have a shared understanding of the environment and their location within it. Distributed Simultaneous Localization and Mapping (SLAM) offers a practical solution to localize the robots without relying on an external positioning system (e.g. GPS) and with minimal information exchange. Unfortunately, current distributed SLAM systems are vulnerable to perception outliers and therefore tend to use very conservative parameters for inter-robot place recognition. However, being too conservative comes at the cost of rejecting many valid loop closure candidates, which results in less accurate trajectory estimates. This paper introduces DOOR-SLAM, a fully distributed SLAM system with an outlier rejection mechanism that can work with less conservative parameters. DOOR-SLAM is based on peer-to-peer communication and does not require full connectivity among the robots. DOOR-SLAM includes two key modules: a pose graph optimizer combined with a distributed pairwise consistent measurement set maximization algorithm to reject spurious inter-robot loop closures;and a distributed SLAM front-end that detects inter-robot loop closures without exchanging raw sensor data. The system has been evaluated in simulations, benchmarking datasets, and field experiments, including tests in GPS-denied subterranean environments. DOOR-SLAM produces more inter-robot loop closures, successfully rejects outliers, and results in accurate trajectory estimates, while requiring low communication bandwidth. Copyright © 2019, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?

arXiv

引用

arXiv 2022年

作者： Karthik, Enamundram Naga Kerbrat, Anne Labauge, Pierre Granberg, Tobias Talbott, Jason Reich, Daniel S. Filippi, Massimo Bakshi, Rohit Callot, Virginie Chandar, Sarath Cohen-Adad, Julien NeuroPoly Lab Polytechnique Montreal Canada MILA Quebec AI Institute Canada Neurology Department CHU Rennes Rennes France MS Unit Department of Neurology CHU Montpellier Montpellier France Department of Clinical Neuroscience Karolinska Institutet Stockholm Sweden Department of Radiology and Biomedical Imaging Zuckerberg San Francisco General Hospital University of California San FranciscoCA United States National Institute of Neurological Disorders and Stroke National Institutes of Health United States Neuroimaging Research Unit Institute of Experimental Neurology Division of Neuroscience Neurology Unit IRCCS San Raffaele Scientific Institute Milan Italy Vita-Salute San Raffaele University Milan Italy Brigham and Women’s Hospital Harvard Medical School Boston United States AP-HM CHU Timone Pole de Neurosciences Cliniques Department of Neurology Marseille France Aix-Marseille Univ CNRS Marseille France Department of Computer and Software Engineering Polytechnique Montreal Canada Functional Neuroimaging Unit CRIUGM Université de Montréal Montréal Canada

Segmentation of Multiple Sclerosis (MS) lesions is a challenging problem. Several deep-learning-based methods have been proposed in recent years. However, most methods tend to be static, that is, a single model trained on a large, specialized dataset, which does not generalize well. Instead, the model should learn across datasets arriving sequentially from different hospitals by building upon the characteristics of lesions in a continual manner. In this regard, we explore experience replay, a well-known continual learning method, in the context of MS lesion segmentation across multi-contrast data from 8 different hospitals. Our experiments show that replay is able to achieve positive backward transfer and reduce catastrophic forgetting compared to sequential fine-tuning. Furthermore, replay outperforms the multi-domain training, thereby emerging as a promising solution for the segmentation of MS lesions. The code is available at this link. © 2022, CC BY.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Flexible architectures for retinal blood vessel segmentation in high-resolution fundus images

Flexible architectures for retinal blood vessel segmentation...

引用

作者： Bendaoudi, Hamza Cheriet, Farida Manraj, Ashley Ben Tahar, Houssem Langlois, J. M. Pierre Department of Computer and Software Engineering Polytechnique Montréal MontrealQC Canada Diagnos Inc. BrossardQC Canada

Blood vessel segmentation from high-resolution fundus images is a necessary step in several retinal pathologies detection. Automatic blood vessel segmentation is a computing-intensive task, which raises the need for acceleration with hardware architectures. In this paper, we propose two architectures for blood vessel segmentation using a matched filter (MF). The first architecture is a scalable hardware architecture, while the second one is an application-specific instruction-set processor. An efficient, real-time hardware implementation of the algorithm is made possible through parallel processing and efficient resource sharing. A tool for the automatic generation of particularized HDL descriptions of the architecture is proposed. The tool starts from a common architecture template and takes as input the parameters of the MF. A designer thus gains a significant amount of flexibility and productivity with the parameter selection problem and the evaluation of corresponding implementations. Several designs were verified and implemented on an FPGA platform. Performance in terms of area utilization and maximum frequency are reported. The results show significant improvement over state-of-the-art implementations, by up to a factor of 14× for high-resolution fundus images. The second architecture is based on the Tensilica Xtensa LX processor. With only two additional custom instructions requiring an additional 4× the area of the basic processor, the ASIP achieves a significant speedup of 7.76× when compared to the basic processor, while retaining all its flexibility. © 2016, Springer-Verlag Berlin Heidelberg.

关键词： Matched filters

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional analysis of two-way fluid-structure interaction on a flexible hydrofoil in viscous flow

引用

International Journal of Fluid Machinery and Systems 2018年第3期11卷 333-343页

作者： Mortazavinia, Zahra Camarero, Ricardo Guibault, Francois Department of Mechanical Engineering École Polytechnique de Montréal 2900 Boulevard Edouard-Montpetit MontrealH3T 1J4 Canada Department of Computer and Software Engineering École Polytechnique de Montréal 2900 Boulevard Edouard-Montpetit MontrealH3T 1J4 Canada

Two-way Fluid-Structure Interaction of a three dimensional hydrofoil subjected to viscous flow at Re=750000 is investigated in this paper. A rectangular, cantilevered NACA66 hydrofoil is simulated using a finite element based CSDcode, while the fluid flow is modeled with the incompressible, unsteady Reynolds Averaged Navier-Stokes equations using a finite volume based CFD code. The numerical computations are carried out through a strong coupling between these two separate solvers. The strongly coupled FSI solver is validated by comparing the present numerical results with experimental measurements in a water tunnel at the French NavalAcademy. To quantify the FSI effects, rigid (stainless steel) and flexible (POM Poly-acetate) hydrofoils with the same undeformed geometry are simulated and compared. © 2018, Turbomachinery Society of Japan. All rights reserved.

关键词： Fluid structure interaction

来源：评论

学校读者我要写书评

暂无评论

Serverless architecture efficiency: An exploratory study

arXiv

引用

arXiv 2019年

作者： Lavoie, Samuel Garant, Anthony Petrillo, Fabio Department of Computer and Software Engineering Ecole Polytechnique de Montreal Quebec Canada Universit du Qubec de Chicoutimi Department of Mathematics and Computer science 555 boulevard de l’Universit Chicoutimi Canada

Cloud service provider propose services to insensitive customers to use their platform. Different services can achieve the same result at different cost. In this paper, we study the efficiency of a serverless architecture for running highly parallelizable tasks to compare theses services in order to find the most efficient in term of performance and cost. More precisely, we look at the compute time and at the cost per task for a given task. The tasks studied is the count of the occurrence of a given word in a corpus. We compare the serverless architecture to the Apache Spark map reduce technique commonly used for this type of task. Using AWS Lambda for the serverless architecture and Amazon EMR for the Apache Spark map reduce, with similar compute power, we show that the serverless technique achieve comparable performance in term of compute time and cost. We observed that the lambda function is a great approach for real time computing, while EMR is preferable for task that require long compute time. Copyright © 2019, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

VM processes state detection by hypervisor tracing

VM processes state detection by hypervisor tracing

引用

Annual IEEE Systems Conference

作者： Hani Nemati Michel R. Dagenais Department of Computer and Software Engineering Polytechnique Montreal Quebec Canada

ISBN: (纸本)9781538636657

The diagnosis of performance issues in cloud environments is a challenging problem, due to the different levels of virtualization, the diversity of applications and their interactions on the same physical host. Moreover, because of privacy, security, ease of deployment and execution overhead, an agent-less method, which limits its data collection to the physical host level, is often the only acceptable solution. In this paper, a precise host-based method, to recover wait state for the processes inside a given Virtual Machine (VM), is proposed. The virtual Process State Detection (vPSD) algorithm computes the state of processes through host kernel tracing. The state of a virtual Process (vProcess) is displayed in an interactive trace viewer (Trace Compass) for further inspection. Our proposed VM trace analysis algorithm has been open-sourced for further enhancements and for the benefit of other developers. Experimental evaluations were conducted using a mix of workload types (CPU, Disk, and Network), with different applications like Hadoop, MySQL, and Apache. vPSD, being based on host hypervisor tracing, brings a lower overhead (around 0.03%) as compared to other approaches.

关键词： Virtual machine monitors Cloud computing Virtual machining Virtualization Security Monitoring Instruction sets

来源：评论

学校读者我要写书评

暂无评论

Wait analysis of virtual machines using host kernel tracing

Wait analysis of virtual machines using host kernel tracing

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Hani Nemati Genevieve Bastieny Michel R. Dagenaisz Department of Computer and Software Engineering Quebec Canada Department of Computer and Software Engineering Polytechnique Montreal Quebec Canada

An agent-less method to understand virtual machines (VMs) behavior its evolution during the VM life-cycle is an essential task for IaaS provider. It allows the IaaS provider to better scale the VMs resources by properly allocating the physical resources. On the other hand, because of privacy, security, ease of deployment and execution overhead issues, the method presented limits its data collection to the physical host level, without internal access to the VMs. We propose a host-based, precise method to recover wait states for the virtual CPUs (vCPUs) of a given VM. The Wait Analysis Algorithm (W2A) computes the state of vCPUs through the host kernel trace. The state of vCPUs is displayed in an interactive trace viewer (TraceCompass) for further inspection. Our proposed VM trace analysis algorithm has been open-sourced for further enhancements and to the benefit of other developers. Our new technique is being evaluated with representative workloads, generated by different benchmarking tools. These approaches are based on host hypervisor tracing, which brings a lower overhead (around 0.03%) as compared to other approaches.

关键词： Virtual machine monitors Kernel Task analysis Tools Cloud computing Servers Security

来源：评论

学校读者我要写书评

暂无评论

Decentralized connectivity control in quadcopters: A field study of communication performance

arXiv

引用

arXiv 2019年

作者： Paneratiy, Jacopo Ramtoulay, Benjamin St-Ongey, David Caoy, Yanjun Kaufmanny, Marcel Cowley, Aidan Sabattiniz, Lorenzo Beltrame, Giovanni Polytechnique Montréal Department of Software and Computer Engineering Montreal Canada European Space Agency European Astronaut Centre Koln Germany Università Degli Studi di Modenae Reggio Emilia Department of Sciences and Methods for Engineering Reggio Emilia

Redundancy and parallelism make decentralized multi-robot systems appealing solutions for the exploration of extreme environments. However, effective cooperation often requires team-wide connectivity and a carefully designed communication strategy. Several recently proposed decentralized connectivity maintenance approaches exploit elegant algebraic results drawn from spectral graph theory. Yet, these proposals are rarely taken beyond simulations or laboratory implementations. In this work, we present two major contributions: (i) we describe the full-stack implementation-from hardware to software-of a decentralized control law for robust connectivity maintenance;and (ii) we assess, in the field, our setup's ability to correctly exchange all the necessary information required to maintain connectivity in a team of quadcopters. Copyright © 2019, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

An analysis of the semantic annotation task on the linked data cloud

引用

International Journal of Metadata, Semantics and Ontologies 2019年第4期13卷 317-329页

作者： Gagnon, Michel Zouaq, Amal Aranha, Francisco Ensan, Faezeh Jean-Louis, Ludovic Department of Computer Engineering and Software Engineering Polytechnique Montréal C.P. 6079 succ. Centre-ville MontréalQCH3C 3A7 Canada School of Electrical Engineering and Computer Science University of Ottawa 800 King Edward Ave. K1N 6N5 OttawaON Canada Fundaçao Getulio Vargas Escola de Administraçao de Empresas de Sao Paulo Rua Itapeva 474 - 9o andar Bela Vista Sao Paulo SPcep 01332-000 Brazil Ferdowsi University of Mashhad Mashhad Iran University of New Brunswick Fredericton Canada Netmail 180 Peel Street Suite 333 MontrealQCH3C 2G7 Canada

Semantic annotation, the process of identifying key phrases in texts and linking them to concepts in a knowledge base, is an important basis for semantic information retrieval and the semantic web uptake. Despite the emergence of semantic annotation systems, very few comparative studies have been published on their performance. In this paper, we provide an evaluation of the performance of existing systems over three tasks: full semantic annotation, named entity recognition, and keyword detection. More specifically, the spotting capability (recognition of relevant surface forms in text) is evaluated for all three tasks, whereas the disambiguation (correctly associating an entity from Wikipedia or DBpedia to the spotted surface forms) is evaluated only for the first two tasks. We use logistic regression to identify significant performance differences. Although some of the annotators are specifically targeted at some task (NE, SA, KW), our results show that they do not necessarily obtain the best performance on those tasks. In fact, systems identified as full semantic annotators beat all other systems on all data sets. We also show that there is still much room for improvement for the identification of the most relevant entities described in a text. Copyright © The Author(s) 2019.

关键词： Linked data

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：