检索结果-内蒙古大学图书馆

13th Annual Genetic and Evolutionary Computation Conference, GECCO 2011

作者： Colmenar, J. Manuel Risco-Martín, José L. Atienza, David Hidalgo, J. Ignacio C.E.S. Felipe II Complutense University of Madrid 28300 Aranjuez Spain Dept. of Computer Architecture and Automation Complutense University of Madrid 28040 Madrid Spain EPFL 1015 Lausanne Switzerland

ISBN: (纸本)9781450305570

The dynamic memory manager (DMM) is a key element whose customization for a target application reports great benefits in terms of execution time, memory usage and energy consumption. Previous works presented algorithms to automatically obtain custom DMMs for a given application. Nevertheless, those approaches are based on grammatical evolution where the fitness is built as an aggregate objective function, which does not completely exploit the search space, returning the designer the DMM solution with best fitness. However, this approach may not find solutions that could fit in a concrete hardware platform due to a very low value of one of the objectives while the others remain high, which may represent a high fitness. In this work we present the first multi-objective optimization methodology applied to DMM optimization where the Pareto dominance is considered, thus providing the designer with a set of non-dominated DMM implementations on each optimization run. Our results show that the multi-objective optimization provides Pareto-optimal alternatives due to a better exploitation of the search space obtaining better hypervolume values than the aggregate objective function approach. Copyright 2011 ACM.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Acceleration of Block Matching Motion Estimation Techniques

FPGA-Based Acceleration of Block Matching Motion Estimation ...

引用

International Conference on Field Programmable Logic and Applications

作者： Diego Gonz´lez Guillermo Botella Soumak Mokheerje Uwe Meyer-Base Computer Architecture Department Complutense University of Madrid Madrid Spain Dept. Electrical and Computer Engineering Florida State University Tallahassee Florida USA

This paper focuses on the hardware acceleration of Block Matching motion estimation techniques (Search reduction family) suitable for the standard H.264/AVC MPEG-4 part 10 video compression. Many representative motion estimation search algorithms are explained here. As hardware, the well known Altera DE2 platform with a Cyclone II EP2C35F672C6 is used with a soft core NIOS II processor. C2H compiler which permits us to speed up the system at least two magnitude order is used to accelerate our source code. The paper shows the results in terms of performance and resources needed. This is the starting point to accelerate motion estimation algorithms using many strategies considering an ad-hoc motion estimation processor.

关键词： Acceleration Hardware Motion estimation Field programmable gate arrays Throughput Transform coding Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Practical applications of intelligent systems: An E-learning platforms recommencer

Practical applications of intelligent systems: An E-learning...

引用

2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2010

作者： Lopez, Victoria Santos, Matilde Esteve, Pablo Roldan, David DeMendoza, Juan C. Dept. Computer Architecture Automatics Complutense University Madrid Spain Informatics Faculty Complutense University Madrid Spain

ISBN: (纸本)9781424467907

This paper shows the advantage of using Intelligent Systems while developing engineering projects. The paper is based on three examples and it is focus into one of them: The Elearning Migration application, developed as a teaching aid tool in different organizations where various platforms coexist;this is the case of some Spanish universities. This tool solves three basic problems, which are shown in three independent modules. The first of these ones, concerns the recording and migration of the data;the second one, refers to the storing and organization of the images. The last one is an E-learning platform recommender based on an ID3 tree-decision. We are going to focus our article in this concrete module. ©2010 IEEE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Improving reliability of embedded systems through dynamic memory manager optimization using grammatical evolution 10

Improving reliability of embedded systems through dynamic me...

引用

12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010

作者： Manuel Colmenar, J. Risco-Martín, José L. Atienza, David Garnica, Osear Hidalgo, J. Ignacio Lanchares, Juan C.E.S. Felipe II Complutense University of Madrid 28300 Aranjuez Spain Dept. of Computer Architecture and Automation Complutense University of Madrid 28040 Madrid Spain EPFL 1015 Lausanne Switzerland

ISBN: (纸本)9781450300728

Technology scaling has offered advantages to embedded systems, such as increased performance, more available memory and reduced energy consumption. However, scaling also brings a number of problems like reliability degradation mechanisms. The intensive activity of devices and high operating temperatures are key factors for reliability degradation in latest technology nodes. Focusing on embedded systems, the memory is prone to suffer reliability problems due to the intensive use of dynamic memory on wireless and multimedia applications. In this work we present a new approach to automatically design dynamic memory managers considering reliability, and improving performance, memory footprint and energy consumption. Our approach, based on Grammatical Evolution, obtains a maximum improvement of 39% in execution time, 38% in memory usage and 50% in energy consumption over state-of-the-art dynamic memory managers for several real-life applications. In addition, the resulting distributions of memory accesses improve reliability. To the best of our knowledge, this is the first proposal for automatic dynamic memory manager design that considers reliability. Copyright 2010 ACM.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Simulation of High-Performance Memory Allocators

Simulation of High-Performance Memory Allocators

引用

Euromicro Symposium on Digital System Design

作者： Jose L. Risco-Martín J. Manuel Colmenar David Atienza J. Ignacio Hidalgo Dept. of Computer Architecture and Automation Complutense University of Madrid Madrid Spain C.E.S. Felipe II Complutense University of Madrid Aranjuez Spain Embedded Systems Laboratory (ESL) EPFL Lausanne Switzerland

Current general-purpose memory allocators do not provide sufficient speed or flexibility for modern high-performance applications. To optimize metrics like performance, memory usage and energy consumption, software engineers often write custom allocators from scratch, which is a difficult and error-prone process. In this paper, we present a flexible and efficient simulator to study Dynamic Memory Managers (DMMs), a composition of one or more memory allocators. This novel approach allows programmers to simulate custom and general DMMs, which can be composed without incurring any additional runtime overhead or additional programming cost. We show that this infrastructure simplifies DMM construction, mainly because the target application does not need to be compiled every time a new DMM must be evaluated. Within a search procedure, the system designer can choose the "best" allocator by simulation for a particular target application. In our evaluation, we show that our scheme will deliver better performance, less memory usage and less energy consumption than single memory allocators.

关键词： Memory management Resource management Energy consumption Dynamic scheduling Software Computational modeling Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Environmental surface boundary tracking and description using a UAV with vision

Environmental surface boundary tracking and description usin...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Pablo Lanillos José J. Ruz Gonzalo Pajares Jesus M. de la Cruz Dept. of Computer Architecture and Automatic Control Complutense University Madrid Spain Dept. of Software Engineering and Artificial Intelligence Complutense University Madrid Spain

This work presents a strategy to track and describe the boundary of an environmental surface using a sequence of incomplete boundary images coming from an UAV with a camera onboard. The algorithm uses all captured images to feed the trajectory, which drives the UAV towards the next point to take the next shot, until the identification is completed. The multiple patterns of the input image make the problem difficult. Our approach orders the points of the image to identify the existent edges, and computes the trajectory as a minimization problem using a multi-objective function that gathers information about the boundary and the polynomial that fit in these edges.

关键词： Unmanned aerial vehicles Cameras Data mining Shape Monitoring Spline Image sensors Fires Surveillance computer architecture

来源：评论

学校读者我要写书评

暂无评论

DSP structure to motion computation on reconfigurable hardware

DSP structure to motion computation on reconfigurable hardwa...

引用

Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering VII

作者： Botella, Guillermo García, Antonio Rodríguez, Manuel Meyer-Baese, Uwe Dept. Computer Architecture Universidad Complutense de Madrid 28040 Madrid Spain Dept. Electronics and Computer Technology University of Granada 18071 Granada Spain Dept. Architecture and and Computer Technology University of Granada 18071 Granada Spain Dept. Electrical and Computer Engineering Tallahassee FL 32310-6046 United States

ISBN: (纸本)9780819476098

Since the world presents a dynamically changing environment, we need synthetic systems that can process and respond to motion. The main contribution of this work is the efficient implementation of a biologically inspired DSP architecture for gradient motion estimation that borrows nature templates as inspiration and makes use of an specific model of human visual motion perception: Multi Channel Gradient Model. This model can be enhanced using psychophysical and bioinspired properties according to biological vision in order to mimic the behavior and the performance of the mammalians. The architecture is designed with an asynchronous pipeline, chaining several signal processing stages. Experimental results and resource consumption are discussed, analyzing the associated customization of the system. This work concludes with several comparisons with the actual contributions and examples for synthetic sequences and real image applications. © 2009 SPIE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Mixed heuristic and mathematical programming using reference points for dynamic data types optimization in multimedia embedded systems

Mixed heuristic and mathematical programming using reference...

引用

11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009

作者： Risco-Martín, José L. Hidalgo, J. Ignacio Atienza, David Lanchares, Juan Garnica, Oscar Dept. of Computer Architecture and Automation Complutense University of Madrid C/ Prof. José García Santesmases s/n 28040 Madrid Spain EPFL-STI-IEL-ESL 1015 Lausanne Switzerland

ISBN: (纸本)9781605583259

New multimedia embedded applications are becoming increasingly dynamic. Thus, they cannot only rely on static data allocation, and must employ Dynamically-allocated Data Types (DDTs) to store their data and efficiently use the limited physical resources of embedded devices. However, the optimization of the DDTs for each target embedded system is a very time-consuming process due to the large design space of possible DDTs implementations and selection for the memory hierarchy of each specific embedded device. Thus, new suitable exploration methods for embedded design metrics (memory accesses, usage and power consumption) need to be developed. In this paper we analyze the benefits of two different exploration techniques for DDTs optimization: Multi-Objective Particle Swarm Optimization (MOPSO) and a Mixed Integer Linear Program (MILP). Furthermore, we propose a novel MOPSO exploration method, OMOPSO*, which uses MILP solutions, as reference points, to guide a MOPSO exploration and reach solutions closer to the real Pareto front of solutions. Our experiments with two real-life embedded applications show that our algorithm achieves 40% better coverage and set of solutions than state-of-the-art optimization methods for DDTs (MOGAs and other MOPSOs). Copyright 2009 ACM.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

FPGA based architecture for Robust Optical Flow Computation

FPGA based Architecture for Robust Optical Flow Computation

引用

Southern Conference on Programmable Logic

作者： Guillermo Botella Eduardo Ros Manuel Rodriguez Antonio Garcia Esther Andres M. Carmen Molina Encarnacion Castillo Luis Parrilla Department of Computer Architecture and Automation Universidad Carlos III De Madrid Spain Dept. of Computer Architecture and Automation Universidad Complutense de Madrid Dept. of Computer Architecture Dept. of Electronics University of Granada Dept. of Electronics University of Granada Spain

ISBN: (纸本)9781424419920

Motion Computation, also called Optical Flow, consists of measuring the motion of an entity attending to the modulus (how fast) and the phase (direction) of its movement. There are a plethora of different models and algorithms whereas none of them cover all problems associated to the real world. Our contribution presents a novel customizable architecture, including resource usage and performance, of a neuromorphic robust optical flow adjustable platform, although its main drawback is the elevated computational complexity. Bioinspiration and robustness properties of the final system provides an extended set of applications fields.

关键词： Optical computing Field programmable gate arrays computer architecture Robustness Image motion analysis Biomedical optical imaging Fluid flow measurement Motion measurement Phase measurement Neuromorphics

来源：评论

学校读者我要写书评

暂无评论

Hybrid heuristic and mathematical programming in oil pipelines networks: Use of immigrants

引用

Journal of Zhejiang university-Science A(Applied Physics & Engineering) 2005年第1期6卷 9-19页

作者： DE LA CRUZ J.M HERRáN-GONZáLEZ A RISCO-MARTíN J.L ANDRéS-TORO B Department of Computer Architecture and Automatic Control Complutense University of Madrid 28040 Madrid SpainDepartment of Computer Architecture and Automatic Control Complutense University of Madrid 28040 Madrid SpainDepartment of Computer Science Engineering C.E.S. Felipe II (U.C.M.) 28300 Aranjuez SpainDepartment of Computer Architecture and Automatic Control Complutense University of Madrid 28040 Madrid Spain

We solve the problem of petroleum products distribution through oil pipelines networks. This problem is modelled and solved using two techniques: A heuristic method like a multiobjective evolutionary algorithm and Mathematical Programming. In the multiobjective evolutionary algorithm, several objective functions are defined to express the goals of the solutions as well as the preferences among them. Some constraints are included as hard objective functions and some are evaluated through a repairing function to avoid infeasible solutions. In the Mathematical Programming approach the multiobjective optimization is solved using the Constraint Method in Mixed Integer Linear Programming. Some constraints of the mathematical model are nonlinear, so they are linearized. The results obtained with both methods for one concrete network are presented. They are compared with a hybrid solution, where we use the results obtained by Mathematical Programming as the seed of the evolutionary algorithm.

关键词： MOEA MILP Hybrid algorithm Constraints

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：