检索结果-内蒙古大学图书馆

Network-Aware Container Scheduling in Multi-Tenant Data Center

学校读者我要写书评

暂无评论

Network-Aware Container Scheduling in Multi-Tenant Data Cent...

IEEE Global Communications Conference

作者： Leonardo R. Rodrigues Marcelo Pasin Omir C. Alves Charles C. Miers Mauricio A. Pillon Pascal Felber Guilherme P. Koslovski Graduate Program in Applied Computing Santa Catarina State University Joinville Brazil University of Neuchâtel (UniNE) Institut d'informatique Switzerland

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Network management on multi-tenant container-based data center has critical impact on performance. Tenants encapsulate applications in containers abstracting away details on hosting infrastructures, and entrust data center management framework with the provisioning of network Quality-of-Service requirements. In this paper, we propose a network-aware multi-criteria container scheduler to jointly process containers and network requirements. We introduce a new Mixed Integer Linear programming formulation for network-aware scheduling encompassing both tenants and providers metrics. We describe two GPU-accelerated modules to address the complexity barrier of the problem and efficiently process scheduling requests. Our experiments show that our scheduling approach accounting for both network and containers outperforms traditional algorithms used by containers orchestrators.

关键词： Containers Servers Bandwidth Quality of service Resource management Scheduling Processor scheduling

A Tutorial on Trusted and Untrusted Non-3GPP Accesses in 5G Systems - First Steps Toward a Unified Communications Infrastructure

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lemes, Mario Teixeira Alberti, Antonio Marcos Both, Cristiano Bonato de Oliveira, Antonio Carlos Cardoso, Kleber Vieira Instituto Federal de Educação Ciência e Tecnologia de Goiás Formosa73813-816 Brazil Instituto de Informática Universidade Federal de Goiás Goiânia74690-900 Brazil Instituto Nacional de Telecomunicações Santa Rita do Sapucaí37540-000 Brazil Applied Computing Graduate Program Universidade do Vale do Rio dos Sinos São Leopoldo93022-750 Brazil Fraunhofer AICOS Porto4200-135 Portugal

fifth-generation (5G) systems are designed to enable convergent access-agnostic service availability. This means that 5G services will be available over 5G New Radio air interface and also through other non-Third Generation Partnership Project (3GPP) access networks, e.g., IEEE 802.11 (Wi-Fi). 3GPP has recently published the Release 16 that includes trusted non-3GPP access network concept and wireless wireline convergence. The main goal of this tutorial is to present an overview of access to 5G core via non-3GPP access networks specified by 3GPP until Release 16 (i.e., untrusted, trusted, and wireline access). The tutorial describes convergence aspects of a 5G system and these non-3GPP access networks, such as the authentication and authorization procedures and the data session establishment from the point of view of the protocol stack and exchanged messages among the network functions. In order to illustrate several concepts and part of 3GPP specification, we present a basic but fully operational implementation of untrusted non-3GPP access using WLAN. We perform experiments illustrating how a Wi-Fi user is authorized in a 5G core, establishing user plane connectivity to a data network. Moreover, we evaluate the performance of this access in terms of time consumed, the number of messages, and protocol overhead to established data sessions. © 2021, CC BY.

关键词： Wi-Fi

Artificial neural network-based method to classify sedimentary rocks 12

学校读者我要写书评

暂无评论

Artificial neural network-based method to classify sedimenta...

12th International Conference on Sensing Technology, ICST 2018

作者： Figueiredo, Rodrigo Marques Veronez, Mauricio Roberto Wohnrath, Francisco Manoel Da Silva, Marcio Rosa Gonzaga, Luiz Kupssinsku, Lucas Silveira Bordin, Fabiane Brum, Diego Cazarin, Caroline Lessio Graduate Program in Geology Unisinos University Saõ Leopoldo Brazil Advanced Visualization and Geoinformatics Laboratory Unisinos University Saõ Leopoldo Brazil Graduate Program in Electrical Engineering Unisinos University Saõ Leopoldo Brazil Graduate Program in Applied Computing Unisinos University Saõ Leopoldo Brazil Rio de Janeiro Brazil

ISBN: (纸本)9781538651476

In a geological study, an important step is to determine the type of sedimentary rock or its grain size. Such a determination requires accurate analysis in the field or in a laboratory. As the size of the study area grows, this activity can be time consuming and error prone because the number of specialists working under rigid criteria also increases. This paper proposes a novel methodology to classify grain size using unique wavelength reflectance data and artificial neural networks. The results indicate that the proposed method can be reliably used in the field. © 2018 IEEE.

关键词： Neural networks

An Analysis of Machine Learning Classifiers in Breast Cancer Diagnosis

学校读者我要写书评

暂无评论

An Analysis of Machine Learning Classifiers in Breast Cancer...

Conferencia Latinoamericana En Informatica (CLEI)

作者： Fabiano Teixeira João Luis Zeni Montenegro Cristiano André da Costa Rodrigo da Rosa Righi Software Innovation Laboratory - SOFTWARELAB Applied Computing Graduate Program Universidade do Vale do Rio dos Sinos - UNISINOS Av Unisinos 950 Sao Leopoldo 93022-750 Brazil

ISBN: (数字)9781728155746

ISBN: (纸本)9781728155753

In the field of assisted cancer diagnosis, it is expected that the involvement of machine learning in diseases will give doctors a second opinion and help them to make a faster / better determination. There are a huge number of studies in this area using traditional machine learning methods and in other cases, using deep learning for this purpose. This article aims to evaluate the predictive models of machine learning classification regarding the accuracy, objectivity, and reproducible of the diagnosis of malignant neoplasm with fine needle aspiration. Also, we seek to add one more class for testing in this database as recommended in previous studies. We present six different classification methods: Multilayer Perceptron, Decision Tree, Random Forest, Support Vector Machine and Deep Neural Network for evaluation. For this work, we used at University of Wisconsin Hospital database which is composed of thirty values which characterize the properties of the nucleus of the breast mass. As we showed in result sections, DNN classifier has a great performance in accuracy level (92%), indicating better results in relation to traditional models. Random forest 50 and 100 presented the best results for the ROC curve metric, considered an excellent prediction when compared to other previous studies published.

关键词： Machine learning Breast cancer Support vector machines Neural networks Forestry

On Cyclic Finite-State Approximation of Data-Driven Systems

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Vides, Fredy Scientific Computing Innovation Center Department of Applied Mathematics Universidad Nacional Autónoma de Honduras UNAH Honduras Graduate Program in Structural Engineering Universidad Tecnológica Centroamericana UNITEC Honduras

In this document, some novel theoretical and computational techniques for constrained approximation of data-driven systems, are presented. The motivation for the development of these techniques came from structure-preserving matrix approximation problems that appear in the fields of system identification and model predictive control, for data-driven systems and processes. The research reported in this document is focused on finite-state approximation of data-driven systems. Some numerical implementations of the aforementioned techniques in the simulation and model predictive control of some generic data-driven systems, that are related to electrical signal transmission models, are outlined.93B28, 47N70 (primary) and 93C57, 93B40 (secondary) Copyright © 2019, The Authors. All rights reserved.

关键词： Singular value decomposition

Experience sharing between cooperative reinforcement learning agents

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Souza, Lucas Oliveira de Oliveira Ramos, Gabriel Ralha, Celia Ghedini Numenta Redwood City United States Graduate Program in Applied Computing Universidade do Vale do Rio dos Sinos São Leopoldo Brazil Computer Science Department University of Brasilia Brasilia Brazil

The idea of experience sharing between cooperative agents naturally emerges from our understanding of how humans learn. Our evolution as a species is tightly linked to the ability to exchange learned knowledge with one another. It follows that experience sharing (ES) between autonomous and independent agents could become the key to accelerate learning in cooperative multiagent settings. We investigate if randomly selecting experiences to share can increase the performance of deep reinforcement learning agents, and propose three new methods for selecting experiences to accelerate the learning process. Firstly, we introduce Focused ES, which prioritizes unexplored regions of the state space. Secondly, we present Prioritized ES, in which temporal-difference error is used as a measure of priority. Finally, we devise Focused Prioritized ES, which combines both previous approaches. The methods are empirically validated in a control problem. While sharing randomly selected experiences between two Deep Q-Network agents shows no improvement over a single agent baseline, we show that the proposed ES methods can successfully outperform the baseline. In particular, the Focused ES accelerates learning by a factor of 2, reducing by 51% the number of episodes required to complete the task. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

Quantum Walks–Based Adaptive Distribution Generation with Efficient CUDA-Q Acceleration

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chang, Yen Jui Wang, Wei-Ting Liu, Chen-Yu Wang, Yun-Yuan Chang, Ching-Ray Master Program in Intelligent Computing and Big Data Chung Yuan Christian University No. 200 Zhongbei Rd. Zhongli Dist Taoyuan City320314 Taiwan Quantum Information Center Chung Yuan Christian University No. 200 Zhongbei Rd. Zhongli Dist Taoyuan City320314 Taiwan Department of Physics National Taiwan University No. 1 Sec. 4 Roosevelt Rd. Taipei106319 Taiwan Graduate Institute of Applied Physics National Taiwan University No. 1 Sec. 4 Roosevelt Rd. Taipei106319 Taiwan NVIDIA AI Technology Center NVIDIA Corp Taipei610101 Taiwan

We present a novel Adaptive Distribution Generator (ADG) that leverages a quantum walks–based approach to generate high precision and efficiency of target probability distributions. Our method integrates variational quantum circuits with discrete-time quantum walks(DTQWs)—specifically, split-step quantum walks(SSQWs) and their entangled extensions—to dynamically tune coin parameters and drive the evolution of quantum states towards desired distributions. This enables accurate one-dimensional probability modeling for applications such as financial simulation and structured two-dimensional pattern generation exemplified by digit representations (0–9). Implemented within the CUDA-Q framework, our approach exploits GPU acceleration to significantly reduce computational overhead and improve scalability relative to conventional methods. Extensive benchmarks demonstrate that our Quantum Walk–Based Adaptive Distribution Generator (QWs-based ADG) achieves high simulation fidelity and bridges the gap between theoretical quantum algorithms and practical high-performance computation. © 2025, CC BY.

关键词： Qubits

3D data acquisition using stereo camera 38

学校读者我要写书评

暂无评论

3D data acquisition using stereo camera

38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018

作者： Kirsten, Evandro Inocencio, Leonardo Campos Veronez, Maurício Roberto Da Silveira, Luiz Gonzaga Bordin, Fabiane Marson, Fernando Pinho Advanced Visualization and Geoinformatics Laboratory UNISINOS Saõ Leopoldo RS Brazil Graduate Program on Applied Computing UNISINOS Av. UNISINOS 950 Saõ Leopoldo RS93022-750 Brazil

ISBN: (纸本)9781538671504

Computer vision systems allow digital reconstruction of targets by capturing information through remote sensors such as video cameras and scanners. In this context, the objective of this work was to evaluate the capacity and quality of three-dimensional reconstruction of static targets using the ZED stereoscopic camera. For this goal, we took images of several environments and objects with different surfaces, textures, lighting, distances and acquisition speeds. The results were compared with high-density and high precision point clouds obtained from the targets using a Leica Viva TS15 total station. The data were processed in the CloudCompare software to calculate the displacement between the models generated by the camera and the total station. Under certain circumstances, this technology is able to reconstruct three-dimensional objects and environments with an error of a few centimeters. © 2018 IEEE.

关键词： Computer vision

SDN4Moodle: an SDN-based Toolset to Enhance QoS of Moodle Platform

学校读者我要写书评

暂无评论

SDN4Moodle: an SDN-based Toolset to Enhance QoS of Moodle Pl...

IEEE Symposium on Computers and Communications (ISCC)

作者： Anderson H. da Silva Marcondes Charles C. Miers Maurcio A. Pillon Guilherme P. Koslovski Graduate Program in Applied Computing Santa Catarina State University Joinville Brazil

Network configuration, performance, and congestion impact the Quality of Service (QoS) of Moodle Learning Management System (LMS). Moreover, LMSs composing modules have different QoS demands for each activity. Upon a network, they compete for resources with applications for social media, streaming, chat, cloud file synchronization, games, among others. Eventually, the network congestion can leave the LMS service unavailable for students and professors. Recently, the popularization of Software Defined Networks (SDN) revolutionized the network management. We propose SDN4Moodle, a toolset to increase the QoS of Moodle services. SDN4Moodle was implemented in conformity to Moodle's plugin guidelines, and it is controlled by internal Moodle events. Each action performed by a Moodle's user is dynamically translated into network forwarding rules, and switches configuration. Our experimental results indicates SDN4Moodle, an open-source system, efficiently achieves flows isolation and bandwidth control on shared networks.

关键词： Quality of service Monitoring Protocols Streaming media Servers Control systems Computers