检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Daniel Leite Pyramo Costa Fernando Gomide Department of Computer Engineering and Automation School of Electrical and Computer Engineering University of Campinas Brazil Graduate Program in Electrical Engineering Pontifical Catholic University of Minas Gerais Brazil

A primary requirement of a broad class of evolving intelligent systems is to process a sequence of numeric data over time. This paper introduces a granular neural network framework for evolving fuzzy system modeling from fuzzy data streams. The evolving granular neural network (eGNN) efficiently handles concept changes, distinctive events of nonstationary environments. eGNN constructs interpretable multi-sized local models using fuzzy neural information fusion. An incremental learning algorithm builds the neural network topology from the information contained in data streams. Here we emphasize fuzzy intervals and objects with trapezoidal membership functions. Triangular fuzzy numbers, intervals, and numeric data are particular instances of trapezoids. An example concerning weather time series forecasting illustrates the neural network performance. The goal is to extract, from monthly temperature data, information of interest to attain accurate one-step forecasts and better rapport with reality. Simulation results suggest that eGNN learns from fuzzy data successfully and is competitive with state-of-the-art approaches.

关键词： Neurons Fuzzy sets Approximation methods Data models Neural networks Pragmatics Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Hybrid clutter canceler with feedback guided predicative filtering on a heterogeneous parallel processing system

Hybrid clutter canceler with feedback guided predicative fil...

引用

International Waveform Diversity and Design Conference

作者： Jeffrey M. Brinkhus Joseph A. Jezak Charles Berdanier Steven P. Levitan Donald M. Chiarulli Electical and Computer Engineering University of Pittsburgh Computer Engineering Graduate Program University of Pittsburgh Electrical Engineering Wright State University Computer Science Department University of Pittsburgh

In this paper we describe a novel clutter cancellation platform based on a two stage approach that combines a feedback guided predictive front-end hybrid clutter canceller with high performance back-end filtering and target detection. The front-end architecture is based on an FPGA implementation of a Kalman filter that predicts target locations in real time and removes the target signals from the incoming data prior to hybrid cancellation. The back-end is user configurable and exploits high performance GPU and multi-core parallel hardware to simultaneously compute multiple clutter suppression and target detection algorithms coupled to an intelligent selection strategy for selecting the most accurate result. These target locations are fed back to the FPGA Kalman filter periodically to update the target predictions.

关键词： Clutter Kalman filters Mathematical model Field programmable gate arrays Radar Clocks Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

A method to validate quantitative high-frequency power Doppler ultrasound with fluorescence in vivo video microscopy

引用

Proceedings of Meetings on Acoustics 2013年第1期19卷

作者： James Lacefield Stephen Z. Pinter Dae-Ro Kim M. N. Hague Ann F. Chambers Ian C. MacDonald Electrical & Computer Engineering and Medical Biophysics Western University Thompson Engineering Bldg Rm 279 London Ontario N6A 5B9 Canada Biomedical Engineering Graduate Program Western University London Ontario Canada Medical Biophysics Western University London Ontario Canada London Regional Cancer Program London Ontario Canada

Flow quantification with high-frequency power Doppler ultrasound can be performed using the wall-filter selection curve (WFSC) method [M. Elfarnawany et al., Ultrasound Med. Biol. 38, 1429-1439 (2012)]. The WFSC method plots color pixel density (CPD) as a function of wall filter cut-off velocity as a means of objectively selecting an operating point cut-off velocity. In this study, an in vivo video microscopy (IVVM) system was used to measure the size of small (140-400 μm diameter) mouse testicular vessels immediately after the vessels were imaged with 30 MHz power Doppler. The mouse remained on the same platform throughout ultrasound and IVVM imaging. Measurements in four image planes from three mice demonstrated that, similar to previously reported flow-phantom data, in vivo WFSCs exhibit distinct, sloped "characteristic intervals" at cut-off velocities where the CPD approaches the gold-standard IVVM estimate of vascular volume fraction. A wide range of operating point cut-off velocities (4.5 to 12 mm/s) was obtained, which indicates that use of a predetermined cut-off can produce substantial errors in cross-sectional studies that employ power Doppler to quantify vascularity. The WFSC method is a promising strategy for adapting the cut-off velocity to intersubject and longitudinal variations in blood flow during microvascular imaging experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accelerated DSP functions on the CBE for the X-Midas Toolkit

Accelerated DSP functions on the CBE for the X-Midas Toolkit

引用

International Waveform Diversity and Design Conference

作者： Joseph A. Jezak Charles Berdanier Steven P. Levitan Donald M. Chiarulli Computer Engineering Graduate Program University of Pittsburgh USAF AFRL/RYMDA Wright Patterson Air Force Base Department of Electrical and Computer Engineering University of Pittsburgh Department of Computer Science University of Pittsburgh

We characterize the impact of the Cell Broadband Engine architecture, on commonly used radar DSP algorithms. We use the capabilities of the CBE to accelerate several key computational kernels including Matrix Multiplication, Matrix Inversion, and the Finite Impulse Response (FIR) filter. These algorithms are implemented and benchmarked as library routines within the X-Midas Toolkit. We observe speedups as large as 1200x for complex matrix multiplication, but speedups of 40x to 60x are more typical. We find that system I/O overhead within the X-Midas toolkit severely limited the performance of the applications.

关键词： Finite impulse response filters Acceleration Benchmark testing computer architecture Pipelines Optimization Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Evolving Neural Fuzzy Network with Adaptive Feature Selection

Evolving Neural Fuzzy Network with Adaptive Feature Selectio...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Alisson Marques Silva Walmir Matos Caminhas André Paim Lemos Fernando Gomide Graduate Program in Electrical Engineering Federal University of Minas Gerais UFMG Belo Horizonte MG Brazil School of Electrical and Computer Engineering University of Campinas UNICAMP Campinas sp Brazil

This paper introduces a neural fuzzy network approach for evolving system modeling. The approach uses neofuzzy neurons and a neural fuzzy structure monished with an incremental learning algorithm that includes adaptive feature selection. The feature selection mechanism starts considering one or more input variables from a given set of variables, and decides if a new variable should be added, or if an existing variable should be excluded or kept as an input. The decision process uses statistical tests and information about the current model performance. The incremental learning scheme simultaneously selects the input variables and updates the neural network weights. The weights are adjusted using a gradient-based scheme with optimal learning rate. The performance of the models obtained with the neural fuzzy modeling approach is evaluated considering weather temperature forecasting problems. Computational results show that the approach is competitive with alternatives reported in the literature, especially in on-line modeling situations where processing time and learning are critical.

关键词： Computational modeling Adaptation models Input variables Neural networks Neurons Adaptive systems Predictive models

来源：评论

学校读者我要写书评

暂无评论

A programmable FPGA-based 8-channel arbitrary waveform generator for medical ultrasound research activities

A programmable FPGA-based 8-channel arbitrary waveform gener...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Amauri Amorin Assef Joaquim Miguel Maia Fabio Kurt Schneider Eduardo Tavares Costa Vera Lúcia da Silveira Nantes Button Electrical/Electronic Engineering Department and the Graduate School of Electrical Engineering and Applied Computer Sciences (DAELT/DAELN/CPGEI) Federal University of Technology of Paraná (UTFPR) Curitiba Parana Brazil Biomedical Engineering Department of the School of Electrical and Computing Engineering (DEB/FEEC) and the Biomedical Engineering Centre (CEB) State University of Campinas Campinas Sao Paulo Brazil

In modern ultrasound imaging systems, digital transmit beamformer module typically generates accurate control of the amplitude of individual elements in a multielement array probe, as well as of the time delays and phase between them, to enable the acoustic beam to be focused and/or steered electronically. However, these systems do not provide the ultrasound researchers access to transmit front-end module. This paper presents the development of a digital transmit beamformer system for generating simultaneous arbitrary waveforms, specifically designed for research purposes. The proposed architecture has 8 independent excitation channels and uses an FPGA (Field programmable Gated Array) device for electronic steering and focusing of ultrasound beam. The system allows operation in pulse-echo mode, with pulse repetition rate of excitation from 62.5 Hz to 8 kHz, center frequency from 500 kHz to 20 MHz, excitation voltage over 100 Vpp, and individual control of amplitude apodization, phase angle and time delay trigger. Experimental results show that this technique is suitable for generating the excitation waveforms needed for medical ultrasound imaging researches.

关键词： Ultrasonic imaging Field programmable gate arrays Transducers Delay effects computer architecture Array signal processing Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

rTMS as a Treatment of Alzheimer's Disease with and without Comorbidity of Depression: A Review

Neuroscience journal

引用

Neuroscience journal 2013年第1期2013卷 679389页

作者： Grant Rutherford Rebecca Gole Zahra Moussavi Department of Electrical and Computer Engineering University of Manitoba Winnipeg MB Canada R3T 5V6 Graduate Program in Biomedical Engineering Faculty of Engineering University of Manitoba Winnipeg MB Canada R3T 5V6. Department of Electrical and Computer Engineering University of Manitoba Winnipeg MB Canada R3T 5V6. Graduate Program in Biomedical Engineering Faculty of Engineering University of Manitoba Winnipeg MB Canada R3T 5V6 Riverview Health Center 1 Morley Avenue Winnipeg MB Canada R3L 2P4.

With an ever-increasing population of Alzheimer's disease (AD) patients worldwide, a noninvasive treatment for AD is needed. In this paper, the application of repetitive transcranial magnetic stimulus (rTMS) as a treatment for patients with probable AD is compared to the application of rTMS as a treatment for depression. Comorbidity of depression and dementia is discussed, as well as possible links between the two diseases. The possible confounding antidepressant effects of rTMS on cognitive improvements in AD patients are discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Device Interoperability and Authentication for Telemedical Appliance based on the ISO/IEEE 11073 Personal Health Device (PHD) Standards

Device Interoperability and Authentication for Telemedical A...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society

作者： Luther Paul R. Caranguian Susan Pancho-Festin Luis G. Sison a graduate student in the MS Electrical Engineering (Instrumentation and Control) program of University of the Philippines Diliman. Festin is with the Department of Computer Science University of the Philippines Diliman. with the Electrical and Electronics Engineering Institute University of the Philippines Diliman.

ISBN: (纸本)9781424441198

In this study, we focused on the interoperability and authentication of medical devices in the context of telemedical systems. A recent standard called the ISO/IEEE 11073 Personal Health Device (X73-PHD) Standards addresses the device interoperability problem by defining common protocols for agent (medical device) and manager (appliance) interface. The X73-PHD standard however has not addressed security and authentication of medical devices which is important in establishing integrity of a telemedical system. We have designed and implemented a security policy within the X73-PHD standards. The policy will enable device authentication using Asymmetric-Key Cryptography and the RSA algorithm as the digital signature scheme. We used two approaches for performing the digital signatures: direct software implementation and use of embedded security modules (ESM). The two approaches were evaluated and compared in terms of execution time and memory requirement. For the standard 2048-bit RSA, ESM calculates digital signatures only 12% of the total time for the direct implementation. Moreover, analysis shows that ESM offers more security advantage such as secure storage of keys compared to using direct implementation. Interoperability with other systems was verified by testing the system with LNI Healthlink, a manager software that implements the X73-PHD standard. Lastly, security analysis was done and the system's response to common attacks on authentication systems was analyzed and several measures were implemented to protect the system against them.

关键词： Interoperability Telemedical Authentication

来源：评论

学校读者我要写书评

暂无评论

Smart Environmental Architecture for Node Localization in a Wireless Sensor Network

Smart Environmental Architecture for Node Localization in a ...

引用

International Conference on Intelligent Environments (IE)

作者： Salvador Jauregui-Ortiz Mario Siller Felix Ramos Edson Scalabrin Electrical Engineering and Computer Science Department Center of Research and Advanced Studies of the IPN Guadalajara Jalisco Mexico Graduate Program in Computer Science Pontifical Catholic University Parana Brazil Curitiba Parana Brazil

As far as we know, there is not a Node Localization Algorithm (NLA) that presents the same accuracy for all possible scenarios. We believe that a NLA should be able to "interpret" the dynamic information of the environment. In this sense, simple NLAs are rather focused and might perform well for specific scenarios and applications. Therefore, information fusion and context awareness seems to be an appropriate approach to address this issue. We propose the Smart Environmental Architecture for Node Localization (SEA-NL), which is composed by two main elements: (i) the Smart Beacon Nodes (SBNs) and (ii) the Logical Position of Nodes (LPN). In (i) the obstruction level indicator is estimated and can improve the estimation of distances among nodes. In (ii) environment information and a one to one relation between a node and an object are used and can also improve location estimation. Via simulation, our architecture was tested indoors and outdoors considering three localization algorithms: the Weighed Centroid Localization (WCL), the Centroid Localization, and the Triangular Centroid Localization. Finally, we present an accuracy comparison among NLAs used in isolated way, and by using the SBNs, the LPN, and the SEA-NL, where our architecture improves WCL up to ~30.88%.

关键词： Wireless sensor networks Accuracy Estimation computer architecture Buildings Attenuation Monitoring

来源：评论

学校读者我要写书评

暂无评论

Phase transition behavior in microcantilevers coated with M 1-phase VO2 and M2-phase VO2:Cr thin films

Phase transition behavior in microcantilevers coated with M ...

引用

作者： Rúa, Armando Cabrera, Rafmag Coy, Horacio Merced, Emmanuelle Sepúlveda, Nelson Fernández, Félix E. Department of Physics University of Puerto Rico Mayagüez 00681-9000 Puerto Rico Doctoral Program in Physics Graduate Center City University of New York New York 10016 United States Applied Materials Group Electrical and Computer Engineering Department Michigan State University E. Lansing MI 48824 United States

Silicon microcantilevers were coated by pulsed laser deposition with vanadium dioxide (VO2) (monoclinic M1 phase) and V 1-xCrxO2 with x near 0.024 (monoclinic M 2 phase), and their mechanical characteristics were studied as a function of temperature through the films' insulator-to-metal transition (IMT). The undoped VO2 films grew with (011)M1 planes parallel to the substrate, while Cr-doped VO2 films grew oriented with (201)M2 and (2 01)M2 planes parallel to the substrate. In both cases, the films transformed reversibly through the IMT to the tetragonal (rutile, R) phase, with film (110)R planes oriented parallel to the substrate. The fundamental resonant frequencies of the cantilevers were measured as the temperature was cycled from ambient temperature, through the IMT, and up to 100 °C. Very high resonant frequency changes were observed through the transition for both types of samples, with increases during heating of over 11 and over 15 for the cantilevers coated with pure and Cr-doped VO2, respectively. From the resonant frequencies measured at room temperature for the bare and coated cantilevers in each case, the effective Young's moduli of the films were determined. The values obtained, assuming bulk densities for the films, are 156 ± 7.5 GPa for VO2 (M1 phase) and 102 ± 3 GPa for Cr-doped VO2 (M2 phase). Strong curvature changes during the transition to the R phase were also observed for cantilevers coated with both types of films, but these were significantly higher in the case for the Cr-doped film. Curvature changes for temperature ranges outside the IMT region were small and attributed to differential thermal expansion between film and silicon substrate. From measured cantilever tip displacements in this post-transition range-for the undoped VO 2-coated microcantilevers-a rough estimate of 110 GPa was obtained for the effective Young's modulus for R-phase VO2. The substantially higher changes in resonant frequency and curvature for V1-xCr xO2-coated cant

关键词： Thin films

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：