检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Cortés, Andoni Rodríguez, Clemente Vélez, Gorka Barandiarán, Javier Nieto, Marcos Deparment of Intelligent Transportation Systems and Engineering Deparment Vicomtech Paseo Mikeletegi 57 San Sebastian20009 Spain Dpt. of Computer Architecture San Sebastian Spain

A major challenges of deep learning (DL) is the necessity to collect huge amounts of training data. Often, the lack of a sufficiently large dataset discourages the use of DL in certain applications. Typically, acquiring the required amounts of data costs considerable time, material and effort. To mitigate this problem, the use of synthetic images combined with real data is a popular approach, widely adopted in the scientific community to effectively train various detectors. In this study, we examined the potential of synthetic data-based training in the field of intelligent transportation systems. Our focus is on camera-based traffic sign recognition applications for advanced driver assistance systems and autonomous driving. The proposed augmentation pipeline of synthetic datasets includes novel augmentation processes such as structured shadows and gaussian specular highlights. A well-known DL model was trained with different datasets to compare the performance of synthetic and real image-based trained models. Additionally, a new, detailed method to objectively compare these models is proposed. Synthetic images are generated using a semi-supervised errors-guide method which is also described. Our experiments showed that a synthetic image-based approach outperforms in most cases real image-based training when applied to cross-domain test datasets (+10% precision for GTSRB dataset) and consequently, the generalization of the model is improved decreasing the cost of acquiring images. © 2024, CC BY-NC-ND.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Decision Support Framework for Automating the Optimization of Edge Computing Federations

Decision Support Framework for Automating the Optimization o...

引用

Annual Modeling and Simulation Conference (ANNSIM)

作者： Antonio F. Rodríguez-Liria Román Cárdenas Patricia Arroba José M. Moya José L. Risco-Martín Gabriel Wainer Laboratorio de Sistemas Integrados (LSI) CCS–Center for Computational Simulation Universidad Politécnica de Madrid Madrid Spain Dpt. of Computer Architecture and Automation Universidad Complutense de Madrid Madrid Spain Dpt. of Systems and Computer Engineering Carleton University Ottawa ON Canada

Modern IoT applications present demanding Quality of Service (QoS) requirements that can no longer rely on a centralized solution to offload compute-intensive tasks. Edge Computing tackles these limitations by extending the Cloud to the edge of the network. However, the distributed and complex nature of Edge infrastructures introduces new technical challenges that must be addressed to develop a successful solution. Modeling, Simulation, and Optimization (M&S&O) tools can aid in the automatic design of modern Edge deployments. Here we present a decision support module that allows practitioners to automatically improve aspects of their Edge infrastructure by applying different optimization algorithms, such as simulated annealing, tabu search, and stochastic hill climbing. Furthermore, the structure of this module allows us to extend the available optimization methods if needed. We illustrate how this tool can help us to improve energy consumption policies of Edge Computing facilities and reduce their operational costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey of Recent Developments in Testability, Safety and Security of RISC-V Processors

A Survey of Recent Developments in Testability, Safety and S...

引用

IEEE European Test Symposium (ETS)

作者： Jens Anders Pablo Andreu Bernd Becker Steffen Becker Riccardo Cantoro Nikolaos I. Deligiannis Nourhan Elhamawy Tobias Faller Carles Hernandez Nele Mentens Mahnaz Namazi Rizi Ilia Polian Abolfazl Sajadi Mathias Sauer Denis Schwachhofer Matteo Sonza Reorda Todor Stefanov Ilya Tuzov Stefan Wagner Nuša Zidarič Institute of Smart Sensors University of Stuttgart Stuttgart Germany Universitat Politècnica de València Spain Dpt. of Computer Science University of Freiburg Freiburg Germany Institute of Software Engineering University of Stuttgart Stuttgart Germany Dpt. of Control and Computer Engineering Politecnico di Torino Turin Italy Institute of Computer Architecture and Computer Engineering University of Stuttgart Stuttgart Germany LIACS Leiden University Leiden Netherlands Advantest Europe Boeblingen Germany

With the continued success of the open RISC-V architecture, practical deployment of RISC-V processors necessitates an in-depth consideration of their testability, safety and security aspects. This survey provides an overview of recent developments in this quickly-evolving field. We start with discussing the application of state-of-the-art functional and system-level test solutions to RISC-V processors. Then, we discuss the use of RISC-V processors for safety-related applications; to this end, we outline the essential techniques necessary to obtain safety both in the functional and in the timing domain and review recent processor designs with safety features. Finally, we survey the different aspects of security with respect to RISC-V implementations and discuss the relationship between cryptographic protocols and primitives on the one hand and the RISC-V processor architecture and hardware implementation on the other. We also comment on the role of a RISC-V processor for system security and its resilience against side-channel attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A HYPOTHESIS-DRIVEN METHOD BASED ON MACHINE LEARNING FOR NEUROIMAGING DATA ANALYSIS

arXiv

引用

arXiv 2022年

作者： Saez, Juan Manuel Gorriz Clemente, R. Martin Puntonet, C.G. Ortiz, A. Ramirez, J. Suckling, John Dasci Institute University of Granada Granada Spain Dpt. Signal Theory and Communications University of Seville Seville Spain Dpt. Computer Architecture and Tech. University of Granada Granada Spain Dpt. Communication Engineering University of Malaga Malaga Spain Department of Psychiatry University of Cambridge Cambridge United Kingdom

There remains an open question about the usefulness and the interpretation of Machine learning (MLE) approaches for discrimination of spatial patterns of brain images between samples or activation states. In the last few decades, these approaches have limited their operation to feature extraction and linear classification tasks for between-group inference. In this context, statistical inference is assessed by randomly permuting image labels or by the use of random effect models that consider between-subject variability. These multivariate MLE-based statistical pipelines, whilst potentially more effective for detecting activations than hypotheses-driven methods, have lost their mathematical elegance, ease of interpretation, and spatial localization of the ubiquitous General linear Model (GLM). Recently, the estimation of the conventional GLM has been demonstrated to be connected to an univariate classification task when the design matrix is expressed as a binary indicator matrix. In this paper we explore the complete connection between the univariate GLM and MLE regressions. To this purpose we derive a refined statistical test with the GLM based on the parameters obtained by a linear Support Vector Regression (SVR) in the inverse problem (SVR-iGLM). Subsequently, random field theory (RFT) is employed for assessing statistical significance following a conventional GLM benchmark. Experimental results demonstrate how parameter estimations derived from each model (mainly GLM and SVR) result in different experimental design estimates that are significantly related to the predefined functional task. Moreover, using real data from a multisite initiative the proposed MLE-based inference demonstrates statistical power and the control of false positives, outperforming the regular GLM. © 2022, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

The DEVStone Metric: Performance Analysis of DEVS Simulation Engines

arXiv

引用

arXiv 2023年

作者： Cárdenas, Román Henares, Kevin Arroba, Patricia Risco-Martín, José L. Wainer, Gabriel A. Integrated Systems Laboratory Universidad Politécnica de Madrid Madrid Spain Dept. of Systems and Computer Engineering Carleton University OttawaON Canada Dpt. of Computer Architecture and Automation Universidad Complutense de Madrid Madrid Spain Center for Computational Simulation Universidad Politécnica de Madrid Madrid Spain

The DEVStone benchmark allows us to evaluate the performance of discrete-event simulators based on the DEVS formalism. It provides model sets with different characteristics, enabling the analysis of specific issues of simulation engines. However, this heterogeneity hinders the comparison of the results among studies, as the results obtained on each research work depend on the chosen subset of DEVStone models. We define the DEVStone metric based on the DEVStone synthetic benchmark and provide a mechanism for specifying objective ratings for DEVS-based simulators. This metric corresponds to the average number of times that a simulator can execute a selection of 12 DEVStone models in one minute. The variety of the chosen models ensures we measure different particularities provided by DEVStone. The proposed metric allows us to compare various simulators and to assess the impact of new features on their performance. We use the DEVStone metric to compare some popular DEVS-based simulators. © 2023, CC BY-SA.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

Enabling Conditions for the Deployment of Integrated Local Energy Communities in Europe

Enabling Conditions for the Deployment of Integrated Local E...

引用

Blockchain for Renewables Integration (BLORIN), Workshop on

作者： Martina Caliano Amedeo Buonanno Marialaura Di Somma Giorgio Graditi Christina Papadimitriou Chrysanthos Charalambous Przemysław Dopierała Leszek Bronk Dept. of Energy Technologies and Renewable Energy Sources ENEA Portici NA Italy Electrical Engineering dpt. Eindhoven University of Technology (TU/e) Eindhoven The Netherlands Department of Electrical and Computer Engineering University of Cyprus FOSS Research Centre for Sustainable Energy Nicosia Cyprus Department of Control Information and Communications Instytut Energetyki - Instytut Badawczy Gdansk Poland Department of Strategy and System Development Instytut Energetyki - Instytut Badawczy Gdansk Poland

ISBN: (纸本)9781665472500

The main goal of eNeuron H2020 project (Nov 2020-Oct. 2024, ID: 957779) is to develop innovative tools for the optimal design and operation of local energy communities, integrating distributed energy resources and multiple energy carriers at different scales. This paper presents a review study of the enabling conditions for the deployment of integrated local energy communities (ILECs) in Europe, performed within the project. The enabling conditions are addressed by defining the key actors and their interests in the implementation of an energy community at local level and through a detailed mapping of the enabling and emerging energy and information and communication technologies at both household and community levels. Special focus is also on mapping of the demand-side flexibility technologies to understand the benefits of local flexibility and impacts on the larger systems. In such analysis, the key issues for implementation and adaptation of this new energy paradigm are investigated through covering technological, socio-economic, environmental, and regulatory aspects.

关键词： Renewable energy sources Conferences Europe Information and communication technology Distributed power generation Blockchains

来源：评论

学校读者我要写书评

暂无评论

Analysis of Crystallization Processes on the Surface of Ge-Ga-Se Glasses for Electronics and IR Photonics

Analysis of Crystallization Processes on the Surface of Ge-G...

引用

IEEE International Conference on Electronics and Nanotechnology (ELNANO)

作者： Halyna Klym Ivan Karbovnyk Yuriy Kostiv Ivanna Vasylchyshyn Specialized Computer System Dpt. Lviv Polytechnic National University Lviv Ukraine Electronics and Computer Technologies Dpt. Ivan Franko National University of Lviv Lviv Ukraine Information Technology Security Dpt. Lviv Polytechnic National University Lviv Ukraine Theoretically and General Electrical Engineering Dpt. Lviv Polytechnic National University Lviv Ukraine

ISBN: (纸本)9781538663844

Surface crystallization processes in the 80GeSe 2 -20Ga 2 Se 3 chalcogenide glasses annealed at 380 °C for 25 h and 80 h were studied using atomic force microscopy method. It is shown that crystallites of GeSe 2 phase are formed in the crystallized glasses on the surface. Optimal conditions of crystallization process were selected for preparation of glasses for IR photonics and sensor electronics.

关键词： Glass Annealing Surface morphology Crystallization Surface treatment Chalcogenides Histograms

来源：评论

学校读者我要写书评

暂无评论

Porous Structure and Exploitation Properties of Nanostructured MgO-Al2O3 Ceramics Technologically Modified by Time-Temperature Regimes

Porous Structure and Exploitation Properties of Nanostructur...

引用

IEEE International Conference on Electronics and Nanotechnology (ELNANO)

作者： Halyna Klym Ivanna Vasylchyshyn Ivan Hadzaman Roman Dunets Specialized Computer System Dpt. Lviv Polytechnic National University Lviv Ukraine Theoretical and General Electrical Engineering Dpt. Lviv Polytechnic National University Lviv Ukraine Drohobych Ivan Franko State Pedagogical University Drohobych Ukraine

ISBN: (纸本)9781538663844

Porous structure and exploitation properties in nanostructured MgO-Al 2 O 3 ceramics prepared at 1300 °C and 1400 °C for 5 and 9 h were studied. In ceramics sintered at higher temperatures and durations there is an increase in the area of contact between grains, and also the open porosity is formed, which leads to an increase in the effective adsorption of humidity. A branched pore structure is required for effective sorption processes. Humidity sensitivity of ceramics and the minimum hysteresis in adsorption-desorption cycles are due to the three-dimensional distribution of pores in size and insignificant number of additional phases. The loss of humidity sensitivity in ceramics sintered at higher temperatures and durations is related with evolution of porous structure of ceramics. The degradation transformations in the investigated ceramic lead to the improvement of their humidity sensitivity.

关键词： Ceramics Humidity Degradation Sensitivity Resistance Periodic structures Sensors

来源：评论

学校读者我要写书评

暂无评论

Multi-objective evolutionary algorithms used in greenhouse planning for recycling biomass into energy

引用

作者： Márquez, A.L. Gil, C. Manzano-Agugliaro, F. Montoya, F.G. Fernández, A. Baños, R. Dpt. of Computer Architecture and Electronics University of Almería Spain Dpt. of Rural Engineering University of Almería Spain

ISBN: (纸本)9783642148828

Advanced parallel Multi-Objective Evolutionary Algorithms (MOEA) have been used in order to solve a wide array of problems, including the planning of greenhouse crops. This paper shows the application of MOEA using the Island Parallel Model to solve a problem involving greenhouse crop planning in order to maximize profits and the production of biomass while reducing economic risks. The interest in maximizing biomass waste lies in the possibility of recycling it into heat and energy. © 2010 Springer-Verlag Berlin Heidelberg.

关键词： Greenhouses

来源：评论

学校读者我要写书评

暂无评论

Empirical characterization of the latency of long asynchronous pipelines with data-dependent module delays

Empirical characterization of the latency of long asynchrono...

引用

Euromicro Conference on Parallel, Distributed and Network-Based Processing

作者： J.M. Colmenar O. Garnica S. Lopez J.I. Hidalgo J. Lanchares R. Hermida C.E.S. Felipe II Universidad Complutense de Madrid Spain Dpt. of Computer Architecture and System Engineering Universidad Complutense de Madrid Spain

The paper has two aims: on one hand, to characterize the nature of the relationship between the latency of an asynchronous pipeline and the stage latencies when the latency of the stages is data-dependent. On the other hand, to find the closed-form expression which relates the mean value of the latency of the pipeline with the parameters which characterize the behaviour of the constituting stages. To attain these two goals, we have followed an empirical approach; we have developed a model of an asynchronous pipeline with n stages, the latency of the stages has been modelled using a probability density function and the pipeline behaviour has been simulated. From the results, we have defined linear equations which estimate the mean latency of the pipeline without needs of simulation. Finally, we have designed and implemented a 32/spl times/32 bit asynchronous pipelined multiplier, and we have tested the estimations on it.

关键词： Pipelines Circuit simulation Asynchronous circuits Delay estimation computer architecture systems engineering and theory Closed-form solution Probability density function Equations Circuit testing

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：