Predictive control with mean derivative based neural euler integrator dynamic model
Paulo M. Tasinaffo
2007-03-01
Full Text Available Neural networks can be trained to get internal working models in dynamic systems control schemes. This has usually been done designing the neural network in the form of a discrete model with delayed inputs of the NARMA type (Non-linear Auto Regressive Moving Average. In recent works the use of the neural network inside the structure of ordinary differential equations (ODE numerical integrators has also been considered to get dynamic systems discrete models. In this paper, an extension of this latter approach, where a feed forward neural network modeling mean derivatives is used in the structure of an Euler integrator, is presented and applied in a Nonlinear Predictive Control (NPC scheme. The use of the neural network to approximate the mean derivative function, instead of the dynamic system ODE instantaneous derivative function, allows any specified accuracy to be attained in the modeling of dynamic systems with the use of a simple Euler integrator. This makes the predictive control implementation a simpler task, since it is only necessary to deal with the linear structure of a first order integrator in the calculations of control actions. To illustrate the effectiveness of the proposed approach, results of tests in a problem of orbit transfer between Earth and Mars and in a problem of three-axis attitude control of a rigid body satellite are presented.Redes neurais podem ser treinadas para obter o modelo de trabalho interno para esquemas de controle de sitemas dinâmicos. A forma usual adotada é projetar a rede neural na forma de um modelo discreto com entradas atrasadas do tipo NARMA (Non-linear Auto Regressive Moving Average. Em trabalhos recentes a utilização de uma rede neural inserida em uma estrutura de integração numérica tem sido também considerada para a obtenção de modelos discretos para sistemas dinâmicos. Neste trabalho, uma extensão da última abordagem é apresentada e aplicada em um esquema de controle n
3D GIS spatial operation based on extended Euler operators
Xu, Hongbo; Lu, Guonian; Sheng, Yehua; Zhou, Liangchen; Guo, Fei; Shang, Zuoyan; Wang, Jing
2008-10-01
The implementation of 3 dimensions spatial operations, based on certain data structure, has a lack of universality and is not able to treat with non-manifold cases, at present. ISO/DIS 19107 standard just presents the definition of Boolean operators and set operators for topological relationship query, and OGC GeoXACML gives formal definitions for several set functions without implementation detail. Aiming at these problems, based mathematical foundation on cell complex theory, supported by non-manifold data structure and using relevant research in the field of non-manifold geometry modeling for reference, firstly, this paper according to non-manifold Euler-Poincaré formula constructs 6 extended Euler operators and inverse operators to carry out creating, updating and deleting 3D spatial elements, as well as several pairs of supplementary Euler operators to convenient for implementing advanced functions. Secondly, we change topological element operation sequence of Boolean operation and set operation as well as set functions defined in GeoXACML into combination of extended Euler operators, which separates the upper functions and lower data structure. Lastly, we develop underground 3D GIS prototype system, in which practicability and credibility of extended Euler operators faced to 3D GIS presented by this paper are validated.
Control theory based airfoil design using the Euler equations
Jameson, Antony; Reuther, James
1994-01-01
This paper describes the implementation of optimization techniques based on control theory for airfoil design. In our previous work it was shown that control theory could be employed to devise effective optimization procedures for two-dimensional profiles by using the potential flow equation with either a conformal mapping or a general coordinate system. The goal of our present work is to extend the development to treat the Euler equations in two-dimensions by procedures that can readily be generalized to treat complex shapes in three-dimensions. Therefore, we have developed methods which can address airfoil design through either an analytic mapping or an arbitrary grid perturbation method applied to a finite volume discretization of the Euler equations. Here the control law serves to provide computationally inexpensive gradient information to a standard numerical optimization method. Results are presented for both the inverse problem and drag minimization problem.
A review of propeller modelling techniques based on Euler methods
Zondervan, G.J.D.
1995-01-01
Future generation civil aircraft will be powered by new, highly efficient propeller propulsion systems. New, advanced design tools like Euler methods will be needed in the design process of these aircraft. This report describes the application of Euler methods to the modelling of flowfields generated by propellers. An introduction is given in the general layout of propellers and the propeller slipstream. It is argued that Euler methods can treat a wider range of flow conditions than the class...
Pierdzioch, Christian; Doepke, Joerg; Buch, Claudia M
2002-01-01
The globalization of international financial markets has renewed interest in the measurement of capital mobility. Consumption-based tests such as the Euler equation test are commonly used. These tests, however, are derived under restrictive assumptions on consumer behavior. In this paper, we ask how the Euler equation test of capital mobility performs if these restrictive assumptions are relaxed. We simulate a dynamic general equilibrium two-country model under alternative assumptions regardi...
A test of Gaussianity based on the Euler characteristic of excursion sets
Di Bernardino, Elena; Estrade, Anne; León, José Rafael
2016-01-01
In the present paper, we deal with a stationary random field $X:\\R^d \\to \\R$ and we assume it is partially observed through some level functionals. We aim at providing a methodology for a test of Gaussianity based on this information. More precisely, the level functionals are given by the Euler characteristic of the excursion sets above some levels. On the one hand, we study the properties of these level functionals under the hypothesis that the random field $X$ is Gaussian. In particular, we...
Valizadeh, Ziba; Shams, Mehrzad
2016-08-01
A numerical scheme for simulating the subcooled flow boiling of water and water-based nanofluids was developed. At first, subcooled flow boiling of water was simulated by the Eulerian multiphase scheme. Then the simulation results were compared with previous experimental data and a good agreement was observed. In the next step, subcooled flow boiling of water-based nanofluid was modeled. In the previous studies in this field, the nanofluid assumed as a homogeneous liquid and the two-phase scheme was used to simulate its boiling. In the present study, a new scheme was used to model the nanofluid boiling. In this scheme, to model the nanofluid flow boiling, three phases, water, vapor and nanoparticles were considered. The Eulerian-Eulerian approach was used for modeling water-vapor interphase and Eulerian-Lagrangian scheme was selected to observe water-nanoparticle interphase behavior. The results from the nanofluid boiling modeling were validated with an experimental investigation. The results of the present work and experimental data were consistent. The addition of 0.0935 % volume fraction of nanoparticles in pure liquid boiling flow increases the vapor volume fraction at the outlet almost by 40.7 %. The results show the three-phase model is a good approach to simulate the nanofluid boiling flow.
A proof of image Euler Number formula
LIN Xiaozhu; SHA Yun; JI Junwei; WANG Yanmin
2006-01-01
Euler Number is one of the most important characteristics in topology. In two- dimension digital images, the Euler characteristic is locally computable. The form of Euler Number formula is different under 4-connected and 8-connected conditions. Based on the definition of the Foreground Segment and Neighbor Number, a formula of the Euler Number computing is proposed and is proved in this paper. It is a new idea to locally compute Euler Number of 2D image.
Development of 3d reactor burnup code based on Monte Carlo method and exponential Euler method
Burnup analysis plays a key role in fuel breeding, transmutation and post-processing in nuclear reactor. Burnup codes based on one-dimensional and two-dimensional transport method have difficulties in meeting the accuracy requirements. A three-dimensional burnup analysis code based on Monte Carlo method and Exponential Euler method has been developed. The coupling code combines advantage of Monte Carlo method in complex geometry neutron transport calculation and FISPACT in fast and precise inventory calculation, meanwhile resonance Self-shielding effect in inventory calculation can also be considered. The IAEA benchmark text problem has been adopted for code validation. Good agreements were shown in the comparison with other participants' results. (authors)
Development of higher-order perturbation approaches based on adaptive euler-lagrange fields
A higher-order generalized perturbation approach, based on a computationally efficient recursive higher-order sensitivity field correction concept (HGPT/RE), is presented. This method enables a higher-order GPT treatment of integral as well as local core response quantities of relevance for reactor core simulation. Examples are integral core reactivity, localised flux and power density. For the integral core reactivity, the HGPT/RE method enables a clear extension of the first-order classical reactivity perturbation formula, thereby enabling arbitrary accuracy, up to exact results, for pure neutronics reactivity perturbation scenarios. For both integral and local response quantities, the typical GPT computational efficiency is preserved, while enabling high accuracy for larger perturbations as well. The developed concept features highly efficient and computationally very inexpensive recursive relationships between successive sensitivity field correction expansion coefficients. The latter depend on the imposed localised core composition variations and are applied to span a perturbation-dependent adjusted sensitivity (Euler-Lagrange) field in terms of a limited number of adjoint unit response fields. The set of unit response fields needs to be computed merely for the unperturbed core. Rigorous mathematical derivations are presented, followed by numerical verifications that include larger in-core composition perturbations as well. (authors)
Claudia Stötzel
Full Text Available In this paper, we present a systematic transition scheme for a large class of ordinary differential equations (ODEs into Boolean networks. Our transition scheme can be applied to any system of ODEs whose right hand sides can be written as sums and products of monotone functions. It performs an Euler-like step which uses the signs of the right hand sides to obtain the Boolean update functions for every variable of the corresponding discrete model. The discrete model can, on one hand, be considered as another representation of the biological system or, alternatively, it can be used to further the analysis of the original ODE model. Since the generic transformation method does not guarantee any property conservation, a subsequent validation step is required. Depending on the purpose of the model this step can be based on experimental data or ODE simulations and characteristics. Analysis of the resulting Boolean model, both on its own and in comparison with the ODE model, then allows to investigate system properties not accessible in a purely continuous setting. The method is exemplarily applied to a previously published model of the bovine estrous cycle, which leads to new insights regarding the regulation among the components, and also indicates strongly that the system is tailored to generate stable oscillations.
Larios, Adam; Titi, Edriss S; Wingate, Beth
2015-01-01
We report the results of a computational investigation of two recently proved blow-up criteria for the 3D incompressible Euler equations. These criteria are based on an inviscid regularization of the Euler equations known as the 3D Euler-Voigt equations. The latter are known to be globally well-posed. Moreover, simulations of the 3D Euler-Voigt equations also require less resolution than simulations of the 3D Euler equations for fixed values of the regularization parameter $\\alpha>0$. Therefore, the new blow-up criteria allow one to gain information about possible singularity formation in the 3D Euler equations indirectly; namely, by simulating the better-behaved 3D Euler-Voigt equations. The new criteria are only known to be sufficient criteria for blow-up. Therefore, to test the robustness of the inviscid-regularization approach, we also investigate analogous criteria for blow-up of the 1D Burgers equation, where blow-up is well-known to occur.
Edwards, S.; Reuther, J.; Chattot, J. J.
The objective of this paper is to present a control theory approach for the design of airfoils in the presence of viscous compressible flows. A coupled system of the integral boundary layer and the Euler equations is solved to provide rapid flow simulations. An adjoint approach consistent with the complete coupled state equations is employed to obtain the sensitivities needed to drive a numerical optimization algorithm. Design to a target pressure distribution is demonstrated on an RAE 2822 airfoil at transonic speeds.
Neural Network based Consumption Forecasting
Madsen, Per Printz
2016-01-01
active participation in the future smart grid environment. One of the main obstacles for making optimal energy consumption is to have good predictions of the future energy consumption. This study is based on real consumption data from eight houses in Denmark. There are designed two different prediction...... models. It is shown that both of the predictions model produce a better consumption prediction then a naïve model. Seen in this perspective is it concluded that it is possible to use Artificial Neural Networks for predicting the energy consumption in ordinary family houses....
Adaptive Control Based On Neural Network
Wei, Sun; Lujin, Zhang; Jinhai, Zou; Siyi, Miao
2009-01-01
In this paper, the adaptive control based on neural network is studied. Firstly, a neural network based adaptive robust tracking control design is proposed for robotic systems under the existence of uncertainties. In this proposed control strategy, the NN is used to identify the modeling uncertainties, and then the disadvantageous effects caused by neural network approximating error and external disturbances in robotic system are counteracted by robust controller. Especially the proposed cont...
Anisotropic optical flow algorithm based on self-adaptive cellular neural network
Zhang, Congxuan; Chen, Zhen; Li, Ming; Sun, Kaiqiong
2013-01-01
An anisotropic optical flow estimation method based on self-adaptive cellular neural networks (CNN) is proposed. First, a novel optical flow energy function which contains a robust data term and an anisotropic smoothing term is projected. Next, the CNN model which has the self-adaptive feedback operator and threshold is presented according to the Euler-Lagrange partial differential equations of the proposed optical flow energy function. Finally, the elaborate evaluation experiments indicate the significant effects of the various proposed strategies for optical flow estimation, and the comparison results with the other methods show that the proposed algorithm has better performance in computing accuracy and efficiency.
Cryptography based on delayed chaotic neural networks
Yu Wenwu [Department of Mathematics, Southeast University, Nanjing 210096 (China); Cao Jinde [Department of Mathematics, Southeast University, Nanjing 210096 (China)]. E-mail: jdcao@seu.edu.cn
2006-08-14
In this Letter, a novel approach of encryption based on chaotic Hopfield neural networks with time varying delay is proposed. We use the chaotic neural network to generate binary sequences which will be used for masking plaintext. The plaintext is masked by switching of chaotic neural network maps and permutation of generated binary sequences. Simulation results were given to show the feasibility and effectiveness in the proposed scheme of this Letter. As a result, chaotic cryptography becomes more practical in the secure transmission of large multi-media files over public data communication network.
Cryptography based on delayed chaotic neural networks
In this Letter, a novel approach of encryption based on chaotic Hopfield neural networks with time varying delay is proposed. We use the chaotic neural network to generate binary sequences which will be used for masking plaintext. The plaintext is masked by switching of chaotic neural network maps and permutation of generated binary sequences. Simulation results were given to show the feasibility and effectiveness in the proposed scheme of this Letter. As a result, chaotic cryptography becomes more practical in the secure transmission of large multi-media files over public data communication network
SAR ATR Based on Convolutional Neural Network
Tian Zhuangzhuang; Zhan Ronghui; Hu Jiemin; Zhang Jun
2016-01-01
This study presents a new method of Synthetic Aperture Radar (SAR) image target recognition based on a convolutional neural network. First, we introduce a class separability measure into the cost function to improve this network’s ability to distinguish between categories. Then, we extract SAR image features using the improved convolutional neural network and classify these features using a support vector machine. Experimental results using moving and stationary target acquisition and recogni...
Zhang, Jingyang; Han, Le; Chang, Haiping; Liu, Nan; Xu, Tiejun
2016-02-01
An accurate critical heat flux (CHF) prediction method is the key factor for realizing the steady-state operation of a water-cooled divertor that works under one-sided high heating flux conditions. An improved CHF prediction method based on Euler's homogeneous model for flow boiling combined with realizable k-ɛ model for single-phase flow is adopted in this paper in which time relaxation coefficients are corrected by the Hertz-Knudsen formula in order to improve the calculation accuracy of vapor-liquid conversion efficiency under high heating flux conditions. Moreover, local large differences of liquid physical properties due to the extreme nonuniform heating flux on cooling wall along the circumference direction are revised by formula IAPWS-IF97. Therefore, this method can improve the calculation accuracy of heat and mass transfer between liquid phase and vapor phase in a CHF prediction simulation of water-cooled divertors under the one-sided high heating condition. An experimental example is simulated based on the improved and the uncorrected methods. The simulation results, such as temperature, void fraction and heat transfer coefficient, are analyzed to achieve the CHF prediction. The results show that the maximum error of CHF based on the improved method is 23.7%, while that of CHF based on uncorrected method is up to 188%, as compared with the experiment results of Ref. [12]. Finally, this method is verified by comparison with the experimental data obtained by International Thermonuclear Experimental Reactor (ITER), with a maximum error of 6% only. This method provides an efficient tool for the CHF prediction of water-cooled divertors. supported by the National Magnetic Confinement Fusion Science Program of China (No. 2010GB104005) and National Natural Science Foundation of China (No. 51406085)
Neural Network Based 3D Surface Reconstruction
Vincy Joseph
2009-11-01
Full Text Available This paper proposes a novel neural-network-based adaptive hybrid-reflectance three-dimensional (3-D surface reconstruction model. The neural network combines the diffuse and specular components into a hybrid model. The proposed model considers the characteristics of each point and the variant albedo to prevent the reconstructed surface from being distorted. The neural network inputs are the pixel values of the two-dimensional images to be reconstructed. The normal vectors of the surface can then be obtained from the output of the neural network after supervised learning, where the illuminant direction does not have to be known in advance. Finally, the obtained normal vectors can be applied to integration method when reconstructing 3-D objects. Facial images were used for training in the proposed approach
EULER - A Real Virtual Library for Mathematics
Jost, Michael
2004-01-01
The EULER project completed its work in November 2002. It forms the last part of a very successful project in the specialized but global discipline of mathematics. After a successful RTD project had created the technology, a take-up project has effectively exploited it to the point where its future is assured through a not-for-profit consortium. EULER is a European based, world class, real virtual library for mathematics with up-to-date technological solutions, well accepted by users. In particular, EULER provides a world reference and delivery service, transparent to the end user and offering full coverage of the mathematics literature world-wide, including bibliographic data, peer reviews and/or abstracts, indexing, classification and search, transparent access to library services, co-operation with commercial information providers (publishers, bookstores). The EULER services provide a gateway to the electronic catalogues and repositories of participating institutions, while the latter retain complete respo...
SAR ATR Based on Convolutional Neural Network
Tian Zhuangzhuang
2016-06-01
Full Text Available This study presents a new method of Synthetic Aperture Radar (SAR image target recognition based on a convolutional neural network. First, we introduce a class separability measure into the cost function to improve this network’s ability to distinguish between categories. Then, we extract SAR image features using the improved convolutional neural network and classify these features using a support vector machine. Experimental results using moving and stationary target acquisition and recognition SAR datasets prove the validity of this method.
Autonomous robot behavior based on neural networks
Grolinger, Katarina; Jerbic, Bojan; Vranjes, Bozo
1997-04-01
The purpose of autonomous robot is to solve various tasks while adapting its behavior to the variable environment, expecting it is able to navigate much like a human would, including handling uncertain and unexpected obstacles. To achieve this the robot has to be able to find solution to unknown situations, to learn experienced knowledge, that means action procedure together with corresponding knowledge on the work space structure, and to recognize working environment. The planning of the intelligent robot behavior presented in this paper implements the reinforcement learning based on strategic and random attempts for finding solution and neural network approach for memorizing and recognizing work space structure (structural assignment problem). Some of the well known neural networks based on unsupervised learning are considered with regard to the structural assignment problem. The adaptive fuzzy shadowed neural network is developed. It has the additional shadowed hidden layer, specific learning rule and initialization phase. The developed neural network combines advantages of networks based on the Adaptive Resonance Theory and using shadowed hidden layer provides ability to recognize lightly translated or rotated obstacles in any direction.
Coirier, William John
1994-01-01
A Cartesian, cell-based scheme for solving the Euler and Navier-Stokes equations in two dimensions is developed and tested. Grids about geometrically complicated bodies are generated automatically, by recursive subdivision of a single Cartesian cell encompassing the entire flow domain. Where the resulting cells intersect bodies, polygonal 'cut' cells are created. The geometry of the cut cells is computed using polygon-clipping algorithms. The grid is stored in a binary-tree data structure which provides a natural means of obtaining cell-to-cell connectivity and of carrying out solution-adaptive refinement. The Euler and Navier-Stokes equations are solved on the resulting grids using a finite-volume formulation. The convective terms are upwinded, with a limited linear reconstruction of the primitive variables used to provide input states to an approximate Riemann solver for computing the fluxes between neighboring cells. A multi-stage time-stepping scheme is used to reach a steady-state solution. Validation of the Euler solver with benchmark numerical and exact solutions is presented. An assessment of the accuracy of the approach is made by uniform and adaptive grid refinements for a steady, transonic, exact solution to the Euler equations. The error of the approach is directly compared to a structured solver formulation. A non smooth flow is also assessed for grid convergence, comparing uniform and adaptively refined results. Several formulations of the viscous terms are assessed analytically, both for accuracy and positivity. The two best formulations are used to compute adaptively refined solutions of the Navier-Stokes equations. These solutions are compared to each other, to experimental results and/or theory for a series of low and moderate Reynolds numbers flow fields. The most suitable viscous discretization is demonstrated for geometrically-complicated internal flows. For flows at high Reynolds numbers, both an altered grid-generation procedure and a
Cacciatori, Sergio; Cerchiai, Bianca Letizia; della Vedova,Alberto; Ortenzi, Giovanni; Scotti, Antonio
2005-03-10
We provide a simple parameterization for the group G2, which is analogous to the Euler parameterization for SU(2). We show how to obtain the general element of the group in a form emphasizing the structure of the fibration of G2 with fiber SO(4) and base H, the variety of quaternionic subalgebras of octonions. In particular this allows us to obtain a simple expression for the Haar measure on G2. Moreover, as a by-product it yields a concrete realization and an Einstein metric for H.
Convolutional Neural Network Based dem Super Resolution
Chen, Zixuan; Wang, Xuewen; Xu, Zekai; Hou, Wenguang
2016-06-01
DEM super resolution is proposed in our previous publication to improve the resolution for a DEM on basis of some learning examples. Meanwhile, the nonlocal algorithm is introduced to deal with it and lots of experiments show that the strategy is feasible. In our publication, the learning examples are defined as the partial original DEM and their related high measurements due to this way can avoid the incompatibility between the data to be processed and the learning examples. To further extent the applications of this new strategy, the learning examples should be diverse and easy to obtain. Yet, it may cause the problem of incompatibility and unrobustness. To overcome it, we intend to investigate a convolutional neural network based method. The input of the convolutional neural network is a low resolution DEM and the output is expected to be its high resolution one. A three layers model will be adopted. The first layer is used to detect some features from the input, the second integrates the detected features to some compressed ones and the final step transforms the compressed features as a new DEM. According to this designed structure, some learning DEMs will be taken to train it. Specifically, the designed network will be optimized by minimizing the error of the output and its expected high resolution DEM. In practical applications, a testing DEM will be input to the convolutional neural network and a super resolution will be obtained. Many experiments show that the CNN based method can obtain better reconstructions than many classic interpolation methods.
A Direct Feedback Control Based on Fuzzy Recurrent Neural Network
李明; 马小平
2002-01-01
A direct feedback control system based on fuzzy-recurrent neural network is proposed, and a method of training weights of fuzzy-recurrent neural network was designed by applying modified contract mapping genetic algorithm. Computer simul ation results indicate that fuzzy-recurrent neural network controller has perfect dynamic and static performances .
SOLVING INVERSE KINEMATICS OF REDUNDANT MANIPULATOR BASED ON NEURAL NETWORK
无
2003-01-01
For the redundant manipulators, neural network is used to tackle the velocity inverse kinematics of robot manipulators. The neural networks utilized are multi-layered perceptions with a back-propagation training algorithm. The weight table is used to save the weights solving the inverse kinematics based on the different optimization performance criteria. Simulations verify the effectiveness of using neural network.
Neural Network Based Hausa Language Speech Recognition
Matthew K Luka
2012-05-01
Full Text Available Speech recognition is a key element of diverse applications in communication systems, medical transcription systems, security systems etc. However, there has been very little research in the domain of speech processing for African languages, thus, the need to extend the frontier of research in order to port in, the diverse applications based on speech recognition. Hausa language is an important indigenous lingua franca in west and central Africa, spoken as a first or second language by about fifty million people. Speech recognition of Hausa Language is presented in this paper. A pattern recognition neural network was used for developing the system.
The Hamiltonian Canonical Form for Euler-Lagrange Equations
ZHENG Yu
2002-01-01
Based on the theory of calculus of variation, some suffcient conditions are given for some Euler-Lagrangcequations to be equivalently represented by finite or even infinite many Hamiltonian canonical equations. Meanwhile,some further applications for equations such as the KdV equation, MKdV equation, the general linear Euler Lagrangeequation and the cylindric shell equations are given.
Euler: Genius Blind Astronomer Mathematician
Musielak, Dora
2014-01-01
Leonhard Euler, the most prolific mathematician in history, contributed to advance a wide spectrum of topics in celestial mechanics. At the Saint Petersburg Observatory, Euler observed sunspots and tracked the movements of the Moon. Combining astronomical observations with his own mathematical genius, he determined the orbits of planets and comets. Euler laid the foundations of the methods of planetary perturbations and solved many of the Newtonian mechanics problems of the eighteenth century...
Approximations to Euler's constant
We study a problem of finding good approximations to Euler's constant γ=lim→∞ Sn, where Sn = Σk=Ln (1)/k-log(n+1), by linear forms in logarithms and harmonic numbers. In 1995, C. Elsner showed that slow convergence of the sequence Sn can be significantly improved if Sn is replaced by linear combinations of Sn with integer coefficients. In this paper, considering more general linear transformations of the sequence Sn we establish new accelerating convergence formulae for γ. Our estimates sharpen and generalize recent Elsner's, Rivoal's and author's results. (author)
LIU Wei-qun; MIAO Xie-xing
2006-01-01
The overbroken rock mass of gob areas is made up of broken and accumulated rock blocks compressed to some extent by the overlying strata. The bearing pressure of the gob can directly affect the safety of mining fields, formation of road retained along the next goaf and seepage of water and methane through the gob. In this paper, the software RFPA'2000 is used to construct numerical models. Especially the Euler method of control volume is proposed to solve the simulation difficulty arising from plastically finite deformations. The results show that three characteristic regions occurred in the gob area: (1) a naturally accumulated region, 0-10 m away from unbroken surrounding rock walls, where the bearing pressure is nearly zero; (2) an overcompacted region, 10-20 m away from unbroken walls, where the bearing pressure results in the maximum value of the gob area; (3) a stable compaction region, more than 20 m away from unbroken walls and occupying absolutely most of the gob area, where the bearing pressures show basically no differences. Such a characteristic can explain the easy-seepaged "O"-ring phenomena around mining fields very well.
Principal Symbol of Euler-Lagrange Operators
Fatibene, Lorenzo
2016-01-01
We shall introduce the principal symbol for Euler-Lagrange operators and use them to charac- terise well-posed initial value problems. We shall clarify how constraints can arise in Lagrangian covariant theories by extending the standard treatment in GR. Finally, we sketch a quantization procedure based on what done in LQG.
Mesh deformation based on artificial neural networks
Stadler, Domen; Kosel, Franc; Čelič, Damjan; Lipej, Andrej
2011-09-01
In the article a new mesh deformation algorithm based on artificial neural networks is introduced. This method is a point-to-point method, meaning that it does not use connectivity information for calculation of the mesh deformation. Two already known point-to-point methods, based on interpolation techniques, are also presented. In contrast to the two known interpolation methods, the new method does not require a summation over all boundary nodes for one displacement calculation. The consequence of this fact is a shorter computational time of mesh deformation, which is proven by different deformation tests. The quality of the deformed meshes with all three deformation methods was also compared. Finally, the generated and the deformed three-dimensional meshes were used in the computational fluid dynamics numerical analysis of a Francis water turbine. A comparison of the analysis results was made to prove the applicability of the new method in every day computation.
Evolving Chart Pattern Sensitive Neural Network Based Forex Trading Agents
Sher, Gene I
2011-01-01
Though machine learning has been applied to the foreign exchange market for quiet some time now, and neural networks have been shown to yield good results, in modern approaches neural network systems are optimized through the traditional methods, and their input signals are vectors containing prices and other indicator elements. The aim of this paper is twofold, the presentation and testing of the application of topology and weight evolving artificial neural network (TWEANN) systems to automated currency trading, and the use of chart images as input to a geometrical regularity aware indirectly encoded neural network systems. This paper presents the benchmark results of neural network based automated currency trading systems evolved using TWEANNs, and compares the generalization capabilities of these direct encoded neural networks which use the standard price vector inputs, and the indirect (substrate) encoded neural networks which use chart images as input. The TWEANN algorithm used to evolve these currency t...
Multispectral thermometry based on neural network
孙晓刚; 戴景民
2003-01-01
In order to overcome the effect of the assumption between emissivity and wavelength on the measurement of true temperature and spectral emissivity for most engineering materials, a neural network based method is proposed for data processing while a blackbody furnace and three optical filters with known spectral transmittance curves were used to make up a true target. The experimental results show that the calculated temperatures are in good agreement with the temperature of the blackbody furnace, and the calculated spectral emissivity curves are in good agreement with the spectral transmittance curves of the filters. The method proposed has been proved to be an effective method for solving the problem of true temperature and emissivity measurement, and it can overcome the effect of the assumption between emissivity and wavelength on the measurement of true temperature and spectral emissivity for most engineering materials.
Clustering-based selective neural network ensemble
FU Qiang; HU Shang-xu; ZHAO Sheng-ying
2005-01-01
An effective ensemble should consist of a set of networks that are both accurate and diverse. We propose a novel clustering-based selective algorithm for constructing neural network ensemble, where clustering technology is used to classify trained networks according to similarity and optimally select the most accurate individual network from each cluster to make up the ensemble. Empirical studies on regression of four typical datasets showed that this approach yields significantly smaller en semble achieving better performance than other traditional ones such as Bagging and Boosting. The bias variance decomposition of the predictive error shows that the success of the proposed approach may lie in its properly tuning the bias/variance trade-offto reduce the prediction error (the sum of bias2 and variance).
Implementation of neural network based non-linear predictive
Sørensen, Paul Haase; Nørgård, Peter Magnus; Ravn, Ole;
1998-01-01
-linear systems. GPC is model-based and in this paper we propose the use of a neural network for the modeling of the system. Based on the neural network model a controller with extended control horizon is developed and the implementation issues are discussed, with particular emphasis on an efficient Quasi...
A Neural Network-Based Interval Pattern Matcher
Jing Lu
2015-07-01
Full Text Available One of the most important roles in the machine learning area is to classify, and neural networks are very important classifiers. However, traditional neural networks cannot identify intervals, let alone classify them. To improve their identification ability, we propose a neural network-based interval matcher in our paper. After summarizing the theoretical construction of the model, we take a simple and a practical weather forecasting experiment, which show that the recognizer accuracy reaches 100% and that is promising.
Digital Watermarking Algorithm Based on Wavelet Transform and Neural Network
WANG Zhenfei; ZHAI Guangqun; WANG Nengchao
2006-01-01
An effective blind digital watermarking algorithm based on neural networks in the wavelet domain is presented. Firstly, the host image is decomposed through wavelet transform. The significant coefficients of wavelet are selected according to the human visual system (HVS) characteristics. Watermark bits are added to them. And then effectively cooperates neural networks to learn the characteristics of the embedded watermark related to them. Because of the learning and adaptive capabilities of neural networks, the trained neural networks almost exactly recover the watermark from the watermarked image. Experimental results and comparisons with other techniques prove the effectiveness of the new algorithm.
Neural bases of accented speech perception
Adank, Patti; Nuttall, Helen E.; Banks, Briony; Kennedy-Higgins, Daniel
2015-01-01
The recognition of unfamiliar regional and foreign accents represents a challenging task for the speech perception system (Floccia et al., 2006; Adank et al., 2009). Despite the frequency with which we encounter such accents, the neural mechanisms supporting successful perception of accented speech are poorly understood. Nonetheless, candidate neural substrates involved in processing speech in challenging listening conditions, including accented speech, are beginning to be identified. This re...
Neural Network Classifier Based on Growing Hyperspheres
Jiřina Jr., Marcel; Jiřina, Marcel
2000-01-01
Roč. 10, č. 3 (2000), s. 417-428. ISSN 1210-0552. [Neural Network World 2000. Prague, 09.07.2000-12.07.2000] Grant ostatní: MŠMT ČR(CZ) VS96047; MPO(CZ) RP-4210 Institutional research plan: AV0Z1030915 Keywords : neural network * classifier * hyperspheres * big -dimensional data Subject RIV: BA - General Mathematics
DEM interpolation based on artificial neural networks
Jiao, Limin; Liu, Yaolin
2005-10-01
This paper proposed a systemic resolution scheme of Digital Elevation model (DEM) interpolation based on Artificial Neural Networks (ANNs). In this paper, we employ BP network to fit terrain surface, and then detect and eliminate the samples with gross errors. This paper uses Self-organizing Feature Map (SOFM) to cluster elevation samples. The study area is divided into many more homogenous tiles after clustering. BP model is employed to interpolate DEM in each cluster. Because error samples are eliminated and clusters are built, interpolation result is better. The case study indicates that ANN interpolation scheme is feasible. It also shows that ANN can get a more accurate result by comparing ANN with polynomial and spline interpolation. ANN interpolation doesn't need to determine the interpolation function beforehand, so manmade influence is lessened. The ANN interpolation is more automatic and intelligent. At the end of the paper, we propose the idea of constructing ANN surface model. This model can be used in multi-scale DEM visualization, and DEM generalization, etc.
Neural Network Based Intelligent Sootblowing System
Mark Rhode
2005-04-01
. Due to the composition of coal, particulate matter is also a by-product of coal combustion. Modern day utility boilers are usually fitted with electrostatic precipitators to aid in the collection of particulate matter. Although extremely efficient, these devices are sensitive to rapid changes in inlet mass concentration as well as total mass loading. Traditionally, utility boilers are equipped with devices known as sootblowers, which use, steam, water or air to dislodge and clean the surfaces within the boiler and are operated based upon established rule or operator's judgment. Poor sootblowing regimes can influence particulate mass loading to the electrostatic precipitators. The project applied a neural network intelligent sootblowing system in conjunction with state-of-the-art controls and instruments to optimize the operation of a utility boiler and systematically control boiler slagging/fouling. This optimization process targeted reduction of NOx of 30%, improved efficiency of 2% and a reduction in opacity of 5%. The neural network system proved to be a non-invasive system which can readily be adapted to virtually any utility boiler. Specific conclusions from this neural network application are listed below. These conclusions should be used in conjunction with the specific details provided in the technical discussions of this report to develop a thorough understanding of the process.
Architecture Analysis of an FPGA-Based Hopfield Neural Network
Miguel Angelo de Abreu de Sousa
2014-01-01
Full Text Available Interconnections between electronic circuits and neural computation have been a strongly researched topic in the machine learning field in order to approach several practical requirements, including decreasing training and operation times in high performance applications and reducing cost, size, and energy consumption for autonomous or embedded developments. Field programmable gate array (FPGA hardware shows some inherent features typically associated with neural networks, such as, parallel processing, modular executions, and dynamic adaptation, and works on different types of FPGA-based neural networks were presented in recent years. This paper aims to address different aspects of architectural characteristics analysis on a Hopfield Neural Network implemented in FPGA, such as maximum operating frequency and chip-area occupancy according to the network capacity. Also, the FPGA implementation methodology, which does not employ multipliers in the architecture developed for the Hopfield neural model, is presented, in detail.
Using Euler buckling springs for vibration isolation
Winterflood, J; Blair, D G
2002-01-01
Difficulties in obtaining ideal vertical vibration isolation with mechanical springs are identified as being due to the mass of the elastic element which is in turn due to its energy storage requirement. A new technique to minimize this energy is presented - being an Euler column undergoing elastic buckling. The design of a high performance vertical vibration isolation stage based on this technique is presented together with its measured performance.
Using Euler buckling springs for vibration isolation
Difficulties in obtaining ideal vertical vibration isolation with mechanical springs are identified as being due to the mass of the elastic element which is in turn due to its energy storage requirement. A new technique to minimize this energy is presented - being an Euler column undergoing elastic buckling. The design of a high performance vertical vibration isolation stage based on this technique is presented together with its measured performance
Network Traffic Prediction based on Particle Swarm BP Neural Network
Yan Zhu; Guanghua Zhang; Jing Qiu
2013-01-01
The traditional BP neural network algorithm has some bugs such that it is easy to fall into local minimum and the slow convergence speed. Particle swarm optimization is an evolutionary computation technology based on swarm intelligence which can not guarantee global convergence. Artificial Bee Colony algorithm is a global optimum algorithm with many advantages such as simple, convenient and strong robust. In this paper, a new BP neural network based on Artificial Bee Colony algorithm and part...
Image watermarking capacity analysis based on Hopfield neural network
Fan Zhang(张帆); Hongbin Zhang(张鸿宾)
2004-01-01
In watermarking schemes, watermarking can be viewed as a form of communication problems. Almost all of previous works on image watermarking capacity are based on information theory, using Shannon formula to calculate the capacity of watermarking. In this paper, we present a blind watermarking algorithm using Hopfield neural network, and analyze watermarking capacity based on neural network. In our watermarking algorithm, watermarking capacity is decided by attraction basin of associative memory.
Implementation of neural network based non-linear predictive
Sørensen, Paul Haase; Nørgård, Peter Magnus; Ravn, Ole; Poulsen, Niels Kjølstad
-linear systems. GPC is model-based and in this paper we propose the use of a neural network for the modeling of the system. Based on the neural network model a controller with extended control horizon is developed and the implementation issues are discussed, with particular emphasis on an efficient Quasi......-Newton optimization algorithm. The performance is demonstrated on a pneumatic servo system....
Contractor Prequalification Based on Neural Networks
ZHANG Jin-long; YANG Lan-rong
2002-01-01
Contractor Prequalification involves the screening of contractors by a project owner, according to a given set of criteria, in order to determine their competence to perform the work if awarded the construction contract. This paper introduces the capabilities of neural networks in solving problems related to contractor prequalification. The neural network systems for contractor prequalification has an input vector of 8 components and an output vector of 1 component. The output vector represents whether a contractor is qualified or not qualified to submit a bid on a project.
Applications of Neural-Based Agents in Computer Game Design
Qualls, Joseph; Russomanno, David J.
2009-01-01
It is clear from the implementation and analysis of the performance of the game Defend and Gather and the many other examples discussed in this chapter that neural-based agents have the ability to overcome some of the shortcomings associated with implementing classical AI techniques in computer game design. Neural networks can be used in many diverse ways in computer games ranging from agent control, environmental evolution, to content generation. As outlined in Section 3 of this chapter, by ...
Neural-Based Models of Semiconductor Devices for SPICE Simulator
Hanene B. Hammouda; Mongia Mhiri; Zièd Gafsi; Kamel Besbes
2008-01-01
The paper addresses a simple and fast new approach to implement Artificial Neural Networks (ANN) models for the MOS transistor into SPICE. The proposed approach involves two steps, the modeling phase of the device by NN providing its input/output patterns, and the SPICE implementation process of the resulting model. Using the Taylor series expansion, a neural based small-signal model is derived. The reliability of our approach is validated through simulations of some circuits in DC and small-...
MOVING TARGETS PATTERN RECOGNITION BASED ON THE WAVELET NEURAL NETWORK
Ge Guangying; Chen Lili; Xu Jianjian
2005-01-01
Based on pattern recognition theory and neural network technology, moving objects automatic detection and classification method integrating advanced wavelet analysis are discussed in detail. An algorithm of moving targets pattern recognition on the combination of inter-frame difference and wavelet neural network is presented. The experimental results indicate that the designed BP wavelet network using this algorithm can recognize and classify moving targets rapidly and effectively.
Dependency-based Convolutional Neural Networks for Sentence Embedding
Ma, Mingbo; Huang, Liang; Xiang, Bing; Zhou, Bowen
2015-01-01
In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequentially and neglect long-distance dependencies. To exploit both deep learning and linguistic structures, we propose a tree-based convolutional neural network model which exploit various long-distance relationships between words. Our model improves the sequential baselines on all three sentiment and question classificat...
Neural Network Predictive Control Based Power System Stabilizer
Ali Mohamed Yousef
2012-01-01
The present study investigates the power system stabilizer based on neural predictive control for improving power system dynamic performance over a wide range of operating conditions. In this study a design and application of the Neural Network Model Predictive Controller (NN-MPC) on a simple power system composed of a synchronous generator connected to an infinite bus through a transmission line is proposed. The synchronous machine is represented in detail, taking into account the effect of ...
Artificial neural network based modelling of internal combustion engine performance
Boruah, Dibakor; Thakur, Pintu Kumar; Baruah, Dipal
2016-01-01
The present study aims to quantify the applicability of artificial neural network as a black-box model for internal combustion engine performance. In consequence, an artificial neural network (ANN) based model for a four cylinder, four stroke internal combustion diesel engine has been developed on the basis of specific input and output factors, which have been taken from experimental readings for different load and engine speed circumstances. The input parameters that have been used to create...
Decoupling Control Method Based on Neural Network for Missiles
ZHAN Li; LUO Xi-shuang; ZHANG Tian-qiao
2005-01-01
In order to make the static state feedback nonlinear decoupling control law for a kind of missile to be easy for implementation in practice, an improvement is discussed. The improvement method is to introduce a BP neural network to approximate the decoupling control laws which are designed for different aerodynamic characteristic points, so a new decoupling control law based on BP neural network is produced after the network training. The simulation results on an example illustrate the approach obtained feasible and effective.
Hopfield neural network based on ant system
洪炳镕; 金飞虎; 郭琦
2004-01-01
Hopfield neural network is a single layer feedforward neural network. Hopfield network requires some control parameters to be carefully selected, else the network is apt to converge to local minimum. An ant system is a nature inspired meta heuristic algorithm. It has been applied to several combinatorial optimization problems such as Traveling Salesman Problem, Scheduling Problems, etc. This paper will show an ant system may be used in tuning the network control parameters by a group of cooperated ants. The major advantage of this network is to adjust the network parameters automatically, avoiding a blind search for the set of control parameters.This network was tested on two TSP problems, 5 cities and 10 cities. The results have shown an obvious improvement.
A Design of Neural-Net Based Decouplers
Tokuda, Makoto; Yamamoto, Toru; Monden, Yoshimi
In process industries such as the chemical plants, a good control performance cannot be obtained by simply using the linear controllers, since most processes are nonlinear multivariable systems with mutual interactions. And now, in various fields, the neural networks are well known as the representative schemes to describe the nonlinear elements included in the systems. Also, many types of neural-net based control systems have been proposed, since they have the ability of function approximation, the training ability and versatility. However, the neural networks tend to require great deal of training iteration or careful adjustments of user-specified parameters. In this paper, a design method of neural-net based decouplers is proposed for nonlinear multivariable systems. Here, the decoupler is generated by the sum of a static decoupler and a neural-net based decoupler. The former is used so that the influence of mutual interactions is roughly removed, and the latter plays a role of compensating the nonlinearities and decoupling the remaining mutual interactions. Thus, by designing the control system as the hybrid system, the burden in training the neural networks can be considerably reduced. Finally, the effectiveness of the proposed control scheme is evaluated on a simulation example.
Nonlinear control structures based on embedded neural system models.
Lightbody, G; Irwin, G W
1997-01-01
This paper investigates in detail the possible application of neural networks to the modeling and adaptive control of nonlinear systems. Nonlinear neural-network-based plant modeling is first discussed, based on the approximation capabilities of the multilayer perceptron. A structure is then proposed to utilize feedforward networks within a direct model reference adaptive control strategy. The difficulties involved in training this network, embedded within the closed-loop are discussed and a novel neural-network-based sensitivity modeling approach proposed to allow for the backpropagation of errors through the plant to the neural controller. Finally, a novel nonlinear internal model control (IMC) strategy is suggested, that utilizes a nonlinear neural model of the plant to generate parameter estimates over the nonlinear operating region for an adaptive linear internal model, without the problems associated with recursive parameter identification algorithms. Unlike other neural IMC approaches the linear control law can then be readily designed. A continuous stirred tank reactor was chosen as a realistic nonlinear case study for the techniques discussed in the paper. PMID:18255659
Numeral eddy current sensor modelling based on genetic neural network
This paper presents a method used to the numeral eddy current sensor modelling based on the genetic neural network to settle its nonlinear problem. The principle and algorithms of genetic neural network are introduced. In this method, the nonlinear model parameters of the numeral eddy current sensor are optimized by genetic neural network (GNN) according to measurement data. So the method remains both the global searching ability of genetic algorithm and the good local searching ability of neural network. The nonlinear model has the advantages of strong robustness, on-line modelling and high precision. The maximum nonlinearity error can be reduced to 0.037% by using GNN. However, the maximum nonlinearity error is 0.075% using the least square method
Learning in neural networks based on a generalized fluctuation theorem
Hayakawa, Takashi; Aoyagi, Toshio
2015-11-01
Information maximization has been investigated as a possible mechanism of learning governing the self-organization that occurs within the neural systems of animals. Within the general context of models of neural systems bidirectionally interacting with environments, however, the role of information maximization remains to be elucidated. For bidirectionally interacting physical systems, universal laws describing the fluctuation they exhibit and the information they possess have recently been discovered. These laws are termed fluctuation theorems. In the present study, we formulate a theory of learning in neural networks bidirectionally interacting with environments based on the principle of information maximization. Our formulation begins with the introduction of a generalized fluctuation theorem, employing an interpretation appropriate for the present application, which differs from the original thermodynamic interpretation. We analytically and numerically demonstrate that the learning mechanism presented in our theory allows neural networks to efficiently explore their environments and optimally encode information about them.
Impulsive Neural Networks Algorithm Based on the Artificial Genome Model
Yuan Gao
2014-05-01
Full Text Available To describe gene regulatory networks, this article takes the framework of the artificial genome model and proposes impulsive neural networks algorithm based on the artificial genome model. Firstly, the gene expression and the cell division tree are applied to generate spiking neurons with specific attributes, neural network structure, connection weights and specific learning rules of each neuron. Next, the gene segment duplications and divergence model are applied to design the evolutionary algorithm of impulsive neural networks at the level of the artificial genome. The dynamic changes of developmental gene regulatory networks are controlled during the whole evolutionary process. Finally, the behavior of collecting food for autonomous intelligent agent is simulated, which is driven by nerves. Experimental results demonstrate that the algorithm in this article has the evolutionary ability on large-scale impulsive neural networks
Numeral eddy current sensor modelling based on genetic neural network
Yu A-Long
2008-01-01
This paper presents a method used to the numeral eddy current sensor modelling based on the genetic neural network to settle its nonlinear problem. The principle and algorithms of genetic neural network are introduced. In this method, the nonlinear model parameters of the numeral eddy current sensor are optimized by genetic neural network (GNN) according to measurement data. So the method remains both the global searching ability of genetic algorithm and the good local searching ability of neural network. The nonlinear model has the advantages of strong robustness,on-line modelling and high precision.The maximum nonlinearity error can be reduced to 0.037% by using GNN.However, the maximum nonlinearity error is 0.075% using the least square method.
Colored Noise Prediction Based on Neural Network
Gao Fei; Zhang Xiaohui
2003-01-01
A method for predicting colored noise by introducing prediction of nonhnear time series is presented By adopting three kinds of neural networks prediction models, the colored noise prediction is studied through changing the filter bandwidth for stochastic noise and the sampling rate for colored noise The results show that colored noise can be predicted The prediction error decreases with the increasing of the sampling rate or the narrowing of the filter bandwidth. If the parameters are selected properly, the prediction precision can meet the requirement of engineering implementation. The results offer a new reference way for increasing the ability for detecting weak signal in signal processing system
Stability analysis of extended discrete-time BAM neural networks based on LMI approach
无
2005-01-01
We propose a new approach for analyzing the global asymptotic stability of the extended discrete-time bidirectional associative memory (BAM) neural networks. By using the Euler rule, we discretize the continuous-time BAM neural networks as the extended discrete-time BAM neural networks with non-threshold activation functions. Here we present some conditions under which the neural networks have unique equilibrium points. To judge the global asymptotic stability of the equilibrium points, we introduce a new neural network model - standard neural network model (SNNM).For the SNNMs, we derive the sufficient conditions for the global asymptotic stability of the equilibrium points, which are formulated as some linear matrix inequalities (LMIs). We transform the discrete-time BAM into the SNNM and apply the general result about the SNNM to the determination of global asymptotic stability of the discrete-time BAM. The approach proposed extends the known stability results, has lower conservativeness, can be verified easily, and can also be applied to other forms of recurrent neural networks.
Image Restoration Technology Based on Discrete Neural network
Zhou Duoying
2015-01-01
Full Text Available With the development of computer science and technology, the development of artificial intelligence advances rapidly in the field of image restoration. Based on the MATLAB platform, this paper constructs a kind of image restoration technology of artificial intelligence based on the discrete neural network and feedforward network, and carries out simulation and contrast of the restoration process by the use of the bionic algorithm. Through the application of simulation restoration technology, this paper verifies that the discrete neural network has a good convergence and identification capability in the image restoration technology with a better effect than that of the feedforward network. The restoration technology based on the discrete neural network can provide a reliable mathematical model for this field.
Network Traffic Prediction based on Particle Swarm BP Neural Network
Yan Zhu
2013-11-01
Full Text Available The traditional BP neural network algorithm has some bugs such that it is easy to fall into local minimum and the slow convergence speed. Particle swarm optimization is an evolutionary computation technology based on swarm intelligence which can not guarantee global convergence. Artificial Bee Colony algorithm is a global optimum algorithm with many advantages such as simple, convenient and strong robust. In this paper, a new BP neural network based on Artificial Bee Colony algorithm and particle swarm optimization algorithm is proposed to optimize the weight and threshold value of BP neural network. After network traffic prediction experiment, we can conclude that optimized BP network traffic prediction based on PSO-ABC has high prediction accuracy and has stable prediction performance.
On Thurston's Euler class one conjecture
Yazdi, Mehdi
2016-01-01
In 1976, Thurston proved that taut foliations on closed hyperbolic 3-manifolds have Euler class of norm at most one, and conjectured that, conversely, any Euler class with norm equal to one is Euler class of a taut foliation. We construct counterexamples to this conjecture and suggest an alternative conjecture.
Data Mining and Neural Network Techniques in Case Based System
无
2001-01-01
This paper first puts forward a case-based system framework basedon data mining techniques. Then the paper examines the possibility of using neural n etworks as a method of retrieval in such a case-based system. In this system we propose data mining algorithms to discover case knowledge and other algorithms.
Unfolding code for neutron spectrometry based on neural nets technology
Ortiz R, J. M.; Vega C, H. R., E-mail: morvymm@yahoo.com.mx [Universidad Autonoma de Zacatecas, Unidad Academica de Ingenieria Electrica, Apdo. Postal 336, 98000 Zacatecas (Mexico)
2012-10-15
The most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Neural Networks have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This unfolding code called Neutron Spectrometry and Dosimetry by means of Artificial Neural Networks was designed in a graphical interface under LabVIEW programming environment. The core of the code is an embedded neural network architecture, previously optimized by the {sup R}obust Design of Artificial Neural Networks Methodology{sup .} The main features of the code are: is easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a {sup 6}Lil(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, only seven rate counts measurement with a Bonner spheres spectrometer are required for simultaneously unfold the 60 energy bins of the neutron spectrum and to calculate 15 dosimetric quantities, for radiation protection porpoises. This code generates a full report in html format with all relevant information. (Author)
Unfolding code for neutron spectrometry based on neural nets technology
The most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. The drawbacks associated with traditional unfolding procedures have motivated the need of complementary approaches. Novel methods based on Artificial Neural Networks have been widely investigated. In this work, a neutron spectrum unfolding code based on neural nets technology is presented. This unfolding code called Neutron Spectrometry and Dosimetry by means of Artificial Neural Networks was designed in a graphical interface under LabVIEW programming environment. The core of the code is an embedded neural network architecture, previously optimized by the Robust Design of Artificial Neural Networks Methodology. The main features of the code are: is easy to use, friendly and intuitive to the user. This code was designed for a Bonner Sphere System based on a 6Lil(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation. The main feature of the code is that as entrance data, only seven rate counts measurement with a Bonner spheres spectrometer are required for simultaneously unfold the 60 energy bins of the neutron spectrum and to calculate 15 dosimetric quantities, for radiation protection porpoises. This code generates a full report in html format with all relevant information. (Author)
Forest Fire Image Intelligent Recognition based on the Neural Network
Yan Qiang; Bo Pei; Juanjuan Zhao
2014-01-01
To avoid the drawbacks caused by the long-distance and large-area features of the outdoor forest fires in the traditional fire detection methods. A new forest fire recognition method based on the neural network is proposed, which recognizes the fire based on the static and dynamic features of the fire. The method combines the multiple parameters of the flames and the shapes of the fire to distinguish fire image. Then the extracted features were tested by the Back Propagation Neural Network. T...
Neural network based electron identification in the ZEUS calorimeter
We present an electron identification algorithm based on a neural network approach applied to the ZEUS uranium calorimeter. The study is motivated by the need to select deep inelastic, neutral current, electron proton interactions characterized by the presence of a scattered electron in the final state. The performance of the algorithm is compared to an electron identification method based on a classical probabilistic approach. By means of a principle component analysis the improvement in the performance is traced back to the number of variables used in the neural network approach. (orig.)
The neural bases of orthographic working memory
Jeremy Purcell
2014-04-01
First, these results reveal a neurotopography of OWM lesion sites that is well-aligned with results from neuroimaging of orthographic working memory in neurally intact participants (Rapp & Dufor, 2011. Second, the dorsal neurotopography of the OWM lesion overlap is clearly distinct from what has been reported for lesions associated with either lexical or sublexical deficits (e.g., Henry, Beeson, Stark, & Rapcsak, 2007; Rapcsak & Beeson, 2004; these have, respectively, been identified with the inferior occipital/temporal and superior temporal/inferior parietal regions. These neurotopographic distinctions support the claims of the computational distinctiveness of long-term vs. working memory operations. The specific lesion loci raise a number of questions to be discussed regarding: (a the selectivity of these regions and associated deficits to orthographic working memory vs. working memory more generally (b the possibility that different lesion sub-regions may correspond to different components of the OWM system.
Neural second-level trigger system based on calorimetry
Seixas, J. M.; Caloba, L. P.; Souza, M. N.; Braga, A. L.; Rodrigues, A. P.
1996-06-01
A second-level triggering system based on calorimetry is analyzed using neural networks. Calorimeter data in a LHC environment is obtained with Monte Carlo simulations and an algorithm for the first-level trigger operation is applied. The surviving events are then available as a 20×20 matrix information corresponding to the calorimeter towers in the region of interest. The dominant background for triggering on electrons is assumed to consist of QCD jets which passed the first-level trigger condition. The main features of the calorimeter are extracted. Matrix information, shower deposition in concentric rings and tail weighting procedures are studied. The processed information is sent to a fully connected backpropagation neural network. In this analysis we also consider pileup effects of an average of 20 minimum bias events. The neural network based system achieved up to 99% electron efficiency with less than 9% of jets being misclassified as electrons. Implementation on digital signal processors is suggested.
Blur identification by multilayer neural network based on multivalued neurons.
Aizenberg, Igor; Paliy, Dmitriy V; Zurada, Jacek M; Astola, Jaakko T
2008-05-01
A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of specific different features. Its backpropagation learning algorithm is derivative-free. The functionality of MLMVN is superior to that of the traditional feedforward neural networks and of a variety kernel-based networks. Its higher flexibility and faster adaptation to the target mapping enables to model complex problems using simpler networks. In this paper, the MLMVN is used to identify both type and parameters of the point spread function, whose precise identification is of crucial importance for the image deblurring. The simulation results show the high efficiency of the proposed approach. It is confirmed that the MLMVN is a powerful tool for solving classification problems, especially multiclass ones. PMID:18467216
From neural-based object recognition toward microelectronic eyes
Sheu, Bing J.; Bang, Sa Hyun
1994-01-01
Engineering neural network systems are best known for their abilities to adapt to the changing characteristics of the surrounding environment by adjusting system parameter values during the learning process. Rapid advances in analog current-mode design techniques have made possible the implementation of major neural network functions in custom VLSI chips. An electrically programmable analog synapse cell with large dynamic range can be realized in a compact silicon area. New designs of the synapse cells, neurons, and analog processor are presented. A synapse cell based on Gilbert multiplier structure can perform the linear multiplication for back-propagation networks. A double differential-pair synapse cell can perform the Gaussian function for radial-basis network. The synapse cells can be biased in the strong inversion region for high-speed operation or biased in the subthreshold region for low-power operation. The voltage gain of the sigmoid-function neurons is externally adjustable which greatly facilitates the search of optimal solutions in certain networks. Various building blocks can be intelligently connected to form useful industrial applications. Efficient data communication is a key system-level design issue for large-scale networks. We also present analog neural processors based on perceptron architecture and Hopfield network for communication applications. Biologically inspired neural networks have played an important role towards the creation of powerful intelligent machines. Accuracy, limitations, and prospects of analog current-mode design of the biologically inspired vision processing chips and cellular neural network chips are key design issues.
Data Process of Diagnose Expert System based on Neural Network
Shupeng Zhao
2013-12-01
Full Text Available Engine fault has a high rate in the car. Considering about the distinguishing feature of the engine, Engine Diagnosis Expert System was investigated based on Diagnosis Tree module, Fuzzy Neural Network module, and commix reasoning module. It was researched including Knowledge base and Reasoning machine, and so on. In Diagnosis Tree module, the origin problem was searched in right method. In which module distinguishing rate and low error and least cost was the aim. By means of synthesize judge and fuzzy relation reasoning to get fault origin from symptom, fuzzy synthesize reasoning diagnosis module was researched. Expert knowledge included failure symptom, engine system failure and engine part failure. In the system, Self-diagnosis method and general instruments method worked together, complex failure diagnosis became efficient. The system was intelligent, which was combined by fuzzy logic reasoning and the traditional neural network system. And it became more convenience for failure origin searching, because of utilizing the three methods. The system fuzzy neural networks were combined with fuzzy reasoning and traditional neural networks. Fuzzy neural network failure diagnosis module of system, as a important model was applied to engine diagnosis, with more advantages such as higher efficiency of searching and higher self-learning ability, which was compared with the traditional BP network
Neural Cell Chip Based Electrochemical Detection of Nanotoxicity
Md. Abdul Kafi
2015-07-01
Full Text Available Development of a rapid, sensitive and cost-effective method for toxicity assessment of commonly used nanoparticles is urgently needed for the sustainable development of nanotechnology. A neural cell with high sensitivity and conductivity has become a potential candidate for a cell chip to investigate toxicity of environmental influences. A neural cell immobilized on a conductive surface has become a potential tool for the assessment of nanotoxicity based on electrochemical methods. The effective electrochemical monitoring largely depends on the adequate attachment of a neural cell on the chip surfaces. Recently, establishment of integrin receptor specific ligand molecules arginine-glycine-aspartic acid (RGD or its several modifications RGD-Multi Armed Peptide terminated with cysteine (RGD-MAP-C, C(RGD4 ensure farm attachment of neural cell on the electrode surfaces either in their two dimensional (dot or three dimensional (rod or pillar like nano-scale arrangement. A three dimensional RGD modified electrode surface has been proven to be more suitable for cell adhesion, proliferation, differentiation as well as electrochemical measurement. This review discusses fabrication as well as electrochemical measurements of neural cell chip with particular emphasis on their use for nanotoxicity assessments sequentially since inception to date. Successful monitoring of quantum dot (QD, graphene oxide (GO and cosmetic compound toxicity using the newly developed neural cell chip were discussed here as a case study. This review recommended that a neural cell chip established on a nanostructured ligand modified conductive surface can be a potential tool for the toxicity assessments of newly developed nanomaterials prior to their use on biology or biomedical technologies.
Super congruences and Euler numbers
Sun, Zhi-Wei
2010-01-01
Let $p>3$ be a prime. We prove that $$\\sum_{k=0}^{p-1}\\binom{2k}{k}/2^k=(-1)^{(p-1)/2}-p^2E_{p-3} (mod p^3),$$ $$\\sum_{k=1}^{(p-1)/2}\\binom{2k}{k}/k=(-1)^{(p+1)/2}8/3*pE_{p-3} (mod p^2),$$ $$\\sum_{k=0}^{(p-1)/2}\\binom{2k}{k}^2/16^k=(-1)^{(p-1)/2}+p^2E_{p-3} (mod p^3)$$, where E_0,E_1,E_2,... are Euler numbers. Our new approach is of combinatorial nature. We also formulate many conjectures concerning super congruences and relate most of them to Euler numbers or Bernoulli numbers. Motivated by ...
Neural Network-Based Active Control for Offshore Platforms
周亚军; 赵德有
2003-01-01
A new active control scheme, based on neural network, for the suppression of oscillation in multiple-degree-of-freedom (MDOF) offshore platforms, is studied in this paper. With the main advantages of neural network, i.e. the inherent robustness, fault tolerance, and generalized capability of its parallel massive interconnection structure, the active structural control of offshore platforms under random waves is accomplished by use of the BP neural network model. The neural network is trained offline with the data generated from numerical analysis, and it simulates the process of Classical Linear Quadratic Regular Control for the platform under random waves. After the learning phase, the trained network has learned about the nonlinear dynamic behavior of the active control system, and is capable of predicting the active control forces of the next time steps. The results obtained show that the active control is feasible and effective, and it finally overcomes time delay owing to the robustness, fault tolerance, and generalized capability of artificial neural network.
Neural-Based Models of Semiconductor Devices for SPICE Simulator
Hanene B. Hammouda
2008-01-01
Full Text Available The paper addresses a simple and fast new approach to implement Artificial Neural Networks (ANN models for the MOS transistor into SPICE. The proposed approach involves two steps, the modeling phase of the device by NN providing its input/output patterns, and the SPICE implementation process of the resulting model. Using the Taylor series expansion, a neural based small-signal model is derived. The reliability of our approach is validated through simulations of some circuits in DC and small-signal analyses.
Adaptive Synchronization of Memristor-based Chaotic Neural Systems
Xiaofang Hu
2014-11-01
Full Text Available Chaotic neural networks consisting of a great number of chaotic neurons are able to reproduce the rich dynamics observed in biological nervous systems. In recent years, the memristor has attracted much interest in the efficient implementation of artificial synapses and neurons. This work addresses adaptive synchronization of a class of memristor-based neural chaotic systems using a novel adaptive backstepping approach. A systematic design procedure is presented. Simulation results have demonstrated the effectiveness of the proposed adaptive synchronization method and its potential in practical application of memristive chaotic oscillators in secure communication.
Neural Network Model Based Cluster Head Selection for Power Control
Krishan Kumar
2011-01-01
Full Text Available Mobile ad-hoc network has challenge of the limited power to prolong the lifetime of the network, because power is a valuable resource in mobile ad-hoc network. The status of power consumption should be continuously monitored after network deployment. In this paper, we propose coverage aware neural network based power control routing with the objective of maximizing the network lifetime. Cluster head selection is proposed using adaptive learning in neural networks followed by coverage. The simulation results show that the proposed scheme can be used in wide area of applications in mobile ad-hoc network.
Control of Unknown Chaotic Systems Based on Neural Predictive Control
LIDong-Mei; WANGZheng-Ou
2003-01-01
We introduce the predictive control into the control of chaotic system and propose a neural network control algorithm based on predictive control. The proposed control system stabilizes the chaotic motion in an unknown chaotic system onto the desired target trajectory. The proposed algorithm is simple and its convergence speed is much higher than existing similar algorithms. The control system can control hyperchaos. We analyze the stability of the control system and prove the convergence property of the neural controller. The theoretic derivation and simulations demonstrate the effectiveness of the algorithm.
Control of Unknown Chaotic Systems Based on Neural Predictive Control
LI Dong-Mei; WANG Zheng-Ou
2003-01-01
We introduce the predictive control into the control of chaotic system and propose a neural networkcontrol algorithm based on predictive control. The proposed control system stabilizes the chaotic motion in an unknownchaotic system onto the desired target trajectory. The proposed algorithm is simple and its convergence speed is muchhigher than existing similar algorithms. The control system can control hyperchaos. We analyze the stability of thecontrol system and prove the convergence property of the neural controller. The theoretic derivation and simulationsdemonstrate the effectiveness of the algorithm.
Clustering in mobile ad hoc network based on neural network
CHEN Ai-bin; CAI Zi-xing; HU De-wen
2006-01-01
An on-demand distributed clustering algorithm based on neural network was proposed. The system parameters and the combined weight for each node were computed, and cluster-heads were chosen using the weighted clustering algorithm, then a training set was created and a neural network was trained. In this algorithm, several system parameters were taken into account, such as the ideal node-degree, the transmission power, the mobility and the battery power of the nodes. The algorithm can be used directly to test whether a node is a cluster-head or not. Moreover, the clusters recreation can be speeded up.
Electronic implementation of associative memory based on neural network models
Moopenn, A.; Lambe, John; Thakoor, A. P.
1987-01-01
An electronic embodiment of a neural network based associative memory in the form of a binary connection matrix is described. The nature of false memory errors, their effect on the information storage capacity of binary connection matrix memories, and a novel technique to eliminate such errors with the help of asymmetrical extra connections are discussed. The stability of the matrix memory system incorporating a unique local inhibition scheme is analyzed in terms of local minimization of an energy function. The memory's stability, dynamic behavior, and recall capability are investigated using a 32-'neuron' electronic neural network memory with a 1024-programmable binary connection matrix.
A Neural Network-based ARX Model of Virgo Noise
Barone, F.; Rosa, R; Eleuteri, A.; Garufi, F.; Milano, L; Tagliaferri, R.
1999-01-01
In this paper a Neural Network based approach is presented to identify the noise in the VIRGO context. VIRGO is an experiment to detect Gravitational Waves by means of a Laser Interferometer. Preliminary results appear to be very promising for data analysis of realistic Interferometer outputs.
On the Nature, Modeling, and Neural Bases of Social Ties
F.A.A.M. Winden, van (Frans); M. Stallen (Mirre); K.R. Ridderinkhof (Richard)
2008-01-01
textabstractThis paper addresses the nature, formalization, and neural bases of (affective) social ties and discusses the relevance of ties for health economics. A social tie is defined as an affective weight attached by an individual to the well-being of another individual (‘utility interdependence
A NEURAL NETWORK BASED IRIS RECOGNITION SYSTEM FOR PERSONAL IDENTIFICATION
Usham Dias
2010-10-01
Full Text Available This paper presents biometric personal identification based on iris recognition using artificial neural networks. Personal identification system consists of localization of the iris region, normalization, enhancement and then iris pattern recognition using neural network. In this paper, through results obtained, we have shown that a person’s left and right eye are unique. In this paper, we also show that the network is sensitive to the initial weights and that over-training gives bad results. We also propose a fast algorithm for the localization of the inner and outer boundaries of the iris region. Results of simulations illustrate the effectiveness of the neural system in personal identification. Finally a hardware iris recognition model is proposed and implementation aspects are discussed.
Dissipative-based adaptive neural control for nonlinear systems
Yugang NIU; Xingyu WANG; Junwei LU
2004-01-01
A dissipative-based adaptive neural control scheme was developed for a class of nonlinear uncertain systems with unknown nonlinearities that might not be linearly parameterized. The major advantage of the present work was to relax the requirement of matching condition, I.e., the unknown nonlinearities appear on the same equation as the control input in a state-space representation, which was required in most of the available neural network controllers. By synthesizing a state-feedback neural controller to nake the closed-loop system dissipative with respect to a quadratic supply rate, the developed control scheme guarantees that the L2-gain of controlled system was less than or equal to a prescribed level. And then, it is shown that the output tracking error is uniformly ultimate bounded. The design scheme is illustrated using a numerical simulation.
Numerical Analysis of Modeling Based on Improved Elman Neural Network
Shao Jie
2014-01-01
Full Text Available A modeling based on the improved Elman neural network (IENN is proposed to analyze the nonlinear circuits with the memory effect. The hidden layer neurons are activated by a group of Chebyshev orthogonal basis functions instead of sigmoid functions in this model. The error curves of the sum of squared error (SSE varying with the number of hidden neurons and the iteration step are studied to determine the number of the hidden layer neurons. Simulation results of the half-bridge class-D power amplifier (CDPA with two-tone signal and broadband signals as input have shown that the proposed behavioral modeling can reconstruct the system of CDPAs accurately and depict the memory effect of CDPAs well. Compared with Volterra-Laguerre (VL model, Chebyshev neural network (CNN model, and basic Elman neural network (BENN model, the proposed model has better performance.
Numerical analysis of modeling based on improved Elman neural network.
Jie, Shao; Li, Wang; WeiSong, Zhao; YaQin, Zhong; Malekian, Reza
2014-01-01
A modeling based on the improved Elman neural network (IENN) is proposed to analyze the nonlinear circuits with the memory effect. The hidden layer neurons are activated by a group of Chebyshev orthogonal basis functions instead of sigmoid functions in this model. The error curves of the sum of squared error (SSE) varying with the number of hidden neurons and the iteration step are studied to determine the number of the hidden layer neurons. Simulation results of the half-bridge class-D power amplifier (CDPA) with two-tone signal and broadband signals as input have shown that the proposed behavioral modeling can reconstruct the system of CDPAs accurately and depict the memory effect of CDPAs well. Compared with Volterra-Laguerre (VL) model, Chebyshev neural network (CNN) model, and basic Elman neural network (BENN) model, the proposed model has better performance. PMID:25054172
Hedgehog theory via Euler calculus
Martinez-Maure, Yves
2013-01-01
Hedgehogs are (possibly singular and self-intersecting) hypersurfaces that describe Minkowski di¤erences of convex bodies in R^(n+1). They are the natural geometrical objects when one seeks to extend parts of the Brunn-Minkowski theory to a vector space which contains convex bodies. There is a close relationship between Minkowski addition and convolution with respect to the Euler characteristic. In this paper, we extend it to hedgehogs with an analytic support function. In this context, resor...
Robust face recognition using posterior union model based neural networks
Lin, J.; J., Ming; Crookes, D.
2009-01-01
Face recognition with unknown, partial distortion and occlusion is a practical problem, and has a wide range of applications, including security and multimedia information retrieval. The authors present a new approach to face recognition subject to unknown, partial distortion and occlusion. The new approach is based on a probabilistic decision-based neural network, enhanced by a statistical method called the posterior union model (PUM). PUM is an approach for ignoring severely mismatched loca...
Quantum Neural Network Based Machine Translator for Hindi to English
Ravi Narayan; Singh, V.P.; Chakraverty, S.
2014-01-01
This paper presents the machine learning based machine translation system for Hindi to English, which learns the semantically correct corpus. The quantum neural based pattern recognizer is used to recognize and learn the pattern of corpus, using the information of part of speech of individual word in the corpus, like a human. The system performs the machine translation using its knowledge gained during the learning by inputting the pair of sentences of Devnagri-Hindi and English. To analyze t...
Image Restoration Technology Based on Discrete Neural network
Zhou Duoying
2015-01-01
With the development of computer science and technology, the development of artificial intelligence advances rapidly in the field of image restoration. Based on the MATLAB platform, this paper constructs a kind of image restoration technology of artificial intelligence based on the discrete neural network and feedforward network, and carries out simulation and contrast of the restoration process by the use of the bionic algorithm. Through the application of simulation restoration technology, ...
Data Process of Diagnose Expert System based on Neural Network
Shupeng Zhao; Miao Tian; Shifang Zhang; Jiuxi Li; Lijuan Du; Ye Wang
2013-01-01
Engine fault has a high rate in the car. Considering about the distinguishing feature of the engine, Engine Diagnosis Expert System was investigated based on Diagnosis Tree module, Fuzzy Neural Network module, and commix reasoning module. It was researched including Knowledge base and Reasoning machine, and so on. In Diagnosis Tree module, the origin problem was searched in right method. In which module distinguishing rate and low error and least cost was the aim. By means of synthesize judge...
Boyd, John P
2010-01-01
When a function $f(x)$ is singular at a point $x_{s}$ on the real axis, its Fourier series, when truncated at the $N$-th term, gives a pointwise error of only $O(1/N)$ over the entire real axis. Such singularities spontaneously arise as "fronts" in meteorology and oceanography and "shocks" in other branches of fluid mechanics. It has been previously shown that it is possible to recover an exponential rate of convegence at all points away from the singularity in the sense that $|f(x) - f_{N}^{\\sigma}(x) | \\sim O(\\exp(- q(x) N))$ where $f_{N}^{\\sigma}(x)$ is the result of applying a filter or summability method to the partial sum $f_{N}(x)$ and $q(x)$ is a proportionality constant that is a function of $d(x) \\equiv |x-x_{s}|$, the distance from $x$ to the singularity. Here we give an elementary proof of great generality using conformal mapping in a dummy variable $z$; this is equivalent to applying the Euler acceleration. We show that $q(x) \\approx \\log(\\cos(d(x)/2))$ for the Euler filter when the Fourier perio...
Neural Network Predictive Control Based Power System Stabilizer
Ali Mohamed Yousef
2012-04-01
Full Text Available The present study investigates the power system stabilizer based on neural predictive control for improving power system dynamic performance over a wide range of operating conditions. In this study a design and application of the Neural Network Model Predictive Controller (NN-MPC on a simple power system composed of a synchronous generator connected to an infinite bus through a transmission line is proposed. The synchronous machine is represented in detail, taking into account the effect of the machine saliency and the damper winding. Neural network model predictive control combines reliable prediction of neural network model with excellent performance of model predictive control using nonlinear Levenberg-Marquardt optimization. This control system is used the rotor speed deviation as a feedback signal. Furthermore, the using performance system of the proposed controller is compared with the system performance using conventional one (PID controller through simulation studies. Digital simulation has been carried out in order to validate the effectiveness proposed NN-MPC power system stabilizer for achieving excellent performance. The results demonstrate that the effectiveness and superiority of the proposed controller in terms of fast response and small settling time.
Hand Gesture and Neural Network Based Human Computer Interface
Aekta Patel
2014-06-01
Full Text Available Computer is used by every people either at their work or at home. Our aim is to make computers that can understand human language and can develop a user friendly human computer interfaces (HCI. Human gestures are perceived by vision. The research is for determining human gestures to create an HCI. Coding of these gestures into machine language demands a complex programming algorithm. In this project, We have first detected, recognized and pre-processing the hand gestures by using General Method of recognition. Then We have found the recognized image’s properties and using this, mouse movement, click and VLC Media player controlling are done. After that we have done all these functions thing using neural network technique and compared with General recognition method. From this we can conclude that neural network technique is better than General Method of recognition. In this, I have shown the results based on neural network technique and comparison between neural network method & general method.
Rule extraction based on neural networks for satellite image interpretation
Mascarilla, Laurent
1994-12-01
In the frame of an image interpretation system for automatic cartography based on remote sensing image classification improved by a photo interpreter knowledge, we propose a system using neural networks to produce fuzzy production rules. These rules are intended to describe class vegetation context relatively to out image data (generally a G.I.S.) as a human expert could do. In the system, the expert only gives samples of concerned classes via a G.U.I. (Graphic User Interface) connected to a G.I.S. In a first stage, a Kohonen neural network is used to found clusters and membership functions, and then to compute a first set of fuzzy 'IF-THEN' rules with certainty factors. The human expert then updates these rules, and the given samples, according to his own experience. Once satisfying and discriminating classification rules are found, a second kind of neural network using back propagation is used to tune the final set of rules. At the same time, it produces neural nets able to give for each pixel and each class, the realisation degree of the favourable context relatively to the knowledge inferred by the samples.
Euler Sums of Hyperharmonic Numbers
Dil, Ayhan; Khristo N. Boyadzhiev
2012-01-01
The hyperharmonic numbers h_{n}^{(r)} are defined by means of the classical harmonic numbers. We show that the Euler-type sums with hyperharmonic numbers: {\\sigma}(r,m)=\\sum_{n=1}^{\\infty}((h_{n}^{(r)})/(n^{m})) can be expressed in terms of series of Hurwitz zeta function values. This is a generalization of a result of Mez\\H{o} and Dil. We also provide an explicit evaluation of {\\sigma}(r,m) in a closed form in terms of zeta values and Stirling numbers of the first kind. Furthermore, we evalu...
Neural Bases of Recovery after Brain Injury
Nudo, Randolph J.
2011-01-01
Substantial data have accumulated over the past decade indicating that the adult brain is capable of substantial structural and functional reorganization after stroke. While some limited recovery is known to occur spontaneously, especially within the first month post-stroke, there is currently significant optimism that new interventions based on…
Neural bases for anticipation skill in soccer: an FMRI study.
Bishop, Daniel T; Wright, Michael J; Jackson, Robin C; Abernethy, Bruce
2013-02-01
The aim of this study was to examine the neural bases for perceptual-cognitive superiority in a soccer anticipation task using functional magnetic resonance imaging (fMRI). Thirty-nine participants lay in an MRI scanner while performing a video-based task in which they predicted an oncoming opponent's movements. Video clips were occluded at four time points, and participants were grouped according to in-task performance. Early occlusion reduced prediction accuracy significantly for all participants, as did the opponent's execution of a deceptive maneuver; however, high-skill participants were significantly more accurate than their low-skill counterparts under deceptive conditions. This perceptual-cognitive superiority was associated with greater activation of cortical and subcortical structures involved in executive function and oculomotor control. The contributions of the present findings to an existing neural model of anticipation in sport are highlighted. PMID:23404883
Artificial Neural Network Based Approach for short load forecasting
Mr. Rajesh Deshmukh
2011-12-01
Full Text Available Accurate models for electric power load forecasting are essential to the operation and planning of a power utility company. Load forecasting helps electric utility to make important decisions on trading of power, load switching, and infrastructure development. Load forecasts are extremely important for power utilizes ISOs, financial institutions, and other stakeholder of power sector. Short term load forecasting is a essential part of electric power system planning and operation forecasting made for unit commitment and security assessment, which have a direct impact on operational casts and system security. Conventional ANN based load forecasting method deal with 24 hour ahead load forecasting by using forecasted temp. This can lead to high forecasting errors in case of rapid temperature changes. This paper present a neural network based approach for short term load forecasting considering data for training, validation and testing of neural network.
Composite Taste Recognition Method Based on Fuzzy Neural Network
Yu Zhang
2013-09-01
Full Text Available In order to make recognition for the composite taste, the paper puts forward the research on the composite taste recognition method based on fuzzy neural network based on the wavelet transform. According to the wavelet transformation and the compression and extraction of the data of the taste signals that are collected by the sensor, we use the fuzzy neutral network as the recognition tool of the taste signal. Besides, we add genetic algorithm to make the function optimization for the network weights and the data processing and fuzzy recognition of the composite taste signal are presented. Finally, we make the test for the network performance. The results show that it has feasibility and effectiveness that the fuzzy neural network is introduced into the fuzzy identification of the taste signals.
Artificial Neural Network Based State Estimators Integrated into Kalmtool
Bayramoglu, Enis; Ravn, Ole; Poulsen, Niels Kjølstad
2012-01-01
In this paper we present a toolbox enabling easy evaluation and comparison of dierent ltering algorithms. The toolbox is called Kalmtool and is a set of MATLAB tools for state estimation of nonlinear systems. The toolbox now contains functions for Articial Neural Network Based State Estimation as...... well as for DD1 lter and the DD2 lter, as well as functions for Unscented Kalman lters and several versions of particle lters. The toolbox requires MATLAB version 7, but no additional toolboxes are required.......In this paper we present a toolbox enabling easy evaluation and comparison of dierent ltering algorithms. The toolbox is called Kalmtool and is a set of MATLAB tools for state estimation of nonlinear systems. The toolbox now contains functions for Articial Neural Network Based State Estimation as...
ADAPTATIVE IMAGE WATERMARKING SCHEME BASED ON NEURAL NETWORK
BASSEL SOLAIMANE
2011-01-01
Full Text Available Digital image watermarking has been proposed as a method to enhance medical data security, confidentiality and integrity. Medical image watermarking requires extreme care when embedding additional data, given their importance to clinical diagnosis, treatment, and research. In this paper, a novel image watermarking approach based on the human visual system (HVS model and neural network technique is proposed. The watermark was inserted into the middle frequency coefficients of the cover image’s blocked DCT based transform domain. In order to make the watermark stronger and less susceptible to different types of attacks, it is essential to find the maximum amount of interested watermark before the watermark becomes visible. In this paper, neural networks are used to implement an automated system of creating maximum-strength watermarks. The experimental results show that such method can survive of common image processing operations and has good adaptability for automated watermark embedding.
Image Compression of Neural Network Based on Corner Block
Wenjing Zhang
2014-01-01
Full Text Available Most information received by the human is acquired through vision. However, image has the largest data amount in three information forms. If the image is not compressed, high transmission rate for digital image transmission and tremendous capacity for digital image storage can hinder the development of digital image. For example, for a color image whose resolution rate is 1280×1024, each pixel needs 24B for storage, and the total data amount is about 3.75MB. If the earth satellite transmits the acquired image to the earth at 30 frames per second, the transmitting data size in 1 second is about 112.5MB. Under the condition of the existing communication capacity, if the image is not compressed, the real-time transmission of most multimedia information can’t be completed. High-speed transmission and storage of digital image has become the biggest obstacle of promoting digital image communication. So it is necessary to compress image. Data compression not only can rapidly transmit various information sources, improve the utilization rage of information channel and reduce transmitted power, but also can save energy and reduce storage capacity. More and more attentions of people have been paid to the application of artificial neural network to image compression, the reason for which is that artificial neural network has good fault tolerance, self-organization and adaptivity compared with traditional compression methods. So the predetermined data coding algorithm is not needed in the process of image compression. Neural network can independently complete the image coding and compression according to the characteristics of image. The paper combines corner detection technology with artificial neural network image compression, and designs a new neural network image compression encoding based on corner block with reasonable structure, high compression rate and rapid convergence rate
Research on Transformer Fault Based on Probabilistic Neural Network
Li Yingshun; Li Jingjing; Han Junfeng
2015-01-01
With the development of computer science and technology, and increasingly intelligent industrial production, the application of big data in industry also advances rapidly, and the development of artificial intelligence in the aspect of fault diagnosis is particularly prominent. On the basis of MATLAB platform, this paper constructs a fault diagnosis expert system of artificial intelligence machine based on the probabilistic neural network, and it also carries out a simulation of production pr...
ADAPTATIVE IMAGE WATERMARKING SCHEME BASED ON NEURAL NETWORK
BASSEL SOLAIMANE; ADNENE CHERIF; SAMEH OUESLATI,
2011-01-01
Digital image watermarking has been proposed as a method to enhance medical data security, confidentiality and integrity. Medical image watermarking requires extreme care when embedding additional data, given their importance to clinical diagnosis, treatment, and research. In this paper, a novel image watermarking approach based on the human visual system (HVS) model and neural network technique is proposed. The watermark was inserted into the middle frequency coefficients of the cover image’...
Consensus Attention-based Neural Networks for Chinese Reading Comprehension
Cui, Yiming; Liu, Ting; Chen, Zhipeng; Wang, Shijin; Hu, Guoping
2016-01-01
Reading comprehension has embraced a booming in recent NLP research. Several institutes have released the Cloze-style reading comprehension data, and these have greatly accelerated the research of machine comprehension. In this work, we firstly present Chinese reading comprehension datasets, which consist of People Daily news dataset and Children's Fairy Tale (CFT) dataset. Also, we propose a consensus attention-based neural network architecture to tackle the Cloze-style reading comprehension...
Fuzzy neural network image filter based on GA
刘涵; 刘丁; 李琦
2004-01-01
A new nonlinear image filter using fuzzy neural network based on genetic algorithm is proposed. The learning of network parameters is performed by genetic algorithm with the efficient binary encoding scheme. In the following,fuzzy reasoning embedded in the network aims at restoring noisy pixels without degrading the quality of fine details. It is shown by experiments that the filter is very effective in removing impulse noise and significantly outperforms conventional filters.
Cryptography based on neural networks - analytical results
The mutual learning process between two parity feed-forward networks with discrete and continuous weights is studied analytically, and we find that the number of steps required to achieve full synchronization between the two networks in the case of discrete weights is finite. The synchronization process is shown to be non-self-averaging and the analytical solution is based on random auxiliary variables. The learning time of an attacker that is trying to imitate one of the networks is examined analytically and is found to be much longer than the synchronization time. Analytical results are found to be in agreement with simulations. (letter to the editor)
Data systems and computer science: Neural networks base R/T program overview
Gulati, Sandeep
1991-01-01
The research base, in the U.S. and abroad, for the development of neural network technology is discussed. The technical objectives are to develop and demonstrate adaptive, neural information processing concepts. The leveraging of external funding is also discussed.
Euler's Identity, Leibniz Tables, and the Irrationality of Pi
Jones, Timothy W.
2012-01-01
Using techniques that show that e and pi are transcendental, we give a short, elementary proof that pi is irrational based on Euler's identity. The proof involves evaluations of a polynomial using repeated applications of Leibniz formula as organized in a Leibniz table.
A study of task-based strategies for adaptively constructive neural networks
The authors investigated the strategies for optimizing neural networks under the unified frame based on task, focused for constructive neural networks on two typical and practical schemes, which are adaptively constructive neural networks by growing hidden or layers of hidden nodes and by growing sub net. With the Layer Multinet Model proposed by the research group, the authors investigated task-based algorithms for constructive neural networks, their perspective, strength and weakness
Feature Selection for Neural Network Based Stock Prediction
Sugunnasil, Prompong; Somhom, Samerkae
We propose a new methodology of feature selection for stock movement prediction. The methodology is based upon finding those features which minimize the correlation relation function. We first produce all the combination of feature and evaluate each of them by using our evaluate function. We search through the generated set with hill climbing approach. The self-organizing map based stock prediction model is utilized as the prediction method. We conduct the experiment on data sets of the Microsoft Corporation, General Electric Co. and Ford Motor Co. The results show that our feature selection method can improve the efficiency of the neural network based stock prediction.
Neural Net Gains Estimation Based on an Equivalent Model
Aguilar Cruz, Karen Alicia; Medel Juárez, José de Jesús; Fernández Muñoz, José Luis; Esmeralda Vigueras Velázquez, Midory
2016-01-01
A model of an Equivalent Artificial Neural Net (EANN) describes the gains set, viewed as parameters in a layer, and this consideration is a reproducible process, applicable to a neuron in a neural net (NN). The EANN helps to estimate the NN gains or parameters, so we propose two methods to determine them. The first considers a fuzzy inference combined with the traditional Kalman filter, obtaining the equivalent model and estimating in a fuzzy sense the gains matrix A and the proper gain K into the traditional filter identification. The second develops a direct estimation in state space, describing an EANN using the expected value and the recursive description of the gains estimation. Finally, a comparison of both descriptions is performed; highlighting the analytical method describes the neural net coefficients in a direct form, whereas the other technique requires selecting into the Knowledge Base (KB) the factors based on the functional error and the reference signal built with the past information of the system. PMID:27366146
Spacecraft power system controller based on neural network
El-madany, Hanaa T.; Fahmy, Faten H.; El-Rahman, Ninet M. A.; Dorrah, Hassen T.
2011-09-01
Neural control is a branch of the general field of intelligent control, which is based on the concept of artificial intelligence. This work presents the spacecraft orbit determination, dimensioning of the renewable power system, and mathematical modeling of spacecraft power system which are required for simulating the system. The complete system is simulated using MATLAB-SIMULINK. The NN controller outperform PID in the extreme range of non-linearity. Well trained neural controller can operate at different conditions of load current at different orbital periods without any tuning such in case of PID controller. So an artificial neural network (ANN) based model has been developed for the optimum operation of spacecraft power system. An ANN is trained using a back propagation with Levenberg-Marquardt algorithm. The best validation performance is obtained for mean square error is equal to 9.9962×10 -11 at epoch 637. The regression between the network output and the corresponding target is equal to 100% which means a high accuracy. NNC architecture gives satisfactory results with small number of neurons, hence better in terms of memory and time are required for NNC implementation. The results indicate that the proposed control unit using ANN can be successfully used for controlling the spacecraft power system in low earth orbit (LEO). Therefore, this technique is going to be a very useful tool for the interested designers in space field.
Research on Transformer Fault Based on Probabilistic Neural Network
Li Yingshun
2015-01-01
Full Text Available With the development of computer science and technology, and increasingly intelligent industrial production, the application of big data in industry also advances rapidly, and the development of artificial intelligence in the aspect of fault diagnosis is particularly prominent. On the basis of MATLAB platform, this paper constructs a fault diagnosis expert system of artificial intelligence machine based on the probabilistic neural network, and it also carries out a simulation of production process by the use of bionic algorithm. This paper makes a diagnosis of transformer fault by the use of an expert system developed by this paper, and verifies that the probabilistic neural network has a good convergence, fault-tolerant ability and big data handling capability in the fault diagnosis. It is suitable for industrial production, which can provide a reliable mathematical model for the construction of fault diagnosis expert system in the industrial production.
Neural cell image segmentation method based on support vector machine
Niu, Shiwei; Ren, Kan
2015-10-01
In the analysis of neural cell images gained by optical microscope, accurate and rapid segmentation is the foundation of nerve cell detection system. In this paper, a modified image segmentation method based on Support Vector Machine (SVM) is proposed to reduce the adverse impact caused by low contrast ratio between objects and background, adherent and clustered cells' interference etc. Firstly, Morphological Filtering and OTSU Method are applied to preprocess images for extracting the neural cells roughly. Secondly, the Stellate Vector, Circularity and Histogram of Oriented Gradient (HOG) features are computed to train SVM model. Finally, the incremental learning SVM classifier is used to classify the preprocessed images, and the initial recognition areas identified by the SVM classifier are added to the library as the positive samples for training SVM model. Experiment results show that the proposed algorithm can achieve much better segmented results than the classic segmentation algorithms.
Artificial Neural Network Based Control Strategies for Paddy Drying Process
Shekhar F. Lilhare
2014-10-01
Full Text Available Paddy drying process depends upon ambient conditions, paddy quality, temperature and mass of hot drying air. Existing techniques of paddy drying process are highly nonlinear. In this paper, a neural network based automated controller for paddy drying is designed. The designed controller manages the steam temperature and blower motor speed to achieve constant paddy drying time. A Layer recurrent neural network is adopted for the controller. Atmospheric conditions such as temperature and humidity along with the size of the paddy are used as input to the network. Experimental results show that the developed controller can be used to control the paddy drying process. Implementation of developed controller will help in controlling the drying time at almost constant value which will definitely improve the quality of rice.
Distribution network planning algorithm based on Hopfield neural network
GAO Wei-xin; LUO Xian-jue
2005-01-01
This paper presents a new algorithm based on Hopfield neural network to find the optimal solution for an electric distribution network. This algorithm transforms the distribution power network-planning problem into a directed graph-planning problem. The Hopfield neural network is designed to decide the in-degree of each node and is in combined application with an energy function. The new algorithm doesn't need to code city streets and normalize data, so the program is easier to be realized. A case study applying the method to a district of 29 street proved that an optimal solution for the planning of such a power system could be obtained by only 26 iterations. The energy function and algorithm developed in this work have the following advantages over many existing algorithms for electric distribution network planning: fast convergence and unnecessary to code all possible lines.
Automated neural network-based instrument validation system
Xu, Xiao
2000-10-01
In a complex control process, instrument calibration is periodically performed to maintain the instruments within the calibration range, which assures proper control and minimizes down time. Instruments are usually calibrated under out-of-service conditions using manual calibration methods, which may cause incorrect calibration or equipment damage. Continuous in-service calibration monitoring of sensors and instruments will reduce unnecessary instrument calibrations, give operators more confidence in instrument measurements, increase plant efficiency or product quality, and minimize the possibility of equipment damage during unnecessary manual calibrations. In this dissertation, an artificial neural network (ANN)-based instrument calibration verification system is designed to achieve the on-line monitoring and verification goal for scheduling maintenance. Since an ANN is a data-driven model, it can learn the relationships among signals without prior knowledge of the physical model or process, which is usually difficult to establish for the complex non-linear systems. Furthermore, the ANNs provide a noise-reduced estimate of the signal measurement. More importantly, since a neural network learns the relationships among signals, it can give an unfaulted estimate of a faulty signal based on information provided by other unfaulted signals; that is, provide a correct estimate of a faulty signal. This ANN-based instrument verification system is capable of detecting small degradations or drifts occurring in instrumentation, and preclude false control actions or system damage caused by instrument degradation. In this dissertation, an automated scheme of neural network construction is developed. Previously, the neural network structure design required extensive knowledge of neural networks. An automated design methodology was developed so that a network structure can be created without expert interaction. This validation system was designed to monitor process sensors plant
Euler and His Contribution Number Theory
Len, Amy; Scott, Paul
2004-01-01
Born in 1707, Leonhard Euler was the son of a Protestant minister from the vicinity of Basel, Switzerland. With the aim of pursuing a career in theology, Euler entered the University of Basel at the age of thirteen, where he was tutored in mathematics by Johann Bernoulli (of the famous Bernoulli family of mathematicians). He developed an interest…
Embedding Task-Based Neural Models into a Connectome-Based Model of the Cerebral Cortex
Ulloa, Antonio; Horwitz, Barry
2016-01-01
A number of recent efforts have used large-scale, biologically realistic, neural models to help understand the neural basis for the patterns of activity observed in both resting state and task-related functional neural imaging data. An example of the former is The Virtual Brain (TVB) software platform, which allows one to apply large-scale neural modeling in a whole brain framework. TVB provides a set of structural connectomes of the human cerebral cortex, a collection of neural processing units for each connectome node, and various forward models that can convert simulated neural activity into a variety of functional brain imaging signals. In this paper, we demonstrate how to embed a previously or newly constructed task-based large-scale neural model into the TVB platform. We tested our method on a previously constructed large-scale neural model (LSNM) of visual object processing that consisted of interconnected neural populations that represent, primary and secondary visual, inferotemporal, and prefrontal cortex. Some neural elements in the original model were “non-task-specific” (NS) neurons that served as noise generators to “task-specific” neurons that processed shapes during a delayed match-to-sample (DMS) task. We replaced the NS neurons with an anatomical TVB connectome model of the cerebral cortex comprising 998 regions of interest interconnected by white matter fiber tract weights. We embedded our LSNM of visual object processing into corresponding nodes within the TVB connectome. Reciprocal connections between TVB nodes and our task-based modules were included in this framework. We ran visual object processing simulations and showed that the TVB simulator successfully replaced the noise generation originally provided by NS neurons; i.e., the DMS tasks performed with the hybrid LSNM/TVB simulator generated equivalent neural and fMRI activity to that of the original task-based models. Additionally, we found partial agreement between the functional
Embedding Task-Based Neural Models into a Connectome-Based Model of the Cerebral Cortex.
Ulloa, Antonio; Horwitz, Barry
2016-01-01
A number of recent efforts have used large-scale, biologically realistic, neural models to help understand the neural basis for the patterns of activity observed in both resting state and task-related functional neural imaging data. An example of the former is The Virtual Brain (TVB) software platform, which allows one to apply large-scale neural modeling in a whole brain framework. TVB provides a set of structural connectomes of the human cerebral cortex, a collection of neural processing units for each connectome node, and various forward models that can convert simulated neural activity into a variety of functional brain imaging signals. In this paper, we demonstrate how to embed a previously or newly constructed task-based large-scale neural model into the TVB platform. We tested our method on a previously constructed large-scale neural model (LSNM) of visual object processing that consisted of interconnected neural populations that represent, primary and secondary visual, inferotemporal, and prefrontal cortex. Some neural elements in the original model were "non-task-specific" (NS) neurons that served as noise generators to "task-specific" neurons that processed shapes during a delayed match-to-sample (DMS) task. We replaced the NS neurons with an anatomical TVB connectome model of the cerebral cortex comprising 998 regions of interest interconnected by white matter fiber tract weights. We embedded our LSNM of visual object processing into corresponding nodes within the TVB connectome. Reciprocal connections between TVB nodes and our task-based modules were included in this framework. We ran visual object processing simulations and showed that the TVB simulator successfully replaced the noise generation originally provided by NS neurons; i.e., the DMS tasks performed with the hybrid LSNM/TVB simulator generated equivalent neural and fMRI activity to that of the original task-based models. Additionally, we found partial agreement between the functional
Nanotechnology-Based Approaches for Guiding Neural Regeneration.
Shah, Shreyas; Solanki, Aniruddh; Lee, Ki-Bum
2016-01-19
The mammalian brain is a phenomenal piece of "organic machinery" that has fascinated scientists and clinicians for centuries. The intricate network of tens of billions of neurons dispersed in a mixture of chemical and biochemical constituents gives rise to thoughts, feelings, memories, and life as we know it. In turn, subtle imbalances or damage to this system can cause severe complications in physical, motor, psychological, and cognitive function. Moreover, the inevitable loss of nerve tissue caused by degenerative diseases and traumatic injuries is particularly devastating because of the limited regenerative capabilities of the central nervous system (i.e., the brain and spinal cord). Among current approaches, stem-cell-based regenerative medicine has shown the greatest promise toward repairing and regenerating destroyed neural tissue. However, establishing controlled and reliable methodologies to guide stem cell differentiation into specialized neural cells of interest (e.g., neurons and oligodendrocytes) has been a prevailing challenge in the field. In this Account, we summarize the nanotechnology-based approaches our group has recently developed to guide stem-cell-based neural regeneration. We focus on three overarching strategies that were adopted to selectively control this process. First, soluble microenvironmental factors play a critical role in directing the fate of stem cells. Multiple factors have been developed in the form of small-molecule drugs, biochemical analogues, and DNA/RNA-based vectors to direct neural differentiation. However, the delivery of these factors with high transfection efficiency and minimal cytotoxicity has been challenging, especially to sensitive cell lines such as stem cells. In our first approach, we designed nanoparticle-based systems for the efficient delivery of such soluble factors to control neural differentiation. Our nanoparticles, comprising either organic or inorganic elements, were biocompatible and offered
Neural Network Based Popularity Prediction For IPTV System
Jun Li
2012-12-01
Full Text Available Internet protocol television (IPTV, being an emerging Internet application, plays an important and indispensable role in our daily life. In order to maximize user experience and on the same time to minimize service cost, we must take into pay attention to how to reduce the storage and transport costs. A lot of previous work has been done before to do this. There is a challenging problem in this: how to predict the popularities of videos as accurate as possible. To solve the problem, this paper presents a Neural Network model for the popularity prediction of the programs in the IPTV system. And we use the actual historical logs to validate our method. The historical logs are divided to two parts, one is used to train the neural network by extract input/output vectors, and the other part is used to verify the model. The experimental results from our validation show the Neural Network based method can gain better accuracy than the comparative method.
Entropy based comparison of neural networks for classification
Draghici, S. [Wayne State Univ., Detroit, MI (United States). Vision and Neural Networks Lab.; Beiu, V. [Los Alamos National Lab., NM (United States)
1997-04-01
In recent years, multilayer feedforward neural networks (NN) have been shown to be very effective tools in many different applications. A natural and essential step in continuing the diffusion of these tools in day by day use is their hardware implementation which is by far the most cost effective solution for large scale use. When the hardware implementation is contemplated, the issue of the size of the NN becomes crucial because the size is directly proportional with the cost of the implementation. In this light, any theoretical results which establish bounds on the size of a NN for a given problem is extremely important. In the same context, a particularly interesting case is that of the neural networks using limited integer weights. These networks are particularly suitable for hardware implementation because they need less space for storing the weights and the fixed point, limited precision arithmetic has much cheaper implementations in comparison with its floating point counterpart. This paper presents an entropy based analysis which completes, unifies and correlates results partially presented in [Beiu, 1996, 1997a] and [Draghici, 1997]. Tight bounds for real and integer weight neural networks are calculated.
Beam pattern evaluation for cyclotron operations based on neural networks
A beam pattern evaluation method using neural network has been developed to assist non-expert cyclotron operators. While an expert operator can easily tell beam accelerating conditions by the beam pattern measured by a scanned beam probe, it is not easy for non-expert operators to evaluate the pattern. The followings are the summarized procedure of the proposed method. First, the features of the beam patterns, which correspond to the view points of the experts, are extracted using Gabor expansion. A neural network algorithm is applied to calculate the Gabor expansion. Next, the number of the extracted features is reduced by averaging the features of high frequency ranges in five partial zones. The idea of this process is based on the fact that the operators do not pay attention to the details of the high frequency components of the patterns. Finally, the pattern evaluation process by the expert operators is learned by the back-propagation algorithm on a multi-layered feed forward neural network. Parallel processing architecture of the feature extraction network, and the learning capability of the non-linear clustering network are very useful for the evaluation model of beam patterns. (author)
Rainfall Prediction using Data-Core Based Fuzzy Min-Max Neural Network for Classification
Rajendra Palange,; Nishikant Pachpute
2015-01-01
This paper proposes the Rainfall Prediction System by using classification technique. The advanced and modified neural network called Data Core Based Fuzzy Min Max Neural Network (DCFMNN) is used for pattern classification. This classification method is applied to predict Rainfall. The neural network called fuzzy min max neural network (FMNN) that creates hyperboxes for classification and predication, has a problem of overlapping neurons that resoled in DCFMNN to give greater accu...
Stochastic Synchronization of Neutral-Type Neural Networks with Multidelays Based on M-Matrix
Wuneng Zhou; Xueqing Yang; Jun Yang; Jun Zhou
2015-01-01
The problem of stochastic synchronization of neutral-type neural networks with multidelays based on M-matrix is researched. Firstly, we designed a control law of stochastic synchronization of the neural-type and multiple time-delays neural network. Secondly, by making use of Lyapunov functional and M-matrix method, we obtained a criterion under which the drive and response neutral-type multiple time-delays neural networks with stochastic disturbance and Markovian switc...
Fuzzy Neural Network Based Traffic Prediction and Congestion Control in High-Speed Networks
费翔; 何小燕; 罗军舟; 吴介一; 顾冠群
2000-01-01
Congestion control is one of the key problems in high-speed networks, such as ATM. In this paper, a kind of traffic prediction and preventive congestion control scheme is proposed using neural network approach. Traditional predictor using BP neural network has suffered from long convergence time and dissatisfying error. Fuzzy neural network developed in this paper can solve these problems satisfactorily. Simulations show the comparison among no-feedback control scheme,reactive control scheme and neural network based control scheme.
A Neural Network Based Collision Detection Engine for Multi-Arm Robotic Systems
Rana, A. S.; Zalzala, A.M.S.
1996-01-01
A neural ntwork is proposed for collision detection among multiple robotic arms sharing a common workspace. The structure of the neural network is a hybrid between Guassian Radial Basis Function (RBF) neural networks and Multi-layer perceptron back-propagation (BP) neural networks. This network is used to generate potential fields in the configuration space of the robotic arms. A path planning algorithm based on heuristics is presented. It is shown that this algorithm works better than the c...
Convolutional Neural Network Based Fault Detection for Rotating Machinery
Janssens, Olivier; Slavkovikj, Viktor; Vervisch, Bram; Stockman, Kurt; Loccufier, Mia; Verstockt, Steven; Van de Walle, Rik; Van Hoecke, Sofie
2016-09-01
Vibration analysis is a well-established technique for condition monitoring of rotating machines as the vibration patterns differ depending on the fault or machine condition. Currently, mainly manually-engineered features, such as the ball pass frequencies of the raceway, RMS, kurtosis an crest, are used for automatic fault detection. Unfortunately, engineering and interpreting such features requires a significant level of human expertise. To enable non-experts in vibration analysis to perform condition monitoring, the overhead of feature engineering for specific faults needs to be reduced as much as possible. Therefore, in this article we propose a feature learning model for condition monitoring based on convolutional neural networks. The goal of this approach is to autonomously learn useful features for bearing fault detection from the data itself. Several types of bearing faults such as outer-raceway faults and lubrication degradation are considered, but also healthy bearings and rotor imbalance are included. For each condition, several bearings are tested to ensure generalization of the fault-detection system. Furthermore, the feature-learning based approach is compared to a feature-engineering based approach using the same data to objectively quantify their performance. The results indicate that the feature-learning system, based on convolutional neural networks, significantly outperforms the classical feature-engineering based approach which uses manually engineered features and a random forest classifier. The former achieves an accuracy of 93.61 percent and the latter an accuracy of 87.25 percent.
Content Based Image Retrieval : Classification Using Neural Networks
Shereena V.B
2014-11-01
Full Text Available In a content-based image retrieval system (CBIR, the main issue is to extract the image features that effectively represent the image contents in a database. Such an extraction requires a detailed evaluation of retrieval performance of image features. This paper presents a review of fundamental aspects of content based image retrieval including feature extraction of color and texture features. Commonly used color features including color moments, color histogram and color correlogram and Gabor texture are compared. The paper reviews the increase in efficiency of image retrieval when the color and texture features are combined. The similarity measures based on which matches are made and images are retrieved are also discussed. For effective indexing and fast searching of images based on visual features, neural network based pattern learning can be used to achieve effective classification.
Content Based Image Retrieval : Classification Using Neural Networks
Shereena V.B
2014-10-01
Full Text Available In a content-based image retrieval system (CBIR, the main issue is to extract the image features that effectively represent the image contents in a database. Such an extraction requires a detailed evaluation of retrieval performance of image features. This paper presents a review of fundamental aspects of content based image retrieval including feature extraction of color and texture features. Commonly used color features including color moments, color histogram and color correlogram and Gabor texture are compared. The paper reviews the increase in efficiency of image retrieval when the color and texture features are combined. The similarity measures based on which matches are made and images are retrieved are also discussed. For effective indexing and fast searching of images based on visual features, neural network based pattern learning can be used to achieve effective classification.
Neural Network Based Montioring and Control of Fluidized Bed.
Bodruzzaman, M.; Essawy, M.A.
1996-04-01
The goal of this project was to develop chaos analysis and neural network-based modeling techniques and apply them to the pressure-drop data obtained from the Fluid Bed Combustion (FBC) system (a small scale prototype model) located at the Federal Energy Technology Center (FETC)-Morgantown. The second goal was to develop neural network-based chaos control techniques and provide a suggestive prototype for possible real-time application to the FBC system. The experimental pressure data were collected from a cold FBC experimental set-up at the Morgantown Center. We have performed several analysis on these data in order to unveil their dynamical and chaotic characteristics. The phase-space attractors were constructed from the one dimensional time series data, using the time-delay embedding method, for both normal and abnormal conditions. Several identifying parameters were also computed from these attractors such as the correlation dimension, the Kolmogorov entropy, and the Lyapunov exponents. These chaotic attractor parameters can be used to discriminate between the normal and abnormal operating conditions of the FBC system. It was found that, the abnormal data has higher correlation dimension, larger Kolmogorov entropy and larger positive Lyapunov exponents as compared to the normal data. Chaotic system control using neural network based techniques were also investigated and compared to conventional chaotic system control techniques. Both types of chaotic system control techniques were applied to some typical chaotic systems such as the logistic, the Henon, and the Lorenz systems. A prototype model for real-time implementation of these techniques has been suggested to control the FBC system. These models can be implemented for real-time control in a next phase of the project after obtaining further measurements from the experimental model. After testing the control algorithms developed for the FBC model, the next step is to implement them on hardware and link them to
Neutron spectrometry and dosimetry based on a new approach called Genetic Artificial Neural Networks
Artificial Neural Networks and Genetic Algorithms are two relatively young research areas that were subject to a steadily growing interest during the past years. The structure of a neural network is a significant contributing factor to its performance and the structure is generally heuristically chosen. The use of evolutionary algorithms as search techniques has allowed different properties of neural networks to be evolved. This paper focuses on the intersection on neural networks and evolutionary computation, namely on how evolutionary algorithms can be used to assist neural network design and training, as a novel approach. In this research, a new evolvable artificial neural network modelling approach is presented, which utilizes an optimization process based on the combination of genetic algorithms and artificial neural networks, and is applied in the design of a neural network, oriented to solve the neutron spectrometry and simultaneous dosimetry problems, using only the count rates measured with a Bonner spheres spectrometer system as entrance data. (author)
ARTIFICIAL NEURAL NETWORKS BASED GEARS MATERIAL SELECTION HYBRID INTELLIGENT SYSTEM
X.C. Li; W.X. Zhu; G. Chen; D.S. Mei; J. Zhang; K.M. Chen
2003-01-01
An artificial neural networks(ANNs) based gear material selection hybrid intelligent system is established by analyzing the individual advantages and weakness of expert system (ES) and ANNs and the applications in material select of them. The system mainly consists of tow parts: ES and ANNs. By being trained with much data samples,the back propagation (BP) ANN gets the knowledge of gear materials selection, and is able to inference according to user input. The system realizes the complementing of ANNs and ES. Using this system, engineers without materials selection experience can conveniently deal with gear materials selection.
Star pattern recognition method based on neural network
LI Chunyan; LI Ke; ZHANG Longyun; JIN Shengzhen; ZU Jifeng
2003-01-01
Star sensor is an avionics instrument used to provide the absolute 3-axis attitude of a spacecraft by utilizing star observations. The key function is to recognize the observed stars by comparing them with the reference catalogue. Autonomous star pattern recognition requires that similar patterns can be distinguished from each other with a small training set. Therefore, a new method based on neural network technology is proposed and a recognition system containing parallel backpropagation (BP) multi-subnets is designed. The simulation results show that the method performs much better than traditional algorithms and the proposed system can achieve both higher recognition accuracy and faster recognition speed.
Pulse frequency classification based on BP neural network
WANG Rui; WANG Xu; YANG Dan; FU Rong
2006-01-01
In Traditional Chinese Medicine (TCM), it is an important parameter of the clinic disease diagnosis to analysis the pulse frequency. This article accords to pulse eight major essentials to identify pulse type of the pulse frequency classification based on back-propagation neural networks (BPNN). The pulse frequency classification includes slow pulse, moderate pulse, rapid pulse etc. By feature parameter of the pulse frequency analysis research and establish to identify system of pulse frequency features. The pulse signal from detecting system extracts period, frequency etc feature parameter to compare with standard feature value of pulse type. The result shows that identify-rate attains 92.5% above.
Numerical Analysis of Modeling Based on Improved Elman Neural Network
Shao Jie; Wang Li; Zhao WeiSong; Zhong YaQin; Reza Malekian
2014-01-01
A modeling based on the improved Elman neural network (IENN) is proposed to analyze the nonlinear circuits with the memory effect. The hidden layer neurons are activated by a group of Chebyshev orthogonal basis functions instead of sigmoid functions in this model. The error curves of the sum of squared error (SSE) varying with the number of hidden neurons and the iteration step are studied to determine the number of the hidden layer neurons. Simulation results of the half-bridge class-D power...
On units generated by Euler systems
Saikia, Anupam
2009-01-01
In the context of cyclotomic fields, it is still unknown whether there exist Euler systems other than the ones derived from cyclotomic units. Nevertheless, we first give an exposition on how norm-compatible units are generated by any Euler system, following work of Coates. Then we prove that the units obtained from Euler systems and the cyclotomic units generate the same $\\mathbb{Z}_{p}$-module for any odd prime $p$. The techniques adopted for the Iwasawa theoretic proof in latter part of this article originated in Rubin's work on main conjectures of Iwasawa theory.
Federico Lince Klinger
2008-06-01
Full Text Available Se aplicaron técnicas de señal analítica y deconvolución de Euler a valores de anomalías de Bouguer de la cuenca de Bermejo y de la sierra de Valle Fértil, en el sector occidental de las Sierras Pampeanas. A partir de las soluciones encontradas por estas técnicas, se han interpretado la ubicación y profundidad de las fuentes causantes de anomalías, las que se vinculan con las estructuras geológicas que involucran al basamento. Con el objeto de verificar los resultados obtenidos y de minimizar las ambigüedades de los métodos potenciales, se preparó un modelo gravimétrico directo basado en un modelo estructural del área. A la respuesta gravimétrica de este modelo directo se le aplicó la técnica de señal analítica 2D, encontrándose soluciones que son consistentes con la profundidad y geometría de las fuentes previamente interpretadas, corroborando los resultados obtenidos.These geophysical techniques were applied to the Bouguer anomalies in the Bermejo Basin and Valle Fértil range. The location and depth to source of the anomalies were interpreted from the solutions obtained by these techniques. The found sources have been related with the geologic structures affecting the basement. In order to verify the results obtained and minimize the ambiguity of these potential methods, a forward gravimetric model was prepared, based on a geological and structural model of the area. The 2D analytic signal technique was applied to the gravimetric response of the model, and the solutions found are consistent with the depth and geometry of the above recognized sources, confirming the results obtained.
Neural Network Based Intrusion Detection System for Critical Infrastructures
Todd Vollmer; Ondrej Linda; Milos Manic
2009-07-01
Resiliency and security in control systems such as SCADA and Nuclear plant’s in today’s world of hackers and malware are a relevant concern. Computer systems used within critical infrastructures to control physical functions are not immune to the threat of cyber attacks and may be potentially vulnerable. Tailoring an intrusion detection system to the specifics of critical infrastructures can significantly improve the security of such systems. The IDS-NNM – Intrusion Detection System using Neural Network based Modeling, is presented in this paper. The main contributions of this work are: 1) the use and analyses of real network data (data recorded from an existing critical infrastructure); 2) the development of a specific window based feature extraction technique; 3) the construction of training dataset using randomly generated intrusion vectors; 4) the use of a combination of two neural network learning algorithms – the Error-Back Propagation and Levenberg-Marquardt, for normal behavior modeling. The presented algorithm was evaluated on previously unseen network data. The IDS-NNM algorithm proved to be capable of capturing all intrusion attempts presented in the network communication while not generating any false alerts.
Implementation of neural networks using quantum well based excitonic devices
Implementation is a key bottleneck for tapping the vast potential of neural networks. In this paper the authors examine experimentally and theoretically two devices based on III-V technology, which are critical in the implementation of the Hopfield model as well as other neural type networks for associative memories. The devices are based on Stark effect of excitonic transitions. P-1 (multiquantum wells)-n structures using GaAs/AlGaAs provide a controller-modulator device which has integrating-thresholding properties required of neurons. The p-i-n structures also provide programmable modulators which can serve as a synaptic mask. Using Monte Carlo techniques they examine an all-optical architecture to implement the Hopfield network. No external feedback-thresholding circuitry is required in this implementation due to special design of the controller-modulator device. Speed and stability issues of this architecture are also addressed. The computer simulation results provide valuable insight into how the controller-modulator device should be improved for better network implementation. It is also important to note that the basic technology now exists for such an implementation
The Euler characteristic of a bicategory and the product formula for fibered bicategories
Tanaka, Kohei
2014-01-01
This paper studies the Euler characteristic of a bicategory based on the concept of magnitudes introduced by Leinster. We focus on its invariance with respect to biequivalence and on the product formula for Buckley's fibered bicategories.
Willführ, Alper; Brandenberger, Christina; Piatkowski, Tanja; Grothausmann, Roman; Nyengaard, Jens Randel; Ochs, Matthias; Mühlfeld, Christian
2015-12-01
The lung parenchyma provides a maximal surface area of blood-containing capillaries that are in close contact with a large surface area of the air-containing alveoli. Volume and surface area of capillaries are the classic stereological parameters to characterize the alveolar capillary network (ACN) and have provided essential structure-function information of the lung. When loss (rarefaction) or gain (angiogenesis) of capillaries occurs, these parameters may not be sufficient to provide mechanistic insight. Therefore, it would be desirable to estimate the number of capillaries, as it contains more distinct and mechanistically oriented information. Here, we present a new stereological method to estimate the number of capillary loops in the ACN. One advantage of this method is that it is independent of the shape, size, or distribution of the capillaries. We used consecutive, 1 μm-thick sections from epoxy resin-embedded material as a physical disector. The Euler-Poincaré characteristic of capillary networks can be estimated by counting the easily recognizable topological constellations of "islands," "bridges," and "holes." The total number of capillary loops in the ACN can then be calculated from the Euler-Poincaré characteristic. With the use of the established estimator of alveolar number, it is possible to obtain the mean number of capillary loops per alveolus. In conclusion, estimation of alveolar capillaries by design-based stereology is an efficient and unbiased method to characterize the ACN and may be particularly useful for studies on emphysema, pulmonary hypertension, or lung development. PMID:26432874
VoIP attacks detection engine based on neural network
Safarik, Jakub; Slachta, Jiri
2015-05-01
The security is crucial for any system nowadays, especially communications. One of the most successful protocols in the field of communication over IP networks is Session Initiation Protocol. It is an open-source project used by different kinds of applications, both open-source and proprietary. High penetration and text-based principle made SIP number one target in IP telephony infrastructure, so security of SIP server is essential. To keep up with hackers and to detect potential malicious attacks, security administrator needs to monitor and evaluate SIP traffic in the network. But monitoring and following evaluation could easily overwhelm the security administrator in networks, typically in networks with a number of SIP servers, users and logically or geographically separated networks. The proposed solution lies in automatic attack detection systems. The article covers detection of VoIP attacks through a distributed network of nodes. Then the gathered data analyze aggregation server with artificial neural network. Artificial neural network means multilayer perceptron network trained with a set of collected attacks. Attack data could also be preprocessed and verified with a self-organizing map. The source data is detected by distributed network of detection nodes. Each node contains a honeypot application and traffic monitoring mechanism. Aggregation of data from each node creates an input for neural networks. The automatic classification on a centralized server with low false positive detection reduce the cost of attack detection resources. The detection system uses modular design for easy deployment in final infrastructure. The centralized server collects and process detected traffic. It also maintains all detection nodes.
Conjugate points in Euler's elastic problem
Sachkov, Yu L
2007-01-01
For the classical Euler's elastic problem, conjugate points are described. Inflectional elasticae admit the first conjugate point between the first and the third inflection points. All the rest elasticae do not have conjugate points.
Speech Recognition Method Based on Multilayer Chaotic Neural Network
REN Xiaolin; HU Guangrui
2001-01-01
In this paper,speech recognitionusing neural networks is investigated.Especially,chaotic dynamics is introduced to neurons,and a mul-tilayer chaotic neural network (MLCNN) architectureis built.A learning algorithm is also derived to trainthe weights of the network.We apply the MLCNNto speech recognition and compare the performanceof the network with those of recurrent neural net-work (RNN) and time-delay neural network (TDNN).Experimental results show that the MLCNN methodoutperforms the other neural networks methods withrespect to average recognition rate.
Neural Network Based Parking via Google Map Guidance
A.Saranya
2015-02-01
Full Text Available Intelligent transportation systems (ITS focus to generate and spread creative services related to different transport modes for traffic management and hence enables the passenger informed about the traffic and to use the transport networks in a better way. Intelligent Trip Modeling System (ITMS uses machine learning to forecast the traveling speed profile for a selected route based on the traffic information available at the trip starting time. The intelligent Parking Information Guidance System provides an eminent Neural Network based intelligence system which provides automatic allocate ion of parking's through the Global Information system across the path of the users travel. In this project using efficient lookup table searches and a Lagrange-multiplier bisection search, Computational Optimized Allocation Algorithm converges faster to the optimal solution than existing techniques. The purpose of this project is to simulate and implement a real parking environment that allocates vacant parking slots using Allocation algorithm.
Neural network based feed-forward high density associative memory
Daud, T.; Moopenn, A.; Lamb, J. L.; Ramesham, R.; Thakoor, A. P.
1987-01-01
A novel thin film approach to neural-network-based high-density associative memory is described. The information is stored locally in a memory matrix of passive, nonvolatile, binary connection elements with a potential to achieve a storage density of 10 to the 9th bits/sq cm. Microswitches based on memory switching in thin film hydrogenated amorphous silicon, and alternatively in manganese oxide, have been used as programmable read-only memory elements. Low-energy switching has been ascertained in both these materials. Fabrication and testing of memory matrix is described. High-speed associative recall approaching 10 to the 7th bits/sec and high storage capacity in such a connection matrix memory system is also described.
Control of GMA Butt Joint Welding Based on Neural Networks
Christensen, Kim Hardam; Sørensen, Torben
2004-01-01
This paper presents results from an experimentally based research on Gas Metal Arc Welding (GMAW), controlled by the artificial neural network (ANN) technology. A system has been developed for modeling and online adjustment of welding parameters, appropriate to guarantee a high degree of quality in...... the challenging field of butt joint welding with full penetration under stochastically changing boundary conditions, e.g. major gap width variations. GMAW experiments performed on mild-steel plates (3 mm of thickness), show that high quality welds with uniform back-bead geometry are achievable for gap...... width variations from 0.5 mm to 2.3 mm - scanned 10 mm in front of the electrode location. In this research, the mapping from joint geometry and reference weld quality to significant welding parameters has been based on a static multi-layer feed-forward network. The Levenberg-Marquardt algorithm, for...
Neural Network Based Model for Predicting Housing Market Performance
Ahmed Khalafallah
2008-01-01
The United States real estate market is currently facing its worst hit in two decades due to the slowdown of housing sales. The most affected by this decline are real estate investors and home develop-ers who are currently struggling to break-even financially on their investments. For these investors, it is of utmost importance to evaluate the current status of the market and predict its performance over the short-term in order to make appropriate financial decisions. This paper presents the development of artificial neu-ral network based models to support real estate investors and home developers in this critical task. The pa-per describes the decision variables, design methodology, and the implementation of these models. The models utilize historical market performance data sets to train the artificial neural networks in order to pre-dict unforeseen future performances. An application example is analyzed to demonstrate the model capabili-ties in analyzing and predicting the market performance. The model testing and validation showed that the error in prediction is in the range between -2% and +2%.
Neural Network based Vehicle Classification for Intelligent Traffic Control
Saeid Fazli
2012-06-01
Full Text Available Nowadays, number of vehicles has been increased and traditional systems of traffic controlling couldn’t be able to meet the needs that cause to emergence of Intelligent Traffic Controlling Systems. They improve controlling and urban management and increase confidence index in roads and highways. The goal of thisarticle is vehicles classification base on neural networks. In this research, it has been used a immovable camera which is located in nearly close height of the road surface to detect and classify the vehicles. The algorithm that used is included two general phases; at first, we are obtaining mobile vehicles in the traffic situations by using some techniques included image processing and remove background of the images and performing edge detection and morphology operations. In the second phase, vehicles near the camera areselected and the specific features are processed and extracted. These features apply to the neural networks as a vector so the outputs determine type of vehicle. This presented model is able to classify the vehicles in three classes; heavy vehicles, light vehicles and motorcycles. Results demonstrate accuracy of the algorithm and its highly functional level.
Comparison Of Power Quality Disturbances Classification Based On Neural Network
Nway Nway Kyaw Win
2015-07-01
Full Text Available Abstract Power quality disturbances PQDs result serious problems in the reliability safety and economy of power system network. In order to improve electric power quality events the detection and classification of PQDs must be made type of transient fault. Software analysis of wavelet transform with multiresolution analysis MRA algorithm and feed forward neural network probabilistic and multilayer feed forward neural network based methodology for automatic classification of eight types of PQ signals flicker harmonics sag swell impulse fluctuation notch and oscillatory will be presented. The wavelet family Db4 is chosen in this system to calculate the values of detailed energy distributions as input features for classification because it can perform well in detecting and localizing various types of PQ disturbances. This technique classifies the types of PQDs problem sevents.The classifiers classify and identify the disturbance type according to the energy distribution. The results show that the PNN can analyze different power disturbance types efficiently. Therefore it can be seen that PNN has better classification accuracy than MLFF.
This paper proposes an identification-based adaptive backstepping control (IABC) for the chaotic systems. The IABC system is comprised of a neural backstepping controller and a robust compensation controller. The neural backstepping controller containing a self-organizing fuzzy neural network (SOFNN) identifier is the principal controller, and the robust compensation controller is designed to dispel the effect of minimum approximation error introduced by the SOFNN identifier. The SOFNN identifier is used to online estimate the chaotic dynamic function with structure and parameter learning phases of fuzzy neural network. The structure learning phase consists of the growing and pruning of fuzzy rules; thus the SOFNN identifier can avoid the time-consuming trial-and-error tuning procedure for determining the neural structure of fuzzy neural network. The parameter learning phase adjusts the interconnection weights of neural network to achieve favorable approximation performance. Finally, simulation results verify that the proposed IABC can achieve favorable tracking performance.
Advanced neural network-based computational schemes for robust fault diagnosis
Mrugalski, Marcin
2014-01-01
The present book is devoted to problems of adaptation of artificial neural networks to robust fault diagnosis schemes. It presents neural networks-based modelling and estimation techniques used for designing robust fault diagnosis schemes for non-linear dynamic systems. A part of the book focuses on fundamental issues such as architectures of dynamic neural networks, methods for designing of neural networks and fault diagnosis schemes as well as the importance of robustness. The book is of a tutorial value and can be perceived as a good starting point for the new-comers to this field. The book is also devoted to advanced schemes of description of neural model uncertainty. In particular, the methods of computation of neural networks uncertainty with robust parameter estimation are presented. Moreover, a novel approach for system identification with the state-space GMDH neural network is delivered. All the concepts described in this book are illustrated by both simple academic illustrative examples and practica...
Silicon-based wire electrode array for neural interfaces
Objectives. Metal-wire electrode arrays are widely used to record and stimulate neurons. Commonly, these devices are fabricated from a long insulated metal wire by cutting it into the proper length and using the cross-section as the electrode site. The assembly of a micro-wire electrode array with regular spacing is difficult. With the help of micro-machine technology, a silicon-based wire electrode array (SWEA) is proposed to simplify the assembling process and provide a wire-type electrode with tapered tips. Approach. Silicon wires with regular spacing coated with metal are generated from a silicon wafer through micro-fabrication and are ordered into a 3D array. A silicon wafer is cut into a comb-like structure with hexagonal teeth on both sides by anisotropic etching. To establish an array of silicon-based linear needles through isotropic wet etching, the diameters of these hexagonal teeth are reduced; their sharp edges are smoothed out and their tips are sharpened. The needle array is coated with a layer of parylene after metallization. The tips of the needles are then exposed to form an array of linear neural electrodes. With these linear electrode arrays, an array of area electrodes can be fabricated. Main results. A 6 × 6 array of wire-type electrodes based on silicon is developed using this method. The time required to manually assemble the 3D array decreases significantly with the introduction of micro-fabricated 2D array. Meanwhile, the tip intervals in the 2D array are accurate and are controlled at no more than 1%. The SWEA is effective both in vitro and in vivo. Significance. Using this method, the SWEA can be batch-prepared in advance along with its parameters, such as spacing, length, and diameter. Thus, neural scientists can assemble proper electrode arrays in a short time. (paper)
Variational iteration method for solving compressible Euler equations
This paper applies the variational iteration method to obtain approximate analytic solutions of compressible Euler equations in gas dynamics. This method is based on the use of Lagrange multiplier for identification of optimal values of parameters in a functional. Using this method, a rapid convergent sequence is produced which converges to the exact solutions of the problem. Numerical results and comparison with other two numerical solutions verify that this method is very convenient and efficient. (general)
A Rapid Aerodynamic Design Procedure Based on Artificial Neural Networks
Rai, Man Mohan
2001-01-01
An aerodynamic design procedure that uses neural networks to model the functional behavior of the objective function in design space has been developed. This method incorporates several improvements to an earlier method that employed a strategy called parameter-based partitioning of the design space in order to reduce the computational costs associated with design optimization. As with the earlier method, the current method uses a sequence of response surfaces to traverse the design space in search of the optimal solution. The new method yields significant reductions in computational costs by using composite response surfaces with better generalization capabilities and by exploiting synergies between the optimization method and the simulation codes used to generate the training data. These reductions in design optimization costs are demonstrated for a turbine airfoil design study where a generic shape is evolved into an optimal airfoil.
Sub-pixel mapping method based on BP neural network
LI Jiao; WANG Li-guo; ZHANG Ye; GU Yan-feng
2009-01-01
A new sub-pixel mapping method based on BP neural network is proposed in order to determine the spatial distribution of class components in each mixed pixel. The network was used to train a model that describes the relationship between spatial distribution of target components in mixed pixel and its neighboring information. Then the sub-pixel scaled target could be predicted by the trained model. In order to improve the performance of BP network, BP learning algorithm with momentum was employed. The experiments were conducted both on synthetic images and on hyperspectral imagery (HSI). The results prove that this method is capable of estimating land covers fairly accurately and has a great superiority over some other sub-pixel mapping methods in terms of computational complexity.
Image restoration techniques based on fuzzy neural networks
刘普寅; 李洪兴
2002-01-01
By establishing some suitable partitions of input and output spaces, a novel fuzzy neuralnetwork (FNN) which is called selection type FNN is developed. Such a system is a multilayerfeedforward neural network, which can be a universal approximator with maximum norm. Based ona family of fuzzy inference rules that are of real senses, a simple and useful inference type FNN isconstructed. As a result, the fusion of selection type FNN and inference type FNN results in a novelfilter-FNN filter. It is simple in structure. And also it is convenient to design the learning algorithmfor structural parameters. Further, FNN filter can efficiently suppress impulse noise superimposed onimage and preserve fine image structure, simultaneously. Some examples are simulated to confirmthe advantages of FNN filter over other filters, such as median filter and adaptive weighted fuzzymean (AWFM) filter and so on, in suppression of noises and preservation of image structure.
Edge detection of noisy images based on cellular neural networks
Li, Huaqing; Liao, Xiaofeng; Li, Chuandong; Huang, Hongyu; Li, Chaojie
2011-09-01
This paper studies a technique employing both cellular neural networks (CNNs) and linear matrix inequality (LMI) for edge detection of noisy images. Our main work focuses on training templates of noise reduction and edge detection CNNs. Based on the Lyapunov stability theorem, we derive a criterion for global asymptotical stability of a unique equilibrium of the noise reduction CNN. Then we design an approach to train edge detection templates, and this approach can detect the edge precisely and efficiently, i.e., by only one iteration. Finally, we illustrate performance of the proposed methodology from the aspect of peak signal to noise ratio (PSNR) through computer simulations. Moreover, some comparisons are also given to prove that our method outperforms classical operators in gray image edge detection.
Neurally based measurement and evaluation of environmental noise
Soeta, Yoshiharu
2015-01-01
This book deals with methods of measurement and evaluation of environmental noise based on an auditory neural and brain-oriented model. The model consists of the autocorrelation function (ACF) and the interaural cross-correlation function (IACF) mechanisms for signals arriving at the two ear entrances. Even when the sound pressure level of a noise is only about 35 dBA, people may feel annoyed due to the aspects of sound quality. These aspects can be formulated by the factors extracted from the ACF and IACF. Several examples of measuring environmental noise—from outdoor noise such as that of aircraft, traffic, and trains, and indoor noise such as caused by floor impact, toilets, and air-conditioning—are demonstrated. According to the noise measurement and evaluation, applications for sound design are discussed. This book provides an excellent resource for students, researchers, and practitioners in a wide range of fields, such as the automotive, railway, and electronics industries, and soundscape, architec...
Biocompatible benzocyclobutene-based intracortical neural implant with surface modification
Lee, Keekeun; Massia, Stephen; He, Jiping
2005-11-01
This paper presents the fabrication of a benzocyclobutene (BCB) polymer-based intracortical neural implant for reliable and stable long-term implant function. BCB polymer has many attractive features for chronic implant application: flexibility, biocompatibility, low moisture uptake, low dielectric constant and easy surface modification. A 2 µm thick silicon backbone layer was attached underneath a flexible BCB electrode to improve mechanical stiffness. No insertion trauma was observed during penetrating into the dura of a rat. In vitro cytotoxicity tests of the completed BCB electrode revealed no toxic effects on cultured cells. The modified BCB surface with a dextran coating showed a significant reduction in 3T3 cell adhesion and spreading, indicating that this coating has the potential for lowering protein adsorption, minimizing inflammatory cell adhesion and glial scar formation in vivo, and thereby enhancing long-term implant performance.
Intelligent control based on fuzzy logic and neural net theory
Lee, Chuen-Chien
1991-01-01
In the conception and design of intelligent systems, one promising direction involves the use of fuzzy logic and neural network theory to enhance such systems' capability to learn from experience and adapt to changes in an environment of uncertainty and imprecision. Here, an intelligent control scheme is explored by integrating these multidisciplinary techniques. A self-learning system is proposed as an intelligent controller for dynamical processes, employing a control policy which evolves and improves automatically. One key component of the intelligent system is a fuzzy logic-based system which emulates human decision making behavior. It is shown that the system can solve a fairly difficult control learning problem. Simulation results demonstrate that improved learning performance can be achieved in relation to previously described systems employing bang-bang control. The proposed system is relatively insensitive to variations in the parameters of the system environment.
Neural Network Based Color Recognition for Bobbin Sorting Machine
Mu Zhang
2013-07-01
Full Text Available Winding is a key process in the manufacturing process of textile industry. The normal and effective operation of winding process plays a very important role on the textiles’ quality and economic effects. At present, a large proportion of bobbins which collected from winder still have yarn left over. The bobbin recycling is severely limited and quick running of winder is seriously restricted, the invention of the the automatic bobbin sorting machine has solved this problem. The ability to distinguish bobbin which has yarn left over from the rest and the classification accuracy of color are the two important performance indicators for bobbin sorting machine. According to the development and application of the color recognition technology and the artificial intelligence method, this study proposes a novel color recognition method that based on BP neural networks. The result shows that the accuracy of color recognition reaches 98%.
Functional 3D Neural Mini-Tissues from Printed Gel-Based Bioink and Human Neural Stem Cells.
Gu, Qi; Tomaskovic-Crook, Eva; Lozano, Rodrigo; Chen, Yu; Kapsa, Robert M; Zhou, Qi; Wallace, Gordon G; Crook, Jeremy M
2016-06-01
Direct-write printing of stem cells within biomaterials presents an opportunity to engineer tissue for in vitro modeling and regenerative medicine. Here, a first example of constructing neural tissue by printing human neural stem cells that are differentiated in situ to functional neurons and supporting neuroglia is reported. The supporting biomaterial incorporates a novel clinically relevant polysaccharide-based bioink comprising alginate, carboxymethyl-chitosan, and agarose. The printed bioink rapidly gels by stable cross-linking to form a porous 3D scaffold encapsulating stem cells for in situ expansion and differentiation. Differentiated neurons form synaptic contacts, establish networks, are spontaneously active, show a bicuculline-induced increased calcium response, and are predominantly gamma-aminobutyric acid expressing. The 3D tissues will facilitate investigation of human neural development, function, and disease, and may be adaptable for engineering other 3D tissues from different stem cell types. PMID:27028356
Neural model of finite state automaton based on hysteresis microensembles
The artificial neural network approach for the implementation of a deterministic finite state automaton has been considered. The previously proposed model of the micro-ensemble has been used as a building block for the automaton. It has been shown that hysteresis dynamics of such a model provides the memorize property needed for a neural network implementing the automaton. In addition, a method for the transformation of any deterministic finite state automaton into a functionally equivalent neural network has been proposed
Sensor Temperature Compensation Technique Simulation Based on BP Neural Network
Xiangwu Wei
2013-01-01
Innovatively, neural network function programming in the BPNN (BP neural network) tool boxes from MATLAB are applied, and data processing is done about CYJ-101 pressure sensor, and the problem of the sensor temperature compensation is solved. The paper has made the pressure sensors major sensors and temperature sensor assistant sensors, input the voltage signal from the two sensors into the established BP neural network model, and done the simulation under the NN Toolbox environment of MATLAB...
Methods of Forecasting Based on Artificial Neural Networks
Stepčenko, A; Borisovs, A
2014-01-01
This article presents an overview of artificial neural network (ANN) applications in forecasting and possible forecasting accuracy improvements. Artificial neural networks are computational models and universal approximators, which can be applied to the time series forecasting with a high accuracy. A great rise in research activities was observed in using artificial neural networks for forecasting. This paper examines multi-layer perceptrons (MLPs) – back-propagation neur...
Wang, X. R.; P. Yan; Lu, J; C. He
2007-01-01
Based on the modified Landau-Lifshitz-Gilbert equation for an arbitrary Stoner particle under an external magnetic field and a spin-polarized electric current, differential equations for the optimal reversal trajectory, along which the magnetization reversal is the fastest one among all possible reversal routes, are obtained. We show that this is a Euler-Lagrange problem with constrains. The Euler equation of the optimal trajectory is useful in designing a magnetic field pulse and/or a polari...
Optimization of Component Based Software Engineering Model Using Neural Network
Gaurav Kumar
2014-10-01
Full Text Available The goal of Component Based Software Engineering (CBSE is to deliver high quality, more reliable and more maintainable software systems in a shorter time and within limited budget by reusing and combining existing quality components. A high quality system can be achieved by using quality components, framework and integration process that plays a significant role. So, techniques and methods used for quality assurance and assessment of a component based system is different from those of the traditional software engineering methodology. In this paper, we are presenting a model for optimizing Chidamber and Kemerer (CK metric values of component-based software. A deep analysis of a series of CK metrics of the software components design patterns is done and metric values are drawn from them. By using unsupervised neural network- Self Organizing Map, we have proposed a model that provides an optimized model for Software Component engineering model based on reusability that depends on CK metric values. Average, standard deviated and optimized values for the CK metric are compared and evaluated to show the optimized reusability of component based model.
Term Structure of Interest Rates Based on Artificial Neural Network
无
2007-01-01
In light of the nonlinear approaching capability of artificial neural networks ( ANN), the term structure of interest rates is predicted using The generalized regression neural network (GRNN) and back propagation (BP) neural networks models. The prediction performance is measured with US interest rate data. Then, RBF and BP models are compared with Vasicek's model and Cox-Ingersoll-Ross (CIR) model. The comparison reveals that neural network models outperform Vasicek's model and CIR model,which are more precise and closer to the real market situation.
OPTIMAL PWM BASED ON REAL—TIME SOLUTION WITH NEURAL NETWORK
ShenZhongting; YanYangguang
2002-01-01
A novel concept of neural network based control in pulse-width modulation(PWM)voltage source inverters is presented.On the one hand,the optimal switching an-gles are obtained in real time by the neural network based controller；on the other hand,the output voltage is ad-justed to fit the expected value by neural network when input voltage or loads change.The structure of neural network is simple and easy to be realized by DSP hard-ware system.No large memory used for the existing opti-mal PWM schemes is required in the system.Theoreticalanlysis of the proposed so-called sparse neural network is provided,and the stability of the system is proved.Un-der the control of neural network the error of output volt-age descends sharply,and the system outputs ac voltage with high precision.
Xiaoli Dong
2015-01-01
Aiming at the randomness and fuzziness of information security risk assessment factors of Internet of Things, cloud neural network information security risk assessment model was proposed, based on combination of cloud model and neural network and dynamic fusion of heterogeneous security factors. Focus on the research of normal cloud neural network evaluation method and judgment of global and multivalued dependencies characteristics between safety evaluation indicators and risk levels...
Query Based Approach Towards Spam Attacks Using Artificial Neural Network
Gaurav Kumar Tak
2010-10-01
Full Text Available Currently, spam and scams are passive attack over the inbox which can initiated to steal someconfidential information, to spread Worms, Viruses, Trojans, cookies and Sometimes they are used forphishing attacks. Spam mails are the major issue over mail boxes as well as over the internet. Spam mailscan be the cause of phishing attack, hacking of banking accounts, attacks on confidential data. Spammingis growing at a rapid rate since sending a flood of mails is easy and very cheap. Spam mails disturb themind-peace, waste time and consume various resources e.g., memory space and network bandwidth, sofiltering of spam mails is a big issue in cyber security.This paper presents an novel approach of spam filtering which is based on some query generatedapproach on the knowledge base and also use some artificial neural network methods to detect the spammails based on their behavior. analysis of the mail header, cross validation. Proposed methodologyincludes the 7 several steps which are well defined and achieve the higher accuracy. It works well with allkinds of spam mails (text based spam as well as image spam. Our tested data and experiments resultsshows promising results, and spam’s are detected out at least 98.17 % with 0.12% false positive.
Query Based Approach Towards Spam Attacks Using Artificial Neural Network
Gaurav Kumar Tak
2010-10-01
Full Text Available Currently, spam and scams are passive attack over the inbox which can initiated to steal some confidential information, to spread Worms, Viruses, Trojans, cookies and Sometimes they are used for phishing attacks. Spam mails are the major issue over mail boxes as well as over the internet. Spam mails can be the cause of phishing attack, hacking of banking accounts, attacks on confidential data. Spamming is growing at a rapid rate since sending a flood of mails is easy and very cheap. Spam mails disturb the mind-peace, waste time and consume various resources e.g., memory space and network bandwidth, so filtering of spam mails is a big issue in cyber security. This paper presents an novel approach of spam filtering which is based on some query generated approach on the knowledge base and also use some artificial neural network methods to detect the spam mails based on their behavior. analysis of the mail header, cross validation. Proposed methodology includes the 7 several steps which are well defined and achieve the higher accuracy. It works well with all kinds of spam mails (text based spam as well as image spam. Our tested data and experiments results shows promising results, and spam’s are detected out at least 98.17 % with 0.12% false positive.
Fault Localization Analysis Based on Deep Neural Network
Wei Zheng
2016-01-01
Full Text Available With software’s increasing scale and complexity, software failure is inevitable. To date, although many kinds of software fault localization methods have been proposed and have had respective achievements, they also have limitations. In particular, for fault localization techniques based on machine learning, the models available in literatures are all shallow architecture algorithms. Having shortcomings like the restricted ability to express complex functions under limited amount of sample data and restricted generalization ability for intricate problems, the faults cannot be analyzed accurately via those methods. To that end, we propose a fault localization method based on deep neural network (DNN. This approach is capable of achieving the complex function approximation and attaining distributed representation for input data by learning a deep nonlinear network structure. It also shows a strong capability of learning representation from a small sized training dataset. Our DNN-based model is trained utilizing the coverage data and the results of test cases as input and we further locate the faults by testing the trained model using the virtual test suite. This paper conducts experiments on the Siemens suite and Space program. The results demonstrate that our DNN-based fault localization technique outperforms other fault localization methods like BPNN, Tarantula, and so forth.
ZHANG Shuqing; ZHANG Junyan; ZHANG Bai
2004-01-01
By combining geographic information system (GIS), a new conception of "group" in which covers the complex connected region is introduced in the paper. Based on the conception of group, a generalized Euler formula and its properties are deduced and proved. The paper also describes the mathematical principles of generating topological information of polygon in GIS maps and the methods for checking up the veracity of topological relations of the map with Euler formula and general Euler formula. We have also obtained the quantitative relations among real nodes, chains, islands and groups with the formulas. At the same time, the paper introduces Whole Sphere Stereographic (WSS) projection into the GIS, and defines a new conception of "sea". The deduction of general Euler formula and the introduction of WSS projection to GIS have developed new ways of delineating GIS topological models from plane to sphere and even constructing three dimensional (3-D) topological models.
Web based educational tool for neural network robot control
Jure Čas
2007-05-01
Full Text Available Abstract— This paper describes the application for teleoperations of the SCARA robot via the internet. The SCARA robot is used by students of mehatronics at the University of Maribor as a remote educational tool. The developed software consists of two parts i.e. the continuous neural network sliding mode controller (CNNSMC and the graphical user interface (GUI. Application is based on two well-known commercially available software packages i.e. MATLAB/Simulink and LabVIEW. Matlab/Simulink and the DSP2 Library for Simulink are used for control algorithm development, simulation and executable code generation. While this code is executing on the DSP-2 Roby controller and through the analog and digital I/O lines drives the real process, LabVIEW virtual instrument (VI, running on the PC, is used as a user front end. LabVIEW VI provides the ability for on-line parameter tuning, signal monitoring, on-line analysis and via Remote Panels technology also teleoperation. The main advantage of a CNNSMC is the exploitation of its self-learning capability. When friction or an unexpected impediment occurs for example, the user of a remote application has no information about any changed robot dynamic and thus is unable to dispatch it manually. This is not a control problem anymore because, when a CNNSMC is used, any approximation of changed robot dynamic is estimated independently of the remote’s user. Index Terms—LabVIEW; Matlab/Simulink; Neural network control; remote educational tool; robotics
Expert System Based on Data Mining and Neural Networks
NI Zhi-wei; JIA Rui-yu
2001-01-01
On the basis of data mining and neural network, this paper proposes a general framework of the neural network expert system and discusses the key techniques in this kind of system. We apply these ideas on agricultural expert system to find some unknown useful knowledge and get some satisfactory results.
Thermoelastic steam turbine rotor control based on neural network
Rzadkowski, Romuald; Dominiczak, Krzysztof; Radulski, Wojciech; Szczepanik, R.
2015-12-01
Considered here are Nonlinear Auto-Regressive neural networks with eXogenous inputs (NARX) as a mathematical model of a steam turbine rotor for controlling steam turbine stress on-line. In order to obtain neural networks that locate critical stress and temperature points in the steam turbine during transient states, an FE rotor model was built. This model was used to train the neural networks on the basis of steam turbine transient operating data. The training included nonlinearity related to steam turbine expansion, heat exchange and rotor material properties during transients. Simultaneous neural networks are algorithms which can be implemented on PLC controllers. This allows for the application neural networks to control steam turbine stress in industrial power plants.
Artificial neural network based approach to transmission lines protection
The aim of this paper is to present and accurate fault detection technique for high speed distance protection using artificial neural networks. The feed-forward multi-layer neural network with the use of supervised learning and the common training rule of error back-propagation is chosen for this study. Information available locally at the relay point is passed to a neural network in order for an assessment of the fault location to be made. However in practice there is a large amount of information available, and a feature extraction process is required to reduce the dimensionality of the pattern vectors, whilst retaining important information that distinguishes the fault point. The choice of features is critical to the performance of the neural networks learning and operation. A significant feature in this paper is that an artificial neural network has been designed and tested to enhance the precision of the adaptive capabilities for distance protection
Chinese word sense disambiguation based on neural networks
LIU Ting; LU Zhi-mao; LANG Jun; LI Sheng
2005-01-01
The input of a network is the key problem for Chinese word sense disambiguation utilizing the neural network. This paper presents an input model of the neural network that calculates the mutual information between contextual words and the ambiguous word by using statistical methodology and taking the contextual words of a certain number beside the ambiguous word according to ( - M, + N). The experiment adopts triple-layer BP Neural Network model and proves how the size of a training set and the value of M and N affect the performance of the Neural Network Model. The experimental objects are six pseudowords owning three word-senses constructed according to certain principles. The tested accuracy of our approach on a closed-corpus reaches 90. 31% ,and 89. 62% on an open-corpus. The experiment proves that the Neural Network Model has a good performance on Word Sense Disambiguation.
INTERPRETATION TRAINED NEURAL NETWORKS BASED ON GENETIC ALGORITHMS
Safa S. Ibrahim
2013-01-01
Full Text Available In this paper, constructive learning is used to train the neural networks. The results of neural networks are obtained but its result is not in comprehensible form or in a black box form. Our goal is to use an important and desirable model to identify sets of input variable which results in a desired output value. The nature of this model can help to find an optimal set of difficult input variables. Accuracy. Genetic algorithms are used as an interpretation of achieving neural network inversion. On the other hand the inversion of neural network enables to find one or more input patterns which satisfy a specific output. The input patterns obtained from the genetic algorithm can be used for building neural network system explanation facilities.
Stem cell-based therapy in neural repair.
Hsu, Yi-Chao; Chen, Su-Liang; Wang, Dan-Yen; Chiu, Ing-Ming
2013-01-01
Cell-based therapy could aid in alleviating symptoms or even reversing the progression of neurodegenerative diseases and nerve injuries. Fibroblast growth factor 1 (FGF1) has been shown to maintain the survival of neurons and induce neurite outgrowth. Accumulating evidence suggests that combination of FGF1 and cell-based therapy is promising for future therapeutic application. Neural stem cells (NSCs), with the characteristics of self-renewal and multipotency, can be isolated from embryonic stem cells, embryonic ectoderm, and developing or adult brain tissues. For NSC clinical application, several critical problems remain to be resolved: (1) the source of NSCs should be personalized; (2) the isolation methods and protocols of human NSCs should be standardized; (3) the clinical efficacy of NSC transplants must be evaluated in more adequate animal models; and (4) the mechanism of intrinsic brain repair needs to be better characterized. In addition, the ideal imaging technique for tracking NSCs would be safe and yield high temporal and spatial resolution, good sensitivity and specificity. Here, we discuss recent progress and future development of cell-based therapy, such as NSCs, induced pluripotent stem cells, and induced neurons, in neurodegenerative diseases and peripheral nerve injuries. PMID:23806879
Intercurrent fault diagnosis of nuclear power plants based on hybrid artificial neural network
Based on the analysis of the structure of ART-2 and parallel BP neural network, a hybrid artificial neural network is proposed aiming at the intercurrent faults diagnosis of nuclear power plants. Firstly the ART-2 net is used to identify the single fault, then the parallel BP net is used to distinguish intercurrent faults from new fault. The simulation shows that, the hybrid artificial neural network resolves the problem of single neural network in distinguishing intercurrent faults from new fault, and can diagnose the intercurrent fault and new fault efficiently. (authors)
Study on the Robot Robust Adaptive Control Based on Neural Networks
温淑焕; 王洪瑞; 吴丽艳
2003-01-01
Force control based on neural networks is presented. Under the framework of hybrid control, an RBF neural network is used to compensate for all the uncertainties from robot dynamics and unknown environment first. The technique will improve the adaptability to environment stiffness when the end-effector is in contact with the environment, and does not require any a priori knowledge on the upper bound of syste uncertainties. Moreover, it need not compute the inverse of inertia matrix. Learning algorithms for neural networks to minimize the force error directly are designed. Simulation results have shown a better force/position tracking when neural network is used.
Farahnaz SADOUGHI
2014-03-01
Full Text Available Breast cancer is the most commonly diagnosed cancer and the most common cause of death in women all over the world. Use of computer technology supporting breast cancer diagnosing is now widespread and pervasive across a broad range of medical areas. Early diagnosis of this disease can greatly enhance the chances of long-term survival of breast cancer victims. Artificial Neural Networks (ANN as mainly method play important role in early diagnoses breast cancer. This paper studies Levenberg Marquardet Backpropagation (LMBP neural network and Levenberg Marquardet Backpropagation based Particle Swarm Optimization(LMBP-PSO for the diagnosis of breast cancer. The obtained results show that LMBP and LMBP based PSO system provides higher classification efficiency. But LMBP based PSO needs minimum training and testing time. It helps in developing Medical Decision System (MDS for breast cancer diagnosing. It can also be used as secondary observer in clinical decision making.
Electromyogram-based neural network control of transhumeral prostheses
Christopher L. Pulliam, MS
2011-07-01
Full Text Available Upper-limb amputation can cause a great deal of functional impairment for patients, particularly for those with amputation at or above the elbow. Our long-term objective is to improve functional outcomes for patients with amputation by integrating a fully implanted electromyographic (EMG recording system with a wireless telemetry system that communicates with the patient's prosthesis. We believe that this should generate a scheme that will allow patients to robustly control multiple degrees of freedom simultaneously. The goal of this study is to evaluate the feasibility of predicting dynamic arm movements (both flexion/extension and pronation/supination based on EMG signals from a set of muscles that would likely be intact in patients with transhumeral amputation. We recorded movement kinematics and EMG signals from seven muscles during a variety of movements with different complexities. Time-delayed artificial neural networks were then trained offline to predict the measured arm trajectories based on features extracted from the measured EMG signals. We evaluated the relative effectiveness of various muscle subsets. Predicted movement trajectories had average root-mean-square errors of approximately 15.7° and 24.9° and average R2 values of approximately 0.81 and 0.46 for elbow flexion/extension and forearm pronation/supination, respectively.
MR-based imaging of neural stem cells
The efficacy of therapies based on neural stem cells (NSC) has been demonstrated in preclinical models of several central nervous system (CNS) diseases. Before any potential human application of such promising therapies can be envisaged, there are some important issues that need to be solved. The most relevant one is the requirement for a noninvasive technique capable of monitoring NSC delivery, homing to target sites and trafficking. Knowledge of the location and temporospatial migration of either transplanted or genetically modified NSC is of the utmost importance in analyzing mechanisms of correction and cell distribution. Further, such a technique may represent a crucial step toward clinical application of NSC-based approaches in humans, for both designing successful protocols and monitoring their outcome. Among the diverse imaging approaches available for noninvasive cell tracking, such as nuclear medicine techniques, fluorescence and bioluminescence, magnetic resonance imaging (MRI) has unique advantages. Its high temporospatial resolution, high sensitivity and specificity render MRI one of the most promising imaging modalities available, since it allows dynamic visualization of migration of transplanted cells in animal models and patients during clinically useful time periods. Different cellular and molecular labeling approaches for MRI depiction of NSC are described and discussed in this review, as well as the most relevant issues to be considered in optimizing molecular imaging techniques for clinical application. (orig.)
Batch Process Modelling and Optimal Control Based on Neural Network Models
Jie Zhang
2005-01-01
This paper presents several neural network based modelling, reliable optimal control, and iterative learning control methods for batch processes. In order to overcome the lack of robustness of a single neural network, bootstrap aggregated neural networks are used to build reliable data based empirical models. Apart from improving the model generalisation capability, a bootstrap aggregated neural network can also provide model prediction confidence bounds. A reliable optimal control method by incorporating model prediction confidence bounds into the optimisation objective function is presented. A neural network based iterative learning control strategy is presented to overcome the problem due to unknown disturbances and model-plant mismatches. The proposed methods are demonstrated on a simulated batch polymerisation process.
Research on the Prediction of VNN Neural Network Traffic Flow Model Based on Chaotic Algorithm
Yin Lisheng
2013-06-01
Full Text Available This paperresearches on the prediction of traffic flow chaotic time series based on VNNTF neural network. First, the traffic flow time series chaotic feature is extracted by chaos theory. Pretreatment for traffic flow time series and the VNNTP neural networks model was build by this. Second, principles of neural network learning algorithm VNNTF is described. Based on chaotic learning algorithm, the neural network traffic Volterra learning algorithm isdesigned for fast learning algorithm. Last, a single-step prediction of traffic flow chaotic time series is researched by VNNTF network model based on chaotic algorithm. The results showed that the VNNTF network model predictive performance is better than the Volterra prediction filter and the BP neural network by the simulation results and root-mean-square value.
Prediction and Research on Vegetable Price Based on Genetic Algorithm and Neural Network Model
2011-01-01
Considering the complexity of vegetables price forecast,the prediction model of vegetables price was set up by applying the neural network based on genetic algorithm and using the characteristics of genetic algorithm and neural work.Taking mushrooms as an example,the parameters of the model are analyzed through experiment.In the end,the results of genetic algorithm and BP neural network are compared.The results show that the absolute error of prediction data is in the scale of 10%;in the scope that the absolute error in the prediction data is in the scope of 20% and 15%.The accuracy of genetic algorithm based on neutral network is higher than the BP neutral network model,especially the absolute error of prediction data is within the scope of 20%.The accuracy of genetic algorithm based on neural network is obviously better than BP neural network model,which represents the favorable generalization capability of the model.
Underwater vehicle sonar self-noise prediction based on genetic algorithms and neural network
WU Xiao-guang; SHI Zhong-kun
2006-01-01
The factors that influence underwater vehicle sonar self-noise are analyzed, and genetic algorithms and a back propagation (BP) neural network are combined to predict underwater vehicle sonar self-noise. The experimental results demonstrate that underwater vehicle sonar self-noise can be predicted accurately by a GA-BP neural network that is based on actual underwater vehicle sonar data.
Neural network predicts sequence of TP53 gene based on DNA chip
Spicker, J.S.; Wikman, F.; Lu, M.L.;
2002-01-01
We have trained an artificial neural network to predict the sequence of the human TP53 tumor suppressor gene based on a p53 GeneChip. The trained neural network uses as input the fluorescence intensities of DNA hybridized to oligonucleotides on the surface of the chip and makes between zero and...
Euler's fluid equations: Optimal control vs optimization
An optimization method used in image-processing (metamorphosis) is found to imply Euler's equations for incompressible flow of an inviscid fluid, without requiring that the Lagrangian particle labels exactly follow the flow lines of the Eulerian velocity vector field. Thus, an optimal control problem and an optimization problem for incompressible ideal fluid flow both yield the same Euler fluid equations, although their Lagrangian parcel dynamics are different. This is a result of the gauge freedom in the definition of the fluid pressure for an incompressible flow, in combination with the symmetry of fluid dynamics under relabeling of their Lagrangian coordinates. Similar ideas are also illustrated for SO(N) rigid body motion.
Analogues of Euler and Poisson Summation Formulae
Vivek V Rane
2003-08-01
Euler–Maclaurin and Poisson analogues of the summations $\\sum_{a < n ≤ b}(n)f(n), \\sum_{a < n ≤ b}d(n) f(n), \\sum_{a < n ≤ b}d(n)(n) f(n)$ have been obtained in a unified manner, where (()) is a periodic complex sequence; () is the divisor function and () is a sufficiently smooth function on [, ]. We also state a generalised Abel's summation formula, generalised Euler's summation formula and Euler's summation formula in several variables.
Converse theorems assuming a partial Euler product
Farmer, David W.; Wilson, Kevin
2004-01-01
Associated to a newform $f(z)$ is a Dirichlet series $L_f(s)$ with functional equation and Euler product. Hecke showed that if the Dirichlet series $F(s)$ has a functional equation of a particular form, then $F(s)=L_f(s)$ for some holomorphic newform $f(z)$ on $\\Gamma(1)$. Weil extended this result to $\\Gamma_0(N)$ under an assumption on the twists of $F(s)$ by Dirichlet characters. Conrey and Farmer extended Hecke's result for certain small $N$, assuming that the local factors in the Euler p...
Subsonic Euler flows in a divergent nozzle
WENG ShangKun
2014-01-01
We characterize a class of physical boundary conditions that guarantee the existence and uniqueness of the subsonic Euler flow in a general finitely long nozzle.More precisely,by prescribing the incoming flow angle and the Bernoulli’s function at the inlet and the end pressure at the exit of the nozzle,we establish an existence and uniqueness theorem for subsonic Euler flows in a 2-D nozzle,which is also required to be adjacent to some special background solutions.Such a result can also be extended to the 3-D asymmetric case.
Non-fragile H∞ synchronization of memristor-based neural networks using passivity theory.
Mathiyalagan, K; Anbuvithya, R; Sakthivel, R; Park, Ju H; Prakash, P
2016-02-01
In this paper, we formulate and investigate the mixed H∞ and passivity based synchronization criteria for memristor-based recurrent neural networks with time-varying delays. Some sufficient conditions are obtained to guarantee the synchronization of the considered neural network based on the master-slave concept, differential inclusions theory and Lyapunov-Krasovskii stability theory. Also, the memristive neural network is considered with two different types of memductance functions and two types of gain variations. The results for non-fragile observer-based synchronization are derived in terms of linear matrix inequalities (LMIs). Finally, the effectiveness of the proposed criterion is demonstrated through numerical examples. PMID:26655373
Simulation Model of Magnetic Levitation Based on NARX Neural Networks
Dragan Antić
2013-04-01
Full Text Available In this paper, we present analysis of different training types for nonlinear autoregressive neural network, used for simulation of magnetic levitation system. First, the model of this highly nonlinear system is described and after that the Nonlinear Auto Regressive eXogenous (NARX of neural network model is given. Also, numerical optimization techniques for improved network training are described. It is verified that NARX neural network can be successfully used to simulate real magnetic levitation system if suitable training procedure is chosen, and the best two training types, obtained from experimental results, are described in details.
Layered learning of soccer robot based on artificial neural network
无
2001-01-01
Discusses the application of artificial neural network for MIROSOT, introduces a layered model of BP network of soccer robot for learning basic behavior and cooperative behavior, and concludes from experimental results that the model is effective.
Recognition of a Life Distribution Based on a Neural Network
GAO Shang
2004-01-01
In general, we describe three different methods to select an appropriate distribution form:bistogram, probability plots, and hypothesis test. The life distribution is recognized by a neural network method. The relationship among life distribution with life data is described through threshold and weight of neural networks. The method is convenient to use. An example is presented to validate this method, and the results are satisfactory.
BRAIN TUMOR CLASSIFICATION USING NEURAL NETWORK BASED METHODS
Kalyani A. Bhawar*, Prof. Nitin K. Bhil
2016-01-01
MRI (Magnetic resonance Imaging) brain neoplasm pictures Classification may be a troublesome tasks due to the variance and complexity of tumors. This paper presents two Neural Network techniques for the classification of the magnetic resonance human brain images. The proposed Neural Network technique consists of 3 stages, namely, feature extraction, dimensionality reduction, and classification. In the first stage, we have obtained the options connected with tomography pictures victimization d...
Food Safety Evaluation System Construction Based on Artificial Neural Network
Jian Wang; Zhenmin Tang; Xianli Jin
2015-01-01
This study uses regression model and artificial neural network model to apply food safety index in food safety trend predication and makes policy advices in the construction and release of an authoritative food safety index, The results showed that the BP neural network was high-precision, fast and objective, which could be used to food safety evaluation of circulation links of production, processing and sales.
Food Safety Evaluation System Construction Based on Artificial Neural Network
Jian Wang
2015-05-01
Full Text Available This study uses regression model and artificial neural network model to apply food safety index in food safety trend predication and makes policy advices in the construction and release of an authoritative food safety index, The results showed that the BP neural network was high-precision, fast and objective, which could be used to food safety evaluation of circulation links of production, processing and sales.
APPROACH TO FAULT ON-LINE DETECTION AND DIAGNOSIS BASED ON NEURAL NETWORKS FOR ROBOT IN FMS
1998-01-01
Based on radial basis function (RBF) neural networks, the healthy working model of each sub-system of robot in FMS is established. A new approach to fault on-line detection and diagnosis according to neural networks model is presented. Fault double detection based on neural network model and threshold judgement and quick fault identification based on multi-layer feedforward neural networks are applied, which can meet quickness and reliability of fault detection and diagnosis for robot in FMS.
Low-dimensional recurrent neural network-based Kalman filter for speech enhancement.
Xia, Youshen; Wang, Jun
2015-07-01
This paper proposes a new recurrent neural network-based Kalman filter for speech enhancement, based on a noise-constrained least squares estimate. The parameters of speech signal modeled as autoregressive process are first estimated by using the proposed recurrent neural network and the speech signal is then recovered from Kalman filtering. The proposed recurrent neural network is globally asymptomatically stable to the noise-constrained estimate. Because the noise-constrained estimate has a robust performance against non-Gaussian noise, the proposed recurrent neural network-based speech enhancement algorithm can minimize the estimation error of Kalman filter parameters in non-Gaussian noise. Furthermore, having a low-dimensional model feature, the proposed neural network-based speech enhancement algorithm has a much faster speed than two existing recurrent neural networks-based speech enhancement algorithms. Simulation results show that the proposed recurrent neural network-based speech enhancement algorithm can produce a good performance with fast computation and noise reduction. PMID:25913233
Artificial Neural Network-Based System for PET Volume Segmentation
Mhd Saeed Sharif
2010-01-01
Full Text Available Tumour detection, classification, and quantification in positron emission tomography (PET imaging at early stage of disease are important issues for clinical diagnosis, assessment of response to treatment, and radiotherapy planning. Many techniques have been proposed for segmenting medical imaging data; however, some of the approaches have poor performance, large inaccuracy, and require substantial computation time for analysing large medical volumes. Artificial intelligence (AI approaches can provide improved accuracy and save decent amount of time. Artificial neural networks (ANNs, as one of the best AI techniques, have the capability to classify and quantify precisely lesions and model the clinical evaluation for a specific problem. This paper presents a novel application of ANNs in the wavelet domain for PET volume segmentation. ANN performance evaluation using different training algorithms in both spatial and wavelet domains with a different number of neurons in the hidden layer is also presented. The best number of neurons in the hidden layer is determined according to the experimental results, which is also stated Levenberg-Marquardt backpropagation training algorithm as the best training approach for the proposed application. The proposed intelligent system results are compared with those obtained using conventional techniques including thresholding and clustering based approaches. Experimental and Monte Carlo simulated PET phantom data sets and clinical PET volumes of nonsmall cell lung cancer patients were utilised to validate the proposed algorithm which has demonstrated promising results.
Neural network-based expert system for severe accident management
This paper presents the results of the second phase of a three-phase Severe Accident Management expert system program underway. The primary objectives of the second phase were to develop and demonstrate four capabilities of neural networks with respect to nuclear power plant severe accident monitoring and prediction. A second objective of the program was to develop an interactive graphical user interface which presented the system's information in an easily accessible and straightforward manner to the user. This paper describes the technical and regulatory foundation upon which the expert system is based and provides a background on the development of a new severe accident management tool. This tool provides data to assist in; (1) planning and developing priorities for recovery actions, (2) evaluating recovery action feasibility, (3) identifying recovery action options, and (4) assessing the timing and possible effects of potential recovery strategies. These performance characteristics represent the goals identified for the Severe Accident Management Strategies Online Network (SAMSON) which is currently under development. 4 refs, 1 fig., 1 tab
Didactic Strategy Discussion Based on Artificial Neural Networks Results.
Andina, D.; Bermúdez-Valbuena, R.
2009-04-01
Artificial Neural Networks (ANNs) are a mathematical model of the main known characteristics of biological brian dynamics. ANNs inspired in biological reality have been useful to design machines that show some human-like behaviours. Based on them, many experimentes have been succesfully developed emulating several biologial neurons characteristics, as learning how to solve a given problem. Sometimes, experimentes on ANNs feedback to biology and allow advances in understanding the biological brian behaviour, allowing the proposal of new therapies for medical problems involving neurons performing. Following this line, the author present results on artificial learning on ANN, and interpret them aiming to reinforce one of this two didactic estrategies to learn how to solve a given difficult task: a) To train with clear, simple, representative examples and feel confidence in brian generalization capabilities to achieve succes in more complicated cases. b) To teach with a set of difficult cases of the problem feeling confidence that the brian will efficiently solve the rest of cases if it is able to solve the difficult ones. Results may contribute in the discussion of how to orientate the design innovative succesful teaching strategies in the education field.
Route Selection Problem Based on Hopfield Neural Network
N. Kojic
2013-12-01
Full Text Available Transport network is a key factor of economic, social and every other form of development in the region and the state itself. One of the main conditions for transport network development is the construction of new routes. Often, the construction of regional roads is dominant, since the design and construction in urban areas is quite limited. The process of analysis and planning the new roads is a complex process that depends on many factors (the physical characteristics of the terrain, the economic situation, political decisions, environmental impact, etc. and can take several months. These factors directly or indirectly affect the final solution, and in combination with project limitations and requirements, sometimes can be mutually opposed. In this paper, we present one software solution that aims to find Pareto optimal path for preliminary design of the new roadway. The proposed algorithm is based on many different factors (physical and social with the ability of their increase. This solution is implemented using Hopfield's neural network, as a kind of artificial intelligence, which has shown very good results for solving complex optimization problems.
Illicit material detector based on gas sensors and neural networks
Grimaldi, Vincent; Politano, Jean-Luc
1997-02-01
In accordance with its missions, le Centre de Recherches et d'Etudes de la Logistique de la Police Nationale francaise (CREL) has been conducting research for the past few years targeted at detecting drugs and explosives. We have focused our approach of the underlying physical and chemical detection principles on solid state gas sensors, in the hope of developing a hand-held drugs and explosives detector. The CREL and Laboratory and Scientific Services Directorate are research partners for this project. Using generic hydrocarbon, industrially available, metal oxide sensors as illicit material detectors, requires usage precautions. Indeed, neither the product's concentrations, nor even the products themselves, belong to the intended usage specifications. Therefore, the CREL is currently investigating two major research topics: controlling the sensor's environment: with environmental control we improve the detection of small product concentration; determining detection thresholds: both drugs and explosives disseminate low gas concentration. We are attempting to quantify the minimal concentration which triggers detection. In the long run, we foresee a computer-based tool likely to detect a target gas in a noisy atmosphere. A neural network is the suitable tool for interpreting the response of heterogeneous sensor matrix. This information processing structure, alongside with proper sensor environment control, will lessen the repercussions of common MOS sensor sensitivity characteristic dispersion.
Neural Online Filtering Based on Preprocessed Calorimeter Data
Torres, R C; The ATLAS collaboration; Simas Filho, E F; De Seixas, J M
2009-01-01
Among LHC detectors, ATLAS aims at coping with such high event rate by designing a three-level online triggering system. The first level trigger output will be ~75 kHz. This level will mark the regions where relevant events were found. The second level will validate LVL1 decision by looking only at the approved data using full granularity. At the level two output, the event rate will be reduced to ~2 kHz. Finally, the third level will look at full event information and a rate of ~200 Hz events is expected to be approved, and stored in persistent media for further offline analysis. Many interesting events decay into electrons, which have to be identified from the huge background noise (jets). This work proposes a high-efficient LVL2 electron / jet discrimination system based on neural networks fed from preprocessed calorimeter information. The feature extraction part of the proposed system performs a ring structure of data description. A set of concentric rings centered at the highest energy cell is generated ...
Pattern recognition for electroencephalographic signals based on continuous neural networks.
Alfaro-Ponce, M; Argüelles, A; Chairez, I
2016-07-01
This study reports the design and implementation of a pattern recognition algorithm to classify electroencephalographic (EEG) signals based on artificial neural networks (NN) described by ordinary differential equations (ODEs). The training method for this kind of continuous NN (CNN) was developed according to the Lyapunov theory stability analysis. A parallel structure with fixed weights was proposed to perform the classification stage. The pattern recognition efficiency was validated by two methods, a generalization-regularization and a k-fold cross validation (k=5). The classifier was applied on two different databases. The first one was made up by signals collected from patients suffering of epilepsy and it is divided in five different classes. The second database was made up by 90 single EEG trials, divided in three classes. Each class corresponds to a different visual evoked potential. The pattern recognition algorithm achieved a maximum correct classification percentage of 97.2% using the information of the entire database. This value was similar to some results previously reported when this database was used for testing pattern classification. However, these results were obtained when only two classes were considered for the testing. The result reported in this study used the whole set of signals (five different classes). In comparison with similar pattern recognition methods that even considered less number of classes, the proposed CNN proved to achieve the same or even better correct classification results. PMID:27131469
Neural network-based QSAR and insecticide discovery: spinetoram.
Sparks, Thomas C; Crouse, Gary D; Dripps, James E; Anzeveno, Peter; Martynow, Jacek; Deamicis, Carl V; Gifford, James
2008-01-01
Improvements in the efficacy and spectrum of the spinosyns, novel fermentation derived insecticide, has long been a goal within Dow AgroSciences. As large and complex fermentation products identifying specific modifications to the spinosyns likely to result in improved activity was a difficult process, since most modifications decreased the activity. A variety of approaches were investigated to identify new synthetic directions for the spinosyn chemistry including several explorations of the quantitative structure activity relationships (QSAR) of spinosyns, which initially were unsuccessful. However, application of artificial neural networks (ANN) to the spinosyn QSAR problem identified new directions for improved activity in the chemistry, which subsequent synthesis and testing confirmed. The ANN-based analogs coupled with other information on substitution effects resulting from spinosyn structure activity relationships lead to the discovery of spinetoram (XDE-175). Launched in late 2007, spinetoram provides both improved efficacy and an expanded spectrum while maintaining the exceptional environmental and toxicological profile already established for the spinosyn chemistry. PMID:18344004
Mjalli, F.S.; Al-Asheh, S. [Chemical Engineering Department, Qatar University, Doha (Qatar)
2005-10-01
In this work advanced nonlinear neural networks based control system design algorithms are adopted to control a mechanistic model for an ethanol fermentation process. The process model equations for such systems are highly nonlinear. A neural network strategy has been implemented in this work for capturing the dynamics of the mechanistic model for the fermentation process. The neural network achieved has been validated against the mechanistic model. Two neural network based nonlinear control strategies have also been adopted using the model identified. The performance of the feedback linearization technique was compared to neural network model predictive control in terms of stability and set point tracking capabilities. Under servo conditions, the feedback linearization algorithm gave comparable tracking and stability. The feedback linearization controller achieved the control target faster than the model predictive one but with vigorous and sudden controller moves. (Abstract Copyright [2005], Wiley Periodicals, Inc.)
EMP response modeling of TVS based on the recurrent neural network
Zhiqiang JI
2015-04-01
Full Text Available Due to the larger workload in the implementation process and the poor consistence between the test results and actual situation problems when using the transmission line pulse (TLP testing methods, a modeling method based on the recurrent neural network is proposed for EMP response forecast. Based on the TLP testing system, two categories of EMP are increased, which are the machine model ESD EMP and human metal model ESD EMP. Elman neural network, Jordan neural network and their combination namely Elman-Jordan neural network are established for response modeling of NUP2105L transient voltage suppressor (TVS forecasting the response under different EMP. The simulation results show that the recurrent neural network has satisfying modeling effects and high computation efficiency.
Gain Scheduling Control of Nonlinear Systems Based on Neural State Space Models
Bendtsen, Jan Dimon; Stoustrup, Jakob
2003-01-01
This paper presents a novel method for gain scheduling control of nonlinear systems based on extraction of local linear state space models from neural networks with direct application to robust control. A neural state space model of the system is first trained based on in- and output training...... samples from the system, after which linearized state space models are extracted from the neural network in a number of operating points according to a simple and computationally cheap scheme. Robust observer-based controllers can then be designed in each of these operating points,and gain scheduling...
Extended Kalman Filter Based Neural Networks Controller For Hot Strip Rolling mill
The present paper deals with the application of an Extended Kalman filter based adaptive Neural-Network control scheme to improve the performance of a hot strip rolling mill. The suggested Neural Network model was implemented using Bayesian Evidence based training algorithm. The control input was estimated iteratively by an on-line extended Kalman filter updating scheme basing on the inversion of the learned neural networks model. The performance of the controller is evaluated using an accurate model estimated from real rolling mill input/output data, and the usefulness of the suggested method is proved
HAN Liu-xin; WANG Huan-chen; ZHANG Xian-hui
2001-01-01
A detailed study of the capabilities of artificial neural networks to diagnoses cracks in massive concrete structures is presented. This paper includes the components of the expert system such as design thought, basic structure, building of knowledge base and the implementation of neural network applied model. The realizing method of neural network based clustering algorithm in the knowledge base and selfstudy is analyzed emphatically and stimulated by means of the computer. From the above study, some important conclusions have been drawn and some new viewpoints have been suggested.
A novel compensation-based recurrent fuzzy neural network and its learning algorithm
WU Bo; WU Ke; LU JianHong
2009-01-01
Based on detailed atudy on aeveral kinds of fuzzy neural networks, we propose a novel compensation. based recurrent fuzzy neural network (CRFNN) by adding recurrent element and compensatory element to the conventional fuzzy neural network. Then, we propose a sequential learning method for the structure Identification of the CRFNN In order to confirm the fuzzy rules and their correlaUve parameters effectively. Furthermore, we Improve the BP algorithm based on the characteristics of the proposed CRFNN to train the network. By modeling the typical nonlinear systems, we draw the conclusion that the proposed CRFNN has excellent dynamic response and strong learning ability.
Zhang, Wei; Li, Chuandong; Huang, Tingwen; He, Xing
2015-12-01
Synchronization of an array of linearly coupled memristor-based recurrent neural networks with impulses and time-varying delays is investigated in this brief. Based on the Lyapunov function method, an extended Halanay differential inequality and a new delay impulsive differential inequality, some sufficient conditions are derived, which depend on impulsive and coupling delays to guarantee the exponential synchronization of the memristor-based recurrent neural networks. Impulses with and without delay and time-varying delay are considered for modeling the coupled neural networks simultaneously, which renders more practical significance of our current research. Finally, numerical simulations are given to verify the effectiveness of the theoretical results. PMID:26054076
Neural network-based H∞ filtering for nonlinear systems with time-delays
无
2008-01-01
A novel H∞ design methodology for a neural network-based nonlinear filtering scheme is addressed.Firstly,neural networks are employed to approximate the nonlinearities.Next,the nonlinear dynamic system is represented by the mode-dependent linear difference inclusion (LDI).Finally,based on the LDI model,a neural network-based nonlinear filter (NNBNF) is developed to minimize the upper bound of H∞ gain index of the estimation error under some linear matrix inequality (LMI) constraints.Compared with the existing nonlinear filters,NNBNF is time-invariant and numerically tractable.The validity and applicability of the proposed approach are successfully demonstrated in an illustrative example.
Summing up the Euler [phi] Function
Loomis, Paul; Plytage, Michael; Polhill, John
2008-01-01
The Euler [phi] function counts the number of positive integers less than and relatively prime to a positive integer n. Here we look at perfect totient numbers, number for which [phi](n) + [phi]([phi](n)) + [phi]([phi]([phi](n))) + ... + 1 = n.
ECG Signal Recognition based on Wavelet Transform Using Neural and Fuzzy Logic
H. M. Abdul-Ridha
2008-01-01
Full Text Available This work presents aneural and fuzzy based ECG signal recognition system based on wavelet transform. The suitable coefficients that can be used as a feature for each fuzzy network or neural network is found using a proposed best basis technique. Using the proposed best bases reduces the dimension of the input vector and hence reduces the complexity of the classifier. The fuzzy network and the neural network parameters are learned using back propagation algorithm.
Neural Synchronization based Secret Key Exchange over Public Channels: A survey
Chakraborty, Sandip; Dalal, Jiban; Sarkar, Bikramjit; Mukherjee, Debaprasad
2015-01-01
Exchange of secret keys over public channels based on neural synchronization using a variety of learning rules offer an appealing alternative to number theory based cryptography algorithms. Though several forms of attacks are possible on this neural protocol e.g. geometric, genetic and majority attacks, our survey finds that deterministic algorithms that synchronize with the end-point networks have high time complexity, while probabilistic and population-based algorithms have demonstrated abi...
EM-based optimization of microwave circuits using artificial neural networks: the state of the art
Rayas-Sánchez, José E.
2004-01-01
This paper reviews the current state-of-the-art in electromagnetic (EM)-based design and optimization of microwave circuits using artificial neural networks (ANNs). Measurement-based design of microwave circuits using ANNs is also reviewed. The conventional microwave neural optimization approach is surveyed, along with typical enhancing techniques, such as segmentation, decomposition, hierarchy, design of experiments and clusterization. Innovative strategies for ANN-based design exploiting...
ECG Signal Recognition based on Wavelet Transform Using Neural and Fuzzy Logic
H. M. Abdul-Ridha; Abduladhem Abdulkareem Ali
2008-01-01
This work presents aneural and fuzzy based ECG signal recognition system based on wavelet transform. The suitable coefficients that can be used as a feature for each fuzzy network or neural network is found using a proposed best basis technique. Using the proposed best bases reduces the dimension of the input vector and hence reduces the complexity of the classifier. The fuzzy network and the neural network parameters are learned using back propagation algorithm.
Euler Integration of Gaussian Random Fields and Persistent Homology
Bobrowski, Omer
2010-01-01
In this paper we extend the notion of the Euler characteristic to persistent homology and give the relationship between the Euler integral of a function and the Euler characteristic of the function's persistent homology. We then proceed to compute the expected Euler integral of a Gaussian random field using the Gaussian kinematic formula and obtain a simple closed form expression. This results in the first computation of a quantitative descriptor for the persistent homology of a Gaussian random field.
A New Regularization of the One-Dimensional Euler and Homentropic Euler Equations
Norgard, Gregory
2009-01-01
This paper examines an averaging technique in which the nonlinear flux term is expanded and the convective velocities are passed through a low-pass filter. It is the intent that this modification to the nonlinear flux terms will result in an inviscid regularization of the homentropic Euler equations and Euler equations. The physical motivation for this technique is presented and a general method is derived, which is then applied to the homentropic Euler equations and Euler equations. These modified equations are then examined, discovering that they share the conservative properties and traveling wave solutions with the original equations. As the averaging is diminished it is proven that the solutions converge to weak solutions of the original equations. Finally, numerical simulations are conducted finding that the regularized equations appear smooth and capture the relevant behavior in shock tube simulations.
Lag Synchronization of Memristor-Based Coupled Neural Networks via ω-Measure.
Li, Ning; Cao, Jinde
2016-03-01
This paper deals with the lag synchronization problem of memristor-based coupled neural networks with or without parameter mismatch using two different algorithms. Firstly, we consider the memristor-based neural networks with parameter mismatch, lag complete synchronization cannot be achieved due to parameter mismatch, the concept of lag quasi-synchronization is introduced. Based on the ω-measure method and generalized Halanay inequality, the error level is estimated, a new lag quasi-synchronization scheme is proposed to ensure that coupled memristor-based neural networks are in a state of lag synchronization with an error level. Secondly, by constructing Lyapunov functional and applying common Halanary inequality, several lag complete synchronization criteria for the memristor-based neural networks with parameter match are given, which are easy to verify. Finally, two examples are given to illustrate the effectiveness of the proposed lag quasi-synchronization or lag complete synchronization criteria, which well support theoretical results. PMID:26462246
Neural network based method for conversion of solar radiation data
Highlights: ► Generalized regression neural network is used to predict the solar radiation on tilted surfaces. ► The above network, amongst many such as multilayer perceptron, is the most successful one. ► The present neural network returns a relative mean absolute error value of 9.1%. ► The present model leads to a mean absolute error value of estimate of 14.9 Wh/m2. - Abstract: The receiving ends of the solar energy conversion systems that generate heat or electricity from radiation is usually tilted at an optimum angle to increase the solar incident on the surface. Solar irradiation data measured on horizontal surfaces is readily available for many locations where such solar energy conversion systems are installed. Various equations have been developed to convert solar irradiation data measured on horizontal surface to that on tilted one. These equations constitute the conventional approach. In this article, an alternative approach, generalized regression type of neural network, is used to predict the solar irradiation on tilted surfaces, using the minimum number of variables involved in the physical process, namely the global solar irradiation on horizontal surface, declination and hour angles. Artificial neural networks have been successfully used in recent years for optimization, prediction and modeling in energy systems as alternative to conventional modeling approaches. To show the merit of the presently developed neural network, the solar irradiation data predicted from the novel model was compared to that from the conventional approach (isotropic and anisotropic models), with strict reference to the irradiation data measured in the same location. The present neural network model was found to provide closer solar irradiation values to the measured than the conventional approach, with a mean absolute error value of 14.9 Wh/m2. The other statistical values of coefficient of determination and relative mean absolute error also indicate the advantage of
A case study to estimate costs using Neural Networks and regression based models
Nadia Bhuiyan
2012-07-01
Full Text Available Bombardier Aerospace’s high performance aircrafts and services set the utmost standard for the Aerospace industry. A case study in collaboration with Bombardier Aerospace is conducted in order to estimate the target cost of a landing gear. More precisely, the study uses both parametric model and neural network models to estimate the cost of main landing gears, a major aircraft commodity. A comparative analysis between the parametric based model and those upon neural networks model will be considered in order to determine the most accurate method to predict the cost of a main landing gear. Several trials are presented for the design and use of the neural network model. The analysis for the case under study shows the flexibility in the design of the neural network model. Furthermore, the performance of the neural network model is deemed superior to the parametric models for this case study.
A Study on Integrated Wavelet Neural Networks in Fault Diagnosis Based on Information Fusion
ANG Xue-ye
2007-01-01
The tight wavelet neural network was constituted by taking the nonlinear Morlet wavelet radices as the excitation function. The idiographic algorithm was presented. It combined the advantages of wavelet analysis and neural networks. The integrated wavelet neural network fault diagnosis system was set up based on both the information fusion technology and actual fault diagnosis, which took the sub-wavelet neural network as primary diagnosis from different sides, then came to the conclusions through decision-making fusion. The realizable policy of the diagnosis system and established principle of the sub-wavelet neural networks were given . It can be deduced from the examples that it takes full advantage of diversified characteristic information, and improves the diagnosis rate.
Identification Method of Sports Throwing Force Based on Fuzzy Neural Network
Rui Su
2013-07-01
Full Text Available In order to speed up the defects of the neural network computing and recognition, the essay proposes the information identification method research of sports throwing force based on the fuzzy neural network model. Firstly, I use the information, which is the combination of the wavelet transformation and the fuzzy neural network, to identify the new method combining and make the noise-suppressed processing of information. Then, according to the athlete’s throwing action and the extraction of signal processing characteristics, as well as the analysis of the fuzzy neural network algorithm. Finally, in order to verify the effectiveness of the proposed algorithm, I make analysis for the experimental results, which indicates that using this algorithm can not only have less noise than the traditional algorithm, but also have less number of the neural network computation. Besides, its recognition speed and accuracy is also higher.
Application of a real neural collision avoidance system based on the locust to AGV navigation
Rind, F. C.; Allen, Charles R.
1992-11-01
The superb aereal performance of flying insects is achieved with comparatively simple neural machinery. Insects react rapidly to changing visual images. The abilities of insects to perform these computations in real time has already led to a successful prototype autonomous guided vehicle with a sensor and control structure modelled on the fly eye. Increasingly in visual neuroscience it is possible to isolate the critical image cues used by identified neurones to achieve a selective response to a feature or group of features within the changing visual image. In this paper we describe a biological neural network based on the input organization of such an identified motion detecting neurone, which responds selectively to the images of an object approaching on a collision course with the animal. We compare the response of the artificial neural network with the biological neural network in the same colliding stimulus. This approach led to a series of testable predictions about the organization of the biological neural network.