检索结果-内蒙古大学图书馆

5th International Symposium on Search-Based Software Engineering, SSBSE 2013

作者： Pitangueira, Antônio Mauricio Maciel, Rita Suzana P. De Oliveira Barros, Márcio Andrade, Aline Santos Federal University of Bahia Computer Science Department Brazil Post-graduate Information Systems Program Brazil Federal Institute of Bahia Brazil

ISBN: (纸本)9783642397417

Selection and prioritization of software requirements represents an area of interest in Search-Based Software Engineering (SBSE) and its main focus is finding and selecting a set of requirements that may be part of a software release. This paper uses a systematic review to investigate which SBSE approaches have been proposed to address software requirement selection and prioritization problems. The search strategy identified 30 articles in this area and they were analyzed for 18 previously established quality criteria. The results of this systematic review show which aspects of the requirements selection and prioritization problems were addressed by researchers, the methods approaches and search techniques currently adopted to address these problems, and the strengths and weaknesses of each of these techniques. The review provides a map showing the gaps and trends in the field, which can be useful to guide further research. © 2013 Springer-Verlag.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Classification of Bird Species Using Their Audio Recorded Songs

Hierarchical Classification of Bird Species Using Their Audi...

引用

IEEE International Conference on Systems, Man, and Cybernetics

作者： Carlos N. Silla Celso A. A. Kaestner Post-Graduate Program in Informatics (PPGI) Federal University of Technology of Paraná (UTFPR-CP) Cornélio Procópio Brazil Post-Graduate Program in Applied Computer Science (PPGCA) Federal University of Technology of Paraná (UTFPR) Curitiba Brazil

ISBN: (纸本)9781479906505

In this paper we address the task of hierarchical bird species identification from audio recordings. We evaluate three types of approaches to deal with hierarchical classification problems: the flat classification approach, the local-model per parent node classifier approach and the global-model hierarchical-classification approach. For the flat and local-model classification approach we employ the classic Naive Bayes algorithm. For the global-model approach we use the Global Model Naive Bayes (GMNB) algorithm. As in the classical Naive Bayes, the algorithm computes prior probabilities and likelihoods, but these computations take into account the hierarchical classification scenario: it assumes that any example which belongs to a given class will also belong to all its ancestor classes. In the current application, the employed class hierarchy is the standard scientific taxonomy of birds used in Biology. In order to deal with the bird songs we obtain features by computing several acoustic quantities from intervals of the audio signal. We conduct three experiments in order to compare the three different approaches to the hierarchical bird species identification problem. Our experimental results show that the use of the GMNB hierarchical classification algorithm outperforms both the flat and local-model approaches (Using the Hierarchical F-measure metric);hence the use of a global-model approach (such as the GMNB) can be a feasible way to improve the classification performance for problems with a large number of classes.

关键词： Bird species identification Audio classification Hierarchical classification Hierarchical Naive Bayes classifier bird species Hierarchical Bayes Audio recordings audio signals Songs

来源：评论

学校读者我要写书评

暂无评论

Incremental validation of NCL hypermedia documents

引用

Journal of the Brazilian computer Society 2013年第3期19卷 235-256页

作者： Santos, Rodrigo Costa Mesquita Neto, José Rios Cerqueira de Salles Soares Neto, Carlos Teixeira, Mário Meireles Post Graduate Program in Computer Science Federal University of Maranhão Av. dos Portugueses s/n Campus do Bacanga CEP 65080-040 São Luís MA Brazil Department of Informatics Federal University of Maranhão Av. dos Portugueses s/n Campus do Bacanga CEP 65080-040 São Luís MA Brazil

This paper proposes an incremental, structural and contextual validation method for Nested Context Language (NCL) documents. As part of the proposed method, we define a declarative metalanguage to ensure low coupling between NCL structure and the validator code, which simplifies the validation of new language profiles. Requirements such as incremental processing and multilingual messages are also covered by this work. We present an implementation of this method using component architecture as a proof of concept and also conduct a performance evaluation to compare the traditional and incremental validation approaches. © 2013 The Brazilian computer Society.

关键词： NCL Incremental validation Code validation Ginga ISDB-Tb iDTV

来源：评论

学校读者我要写书评

暂无评论

Models of Transit Systems for Optimization of the Grounded Vehicles Fleet

Models of Transit Systems for Optimization of the Grounded V...

引用

International Conference on computer Modeling and Simulation, UKSIM

作者： José Artur Lima Cabral Marques Fábio Nogueira da Silva João Viana da Fonseca Neto UNDB Sao Luis Maranhao Brazil DEE-Post Graduate Program in Electrical Engineering and Computer Science-PPGEE Universidade Federal do Maranhão Sao Luis Maranhao Brazil

In order to operate a public transportation system, it is necessary to plan the grounded fleet lines among the various origin/destination spread all over the city to better attend population displacement during the day, which uses the bus transportation system. To improve planning operation of the public transportation system, it is proposed a linear programming model to optimize the overall performance of transit systems, by setting the optimum buses fleet for every bus line of each company constrained to an accepted delay between any two bus stop on the bus circuit but with a minimum profit for the companies. As the routes are different for time to time during the day such as rush hour. The proposed model can cope with all the kinds of patterns during the day and the propose is to optimise the whole transportation system. It is discussed also the complexity of the nature of the dynamic of the transportation system. The mathematical modelling can show us correctly a way to qualify and quantify the routes, what helps to understand the dynamic behavior of the population through time, different situations and epochs. Simulations present the viability of implantation for real time system to estimate the transportation system as it changes.

关键词： Optimization Sociology Statistics Linear programming Vehicles Adaptation models

来源：评论

学校读者我要写书评

暂无评论

A Data Management in a Private Cloud Storage Environment Utilizing High Performance Distributed File Systems

A Data Management in a Private Cloud Storage Environment Uti...

引用

IEEE International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprises

作者： Tiago S. Soares M. A. R. Dantas Douglas D. J. de Macedo Michael A. Bauer Informatics and Statistic Department (INE) Federal University of Santa Catarina (UFSC) Post-Graduate Program of Knowledge Engineering and Management Federal University of Santa Catarina (UFSC) Computer Science Department (CSD) University of Western Ontario (UWO)

ISBN: (纸本)9781479904051

The new trend in the process of data-intensive management indicates the importance of a distributed file system for both Internet large scale services and cloud computing environments. I/O latency and application buffering sizes are two of a number of issues that are essential to be analysed on different class of distributed file systems. In this paper, it is presented a research work comparing four different high performance distributed file systems. Those systems were employed to support a medical image server application in a private storage environment. Experimental results highlight the importance of an appropriate distributed file system to provide a differential level of performance considering application specific characteristics.

关键词： Distributed File System DICOM HDF5 Telemedicine

来源：评论

学校读者我要写书评

暂无评论

Unified algorithm to improve reinforcement learning in dynamic environments: An instance-based approach

Unified algorithm to improve reinforcement learning in dynam...

引用

14th International Conference on Enterprise Information Systems, ICEIS 2012

作者： Ribeiro, Richardson Favarim, Fábio Barbosa, Marco A.C. Borges, André Pinz Dordal, Osmar Betazzi Koerich, Alessandro L. Enembreck, Fabrício Graduate Program in Computer Engineering Federal Technological University of Paraná Pato Branco Paraná Brazil Post-Graduate Program in Computer Science Pontificial Catholical University of Paraná Curitiba Paraná Brazil

ISBN: (纸本)9789898565105

This paper presents an approach for speeding up the convergence of adaptive intelligent agents using reinforcement learning algorithms. Speeding up the learning of an intelligent agent is a complex task since the choice of inadequate updating techniques may cause delays in the learning process or even induce an unexpected acceleration that causes the agent to converge to a non-satisfactory policy. We have developed a technique for estimating policies which combines instance-based learning and reinforcement learning algorithms in Markovian environments. Experimental results in dynamic environments of different dimensions have shown that the proposed technique is able to speed up the convergence of the agents while achieving optimal action policies, avoiding problems of classical reinforcement learning approaches.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data Assimilation using NeuroEvolution of Augmenting Topologies

Data Assimilation using NeuroEvolution of Augmenting Topolog...

引用

International Joint Conference on Neural Networks

作者： Andre Grahl Pereira Adriano Petry Computer Science Post-graduate Program - PPGCC Federal University of Rio Grande do Sul - UFRGS Southern Regional Space Research Center - CRS National Institute for Space Research - INPE

ISBN: (纸本)9781467314886

The use of numerical prediction models are essential to modern society. Data assimilation is a technique that aims to increase the prediction accuracy by combining a model output with observational data, resulting in a state that is closer to the true state of the problem. Depending on the size of the model output and the number of observations to assimilate, the combination of these two sources of information may require intensive computing and become a challenge, even for supercomputers used in this type of application. Thus neural networks have been proposed as an alternative to perform high quality data assimilation at lower computational cost. This paper investigates the use of NeuroEvolution of Augmenting Topologies (NEAT) in data assimilation. NEAT is capable of adapting the connections weights and the neural network topology using principles of evolutionary computation in a search for a minimum topology and best performance. In this work, two different models were used for testing: the Lorenz Attractor and Shallow Water model. The experiments compared the results obtained with NEAT and backpropagation neural networks, using as benchmark the Best Linear Unbiased Estimator (BLUE). In the experiment with the Lorenz Attractor, NEAT was able to emulate the data assimilation task with smaller error at lower computational cost. For the Shallow Water model, tested using different grid sizes, it was observed that the errors obtained with both neural networks were small, but NEAT showed high error values. On the other hand, NEAT always gets a topology with significantly fewer operations, and the computational cost difference increases with the grid size.

关键词： Data assimilation NEAT Neural networks BLUE Lorenz attractor Shallow water model

来源：评论

学校读者我要写书评

暂无评论

Lung nodules classification in CT images using Shannon and Simpson Diversity Indices and SVM

Lung nodules classification in CT images using Shannon and S...

引用

8th International Conference on Machine Learning and Data Mining in Pattern Recognition, MLDM 2012

作者： Nascimento, Leonardo Barros De Paiva, Anselmo Cardoso Silva, Aristófanes Corrêa Federal University of Maranhão - UFMA Post-graduate Program in Engineering of Electricity Campus Do Bacanga Av. dos Portugueses SN Bacanga 65085-580 São Luis MA Brazil Federal University of Maranhao - UFMA Department of Computer Science Campus Do Bacanga Av. dos Portugueses SN Bacanga 65085-580 Sao Luís MA Brazil

ISBN: (纸本)9783642315367

In this work, we present the use of Shannon and Simpson Diversity Indices as texture descriptors for lung nodules in computerized Tomography (CT) images. These indices will be proposed to characterize the nodules into two classes: benign or malignant. The investigation is done using the Support Vector Machine (SVM) for classification in a dataset consisting of 73 nodules, 47 benign and 26 malignant;the results of the methodology were: sensitivity of 85.64%, specificity of 97.89% and accuracy of 92.78%. © 2012 Springer-Verlag.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Code Compression in ARM Embedded Systems Using Multiple Dictionaries

Code Compression in ARM Embedded Systems Using Multiple Dict...

引用

IEEE International Conference on Computational science and Engineering, CSE

作者： Wanderson Roger Azevedo Dias Edward David Moreno Institute of Computing-IComp Post-graduate Program in Informatics-PPGI Federal University of Amazonas Manaus Amazonas Brazil Center for Exact Sciences and Technology-CCET Department of Computer Science-DComp Federal University of Sergipe Aracaju Sergipe Brazil

This paper presents a new code compression method where we use different dictionaries, all of them are based in traditional Huffman algorithm. Our method reduces code size by up to 34.5% (including all extra costs) and presents an improvement of almost 7% over the traditional Huffman method. We performed simulations using Simple Scalar and analyzes using the applications from benchmark MiBench and use the embedded processor ARM.

关键词： Dictionaries Embedded systems Analytical models Benchmark testing Memory management Decoding Energy consumption

来源：评论

学校读者我要写书评

暂无评论

Multiobjective optimization for project portfolio selection 12

Multiobjective optimization for project portfolio selection

引用

14th International Conference on Genetic and Evolutionary Computation Companion, GECCO'12 Companion

作者： De Barros, Márcio O. Costa, Hélio R. Figueiredo, Fábio V. Da Rocha, Ana Regina C. Post-graduate Information Systems Program - PPGI UNIRIO Av. Pasteur 458 Urca - Rio de Janeiro RJ Brazil COPPE UFRJ System Engineering and Computer Science Department Caixa Postal: 68511 CEP: 21945-970 - Rio de Janeiro Brazil CCA-RJ Brazilian Air Force Ponta do Galeão s/no Ilha do Governador CEP: 21941-510 - Rio de Janeiro Brazil

ISBN: (纸本)9781450311786

This paper proposes a multiobjective heuristic search approach to support a project portfolio selection technique on scenarios with a large number of candidate projects. The original formulation for the technique requires analyzing all combinations of candidate projects, which is unfeasible when more than a few alternatives are available. We have used a multiobjective genetic algorithm to partially explore the search space of project combinations and select the most effective ones. We present an experimental study based on four project selection problems that compares the results found by the genetic algorithm to those yielded by a non-systematic search procedure. Results show evidence that the project selection technique can be used in large-scale scenarios and that GA presents better results than simpler search strategy. Copyright is held by the author/owner(s).

关键词： Multiobjective optimization

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：