检索结果-内蒙古大学图书馆

Latin America Congress on Computational Intelligence (LA-CCI)

作者： Alexandre A. Politi Lincoln C. Zamboni Rodrigo Pasti Leandro N. de Castro Graduate Program in Electrical and Computer Engineering Mackenzie Presbyterian University Center for Information Technology

Choosing the ideal spot to set up an Access Point (AP) in a given plant is no simple task. This paper proposes a mathematical model and computational solution to the following problem: given the plant of an indoor environment, a number of reception points and properly characterized obstacles, locate where the access point should be installed, so as to minimize the propagation losses within the environment and ensure a minimum signal level in all receivers. The model proposed differs from others in the literature by treating each obstacle individually and taking into account the material from which it is made. The proposed design minimizes the sum of the attenuations of the signal generated by the AP as the signal traverses the fewest possible obstacles whose attenuation is large (e.g., concrete walls and metal cabinets). To validate the proposed model simulations were performed in an indoor environment with a certain distribution of obstacles of different kinds. The experiments show that the location of the access point varies significantly in the environment according to the materials composing the obstacles. In the most critical case, with obstacles made of concrete, the optimization algorithm could find no location for the AP so that all receptors received a minimum signal level to establish a connection.

关键词： Attenuation Mathematical model Receivers Simulated annealing Concrete Indoor environments

来源：评论

学校读者我要写书评

暂无评论

Foveated model based on the action potential of ganglion cells to improve objective image quality metrics

Foveated model based on the action potential of ganglion cel...

引用

International Joint Conference on e-Business and Telecommunications (ICETE)

作者： Sergio A. C. Bezerra Alexandre de A. P. Pohl Graduate School of Electrical Engineering and Computer Science Federal University of Technology - Paraná (UTFPR) Curitiba PR Brazil Department of Higher Education (DES) Science and Technology of the Amazonas (IFAM) Manaus AM Brazil Graduate School of Electrical Engineering and Computer Science Federal University of Technology - Paraná (UTFPR) 80230-901 Curitiba Brazil

ISBN: (纸本)9781467385329

In this work, a foveated model (FM) based on the action potential of ganglion cells in the human retina is employed to improve the results obtained by traditional and perceptual image quality metrics. LIVE and VAIQ image databases are used in the experiments to test and validate this model. Statistical techniques, such as the Pearson Linear Correlation Coefficient (PLCC), the Spearman Rank-Order Correlation Coefficient (SROCC) and the Root Mean Square Error (RMSE), are used to evaluate the performance of Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM) metrics, as well as their versions improved by the FM. The results are encouraging because the model proposed improve the performance of the metrics investigated.

关键词： Measurement Visualization Frequency modulation Retina Databases Image quality Videos

来源：评论

学校读者我要写书评

暂无评论

High-speed 3D brain activity quantification with compressive light-field microscopy

High-speed 3D brain activity quantification with compressive...

引用

Novel Techniques in Microscopy, NTM 2015

作者： Pégard, Nicolas Lyall, Evan Mardinly, Alan Antipa, Nick Waller, Laura Adesnik, Hillel Department of Molecular and Cell Biology UC Berkeley CA United States Department of Electrical Engineering and Computer Science UC Berkeley CA United States Biophysics Graduate Program UC Berkeley CA United States

We present a non-imaging light-field microscopy method for volume quantification of neural activity in scattering brain tissue. Individual neuron fluorescence is computed directly by independent component identificati... 详细信息

ISBN: (纸本)9781557529541

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-class classification of objects in images using principal component analysis and genetic programming

Multi-class classification of objects in images using princi...

引用

Latin America Congress on Computational Intelligence (LA-CCI)

作者： Manassés Ribeiro Heitor Silvério Lopes Federal Catarinense Institute of Education Science and Technology (IFC) Videira Santa Catarina Brazil Graduate Program in Electrical and Computer Engineering (CPGEI) Federal University of Technology of Paraná (UTFPR) Curitiba Paraná Brazil

This work presents a methodology for using Principal Component Analysis (PCA) and Genetic programming (GP) for the classification of multi-class objects found in digital images. The image classification process is performed by using features extracted from images, through feature extraction algorithms, reduced by PCA and labeled by similarity comparing with other previously classified objects. GP uses two sets of elements: terminals, composed by the features extracted by PCA; and non-terminals, composed by algebraic operations. The fitness function was defined by the product of sensibility and specificity, two performance measures. A penalty term is also used to decrease the number of nodes of the tree, while minimally affecting the quality of solutions. The proposed approach was applied to set of 2739 digital images divided into objects representing airplanes, motorbikes, background from google, faces and watch classes, provided by the Caltech101 image database. The proposed approach was compared with SVM, Naïve Bayes and C4.5. Results suggest that the approach PCA+GP is able to evolve solutions for the problem as a simple classification rule with true positive rate above 70%. Additionally, we observe that PCA+PG obtained results slightly better than SVM and C4.5, besides these methods give a result that is not comprehensible by humans.

关键词： Principal component analysis Image color analysis Feature extraction Histograms Shape Genetic programming Support vector machines

来源：评论

学校读者我要写书评

暂无评论

TOWARDS WMSN PERFORMANCE USING DIFFERENT PACKET SIZE

TOWARDS WMSN PERFORMANCE USING DIFFERENT PACKET SIZE

引用

IEEE Sensors

作者： Cesar A. da Silva Marcelo A. C. Ismael Claudio M. Zaina Linnyer B. Ruiz Graduate Program in Electrical Engineering Federal University of Minas Gerais Belo Horizonte MG Brazil Department of Computing Federal Institute of São Paulo Presidente Epitácio SP Brazil Graduate Program in Computer Science State University of Maringá Maringá PR Brazil

The task of designing WMSN real scenarios in order to evaluate the network performance is not trivial. This work sheds some light on this challenge by studying the impact of the load size when using ZigBee protocol in WMSN that transmits images. The main feature is to use real nodes for reading and dividing camera data into packages for transmission over the network. We have analyzed the number of packets transmitted by sensor node and the number of packets received by base station as a success parameter of the delivery. We have also analyzed data delay and data delivery for each load size: 64, 80 and 96 bytes. The results reveal that there is a trade-off between latency and success rate and that the packet size definition can promote the productivity of network resources and the quality of the provided services.

关键词： Protocols ZigBee Wireless sensor networks Cameras Base stations Image communication IEEE 802.15 Standard

来源：评论

学校读者我要写书评

暂无评论

A discretized differential evolution algorithm for the inference of Gene Regulatory Networks

A discretized differential evolution algorithm for the infer...

引用

Latin America Congress on Computational Intelligence (LA-CCI)

作者： Leandro T. Hattori Heitor S. Lopes Fabrício M. Lopes Graduate Program in Electrical and Computer Engineering (CPGEI) Federal University of Technology Curitiba Paraná Brazil Graduate Program in Bioinformatics (PPGBIOINFO) Federal University of Technology Paraná Brazil

Feature selection is a very important procedure in the pattern recognition research field. Feature selection algorithms are particularly important in the inference of Gene Regulatory Networks (GRNs) from its gene expression profiles, which usually involves data with a large number of variables and small number of observations. This work presents the inference of GRNs from two different feature selection approaches: classical (deterministic) SFS and SFFS search algorithms, and (meta-heuristic) Discretized Differential Evolution (DDE) algorithm. Several Artificial Gene Networks (AGNs) were probabilistically generated for testing. They had different sizes and topologies following three models: Erdös-Rényi uniformly-random, Watts-Strogatz small-world, and Barabási-Albert scale-free. Results confirm that, as the number of candidate predicting genes increase, the performance of the compared methods decrease, revealing the exponential characteristic of the problem. Notwithstanding, for all network sizes and topologies studies, the DDE algorithm achieved better results than the other approaches, especially for GRNs with hubs.

关键词： Inference algorithms Network topology Prediction algorithms Topology Bioinformatics Gene expression Entropy

来源：评论

学校读者我要写书评

暂无评论

An efficient method to determine strain profiles on FBGs by using differential evolution and GPU

An efficient method to determine strain profiles on FBGs by ...

引用

Latin America Congress on Computational Intelligence (LA-CCI)

作者： Lucas Hermann Negri Heitor Silvério Lopes Marcia Muller José Luís Fabris Aleksander Sade Paterno Graduate Program in Electrical and Computer Engineering Federal University of Technology Curitiba Paraná Brazil Department of Electrical Engineering Santa Catarina State University Joinville Brazil

This paper shows the application of the Differential Evolution algorithm to the recovery of the deformation profile applied to a fiber Bragg grating sensor (FBG). The method uses only the sensor reflectivity, without the need of phase information, and has been shown to be highly parallelizable. The method was specially implemented to run the complex computations required by the fitness function using a Graphical Processing Unit (GPU). This provided an enhancement of 3 orders of magnitude in the computation time when compared to similar methods shown in literature. Three experiments were performed to evaluate the computational performance of the DE algorithm, and its convergence of the solution to the target deformation profile. Overall, the method is very promising and it can be applied to problems that require a fast response, such as the online monitoring of FBG sensors.

关键词： Fiber gratings Sociology Statistics Gratings Mathematical model Strain

来源：评论

学校读者我要写书评

暂无评论

Self-Resonant Frequencies, Standing Waves, and Impedance Behavior of Air-Core Helical Solenoidal Coil

Self-Resonant Frequencies, Standing Waves, and Impedance Beh...

引用

International Conference on Electromagnetics in Advanced Applications

作者： C. M. de Miranda S.F. Pichorim Graduate School of Electrical Engineering and Computer Science (CPGEI) Federal University of Technology - Paraná (UTFPR) Av. Sete de Setembro 3165 80230-901 Curitiba Brasil

ISBN: (纸本)9781479978076

Microwave theory should be used anytime the electrical length of a circuit is comparable with the wavelength of the electromagnetic signal. In this sense, an air-core single-layer solenoid is a critical component, in which this condition is very often attained and lumped element theory is not valid. Besides the electromagnetic analysis of the solenoid helix not be an easy task, for many cases of interest some assumptions and conditions simplify the analysis. In this paper it is shown that the air-core solenoid coil can be treated as a lossless transmission line, or more precisely, as a helical transmission line, and that its impedance behavior and self-resonant frequencies can be found with this theory. Also two new configurations are here presented: a coil with both sides open and a coil with both sides short-circuited. It is shown that, in both configurations, the coils have similar behavior and same resonant frequencies. Simulations and measurements are conducted to validate the presented theory.

关键词： Self-Resonant Frequencies Standing Waves Impedance Behavior Air-Core Helical Solenoidal Coil

来源：评论

学校读者我要写书评

暂无评论

Investigation of interstitial ultrasound ablation of spinal and paraspinal tumors: A patient-specific and parametric simulation study

引用

AIP Conference Proceedings 2017年第1期1821卷

作者： Serena J. Scott Vasant Salgaonkar Punit Prakash E. Clif Burdette Chris J. Diederich Thermal Therapy Research Group Dept. of Radiation Oncology University of California San Francisco 1600 Divisadero St. Suite H-1031 San Francisco CA 94143 USA UC Berkeley – UC San Francisco Graduate Program in Bioengineering CA USA Department of Electrical and Computer Engineering Kansas State University Manhattan KS USA Acoustic MedSystems 208 Burwash Ave. Savoy IL 61874 USA

Preferential acoustic absorption and heating of bone can significantly impact interstitial ultrasound ablation of tumors within or bordering the spine. Furthermore, intervening cortical bone may provide acoustic and thermal insulation that can protect sensitive structures nearby, such as the spinal cord. The objectives of this study are firstly, to apply parametric and patient-specific models to theoretically assess the feasibility of interstitial ultrasound ablation of tumors within and near the spine, and secondly, to identify potential energy delivery strategies, safety criteria, advantages, and disadvantages of interstitial ultrasound in this setting. Transient biothermal models using previously validated approximations for power deposition within bone from interstitial sources were employed. Multilayered axisymmetric models were used to perform a parametric assessment of the impact of tumor dimensions, attenuation (dependent on residual bone content), perfusion, and maximum temperature thresholds on necessary treatment parameters and on treatment effectiveness. 3D patient-specific finite element models were generated based on segmented CT scans for nine representative patient cases selected to bracket a range of clinical interest, with tumors in or near the vertebrae, sacrum, and ilium. Tumors were 10-27 mm in diameter, 10-43 mm long, and 0-14 mm from the spinal canal. Paraspinal tumors, osteolytic vertebral tumors, and a mixed osteolytic/osteoblastic iliac bone tumor were considered. 7 MHz (1.5 mm OD) and 3.0 MHz (3.2 mm OD) applicators with an array of 1-4 tubular transducers (0.5 -1.5 cm long, 150-360° sector angles), were applied in various implant configurations. Variable thicknesses of bone insulating critical anatomy from the tumor and insulation of the spinal cord with injected carbon dioxide were also investigated for definition of safety margins and possible protection of critical structures. 6-44 mm diameter osteolytic tumors surrounded by bone and b

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hyper-Heuristic for the Environmental/Economic Dispatch Optimization Problem

A Hyper-Heuristic for the Environmental/Economic Dispatch Op...

引用

Brazilian Conference on Intelligent Systems (BRACIS)

作者： Richard A. Gonçalves Carolina P. Almeida Sandra M. Venske Josiel N. Kuk Lucas M. Pavelski Myriam R. Delgado Computer Science Department UNICENTRO Guarapuava PR Brazil Graduate Program in Electrical and Computer Engineering Federal University of Paraná Curitiba PR Brazil

Hyper-Heuristics are high-level methodologies developed to select or generate heuristics for solving complex problems. Despite their success, there is a lack of multi-objective hyper-heuristics. In the multi-objective optimization context, MOEA/D decomposes a problem into a number of sub problems handled by individuals in a collaborative manner. Our approach, named MOEA/D-HH SW , expands the MOEA/D framework with a multi-objective selection hyper-heuristic. It uses the proposed adaptive choice function with sliding window to determine which low-level heuristic (differential evolution operators) should be applied by each individual during MOEA/D execution. The proposed approach is tested in three known instances of the multi-objective environmental/economic dispatch problem, formulated as a non-linear constrained optimization problem with competing and non-commensurable objectives. MOEA/D-HH SW outperforms state-of-the-art algorithms reported in the literature for all considered instances.

关键词： Optimization Fuels Generators Sociology Statistics Propagation losses Mathematical model

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：