检索结果-内蒙古大学图书馆

Structure-Exploiting Discriminative Ordinal Multioutput Regression

ieee TRANSACTIONS ON NEURAL networkS AND LEARNING SYSTEMS 2021年第1期32卷 266-280页

作者： Tian, Qing Cao, Meng Chen, Songcan Yin, Hujun Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Collaborat Innovat Ctr Atmospher Environm & Equip Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Jiangsu Engn Ctr Network Monitoring Nanjing 210044 Peoples R China Chinese Acad Sci Natl Lab Pattern Recognit Inst Automat Beijing 100190 Peoples R China Nanjing Univ Aeronaut & Astronaut MIIT Key Lab Pattern Anal & Machine Intelligence Nanjing 210016 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 210016 Peoples R China Univ Manchester Dept Elect & Elect Engn Manchester M13 9PL Lancs England

Although the least-squares regression (LSR) has achieved great success in regression tasks, its discriminating ability is limited since the margins between classes are not specially preserved. To mitigate this issue, dragging techniques have been introduced to remodel the regression targets of LSR. Such variants have gained certain performance improvement, but their generalization ability is still unsatisfactory when handling real data. This is because structure-related information, which is typically contained in the data, is not exploited. To overcome this shortcoming, in this article, we construct a multioutput regression model by exploiting the intraclass correlations and input-output relationships via a structure matrix. We also discriminatively enlarge the regression margins by embedding a metric that is guided automatically by the training data. To better handle such structured data with ordinal labels, we encode the model output as cumulative attributes and, hence, obtain our proposed model, termed structure-exploiting discriminative ordinal multioutput regression (SEDOMOR). In addition, to further enhance its distinguishing ability, we extend the SEDOMOR to its nonlinear counterparts with kernel functions and deep architectures. We also derive the corresponding optimization algorithms for solving these models and prove their convergence. Finally, extensive experiments have testified the effectiveness and superiority of the proposed methods.

关键词： Measurement Data models Optimization Pattern recognition Correlation Kernel Linear programming Discriminative least-squares regression (LSR) least-squares regression multioutput regression ordinal multioutput regression structure-exploiting

来源：评论

学校读者我要写书评

暂无评论

A model-based approach for developing event-driven architectures with AsyncAPI 20

A model-based approach for developing event-driven architect...

引用

23rd ACM/ieee International conference on Model Driven Engineering Languages and Systems (MODELS)

作者： Gomez, Abel Iglesias-Urkia, Markel Urbieta, Aitor Cabot, Jordi Univ Oberta Catalunya Internet Interdisciplinary Inst IN3 Barcelona Spain Basque Res & Technol Alliance Ikerlan Technol Res Ctr Arrasate Mondragon Spain Univ Oberta Catalunya Internet Interdisciplinary Inst IN3 ICREA Barcelona Spain

ISBN: (纸本)9781450370196

In this Internet of Things (IoT) era, our everyday objects have evolved into the so-called cyber-physical systems (CPS). The use and deployment of CPS has especially penetrated the industry, giving rise to the Industry 4.0 or Industrial IoT (IIoT). Typically, architectures in IIoT environments are distributed and asynchronous, communication being guided by events such as the publication of (and corresponding subscription to) messages. While these architectures have some clear advantages (such as scalability and flexibility), they also raise interoperability challenges among the agents in the network. Indeed, the knowledge about the message content and its categorization (topics) gets diluted, leading to consistency problems, potential losses of information and complex processing requirements on the subscriber side to try to understand the received messages. In this paper, we present our proposal relying on AsyncAPI to automate the design and implementation of these architectures using model-based techniques for the generation of (part of) event-driven infrastructures. We have implemented our proposal as an open-source tool freely available online.

关键词： publish-subscribe cyber-physical systems (CPS) event-driven architectures AsyncAPI Industrial Internet of Things (IIoT)

来源：评论

学校读者我要写书评

暂无评论

Magnet: Method-Based Approach Using Graph Neural network for Microservices Identification

Magnet: Method-Based Approach Using Graph Neural Network for...

引用

Working ieee/IFIP conference on Software Architecture

作者： Imen Trabelsi Naouel Moha Yann-Gaël Guéhéneuc Lucas Geffard Software and IT Engineering Department École de technologie supérieure ÉTS Montréal Canada Computer Science and Software Engineering Concordia University Montréal Canada

ISBN: (数字)9798350359169

ISBN: (纸本)9798350359176

Monolithic software systems face significant challenges in terms of maintenance, scalability, and portability. To address these challenges, many companies are embracing the microservices architectural style as a more flexible alternative to their monoliths. Microservices structure systems into modular, independent components, enabling easier development, deployment, and maintenance. However, the migration from a monolith to microservices is challenging due to the laborious task of manually identifying and decomposing a system into microservices. Several earlier studies focused on developing approaches to facilitate the migration process. However, the reliance on domain experts to define various parameters and thresholds restricted their use. In this paper, we introduce Magnet, a fully automated microservice identification approach, based on graph neural networks (GNNs). Magnet integrates a GNN model with a fine-grained method-based graph enriched with semantic and static features of the system. It enables accurate microservices identification while simultaneously promoting microservice cohesion and reducing microservice coupling. To validate the accuracy of Magnet, we performed extensive experiments using a set of open-source systems. Quantitatively, we use a set of quality metrics to assess the resulting microservices quality. We also compare our results to established ground truths. Empirical evidence suggests that our fully-automated approach Magnet achieves precision and recall rates of 56% and 68%. Qualitatively, we assess the modularity and functional independence of the resulting microservices by examining their relationships and semantic integrity. This evaluation demonstrates that our fully automated approach yields promising results, underlining its effectiveness in creating modular and coherent microservices.

关键词： Accuracy Software architecture Scalability Semantics Microservice architectures Magnetic domains Software systems

来源：评论

学校读者我要写书评

暂无评论

Design Space Exploration with Deterministic Latency Guarantees for Crossbar MPSoC architectures

Design Space Exploration with Deterministic Latency Guarante...

引用

ieee International conference on Communications (ieee ICC) / Workshop on NOMA for 5G and Beyond

作者： Uscumlic, Bogdan Enrici, Andrea Pacalet, Renaud Gharbi, Amna Apvrille, Ludovic Natarianni, Lionel Roullet, Laurent Paris Saclay Nokia Bell Labs Gif Sur Yvette France Inst Polytech Paris Telecom Paris LTCI Paris France

ISBN: (纸本)9781728150895

MPSoC and NoC systems are often used in complex telecommunication systems, which in the 5G era need to enable telecommunication services with unprecedented latency characteristics. Indeed, new services emerge, needing deterministic latency guarantees with virtually no system jitter, during the lifetime of the established telecommunication service. In this work, for the first time, we propose an optimal solution for a design space exploration (DSE) optimization problem, that performs all the traditional DSE tasks, but with end-to-end deterministic latency guarantees. We focus on MPSoC or NoC architectures with crossbars, although this work can be easily extended to more complex architectures. More precisely, our contributions in this work are the following: 1) we propose a novel method for deterministic scheduling in MPSoC and NoC architectures with a crossbar;2) we propose an optimal solution in the form of an integer linear program (ILP) for DSE problem with end-to-end deterministic latency guarantees;3) we identify the trade-off between the latency due to the use of crossbar time slots and the application execution time at different processing elements. The numerical results suggest that the proposed deterministic scheduling method can efficiently use all 100% of the crossbar capacity, depending on available application load and system parameters.

关键词： design space exploration data communication linear programming crossbar embedded system architectures

来源：评论

学校读者我要写书评

暂无评论

Dynamic Defense In-Depth Model for SDN Control Layer to Enhance openFlow Protocol Security 21

Dynamic Defense In-Depth Model for SDN Control Layer to Enha...

引用

7th International conference on Engineering and MIS, ICEMIS 2021

作者： Elhejazi, Mahmoud F. Musbah, Mohamed S. University of Benghazi Benghazi Libya

ISBN: (纸本)9781450390446

The traditional long-established networks and networking techniques are no longer suitable for future ever-expanding networking requirements, specifically, the automation and programmability of network communications. Software-Defined networking (SDN) is the most agreeable solution for that. SDN logically uses a centralized controller that applies a standard open Application programming Interface (API) to directly control the packet handling functions of network devices. openFlow is currently the main and widely known communication protocol in SDN architectures. As a result of such centralization, the SDN architecture subjected the controller as a single point with more attacks surfaces for each layer. This entails the search for more security and protection procedures to the SDN architecture without scarifying its swift response to changing business requirements. This paper aims to enhance the protection of the divisions' concept in SDN architecture, which reduces the creation of more attack surfaces that can be targeted by malicious activities. Thus, the research focuses on the design of a dependable SDN controller platform model via Defense In-Depth (DID) techniques, including the requirements for a secure, resilient, and robust controller. The Dynamic Defense In-Depth (DDID) model is proposed to be deployed for the SDN control layer to enhance overall openFlow protocol security. Detailed measurable threats and protection mechanisms, according to the DDID model, were investigated and implemented using a simulation environment (mininet). Also, the paper proposes an evaluation mechanism (and tests) to confirm the applicability of secure structure requirements to the SDN controller layer. The obtained results confirm the promising potential of achieving the required security goals. © 2021 ACM.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

A New Qubits Mapping Mechanism for Multi-programming Quantum Computing 20

A New Qubits Mapping Mechanism for Multi-programming Quantum...

引用

ACM International conference on Parallel architectures and Compilation Techniques (PACT)

作者： Dou, Xinglei Liu, Lei Chinese Acad Sci Sys Inventor Lab ICT SKLCA Beijing Peoples R China

ISBN: (纸本)9781450380751

For a specific quantum chip, multi-programming helps to improve the overall throughput and resource utilization. However, previous solutions for mapping multiple programs often lead to resource under-utilization, high error rate, and low fidelity. In this paper, we propose a new approach to map concurrent quantum programs. Our approach has three critical components. The first one is the Community Detection Assisted Partition (CDAP) algorithm, which partitions physical qubits for concurrent quantum programs by considering physical typology and the error rate, avoiding the waste of robust resources. The second one is the X-SWAP scheme that enables inter-program SWAPs and prioritizes SWAPs associated with critical gates to reduce the SWAP overheads. Finally, we propose a compilation task scheduler, which dynamically selects concurrent quantum programs to be compiled and executed together based on estimated fidelity for the best practice. We evaluate our work on publicly available quantum computer IBMQ16 and a simulated quantum chip IBMQ50. Our work outperforms the state-of-the-art work for multi-programming on fidelity and compilation overheads by 12.0% and 11.6%, respectively.

关键词： multi-programming scheduling quantum computing

来源：评论

学校读者我要写书评

暂无评论

GOPipe: A Granularity-Oblivious programming Framework for Pipelined Stencil Executions on GPU 20

GOPipe: A Granularity-Oblivious Programming Framework for Pi...

引用

ACM International conference on Parallel architectures and Compilation Techniques (PACT)

作者： Oh, Chanyoung Zheng, Zhen Shen, Xipeng Zhai, Jidong Yi, Youngmin Univ Seoul Seoul South Korea Alibaba Grp Hangzhou Peoples R China North Carolina State Univ Raleigh NC 27695 USA Tsinghua Univ BNRist Beijing Peoples R China

ISBN: (纸本)9781450380751

Recent studies have shown promising performance benefits when multiple stages of a pipelined stencil application are mapped to different parts of a GPU to run concurrently. An important factor for the computing efficiency of such pipelines is the granularity of a task. In previous programming frameworks that support true pipelined computations on GPU, the choice has to be made by the programmers during the application development time. Due to many difficulties, programmers' decisions are often far from optimal, causing inferior performance and performance portability. This paper presents GOPipe, a granularity-oblivious programming framework for efficient pipelined stencil executions on GPU. With GOPipe, programmers no longer need to specify the appropriate task granularity. GOPipe automatically finds it, and dynamically schedules tasks of that granularity for efficiency while observing all inter-task and inter-stage data dependencies. In our experiments on six real-life applications and various scenarios, GOPipe outperforms the state-of-the-art system by 1.39x on average with a much better programming productivity.

关键词： programming Framework GPU Optimizations

来源：评论

学校读者我要写书评

暂无评论

network Intelligence for Virtualized RAN Orchestration: The DAEMON Approach

Network Intelligence for Virtualized RAN Orchestration: The ...

引用

European conference on networks and Communications (EuCNC)

作者： Marco Gramaglia Miguel Camelo Lidia Fuentes Joaquí n Ballesteros Gabriele Baldoni Luca Cominardi Andres Garcia-Saavedra Marco Fiore University Carlos III of Madrid IDLab University of Antwerp - imec ITIS Software Universidad de M&#x00E1 laga ADLINK Technology NEC Laboratories Europe IMDEA Networks Institute

Next-generation mobile networks will largely benefit from advances in softwarization and cloudification of network functions. However, fully exploiting the new potential of flexible network architectures in front of increasingly demanding service volumes and requirements calls for an extremely effective integration of network Intelligence (NI) solutions into production infrastructures. While current standardization efforts towards embedding NI in beyond-5G and 6G systems are still in their infancy, the DAEMON project is developing technologies for a NI-native generation of mobile networks. In this paper, we present current evolutions proposed by DAEMON in terms of a general model for the representation of NI instances, which facilitates their synergic integration in network environments. We showcase the practical viability and advantages of the proposed approach with two state-of-the-art NI algorithms for vRAN orchestration implemented into an open-source data flow programming framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bistatic Radar Experiments with UAV: Qualification and Performance of a Miniaturized Instrument

Bistatic Radar Experiments with UAV: Qualification and Perfo...

引用

ieee Aerospace conference (AeroConf)

作者： Oudrhiri, Kamal Rodriguez-Alvarez, Nereida Yang, Yu-Ming Lay, Norman E. Buccino, Dustin Shin, Dong Podest, Erika Brockers, Roland CALTECH Commun Architectures & Res Sect Jet Prop Lab 4800 Oak Grove Dr Pasadena CA 91109 USA CALTECH Planetary Radar & Radio Sci Grp Jet Prop Lab 4800 Oak Grove Dr Pasadena CA 91109 USA CALTECH Deep Space Tracking Syst Grp Jet Prop Lab 4800 Oak Grove Dr Pasadena CA 91109 USA CALTECH Carbon Cycle & Ecosyst Grp Jet Prop Lab 4800 Oak Grove Dr Pasadena CA 91109 USA CALTECH Aerial Mobil Grp Jet Prop Lab 4800 Oak Grove Dr Pasadena CA 91109 USA

ISBN: (纸本)9781728174365

Spacecraft-to-ground bistatic radar is an established technique that has enabled the study of the planetary surfaces and near sub-surfaces properties by using the telecommunication signals amplitude, phase, and polarization. The Planetary Radar and Radio Science group at the Jet Propulsion Laboratory (JPL) has been involved in many planetary bistatic radar experiments since the 1970's using orbiters and Deep Space network (DSN) antennas. The recent advances in Unmanned Aerial Vehicles (UAVs) technologies are making the UAVs more popular in scientific surveying applications. One such application is the use of UAVs in bistatic radar measurements to explore surfaces on Earth. Our analyses show that UAV-based bistatic radar measurements will improve our understanding of the finer-scale characteristic variations of the surface by acquiring the higher resolution data for a specific region of interest compared to data obtained from a spacecraft. The Mars helicopter, a technology demonstration to test the first powered flight on Mars, will be the beginning of a new era of exploration with UAVs on Mars. This leap in planetary UAV technology has renewed the importance of developing a miniaturized bistatic radar instrument (under 1 kg) compatible with a UAV platform able to meet the science requirements for studying surfaces on Earth, Mars, and other planetary bodies. As part of a task at JPL, we have been working on a technology demonstration using a compact bistatic radar instrument designed to be the payload of a UAV employing signals of opportunity from Earth's orbiters, i.e. Global Positioning System (GPS). In this paper, we present our design and development of the instrument, our evaluation of different L-band antennas, the performance of compact open-loop receivers in support of Earth and planetary bistatic radar observations, and the instrument fit test on an UAV platform. As part of this publication, we also highlight the results of a field experiment dedicated to te

关键词： Earth Space vehicles Mars Sensitivity Instruments Bistatic radar Radar antennas

来源：评论

学校读者我要写书评

暂无评论

programming heterogeneous CPU-GPU systems by high-level dataflow synthesis 34

Programming heterogeneous CPU-GPU systems by high-level data...

引用

34th ieee Workshop on Signal Processing Systems (SiPS)

作者： Bloch, Aurelien Bezati, Endri Mattavelli, Marco Ecole Polytech Fed Lausanne SCI STI MM Lausanne Switzerland Ecole Polytech Fed Lausanne VLSC Lausanne Switzerland

ISBN: (纸本)9781728180991

Heterogeneous processing platforms combining in various architectures CPUs, GPUs, and programmable logic, are continuously evolving providing at each generation higher theoretical levels of computing performance. However, the challenge of how efficiently specify and explore the design space of applications executing on the different components of heterogeneous platforms remains an open problem and is the subject of many research efforts. The paper describes a dataflow based approach for the synthesis of applications to be executed on mixed CPU and GPU architectures. The new high-level approach consists of partitioning the application dataflow program written in RVC-CAL into CPU and GPU components, then on generating by automatic synthesis the C++ and CUDA programs that together implement the application executable. The design approach provides portability of applications on CPUs, GPUs, and mixed CPU/GPU architectures as well as the possibility of exploring the design space of all partitioning options without the need of rewriting the application code. The paper describes the essential methodology features at the base of the synthesis of CPU/GPU code and reports some example design cases validating the correctness of the approach.

关键词： dynamic dataflow programs RVC-CAL parallel computing source-to-source compiler GPU programming heterogeneous systems

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：