检索结果-内蒙古大学图书馆

International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA

作者： M. Salhi A. Kallel D.S. Masmoudi N. Derbel National Remote Sensing Centre Limited Tunisia Tunisia Research Unit on Intelligent Control Design and Optimization of Complex Systems Ecole Nationale d'Ingenieurs de Sfax Tunisia

In this paper, we describe an implementation of a new method for olive tree detection based on a remotely sensed data by applying nonlinear correlation technique. In order to look for a known object, we use its mask omega and sweep the considered image for computing the correlation between the mask and windows phi of the image. Accordingly, we defined a doorstep of resemblance decision between the picture and the mask by choice of the maximal correlation measure. Applying this technique for remote sensed image segmentation and olive trees extraction, as well as computing the vegetation indices, we get encouraging results

关键词： Image segmentation Remote sensing Vegetation mapping Spectroscopy Correlators intelligent control design optimization Network address translation Image recognition Image analysis

来源：评论

学校读者我要写书评

暂无评论

FPGA implementation of programmable pulse mode neural network with on chip learning

FPGA implementation of programmable pulse mode neural networ...

引用

International Conference on design and Technology of Integrated systems in Nanoscale Era (DTIS)

作者： A. Damak M. Krid D. Sellami Masmoudi N. Derbel Research unit on Intelligent Control design and Optimisation of complex Systems (ICOS) Sfax Engineering School University of Sfax Sfax Tunisia

This paper presents an implementation of a pulse mode multilayer neural network with on chip learning. Taking advantage of the compactness of the multiplierless solutions proposed in the literature, we apply a multiplierless architecture, in which the synapse is made up with a DDFS and the neuron uses a nonlinear adder. A programmable activation function is proposed by means of an adjustable pulse multiplier so that the activation function slope can be adjusted without any added hardware cost. The proposed architecture was tested in a signature recognition system. It shows good learning capability. The corresponding design was implemented into a Virtex II PRO XC2VP7 Xilinx FPGA

关键词： Field programmable gate arrays Neural networks Network-on-a-chip Artificial neural networks Multi-layer neural network Neurons Frequency synthesizers Pulse modulation Frequency modulation Pulse generation

来源：评论

学校读者我要写书评

暂无评论

FPGA Implementation of Programmable Pulse Mode Neural Network with on Chip Learning for signature application

FPGA Implementation of Programmable Pulse Mode Neural Networ...

引用

IEEE International Conference on Electronics, Circuits and systems (ICECS)

作者： Mohamed Krid Alima Dammak Dorra Sellami Masmoudi Research unit on Intelligent Control design and Optimisation of complex Systems (ICOS) Sfax Engineering School University of Sfax Sfax Tunisia

This paper presents an implementation of a signature recognition system based on pulse mode multilayer neural networks with on chip learning. Taking advantage of the compactness of the multiplierless solutions of pulse mode operations, we apply an architecture, in which the synapse is made up with a DDFS and the neuron uses a nonlinear adder. A programmable activation function is proposed by means of an adjustable pulse multiplier so that the activation function slope can be adjusted without any added hardware cost. Good learning capability is obtained. As illustration, we consider a signature learning application. The corresponding design was implemented into an FPGA platform ( virtex II PRO XC2VP7).

关键词： Field programmable gate arrays Neural networks Network-on-a-chip Multi-layer neural network Neurons Computer architecture System-on-a-chip intelligent control design optimization design engineering

来源：评论

学校读者我要写书评

暂无评论

An optimized low voltage and High Frequency CCII based multifunction Filters

An optimized low voltage and High Frequency CCII based multi...

引用

13th IEEE International Conference on Electronics, Circuits and systems (ICECS'2006), vol.3

作者： Samir Ben Salem Dorra Sellami Masmoudi Ashwek Ben Said Mourad Loulou Laboratoire de lElectronique et des Technologies de lInformation National Engineering School of Sfax (ENIS) Tunisia Laboratoire de 1'Electronique et des Technologies de 1'Information Research unit on Intelligent Design and Control of complex Systems National Engineering School of Sfax Tunisia

In this paper, a low voltage current conveyor (CCII) based multifunction filter is presented. Firstly, thanks to an optimizing heuristic, an optimal sizing of a low voltage low power CMOS current conveyor (CCII) was done. Hence, we improve static and dynamic performances of this configuration. The optimized CCII configuration has a current bandwidth of 1.103GHz and a voltage bandwidth of 1.18GHz and 33.4Ω as RX parasitic resistance value. Secondly, implementation of a multifunction filter based on this configuration was done. The current mode filter has a tunable central frequency in the range [50MHz-800MHz]. PSPICE simulations are presented to demonstrate these results.

关键词： Low voltage current conveyor Multifunction filters Current conveyor Optimizing heuristic

来源：评论

学校读者我要写书评

暂无评论

Path following for underactuated marine craft using line of sight algorithm

Path following for underactuated marine craft using line of ...

引用

7th Middle Eastern Simulation Multiconference (MESM 2005)

作者： Ghommem, J MniF, F Derbel, N Intelligent Control Design and Optimization of Complex Systems Unit ENIS Tunisia Laboratoire de Vision et de Robotique Orlélans France

ISBN: (纸本)907738121X

This work provides algorithms for underactuated ship path guidance using nonlinear control theory. Path following is achieved by a geometric assignment based on a line-of-sight projection algorithm for minimization of the cross-track error to the path. The control laws in surge and yaw are derived using backstepping. This results in a dynamic feedback controller where the dynamics of the uncontrolled sway mode enters the yaw control law. Uniform Global Asymptotic Stability (UGAS) is proven for the tracking error dynamics in surge and yaw while the controller dynamics is bounded. To show the effectiveness of the controller and guidance systems, we simulate our algorithm using Simulink on a marine craft model.

关键词： nonlinear control underactuated marine craft backstepping control Line of Sight Global uniform asymptotic convergence

来源：评论

学校读者我要写书评

暂无评论

Stochastic Approximation Based Adaptive Neural control for a Class of Nonlinear systems

引用

control AND intelligent systems 2005年第3期33卷 190-198页

作者： Mekki, H. Chtourou, M. Derbel, N. Research Unit on Intelligent Control Design and Optimization of Complex System (ICOS) National School of Engineers of Sfax 3038 Sfax BP.W Tunisia

This article presents an adaptive multilayer neural network-based controller that feedback-linearizes the system for a class of single-input single-output (SISO) and multi-input multi-output (MIMO) continuous-time nonlinear systems. control action is used to achieve tracking performances for state-feedback linearizable unknown non-linear system. The control structure consists of a feedback lineariza- tion portion provided by neural networks (NN). In the standard problem of feedback-based control, the cost to minimize is a func- tion of the output derivatives. When the cost function depends on the output error, the gradient method cannot be applied to adjust the neural network parameters. In this context, the stochastic approximation approach allows computation of the cost function derivatives. In order to show the feasibility and performance of this control scheme, two applications are chosen as nonlinear case studies.

关键词： Adaptive control neural networks nonlinear system stochastic

来源：评论

学校读者我要写书评

暂无评论

Face recognition using linear analysis techniques and neural networks based approaches

Face recognition using linear analysis techniques and neural...

引用

7th Annual Middle Eastern Simulation Multiconference, MESM 2005

作者： Aouicha, Ichraq Ben Tray, Torek Masmoudi, Dorra Sellami Research Unit on Intelligent Control Design and Optimization of Complex Systems Ecole Nation ale d'Ingénieurs de Sfax Tunisia

ISBN: (纸本)907738121X

In this papery we are concerned with face recognition techniques using principal component analysis (PCA), Fisher linear discriminant Analysis (FLDA) as linear approaches and Neural Networks. Known as one of the efficient techniques used in dimensionality reduction, PCA is based on information theory concepts, seeking a computational model that best describes a face, by extracting the most relevant information contained in that face. FLDA is a classification method that projects high-dimensional data onto a reduced space and performs classification in it. The projection maximizes the distance between the means of all classes while minimizing the variance within each class. Althoughf offering a good reduction in dimensionality, the reduced dimension remains too high for a decision making process. Neural Networks represents a good solution for decision making by achieving numeric classification. It is shown in this paper that hybrid solution associating dimension reduction techniques and Neural Networks reduces computational efforts required in Neural Networks image classifiers. Indeed, although giving satisfactory solutions, Neural Networks based approaches require high computations in face recognition classification problems. © 2005 EUROSIS-ETI.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A new wavelet based multi-resolution texture segmentation scheme of remotely sensed images for vegetation extraction

A new wavelet based multi-resolution texture segmentation sc...

引用

1st IEEE International Conference on Signal-Image Technology and Internet-Based systems, SITIS 2005

作者： Kallel, Amin Masmoudi, Dorra Sellami Salhi, Mounir Aïcha, Med Amine Ben Kallel, Imene Khanfir Derbel, Nabil Research Unit on Intelligent Control Design and Optimization of Complex Systems Ecole Nationale d'Ingénieurs de Sfax Tunisia National Remote Sensing Centre of Tunisia Tunisia

Texture segmentation via wavelet transform traditionally adopts textural features based approach. However, applying this method can lead to over-segmentation problems. To overcome this limitation, we propose a new scheme of texture segmentation. The proposed approach will be applied to remotely sensed images for vegetation extraction. The key idea is that we precede wavelet transform by a preliminary step for increasing the homogeneity of each texture region and removing noise, consisting on smoothing the image by means of anisotropic diffusion technique. The smoothed image is then decomposed into sub-images with different spatial frequencies. Separating the high spatial frequency details corresponding to vegetations, from the other spatial low frequencies, dictates a wavelet reconstruction while neglecting the approximation coefficients. Then, by applying a triangle algorithm based thresholding, we isolate regions corresponding to vegetations. Natural remote sensed images of olive trees parcels with different geometries and different characteristics were considered for texture segmentation. Simulation results prove that trees textures are successfully extracted. © IEEE SITIS 2005.

关键词： Vegetation

来源：评论

学校读者我要写书评

暂无评论

Recursive backstepping stabilization of a wheeled mobile robot

Recursive backstepping stabilization of a wheeled mobile rob...

引用

作者： Mnif, F. Yahmadi, A.S. Intelligent Control Design and Optimization of Complex Systems Tunisia Department of Electrical and Computer Engineering Sultan Qaboos University Muscat Oman Department of Mechanical and Industrial Engineering Sultan Qaboos University Muscat Oman Department of Electrical Engineering College of Engineering Sultan Qaboos University PO Box 33 Muscat 123 Oman

This research is aimed at the development of a dynamic control to enhance the performance of the existing dynamic controllers for mobile robots. System dynamics of the car-like robot with non-holonomic constraints were employed. A backstepping approach for the design of a discontinuous state feedback controller is used for the design of the controller. It is shown that the origin of the closed-loop system can be made stable in the sense of Lyapunov. The control design is made on the basis of a suitable Lyapunov function candidate. The effectiveness of the proposed approach is tested through simulation on a car-like vehicle mobile robot. © IMechE 2005.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Analog VLSI CMOS implementation of beta neuron in a low power low voltage environment

Analog VLSI CMOS implementation of beta neuron in a low powe...

引用

IEEE International Conference on Electronics, Circuits and systems (ICECS)

作者： Dorra Sellami Masmoudi Mohamed Masmoudi Adel Alimi ICDOS (Intelligent Control Design and Optimisation of Complex Systems) Group Sfax National Engineering School Sfax Tunisia

A new CMOS analog programmable beta function for beta basis function neural networks is proposed. Based on current mode operations and using devices operating in the subthreshold region, low power low voltage operations are carried out. The supply voltage is 1.3 V and the quiescent power consumption is 4 muW. The proposed circuit makes use of the weak inversion MOS model. It carried out a compact implementation of a current mode logarithmic converter, a one quadrant programmable multiplier and a current exponentiator. The beta exponents of the design are tuneable by means of control sources. design modularity concerns also the maximum beta function value. Pspice simulations were done for a 0.35 mum CMOS process of AMS. Correct operations of the different blocks were observed. The relative error between theory and simulations of the beta function is less than 2%.

关键词：

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：