Nguyen-Truong, Hieu T.; Le, Hung M.
2015-06-01
We present in this study a new and robust algorithm for feed-forward neural network (NN) fitting. This method is developed for the application in potential energy surface (PES) construction, in which simultaneous energy-gradient fitting is implemented using the well-established Levenberg-Marquardt (LM) algorithm. Three fitting examples are demonstrated, which include the vibrational PES of H2O, reactive PESs of O3 and ClOOCl. In the three testing cases, our new LM implementation has been shown to work very efficiently. Not only increasing fitting accuracy, it also offers two other advantages: less training iterations are utilized and less data points are required for fitting.
Additive Feed Forward Control with Neural Networks
Sørensen, O.
1999-01-01
This paper demonstrates a method to control a non-linear, multivariable, noisy process using trained neural networks. The basis for the method is a trained neural network controller acting as the inverse process model. A training method for obtaining such an inverse process model is applied....... A suitable 'shaped' (low-pass filtered) reference is used to overcome problems with excessive control action when using a controller acting as the inverse process model. The control concept is Additive Feed Forward Control, where the trained neural network controller, acting as the inverse process model......, is placed in a supplementary pure feed-forward path to an existing feedback controller. This concept benefits from the fact, that an existing, traditional designed, feedback controller can be retained without any modifications, and after training the connection of the neural network feed-forward controller...
Additive Feed Forward Control with Neural Networks
Sørensen, O.
1999-01-01
This paper demonstrates a method to control a non-linear, multivariable, noisy process using trained neural networks. The basis for the method is a trained neural network controller acting as the inverse process model. A training method for obtaining such an inverse process model is applied....... A suitable 'shaped' (low-pass filtered) reference is used to overcome problems with excessive control action when using a controller acting as the inverse process model. The control concept is Additive Feed Forward Control, where the trained neural network controller, acting as the inverse process model......, is placed in a supplementary pure feed-forward path to an existing feedback controller. This concept benefits from the fact, that an existing, traditional designed, feedback controller can be retained without any modifications, and after training the connection of the neural network feed-forward controller...
Patterns of synchrony for feed-forward and auto-regulation feed-forward neural networks.
Aguiar, Manuela A D; Dias, Ana Paula S; Ferreira, Flora
2017-01-01
We consider feed-forward and auto-regulation feed-forward neural (weighted) coupled cell networks. In feed-forward neural networks, cells are arranged in layers such that the cells of the first layer have empty input set and cells of each other layer receive only inputs from cells of the previous layer. An auto-regulation feed-forward neural coupled cell network is a feed-forward neural network where additionally some cells of the first layer have auto-regulation, that is, they have a self-loop. Given a network structure, a robust pattern of synchrony is a space defined in terms of equalities of cell coordinates that is flow-invariant for any coupled cell system (with additive input structure) associated with the network. In this paper, we describe the robust patterns of synchrony for feed-forward and auto-regulation feed-forward neural networks. Regarding feed-forward neural networks, we show that only cells in the same layer can synchronize. On the other hand, in the presence of auto-regulation, we prove that cells in different layers can synchronize in a robust way and we give a characterization of the possible patterns of synchrony that can occur for auto-regulation feed-forward neural networks.
A new C++ implemented feed forward neural network simulator
J. Sütő
2013-12-01
Full Text Available This paper presents the implementation of a simulator application for feed forward neural networks which was made in Qt application framework. The paper demonstrates the object oriented design and the performance of the software. The main topics cover the class organization and some test results where the Matlab neural network toolbox was used as reference.
PSO optimized Feed Forward Neural Network for offline Signature Classification
Pratik R. Hajare
2015-07-01
Full Text Available The paper is based on feed forward neural network (FFNN optimization by particle swarm intelligence (PSI used to provide initial weights and biases to train neural network. Once the weights and biases are found using Particle swarm optimization (PSO with neural network used as training algorithm for specified epoch, the same are used to train the neural network for training and classification of benchmark problems. Further the approach is tested for offline signature classifications. A comparison is made between normal FFNN with random weights and biases and FFNN with particle swarm optimized weights and biases. Firstly, the performance is tested on two benchmark databases for neural network, The Breast Cancer Database and the Diabetic Database. Result shows that neural network performs better with initial weights and biases obtained by Particle Swarm optimization. The network converges faster with PSO obtained initial weights and biases for FFNN and classification accuracy is increased.
Review of feed forward neural network classification preprocessing techniques
Asadi, Roya; Kareem, Sameem Abdul
2014-06-01
The best feature of artificial intelligent Feed Forward Neural Network (FFNN) classification models is learning of input data through their weights. Data preprocessing and pre-training are the contributing factors in developing efficient techniques for low training time and high accuracy of classification. In this study, we investigate and review the powerful preprocessing functions of the FFNN models. Currently initialization of the weights is at random which is the main source of problems. Multilayer auto-encoder networks as the latest technique like other related techniques is unable to solve the problems. Weight Linear Analysis (WLA) is a combination of data pre-processing and pre-training to generate real weights through the use of normalized input values. The FFNN model by using the WLA increases classification accuracy and improve training time in a single epoch without any training cycle, the gradient of the mean square error function, updating the weights. The results of comparison and evaluation show that the WLA is a powerful technique in the FFNN classification area yet.
Feed-forward neural network model for hunger and satiety related VAS score prediction
Krishnan, S.; Hendriks, H.F.J.; Hartvigsen, M.L.; Graaf, A.A. de
2016-01-01
Background: An artificial neural network approach was chosen to model the outcome of the complex signaling pathways in the gastro-intestinal tract and other peripheral organs that eventually produce the satiety feeling in the brain upon feeding. Methods: A multilayer feed-forward neural network was
Feed-forward neural network model for hunger and satiety related VAS score prediction
Krishnan, S.; Hendriks, H.F.J.; Hartvigsen, M.L.; Graaf, A.A. de
2016-01-01
Background: An artificial neural network approach was chosen to model the outcome of the complex signaling pathways in the gastro-intestinal tract and other peripheral organs that eventually produce the satiety feeling in the brain upon feeding. Methods: A multilayer feed-forward neural network was
Using Hybrid Algorithm to Improve Intrusion Detection in Multi Layer Feed Forward Neural Networks
Ray, Loye Lynn
2014-01-01
The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and…
Using Hybrid Algorithm to Improve Intrusion Detection in Multi Layer Feed Forward Neural Networks
Ray, Loye Lynn
2014-01-01
The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and…
Instantaneous Gradient Based Dual Mode Feed-Forward Neural Network Blind Equalization Algorithm
Ying Xiao
2013-01-01
Full Text Available To further improve the performance of feed-forward neural network blind equalization based on Constant Modulus Algorithm (CMA cost function, an instantaneous gradient based dual mode between Modified Constant Modulus Algorithm (MCMA and Decision Directed (DD algorithm was proposed. The neural network weights change quantity of the adjacent iterative process is defined as instantaneous gradient. After the network converges, the weights of neural network to achieve a stable energy state and the instantaneous gradient would be zero. Therefore dual mode algorithm can be realized by criterion which set according to the instantaneous gradient. Computer simulation results show that the dual mode feed-forward neural network blind equalization algorithm proposed in this study improves the convergence rate and convergence precision effectively, at the same time, has good restart and tracking ability under channel burst interference condition.
Feed-forward neural network model for hunger and satiety related VAS score prediction
Krishnan, S.; Hendriks, H. F. J.; Hartvigsen, M.L.; Graaf, A.A. de
2016-01-01
Background: An artificial neural network approach was chosen to model the outcome of the complex signaling pathways in the gastro-intestinal tract and other peripheral organs that eventually produce the satiety feeling in the brain upon feeding. Methods: A multilayer feed-forward neural network was trained with sets of experimental data relating concentration-time courses of plasma satiety hormones to Visual Analog Scales (VAS) scores. The network successfully predicted VAS responses from set...
Single-hidden-layer feed-forward quantum neural network based on Grover learning.
Liu, Cheng-Yi; Chen, Chein; Chang, Ching-Ter; Shih, Lun-Min
2013-09-01
In this paper, a novel single-hidden-layer feed-forward quantum neural network model is proposed based on some concepts and principles in the quantum theory. By combining the quantum mechanism with the feed-forward neural network, we defined quantum hidden neurons and connected quantum weights, and used them as the fundamental information processing unit in a single-hidden-layer feed-forward neural network. The quantum neurons make a wide range of nonlinear functions serve as the activation functions in the hidden layer of the network, and the Grover searching algorithm outstands the optimal parameter setting iteratively and thus makes very efficient neural network learning possible. The quantum neuron and weights, along with a Grover searching algorithm based learning, result in a novel and efficient neural network characteristic of reduced network, high efficient training and prospect application in future. Some simulations are taken to investigate the performance of the proposed quantum network and the result show that it can achieve accurate learning.
Jingzhou Fei
2016-01-01
Full Text Available In this article, a novel artificial neural network integrating feed-forward back-propagation neural network with Gaussian kernel function is proposed for the prediction of compressor performance map. To demonstrate the potential capability of the proposed approach for the typical interpolated and extrapolated predictions, other two classical data-driven modeling methods including feed-forward back-propagation neural network and support vector machine are compared. An assessment is performed and discussed on the sensitivity of different models to the number of training samples (48 training samples, 32 training samples, and 18 training samples. All the results indicate that the proposed neural network in this article has superior prediction performance to the existing feed-forward back-propagation neural network and support vector machine, especially for the extrapolation with small samples. Furthermore, this study can be utilized in refining the existing performance-based modeling for improved simulation analysis, condition monitoring, and fault diagnosis of gas turbine compressor.
FANG Jun-long; ZHANG Chang-li; WANG Shu-wen
2004-01-01
We set up computer vision system for tomato images. By using this system, the RGB value of tomato image was converted into HIS value whose H was used to acquire the color character of the surface of tomato. To use multilayer feed forward neural network with GA can finish automatic identification of tomato maturation. The results of experiment showed that the accuracy was upto 94%.
Automatic identification of terpenoid skeletons by feed-forward neural networks
Emerenciano, Vicente P. [Instituto de Quimica, Universidade de Sao Paulo, Caixa Postal 26077, 05513-970 Sao Paulo, SP (Brazil)]. E-mail: vdpemere@iq.usp.br; Alvarenga, Sandra A.V. [Faculdade de Engenharia de Guaratingueta, UNESP, CEP 12516-410, Guaratingueta, Sao Paulo (Brazil); Scotti, Marcus Tullius [Instituto de Quimica, Universidade de Sao Paulo, Caixa Postal 26077, 05513-970 Sao Paulo, SP (Brazil); Ferreira, Marcelo J.P. [Instituto de Quimica, Universidade de Sao Paulo, Caixa Postal 26077, 05513-970 Sao Paulo, SP (Brazil); Stefani, Ricardo [Departamento de Quimica, FFCLRP, USP, Av. Bandeirantes 3900, CEP 14040-905, Ribeirao Preto, Sao Paulo (Brazil); Nuzillard, Jean-Marc [FRE 2715, University of Reims, Moulin de la Housse, BP 1039, 51687 REIMS Cedex 2 (France)
2006-10-10
Feed-forward neural networks (FFNNs) were used to predict the skeletal type of molecules belonging to six classes of terpenoids. A database that contains the {sup 13}C NMR spectra of about 5000 compounds was used to train the FFNNs. An efficient representation of the spectra was designed and the constitution of the best FFNN input vector format resorted from an heuristic approach. The latter was derived from general considerations on terpenoid structures.
Feed Forward Neural Network and Optimal Control Problem with Control and State Constraints
Kmet', Tibor; Kmet'ová, Mária
2009-09-01
A feed forward neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints. The paper extends adaptive critic neural network architecture proposed by [5] to the optimal control problems with control and state constraints. The optimal control problem is transcribed into a nonlinear programming problem which is implemented with adaptive critic neural network. The proposed simulation method is illustrated by the optimal control problem of nitrogen transformation cycle model. Results show that adaptive critic based systematic approach holds promise for obtaining the optimal control with control and state constraints.
CHAI Yu-hua; PAN Wei; NING Hai-long
2005-01-01
In the paper, a method of building mathematic model employing genetic multilayer feed forward neural network is presented, and the quantitative relationship of chemical measured values and near-infrared spectral data is established. In the paper, quantitative mathematic model related chemical assayed values and near-infrared spectral data is established by means of genetic multilayer feed forward neural network, acquired near-infrared spectral data are taken as input of network with the content of five kinds of fat acids tested from chemical method as output,weight values of multilayer feed forward neural network are trained by genetic algorithms and detection model of neural network of soybean is built. A kind of multilayer feed forward neural network trained by genetic algorithms is designed in the paper. Through experiments, all the related coefficients of five fat acids can approach 0.9 which satisfies the preliminary test of soybean breeding.
Selection of hadronic W-decays in DELPHI with feed forward neural networks - An update
Becks, K H; Müller, U; Wahlen, H
2003-01-01
Since 1998 feed forward neural networks have been successfully applied to select candidates of hadronic W-decays measured at different center of mass-energies by the DELPHI collaboration at the Large Electron Positron collider at CERN. To prepare the final publication, the neural network was adapted to all center of mass- energies. Detailed studies were performed concerning the level of preselection, the choice of network parameters and especially of the network architecture. The number of hidden nodes was optimized by testing different pruning methods. All studies and results will be discussed.
Improving the character recognition efficiency of feed forward BP neural network
Choudhary, Amit
2011-01-01
This work is focused on improving the character recognition capability of feed-forward back-propagation neural network by using one, two and three hidden layers and the modified additional momentum term. 182 English letters were collected for this work and the equivalent binary matrix form of these characters was applied to the neural network as training patterns. While the network was getting trained, the connection weights were modified at each epoch of learning. For each training sample, the error surface was examined for minima by computing the gradient descent. We started the experiment by using one hidden layer and the number of hidden layers was increased up to three and it has been observed that accuracy of the network was increased with low mean square error but at the cost of training time. The recognition accuracy was improved further when modified additional momentum term was used.
Single-Iteration Learning Algorithm for Feed-Forward Neural Networks
Barhen, J.; Cogswell, R.; Protopopescu, V.
1999-07-31
A new methodology for neural learning is presented, whereby only a single iteration is required to train a feed-forward network with near-optimal results. To this aim, a virtual input layer is added to the multi-layer architecture. The virtual input layer is connected to the nominal input layer by a specird nonlinear transfer function, and to the fwst hidden layer by regular (linear) synapses. A sequence of alternating direction singular vrdue decompositions is then used to determine precisely the inter-layer synaptic weights. This algorithm exploits the known separability of the linear (inter-layer propagation) and nonlinear (neuron activation) aspects of information &ansfer within a neural network.
An Adaptive Recursive Least Square Algorithm for Feed Forward Neural Network and Its Application
Qing, Xi-Hong; Xu, Jun-Yi; Guo, Fen-Hong; Feng, Ai-Mu; Nin, Wei; Tao, Hua-Xue
In high dimension data fitting, it is difficult task to insert new training samples and remove old-fashioned samples for feed forward neural network (FFNN). This paper, therefore, studies dynamical learning algorithms with adaptive recursive regression (AR) and presents an advanced adaptive recursive (AAR) least square algorithm. This algorithm can efficiently handle new samples inserting and old samples removing. This AAR algorithm is applied to train FFNN and makes FFNN be capable of simultaneously implementing three processes of new samples dynamical learning, old-fashioned samples removing and neural network (NN) synchronization computing. It efficiently solves the problem of dynamically training of FFNN. This FFNN algorithm is carried out to compute residual oil distribution.
3D Polygon Mesh Compression with Multi Layer Feed Forward Neural Networks
Emmanouil Piperakis
2003-06-01
Full Text Available In this paper, an experiment is conducted which proves that multi layer feed forward neural networks are capable of compressing 3D polygon meshes. Our compression method not only preserves the initial accuracy of the represented object but also enhances it. The neural network employed includes the vertex coordinates, the connectivity and normal information in one compact form, converting the discrete and surface polygon representation into an analytic, solid colloquial. Furthermore, the 3D object in its compressed neural form can be directly - without decompression - used for rendering. The neural compression - representation is viable to 3D transformations without the need of any anti-aliasing techniques - transformations do not disrupt the accuracy of the geometry. Our method does not su.er any scaling problem and was tested with objects of 300 to 107 polygons - such as the David of Michelangelo - achieving in all cases an order of O(b3 less bits for the representation than any other commonly known compression method. The simplicity of our algorithm and the established mathematical background of neural networks combined with their aptness for hardware implementation can establish this method as a good solution for polygon compression and if further investigated, a novel approach for 3D collision, animation and morphing.
Content Based Image Retrieval using Novel Gaussian Fuzzy Feed Forward-Neural Network
C. R.B. Durai
2011-01-01
Full Text Available Problem statement: With extensive digitization of images, diagrams and paintings, traditional keyword based search has been found to be inefficient for retrieval of the required data. Content-Based Image Retrieval (CBIR system responds to image queries as input and relies on image content, using techniques from computer vision and image processing to interpret and understand it, while using techniques from information retrieval and databases to rapidly locate and retrieve images suiting an input query. CBIR finds extensive applications in the field of medicine as it assists a doctor to make better decisions by referring the CBIR system and gain confidence. Approach: Various methods have been proposed for CBIR using image low level image features like histogram, color layout, texture and analysis of the image in the frequency domain. Similarly various classification algorithms like Naïve Bayes classifier, Support Vector Machine, Decision tree induction algorithms and Neural Network based classifiers have been studied extensively. We proposed to extract features from an image using Discrete Cosine Transform, extract relevant features using information gain and Gaussian Fuzzy Feed Forward Neural Network algorithm for classification. Results and Conclusion: We apply our proposed procedure to 180 brain MRI images of which 72 images were used for testing and the remaining for training. The classification accuracy obtained was 95.83% for a three class problem. This research focused on a narrow search, where further investigation is needed to evaluate larger classes.
Forecasting Performance of Random Walk with Drift and Feed Forward Neural Network Models
Augustine D. Pwasong
2015-08-01
Full Text Available In this study, linear and nonlinear methods were used to model forecasting performances on the daily crude oil production data of the Nigerian National Petroleum Corporation (NNPC. The linear model considered here is the random walk with drift, while the nonlinear model is the feed forward neural network model. The results indicate that nonlinear methods have better forecasting performance greater than linear methods based on the mean error square sense. The root mean square error (RMSE and the mean absolute error (MAE were applied to ascertain the assertion that nonlinear methods have better forecasting performance greater than linear methods. Autocorrelation functions emerging from the increment series, that is, log difference series and difference series of the daily crude oil production data of the NNPC indicates significant autocorrelations. As a result of the foregoing assertion we deduced that the daily crude oil production series of the NNPC is not firmly a random walk process. However, the original daily crude oil production series of the NNPC was considered to be a random walk with drift when we are not trying to forecast immediate values. The analysis for this study was simulated using MATLAB software, version 8.03
Feed Forward Neural Network Based Eye Localization and Recognition Using Hough Transform
Shylaja S S, K N Balasubramanya Murthy, S Natarajan Nischith, Muthuraj R, Ajay S
2011-03-01
Full Text Available Eye detection is a pre-requisite stage for many applications such as face recognition, iris recognition, eye tracking, fatigue detection based on eye-blink count and eye-directed instruction control. As the location of the eyes is a dominant feature of the face it can be used as an input to the face recognition engine. In this direction, the paper proposed here localizes eye positions using Hough Transformed (HT coefficients, which are found to be good at extracting geometrical components from any given object. The method proposed here uses circular and elliptical features of eyes in localizing them from a given face. Such geometrical features can be very efficiently extracted using the HT technique. The HT is based on a evidence gathering approach where the evidence is the ones cast in an accumulator array. The purpose of the technique is to find imperfect instances of objects within a certain class of shapes by a voting procedure. Feed forward neural network has been used for classification of eyes and non-eyes as the dimension of the data is large in nature. Experiments have been carried out on standard databases as well as on local DB consisting of gray scale images. The outcome of this technique has yielded very satisfactory results with an accuracy of 98.68%
Hossein Jafari Mansoorian
2017-01-01
Full Text Available Background & Aims of the Study: A feed forward artificial neural network (FFANN was developed to predict the efficiency of total petroleum hydrocarbon (TPH removal from a contaminated soil, using soil washing process with Tween 80. The main objective of this study was to assess the performance of developed FFANN model for the estimation of TPH removal. Materials and Methods: Several independent repressors including pH, shaking speed, surfactant concentration and contact time were used to describe the removal of TPH as a dependent variable in a FFANN model. 85% of data set observations were used for training the model and remaining 15% were used for model testing, approximately. The performance of the model was compared with linear regression and assessed, using Root of Mean Square Error (RMSE as goodness-of-fit measure Results: For the prediction of TPH removal efficiency, a FANN model with a three-hidden-layer structure of 4-3-1 and a learning rate of 0.01 showed the best predictive results. The RMSE and R2 for the training and testing steps of the model were obtained to be 2.596, 0.966, 10.70 and 0.78, respectively. Conclusion: For about 80% of the TPH removal efficiency can be described by the assessed regressors the developed model. Thus, focusing on the optimization of soil washing process regarding to shaking speed, contact time, surfactant concentration and pH can improve the TPH removal performance from polluted soils. The results of this study could be the basis for the application of FANN for the assessment of soil washing process and the control of petroleum hydrocarbon emission into the environments.
Mr. M. Karthik
2014-05-01
Full Text Available Artificial Neural Network (ANN has become a significant modeling tool for predicting the performance of complex systems that provide appropriate mapping between input-output variables without acquiring any empirical relationship due to the intrinsic properties. This paper is focussed towards the modeling of Proton Exchange Membrane (PEM Fuel Cell system using Artificial Neural Networks especially for automotive applications. Three different neural networks such as Static Feed Forward Network (SFFN, Cascaded Feed Forward Network (CFFN & Fully Connected Dynamic Recurrent Network (FCRN are discussed in this paper for modeling the PEM Fuel Cell System. The numerical analysis is carried out between the three Neural Network architectures for predicting the output performance of the PEM Fuel Cell. The performance of the proposed Networks is evaluated using various error criteria such as Mean Square Error, Mean Absolute Percentage Error, Mean Absolute Error, Coefficient of correlation and Iteration Values. The optimum network with high performance indices (low prediction error values and iteration values can be used as an ancillary model in developing the PEM Fuel Cell powered vehicle system. The development of the fuel cell driven vehicle model also incorporates the modeling of DC-DC Power Converter and Vehicle Dynamics. Finally the Performance of the Electric vehicle model is analyzed for two different drive cycle such as M-NEDC & M-UDDS.
P. Pahlavani
2017-09-01
Full Text Available This paper presents an indoor positioning technique based on a multi-layer feed-forward (MLFF artificial neural networks (ANN. Most of the indoor received signal strength (RSS-based WLAN positioning systems use the fingerprinting technique that can be divided into two phases: the offline (calibration phase and the online (estimation phase. In this paper, RSSs were collected for all references points in four directions and two periods of time (Morning and Evening. Hence, RSS readings were sampled at a regular time interval and specific orientation at each reference point. The proposed ANN based model used Levenberg–Marquardt algorithm for learning and fitting the network to the training data. This RSS readings in all references points and the known position of these references points was prepared for training phase of the proposed MLFF neural network. Eventually, the average positioning error for this network using 30% check and validation data was computed approximately 2.20 meter.
Asal Kzar, Ahmed; Mat Jafri, M. Z.; Hwee San, Lim; Al-Zuky, Ali A.; Mutter, Kussay N.; Hassan Al-Saleh, Anwar
2016-06-01
There are many techniques that have been given for water quality problem, but the remote sensing techniques have proven their success, especially when the artificial neural networks are used as mathematical models with these techniques. Hopfield neural network is one type of artificial neural networks which is common, fast, simple, and efficient, but it when it deals with images that have more than two colours such as remote sensing images. This work has attempted to solve this problem via modifying the network that deals with colour remote sensing images for water quality mapping. A Feed-forward Hopfield Neural Network Algorithm (FHNNA) was modified and used with a satellite colour image from type of Thailand earth observation system (THEOS) for TSS mapping in the Penang strait, Malaysia, through the classification of TSS concentrations. The new algorithm is based essentially on three modifications: using HNN as feed-forward network, considering the weights of bitplanes, and non-self-architecture or zero diagonal of weight matrix, in addition, it depends on a validation data. The achieved map was colour-coded for visual interpretation. The efficiency of the new algorithm has found out by the higher correlation coefficient (R=0.979) and the lower root mean square error (RMSE=4.301) between the validation data that were divided into two groups. One used for the algorithm and the other used for validating the results. The comparison was with the minimum distance classifier. Therefore, TSS mapping of polluted water in Penang strait, Malaysia, can be performed using FHNNA with remote sensing technique (THEOS). It is a new and useful application of HNN, so it is a new model with remote sensing techniques for water quality mapping which is considered important environmental problem.
Lary, David J.; Mussa, Yussuf
2004-01-01
In this study a new extended Kalman filter (EKF) learning algorithm for feed-forward neural networks (FFN) is used. With the EKF approach, the training of the FFN can be seen as state estimation for a non-linear stationary process. The EKF method gives excellent convergence performances provided that there is enough computer core memory and that the machine precision is high. Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH4 volume mixing ratio (v.m.r.). The neural network was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9997. The neural network Fortran code used is available for download.
D. J. Lary
2004-06-01
Full Text Available In this study a new extended Kalman filter (EKF learning algorithm for feed-forward neural networks (FFN is used. With the EKF approach, the training of the FFN can be seen as state estimation for a non-linear stationary process. The EKF method gives excellent convergence performances provided that there is enough computer core memory and that the machine precision is high. Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH_{4}-N_{2}O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH_{4} volume mixing ratio (v.m.r.. The neural network was able to reproduce the CH_{4}-N_{2}O correlation with a correlation coefficient between simulated and training values of 0.9997. The neural network Fortran code used is available for download.
Han, Ruixue; Wang, Jiang; Yu, Haitao; Deng, Bin; Wei, Xilei; Qin, Yingmei; Wang, Haixu
2015-04-01
Reliable signal propagation across distributed brain areas is an essential requirement for cognitive function, and it has been investigated extensively in computational studies where feed-forward network (FFN) is taken as a generic model. But it is still unclear how distinct local network states, which are intrinsically generated by synaptic interactions within each layer, would affect the ability of FFN to transmit information. Here we investigate the impact of such network states on propagating transient synchrony (synfire) and firing rate by a combination of numerical simulations and analytical approach. Specifically, local network dynamics is attributed to the competition between excitatory and inhibitory neurons within each layer. Our results show that concomitant with different local network states, the performance of signal propagation differs dramatically. For both synfire propagation and firing rate propagation, there exists an optimal local excitability state, respectively, that optimizes the performance of signal propagation. Furthermore, we find that long-range connections strongly change the dependence of spiking activity propagation on local network state and propose that these two factors work jointly to determine information transmission across distributed networks. Finally, a simple mean field approach that bridges response properties of long-range connectivity and local subnetworks is utilized to reveal the underlying mechanism.
Fereydoon Sarmadian
2014-01-01
Full Text Available The two common methods used to develop PTFs are multiple-linear regression method and Artificial Neural Network. One of the advantages of neural networks compared to traditional regression PTFs is that they do not require a priori regression model, which relates input and output data and in general is difficult because these models are not known. So at present research, we compare performance of feed-forward back-propagation network to predict soil properties. Soil samples were collected from different horizons profiles located in the Gorgan Province, North of Iran. Measured soil variables included texture, organic carbon, water saturation percentage Bulk density, Infiltration rate and deep percolation. Then, multiple linear regression and neural network model were employed to develop a pedotransfer function for predicting soil parameters using easily measurable characteristics of clay, silt, SP, Bd and organic carbon. The performance of the multiple linear regression and neural network model was evaluated using a test data set by R2, RMSE and RSE. Results showed that artificial neural network with two and five neurons in hidden layer had better performance in predicting soil hydraulic properties than multivariate regression. In conclusion, the result of this study showed that both ANN and regression predicted soil properties with relatively high accuracy that showed that strong relationship between input and output data and also high accuracy in determining of data.
Spike-timing computation properties of a feed-forward neural network model
Drew Benjamin Sinha
2014-01-01
Full Text Available Brain function is characterized by dynamical interactions among networks of neurons. These interactions are mediated by network topology at many scales ranging from microcircuits to brain areas. Understanding how networks operate can be aided by understanding how the transformation of inputs depends upon network connectivity patterns, e.g. serial and parallel pathways. To tractably determine how single synapses or groups of synapses in such pathways shape transformations, we modeled feed-forward networks of 7-22 neurons in which synaptic strength changed according to a spike-timing dependent plasticity rule. We investigated how activity varied when dynamics were perturbed by an activity-dependent electrical stimulation protocol (spike-triggered stimulation; STS in networks of different topologies and background input correlations. STS can successfully reorganize functional brain networks in vivo, but with a variability in effectiveness that may derive partially from the underlying network topology. In a simulated network with a single disynaptic pathway driven by uncorrelated background activity, structured spike-timing relationships between polysynaptically connected neurons were not observed. When background activity was correlated or parallel disynaptic pathways were added, however, robust polysynaptic spike timing relationships were observed, and application of STS yielded predictable changes in synaptic strengths and spike-timing relationships. These observations suggest that precise input-related or topologically induced temporal relationships in network activity are necessary for polysynaptic signal propagation. Such constraints for polysynaptic computation suggest potential roles for higher-order topological structure in network organization, such as maintaining polysynaptic correlation in the face of relatively weak synapses.
Multilayered feed forward neural network based on particle swarm optimizer algorithm
无
2005-01-01
BP is a commonly used neural network training method, which has some disadvantages, such as local minima,sensitivity of initial value of weights, total dependence on gradient information. This paper presents some methods to train a neural network, including standard particle swarm optimizer (PSO), guaranteed convergence particle swarm optimizer (GCPSO), an improved PSO algorithm, and GCPSO-BP, an algorithm combined GCPSO with BP. The simulation results demonstrate the effectiveness of the three algorithms for neural network training.
K. Gayathri Devi
2015-01-01
Full Text Available Purpose. Colon segmentation is an essential step in the development of computer-aided diagnosis systems based on computed tomography (CT images. The requirement for the detection of the polyps which lie on the walls of the colon is much needed in the field of medical imaging for diagnosis of colorectal cancer. Methods. The proposed work is focused on designing an efficient automatic colon segmentation algorithm from abdominal slices consisting of colons, partial volume effect, bowels, and lungs. The challenge lies in determining the exact colon enhanced with partial volume effect of the slice. In this work, adaptive thresholding technique is proposed for the segmentation of air packets, machine learning based cascade feed forward neural network enhanced with boundary detection algorithms are used which differentiate the segments of the lung and the fluids which are sediment at the side wall of colon and by rejecting bowels based on the slice difference removal method. The proposed neural network method is trained with Bayesian regulation algorithm to determine the partial volume effect. Results. Experiment was conducted on CT database images which results in 98% accuracy and minimal error rate. Conclusions. The main contribution of this work is the exploitation of neural network algorithm for removal of opacified fluid to attain desired colon segmentation result.
Zeinab eBirjandian
2013-11-01
Full Text Available The inhibition of excitatory (pyramidal neurons directly dampens their activity resulting in a suppression of neural network output. The inhibition of inhibitory cells is more complex. Inhibitory drive is known to gate neural network synchrony, but there is also a widely held view that it may augment excitability by reducing inhibitory cell activity, a process termed disinhibition. Surprisingly, however, disinhibition has never been demonstrated to be an important mechanism that augments or drives the activity of excitatory neurons in a functioning neural circuit. Using voltage sensitive dye imaging (VSDI we show that 20-80 Hz stimulus trains, (beta-gamma activation, of the olfactory cortex pyramidal cells in layer II leads to a subsequent reduction in inhibitory interneuron activity that augments the efficacy of the initial stimulus. This disinhibition occurs with a lag of about 150-250 ms after the initial excitation of the layer 2 pyramidal cell layer. In addition activation of the endopiriform nucleus also arises just before the disinhibitory phase with a lag of about 40-80 ms. Preventing the spread of action potentials from layer II stopped the excitation of the endopiriform nucleus, abolished the disinhibitory activity and reduced the excitation of layer II cells. After the induction of experimental epilepsy the disinhibition was more intense with a concomitant increase in excitatory cell activity. Our observations provide the first evidence of feed forward disinhibition loop that augments excitatory neurotransmission, a mechanism that could play an important role in the development of epileptic seizures.
Wang, Jiang; Han, Ruixue; Wei, Xilei; Qin, Yingmei; Yu, Haitao; Deng, Bin
2016-12-01
Reliable signal propagation across distributed brain areas provides the basis for neural circuit function. Modeling studies on cortical circuits have shown that multilayered feed-forward networks (FFNs), if strongly and/or densely connected, can enable robust signal propagation. However, cortical networks are typically neither densely connected nor have strong synapses. This paper investigates under which conditions spiking activity can be propagated reliably across diluted FFNs. Extending previous works, we model each layer as a recurrent sub-network constituting both excitatory (E) and inhibitory (I) neurons and consider the effect of interactions between local excitation and inhibition on signal propagation. It is shown that elevation of cellular excitation-inhibition (EI) balance in the local sub-networks (layers) softens the requirement for dense/strong anatomical connections and thereby promotes weak signal propagation in weakly connected networks. By means of iterated maps, we show how elevated local excitability state compensates for the decreased gain of synchrony transfer function that is due to sparse long-range connectivity. Finally, we report that modulations of EI balance and background activity provide a mechanism for selectively gating and routing neural signal. Our results highlight the essential role of intrinsic network states in neural computation.
Kumar, Somesh; Pratap Singh, Manu; Goel, Rajkumar; Lavania, Rajesh
2013-12-01
In this work, the performance of feedforward neural network with a descent gradient of distributed error and the genetic algorithm (GA) is evaluated for the recognition of handwritten 'SWARS' of Hindi curve script. The performance index for the feedforward multilayer neural networks is considered here with distributed instantaneous unknown error i.e. different error for different layers. The objective of the GA is to make the search process more efficient to determine the optimal weight vectors from the population. The GA is applied with the distributed error. The fitness function of the GA is considered as the mean of square distributed error that is different for each layer. Hence the convergence is obtained only when the minimum of different errors is determined. It has been analysed that the proposed method of a descent gradient of distributed error with the GA known as hybrid distributed evolutionary technique for the multilayer feed forward neural performs better in terms of accuracy, epochs and the number of optimal solutions for the given training and test pattern sets of the pattern recognition problem.
Singh, Y.; Nair, R.R.; Singh, H.; Datta, P.; Jaiswal, P.; Dewangan, P.; Ramprasad, T.
-Godavari basin. Log prediction process, with uncertainties based on root mean square error properties, was implemented by way of a multi-layer feed forward neural network. The log properties were merged with seismic data by applying a non-linear transform...
FPGA Implementations of Feed Forward Neural Network by using Floating Point Hardware Accelerators
Gabriele-Maria Lozito
2014-01-01
Full Text Available This paper documents the research towards the analysis of different solutions to implement a Neural Network architecture on a FPGA design by using floating point accelerators. In particular, two different implementations are investigated: a high level solution to create a neural network on a soft processor design, with different strategies for enhancing the performance of the process; a low level solution, achieved by a cascade of floating point arithmetic elements. Comparisons of the achieved performance in terms of both time consumptions and FPGA resources employed for the architectures are presented.
A Bhavani Sankar; J Arputha Vijaya Selvi; D Kumar; K Seetha Lakshmi
2013-06-01
In biomedical signal analysis, Artiﬁcial Neural Networks are frequently used for classiﬁcation, owing to their capability to resolve nonlinearly separable problems and the ﬂexibility to implement them on-chip processor, competently. Artiﬁcial Neural Network for a classiﬁcation task attempts to hand design a network topology and to ﬁnd a set of network parameters using a back propagation training algorithm. This work presents an intelligent diagnosis system using artiﬁcial neural network. Features were extracted from respiratory effort signal based on the threshold-based scheme and the respiratory states were classiﬁed into normal, sleep apnea and motion artifacts. The introduced neural classiﬁer was then trained with different back propagation training algorithms and the classiﬁed output was compared with the hand designed results. Five different back propagation training algorithms were used for training, such as Levenberg–Marquardt, scaled conjugate gradient, BFGS algorithm, one step secant and Powell–Beale restarts. Our results revealed that the system could correctly classify at an average of 98.7%, when the LM training method was used. Receiver Operating Characteristic (ROC) analysis and confusion matrix showed that the LM method conferred a more balanced and an apt classiﬁcation of sleep apnea and normal states.
Precision requirements for single-layer feed-forward neural networks
Annema, Anne J.; Hoen, K.; Hoen, Klaas; Wallinga, Hans
1994-01-01
This paper presents a mathematical analysis of the effect of limited precision analog hardware for weight adaptation to be used in on-chip learning feedforward neural networks. Easy-to-read equations and simple worst-case estimations for the maximum tolerable imprecision are presented. As an
Roger A. Kemp
1997-01-01
Full Text Available Normal cells in the presence of a precancerous lesion undergo subtle changes of their DNA distribution when observed by visible microscopy. These changes have been termed Malignancy Associated Changes (MACs. Using statistical models such as neural networks and discriminant functions it is possible to design classifiers that can separate these objects from truly normal cells. The correct classification rate using feed‐forward neural networks is compared to linear discriminant analysis when applied to detecting MACs. Classifiers were designed using 53 nuclear features calculated from images for each of 25,360 normal appearing cells taken from 344 slides diagnosed as normal or containing severe dysplasia. A linear discriminant function achieved a correct classification rate of 61.6% on the test data while neural networks scored as high as 72.5% on a cell‐by‐cell basis. The cell classifiers were applied to a library of 93,494 cells from 395 slides, and the results were jackknifed using a single slide feature. The discriminant function achieved a correct classification rate of 67.6% while the neural networks managed as high as 76.2%.
Training a Feed-Forward Neural Network with Artificial Bee Colony based Backpropagation Method
Sudarshan Nandy
2012-09-01
Full Text Available Back-propagation algorithm is one of the most widely used and popular techniques to optimize the feedforward neural network training. Nature inspired meta-heuristic algorithms also provide derivative-freesolution to optimize complex problem. Artificial bee colony algorithm is a nature inspired meta-heuristicalgorithm, mimicking the foraging or food source searching behaviour of bees in a bee colony and thisalgorithm is implemented in several applications for an improved optimized outcome. The proposedmethod in this paper includes an improved artificial bee colony algorithm based back-propagation neuralnetwork training method for fast and improved convergence rate of the hybrid neural network learningmethod. The result is analysed with the genetic algorithm based back-propagation method, and it isanother hybridized procedure of its kind. Analysis is performed over standard data sets, reflecting the lightof efficiency of proposed method in terms of convergence speed and rate.
Stromatias, Evangelos
2011-01-01
Spiking neural networks have been referred to as the third generation of artificial neural networks where the information is coded as time of the spikes. There are a number of different spiking neuron models available and they are categorized based on their level of abstraction. In addition, there are two known learning methods, unsupervised and supervised learning. This thesis focuses on supervised learning where a new algorithm is proposed, based on genetic algorithms. The proposed algorithm is able to train both synaptic weights and delays and also allow each neuron to emit multiple spikes thus taking full advantage of the spatial-temporal coding power of the spiking neurons. In addition, limited synaptic precision is applied; only six bits are used to describe and train a synapse, three bits for the weights and three bits for the delays. Two limited precision schemes are investigated. The proposed algorithm is tested on the XOR classification problem where it produces better results for even smaller netwo...
Feature Extraction of Olive Ridley Sea Turtle Using Feed Forward neural Network
Capt. Dr.S.Santhosh Baboo
2014-10-01
Full Text Available The paper deals with the computer based auto detection of particular species of sea turtles. In this process, three parameters have been taken and trained in artificial neural network for detecting the particular species among the popular seven species of the world. The existing algorithm for auto photo identification of detecting the particular species is much complicated due to classification process in the algorithm. To improve this algorithm, new technique has been used in feature extraction of the image and there are 10 images where trained and then finally particular species Olive Ridely is retrieved. These images are trained through artificial neural network and result of the images is plotted in the graphs.
Gaonkar, Bilwaj; Hovda, David; Martin, Neil; Macyszyn, Luke
2016-03-01
Deep Learning, refers to large set of neural network based algorithms, have emerged as promising machine- learning tools in the general imaging and computer vision domains. Convolutional neural networks (CNNs), a specific class of deep learning algorithms, have been extremely effective in object recognition and localization in natural images. A characteristic feature of CNNs, is the use of a locally connected multi layer topology that is inspired by the animal visual cortex (the most powerful vision system in existence). While CNNs, perform admirably in object identification and localization tasks, typically require training on extremely large datasets. Unfortunately, in medical image analysis, large datasets are either unavailable or are extremely expensive to obtain. Further, the primary tasks in medical imaging are organ identification and segmentation from 3D scans, which are different from the standard computer vision tasks of object recognition. Thus, in order to translate the advantages of deep learning to medical image analysis, there is a need to develop deep network topologies and training methodologies, that are geared towards medical imaging related tasks and can work in a setting where dataset sizes are relatively small. In this paper, we present a technique for stacked supervised training of deep feed forward neural networks for segmenting organs from medical scans. Each `neural network layer' in the stack is trained to identify a sub region of the original image, that contains the organ of interest. By layering several such stacks together a very deep neural network is constructed. Such a network can be used to identify extremely small regions of interest in extremely large images, inspite of a lack of clear contrast in the signal or easily identifiable shape characteristics. What is even more intriguing is that the network stack achieves accurate segmentation even when it is trained on a single image with manually labelled ground truth. We validate
Meier, E., E-mail: evelyne.meier@synchrotron.org.a [School of Physics, Monash University, Wellington Rd, Clayton, VIC 3800 (Australia) and Australian Synchrotron, 800 Blackburn Rd, Clayton, VIC 3168 (Australia) and FERMI-Elettra, Sincrotrone Trieste, S.S. 14km 163.5 in AREA Science Park, 34012 Basovizza, Trieste (Italy); Biedron, S.G., E-mail: biedron@anl.go [Department of Defense Project Office, Argonne National Laboratory, IL 60439 (United States); FERMI-Elettra, Sincrotrone Trieste, S.S. 14km 163.5 in AREA Science Park, 34012 Basovizza, Trieste (Italy); LeBlanc, G., E-mail: Greg.LeBlanc@synchrotron.org.a [Australian Synchrotron, 800 Blackburn Rd, Clayton, VIC 3168 (Australia); Morgan, M.J., E-mail: Michael.Morgan@sci.monash.edu.a [School of Physics, Monash University, Wellington Rd, Clayton, VIC 3800 (Australia); Wu, J., E-mail: jhwu@slac.stanford.ed [LCLS, SLAC National Accelerator Laboratory, 2575 Sand Hill Rd, Menlo Park, CA 94025 (United States)
2009-11-11
This paper describes the results of an advanced control algorithm for the stabilization of electron beam energy in a Linac. The approach combines a conventional Proportional-Integral (PI) controller with a neural network (NNET) feed forward algorithm; it utilizes the robustness of PI control and the ability of a feed forward system in order to exert control over a wider range of frequencies. The NNET is trained to recognize jitter occurring in the phase and voltage of one of the klystrons, based on a record of these parameters, and predicts future energy deviations. A systematic approach is developed to determine the optimal NNET parameters that are then applied to the Australian Synchrotron Linac. The system's capability to fully cancel multi-frequency jitter is demonstrated. The NNET system is then augmented with the PI algorithm, and further jitter attenuation is achieved when the NNET is not operating optimally.
Two-Layer Feedback Neural Networks with Associative Memories
WU Gui-Kun; ZHAO Hong
2008-01-01
We construct a two-layer feedback neural network by a Monte Carlo based algorithm to store memories as fixed-point attractors or as limit-cycle attractors. Special attention is focused on comparing the dynamics of the network with limit-cycle attractors and with fixed-point attractors. It is found that the former has better retrieval property than the latter. Particularly, spurious memories may be suppressed completely when the memories are stored as a long-limit cycle. Potential application of limit-cycle-attractor networks is discussed briefly.
Rishi, Rahul; Choudhary, Amit; Singh, Ravinder; Dhaka, Vijaypal Singh; Ahlawat, Savita; Rao, Mukta
2010-02-01
In this paper we propose a system for classification problem of handwritten text. The system is composed of preprocessing module, supervised learning module and recognition module on a very broad level. The preprocessing module digitizes the documents and extracts features (tangent values) for each character. The radial basis function network is used in the learning and recognition modules. The objective is to analyze and improve the performance of Multi Layer Perceptron (MLP) using RBF transfer functions over Logarithmic Sigmoid Function. The results of 35 experiments indicate that the Feed Forward MLP performs accurately and exhaustively with RBF. With the change in weight update mechanism and feature-drawn preprocessing module, the proposed system is competent with good recognition show.
Dr.J.P.Ganjigatti
2016-05-01
Full Text Available The development of an intelligent system for the establishment of relationship between input parameters and the responses utilizing both reverse and forward modeling of artificial neural networks is the main objective of the present research work. Prediction of quality characteristics such as front width, back width, front height and back height of the weld bead geometry in Tungsten Inert Gas welding process of AA5083; H111 Aluminum alloy is the aim in forward modeling from known set of process parameters such as current, %balance, welding speed, arc gap, gas flow rate, and frequency. Reverse modeling meets the industrial requirements of automatic welding to predict the recommended weld bead geometry characteristics. Comprehensive approach for the development of two back propagation networks viz. feed forward back propagation (FFBP and Elman back propagation (EBP neural networks is adopted. 212 Face centered central composite design based experimental data is utilized for the development of both supervised learning networks with batch mode training approach. A comparison of performance of FFBPP and EBP neural networks are made with that of stepwise multiple regression statistical modeling. Analysis of results showed that both neural network modeling outperformed the statistical approach in making better predictions and the models are efficient in selection of parameters effectively for the desired responses. FFBP performance found to marginally better than that of EBP neural network. Also the forward modeling performance was better than that of reverse modeling in both neural networks
Gentili, Pier Luigi, E-mail: pierluigi.gentili@unipg.it [Department of Chemistry, Biology and Biotechnology, University of Perugia, 06123 Perugia (Italy); Gotoda, Hiroshi [Department of Mechanical Engineering, Ritsumeikan University, 1-1-1 Nojihigashi, Kusatsu-shi, Shiga 525-8577 (Japan); Dolnik, Milos; Epstein, Irving R. [Department of Chemistry, Brandeis University, Waltham, Massachusetts 02454-9110 (United States)
2015-01-15
Forecasting of aperiodic time series is a compelling challenge for science. In this work, we analyze aperiodic spectrophotometric data, proportional to the concentrations of two forms of a thermoreversible photochromic spiro-oxazine, that are generated when a cuvette containing a solution of the spiro-oxazine undergoes photoreaction and convection due to localized ultraviolet illumination. We construct the phase space for the system using Takens' theorem and we calculate the Lyapunov exponents and the correlation dimensions to ascertain the chaotic character of the time series. Finally, we predict the time series using three distinct methods: a feed-forward neural network, fuzzy logic, and a local nonlinear predictor. We compare the performances of these three methods.
Jie-Sheng Wang
2015-01-01
Full Text Available For predicting the key technology indicators (concentrate grade and tailings recovery rate of flotation process, a feed-forward neural network (FNN based soft-sensor model optimized by the hybrid algorithm combining particle swarm optimization (PSO algorithm and gravitational search algorithm (GSA is proposed. Although GSA has better optimization capability, it has slow convergence velocity and is easy to fall into local optimum. So in this paper, the velocity vector and position vector of GSA are adjusted by PSO algorithm in order to improve its convergence speed and prediction accuracy. Finally, the proposed hybrid algorithm is adopted to optimize the parameters of FNN soft-sensor model. Simulation results show that the model has better generalization and prediction accuracy for the concentrate grade and tailings recovery rate to meet the online soft-sensor requirements of the real-time control in the flotation process.
张长江; 付梦印; 金梅
2003-01-01
A kind of second-order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluctant, which led to the loss of valuable information and affected performance of the algorithm to certain extent. For multi-layer feed-forward neural networks, the second-order back-propagation recursive algorithm based generalized cost criteria was proposed. It is proved that it is equivalent to Newton recursive algorithm and has a second-order convergent rate. The performance and application prospect are analyzed. Lots of simulation experiments indicate that the calculation of the new algorithm is almost equivalent to the recursive least square multiple algorithm. The algorithm and selection of networks parameters are significant and the performance is more excellent than BP algorithm and the second-order learning algorithm that was given by Karayiannis.
Mörchen, Fabian
2004-03-01
The performance of feed-forward neural networks trained with the backpropagation algorithm on a dedicated Beowulf cluster is analyzed. The concept of training set parallelism is applied. A new model for run time and speedup prediction is developed. With the model the speedup and efficiency of one iteration of the neural networks can be estimated as a function of block size and cluster size. The model is applied to three example problems representing different applications and network architectures. The estimation of the model has a higher accuracy than traditional methods for run time estimation and can be efficiently calculated. Experiments show that speedup of one iteration does not necessarily translate to a shorter training time toward a given error level. To overcome this problem a heuristic extension to training set parallelism called weight averaging is developed. The results show that training in parallel should only be done on clusters with high performance network connections or a multiprocessor machine. A rule of thumb is given for how much network performance of the cluster is needed to achieve speedup of the training time for a neural network.
Afkhami, Abbas; Abbasi-Tarighat, Maryam
2008-06-01
In the present study, chemometric analysis of visible spectral data of phospho-and silico-molybdenum blue complexes was used to develop artificial neural networks (ANNs) for the simultaneous determination of the phosphate and silicate. Combinations of principal component analysis (PCA) with feed-forward neural networks (FFNNs) and radial basis function networks (RBFNs) were built and investigated. The structures of the models were simplified by using the corresponding important principal components as input instead of the original spectra. Number of inputs and hidden nodes, learning rate, transfer functions and number of epochs and SPREAD values were optimized. Performances of methods were tested with root mean square errors prediction (RMSEP, %), using synthetic solutions. The obtained satisfactory results indicate the applicability of this ANN approach based on PCA input selection for determination in highly spectral overlapping. The results obtained by FFNNs and by RBF networks were compared. The applicability of methods was investigated for synthetic samples, for detergent formulations, and for a river water sample.
Sudibyo, Aji, B. B.; Priyanto, S.
2017-03-01
Cobalt is one of the precious ferromagnetic metals, which widely used in the preparation of magnetic, wear-resistant and high-strength alloys. This metal was not found naturally in single metal form but is found as impurities in nickel or copper ore. The extraction process is one of the methods to separate cobalt from its impurities. However, this process needs an expensive organic solution. In practice, changing the composition of chemicals composition in extraction process always affect at a high cost. Therefore, the development of the artificial neural network (ANN) model to model the cobalt extraction process can serve as an important tool for predicting and investigating the optimum production for the cobalt extraction without the need to run the actual experiment. Hence, the development of the ANN model of cobalt extraction model is essential to simulate the process, which can lead to high yields of cobalt production. In this work a selected optimum multiple-input-single-output (MISO) model of feed forward neural network (FFNN) was used to predict the percentage of cobalt extraction. MISO FFNN with 20, 30 and 50 hidden nodes were used to simulate cobalt extraction process. The simulation results achieved was compared with data available in the literature. The results show that MISO FFNN with 50 hidden nodes has the best performance. The optimum result of MISO FFNN then exported to Simulink model in Matlab environment, hence make it easy to use in predicting and investigating for the optimum production of the cobalt extraction.
Y. Srinivas
2012-09-01
Full Text Available The applications of intelligent techniques have increased exponentially in recent days to study most of the non-linear parameters. In particular, the behavior of earth resembles the non-linearity applications. An efficient tool is needed for the interpretation of geophysical parameters to study the subsurface of the earth. Artificial Neural Networks (ANN perform certain tasks if the structure of the network is modified accordingly for the purpose it has been used. The three most robust networks were taken and comparatively analyzed for their performance to choose the appropriate network. The single-layer feed-forward neural network with the back propagation algorithm is chosen as one of the well-suited networks after comparing the results. Initially, certain synthetic data sets of all three-layer curves have been taken for training the network, and the network is validated by the field datasets collected from Tuticorin Coastal Region (78°7′30"E and 8°48′45"N, Tamil Nadu, India. The interpretation has been done successfully using the corresponding learning algorithm in the present study. With proper training of back propagation networks, it tends to give the resistivity and thickness of the subsurface layer model of the field resistivity data concerning the synthetic data trained earlier in the appropriate network. The network is trained with more Vertical Electrical Sounding (VES data, and this trained network is demonstrated by the field data. Groundwater table depth also has been modeled.
Jafri, Madiha; Ely, Jay; Vahala, Linda
2006-01-01
Neural Network Modeling is introduced in this paper to classify and predict Interference Path Loss measurements on Airbus 319 and 320 airplanes. Interference patterns inside the aircraft are classified and predicted based on the locations of the doors, windows, aircraft structures and the communication/navigation system-of-concern. Modeled results are compared with measured data and a plan is proposed to enhance the modeling for better prediction of electromagnetic coupling problems inside aircraft.
P.V.V.Kishore
2013-10-01
Full Text Available This research paper highlights the use of shape and texture information for recognizing gestures of Indian sign language. The proposed method involves extracting the hand segments from theoriginal color gesture images and subjecting them to further processing. In the next stage texture information of the hands in extracted using gabor filter. Again from the segmented hand portions shape is modeled using Chan-Vese(CV active contour model. Finally both the shape and texture information are merged together to produce a feature vector that essentially represents a sign in Indian SignLanguage. To reduce the dimensionality of the feature matrix principle component analysis is applied on the feature matrix. The obtained feature matrix will train a artificial neural network the learns using error back propagation algorithm. Indian sign language database was created for around 36 signs with 10 different signers. For training 4 sets gesture images were used and the remaining 6 sets were used for testing. After extensive testing under various conditions the average recognition rate stands at 98.2%.
自适应前馈神经网络结构优化设计%An adaptive algorithm for designing optimal feed-forward neural network architecture
张昭昭; 乔俊飞; 杨刚
2011-01-01
针对多数前馈神经网络结构设计算法采取贪婪搜索策略而易陷入局部最优结构的问题,提出一种自适应前馈神经网络结构设计算法.该算法在网络训练过程中采取自适应寻优策略合并和分裂隐节点,达到设计最优神经网络结构的目的.在合并操作中,以互信息为准则对输出线性相关的隐节点进行合并；在分裂操作中,引入变异系数,有助于跳出局部最优网络结构.算法将合并和分裂操作之后的权值调整与网络对样本的学习过程结合,减少了网络对样本的学习次数,提高了网络的学习速度,增强了网络的泛化性能.非线性函数逼近结果表明,所提算法能得到更小的检测误差,最终网络结构紧凑.%Due to the fact that most algorithms use a greedy strategy in designing artificial neural networks which are susceptible to becoming trapped at the architectural local optimal point, an adaptive algorithm for designing an optimal feed-forward neural network was proposed. During the training process of the neural network, the adaptive optimization strategy was adopted to merge and split the hidden unit to design optimal neural network architecture. In the merge operation, the hidden units were merged based on mutual information criterion. In the split operation, a mutation coefficient was introduced to help jump out of locally optimal network. The process of adjusting the connection weight after merge and split operations was combined with the process of training the neural network. Therefore, the number of training samples was reduced, the training speed was increased, and the generalization performance was improved. The results of approximating non-linear functions show that the proposed algorithm can limit testing errors and a compact neural network structure.
Afkhami, Abbas; Abbasi-Tarighat, Maryam; Bahram, Morteza
2008-03-15
In this work feed-forward neural networks and radial basis function networks were used for the determination of enantiomeric composition of alpha-phenylglycine using UV spectra of cyclodextrin host-guest complexes and the data provided by two techniques were compared. Wavelet transformation (WT) and principal component analysis (PCA) were used for data compression prior to neural network construction and their efficiencies were compared. The structures of the wavelet transformation-radial basis function networks (WT-RBFNs) and wavelet transformation-feed-forward neural networks (WT-FFNNs), were simplified by using the corresponding wavelet coefficients of three mother wavelets (Mexican hat, daubechies and symlets). Dilation parameters, number of inputs, hidden nodes, learning rate, transfer functions, number of epochs and SPREAD values were optimized. Performances of the proposed methods were tested with regard to root mean square errors of prediction (RMSE%), using synthetic solutions containing a fixed concentration of beta-cyclodextrin (beta-CD) and fixed concentration of alpha-phenylglycine (alpha-Gly) with different enantiomeric compositions. Although satisfactory results with regard to some statistical parameters were obtained for all the investigated methods but the best results were achieved by WT-RBFNs.
Learning behavior and temporary minima of two-layer neural networks
Annema, Anne J.; Hoen, Klaas; Hoen, Klaas; Wallinga, Hans
1994-01-01
This paper presents a mathematical analysis of the occurrence of temporary minima during training of a single-output, two-layer neural network, with learning according to the back-propagation algorithm. A new vector decomposition method is introduced, which simplifies the mathematical analysis of
A two-layer recurrent neural network for nonsmooth convex optimization problems.
Qin, Sitian; Xue, Xiaoping
2015-06-01
In this paper, a two-layer recurrent neural network is proposed to solve the nonsmooth convex optimization problem subject to convex inequality and linear equality constraints. Compared with existing neural network models, the proposed neural network has a low model complexity and avoids penalty parameters. It is proved that from any initial point, the state of the proposed neural network reaches the equality feasible region in finite time and stays there thereafter. Moreover, the state is unique if the initial point lies in the equality feasible region. The equilibrium point set of the proposed neural network is proved to be equivalent to the Karush-Kuhn-Tucker optimality set of the original optimization problem. It is further proved that the equilibrium point of the proposed neural network is stable in the sense of Lyapunov. Moreover, from any initial point, the state is proved to be convergent to an equilibrium point of the proposed neural network. Finally, as applications, the proposed neural network is used to solve nonlinear convex programming with linear constraints and L1 -norm minimization problems.
A TWO-LAYER RECURRENT NEURAL NETWORK BASED APPROACH FOR OVERLAY MULTICAST
Liu Shidong; Zhang Shunyi; Zhou Jinquan; Qiu Gong'an
2008-01-01
Overlay multicast has become one of the most promising multicast solutions for IP network, and Neutral Network(NN) has been a good candidate for searching optimal solutions to the constrained shortest routing path in virtue of its powerful capacity for parallel computation. Though traditional Hopfield NN can tackle the optimization problem, it is incapable of dealing with large scale networks due to the large number of neurons. In this paper, a neural network for overlay multicast tree computation is presented to reliably implement routing algorithm in real time. The neural network is constructed as a two-layer recurrent architecture, which is comprised of Independent Variable Neurons (IDVN) and Dependent Variable Neurons (DVN), according to the independence of the decision variables associated with the edges in directed graph. Compared with the heuristic routing algorithms, it is characterized as shorter computational time, fewer neurons, and better precision.
Neuronal networks: enhanced feedback feeds forward.
Calabrese, Ronald L
2012-09-25
Modulatory projection neurons gate neuronal networks, such as those comprising motor central pattern generators; in turn, they receive feedback from the networks they gate. A recent study has shown that, in the crab stomatogastric ganglion, this feedback is also subject to modulation: the enhanced feedback feeds forward through the projection neurons to modify circuit output.
Feed forward control of estimated wind speed
Van Engelen, T.G.; Van der Hooft, E.L. [ECN Wind Energy, Petten (Netherlands)
2003-12-01
A control structure 'feed forward of estimated wind speed' is described, as it were: 'the wind turbine rotor will be used as a wind meter'. The control structure is based on 'estimation' of wind speed as well as a non-linear compensation of a wind speed dependent pitch speed setpoint, which is optimised to maintain (stationary) rated electric power. It is required to know the rotor properties with moderate accuracy. In time domain simulations, inclusion of a feed forward of estimated wind speed control action has shown to be a powerful extension to current ECN wind turbine control structures: reduction of rotor speed variations: 0.2 rpm decreased standard deviation; improved turbine behaviour to large wind gusts; increase of energy yield of 0.9%; For reasons of simplicity and robustness, a tabular implementation approach is preferred above polynomial implementation. The resulting brief algorithm uses small sized tables, requires low hardware requirements and needs a minimum of easy interpretable parameters for design and tuning. Both stability, robustness and parametric uncertainties were observed. The addition control loop has a slightly positive effect on overall stability and robustness. Appeared offsets in the estimated wind speed value due to parameter uncertainties do not have impact on the effectuation of the wind speed feed forward loop.
Topological reversibility and causality in feed-forward networks
Corominas-Murtra, Bernat; RodrIguez-Caso, Carlos; Sole, Ricard [ICREA-Complex Systems Lab, Universitat Pompeu Fabra (Parc de Recerca Biomedica de Barcelona), Dr Aiguader 88, 08003 Barcelona (Spain); Goni, JoaquIn, E-mail: bernat.corominas@upf.ed [Functional Neuroimaging Laboratory, Department of Neurosciences, Center for Applied Medical Research, University of Navarra, Pamplona (Spain)
2010-11-15
Systems whose organization displays causal asymmetry constraints, from evolutionary trees to river basins or transport networks, can often be described in terms of directed paths on a discrete set of arbitrary units including states in state spaces, feed-forward neural nets, the evolutionary history of a given collection of events or the chart of computational states visited along a complex computation. Such a set of paths defines a feed-forward, acyclic network. A key problem associated with these systems involves characterizing their intrinsic degree of path reversibility: given an end node in the graph, what is the uncertainty of recovering the process backwards until the origin? Here, we propose a novel concept, topological reversibility, which is a measure of the complexity of the net that rigorously weights such uncertainty in path dependency, quantifying the minimum amount of information required to successfully reverse a causal path. Within the proposed framework, we also analytically characterize limit cases for both topologically reversible and maximally entropic structures. The relevance of these measures within the context of evolutionary dynamics is highlighted.
V. Rezan USLU
2010-01-01
Full Text Available Obtaining the inflation prediction is an important problem. Having this prediction accurately will lead to more accurate decisions. Various time series techniques have been used in the literature for inflation prediction. Recently, Artificial Neural Network (ANN is being preferred in the time series prediction problem due to its flexible modeling capacity. Artificial neural network can be applied easily to any time series since it does not require prior conditions such as a linear or curved specific model pattern, stationary and normal distribution. In this study, the predictions have been obtained using the feed forward and recurrent artificial neural network for the Consumer Price Index (CPI. A new combined forecast has been proposed based on ANN in which the ANN model predictions employed in analysis were used as data.
The mechanism of synchronization in feed-forward neuronal networks
Goedeke, S; Diesmann, M [Bernstein Center for Computational Neuroscience, Albert-Ludwigs-University, Freiburg (Germany)], E-mail: diesmann@brain.riken.jp
2008-01-15
Synchronization in feed-forward subnetworks of the brain has been proposed to explain the precisely timed spike patterns observed in experiments. While the attractor dynamics of these networks is now well understood, the underlying single neuron mechanisms remain unexplained. Previous attempts have captured the effects of the highly fluctuating membrane potential by relating spike intensity f(U) to the instantaneous voltage U generated by the input. This article shows that f is high during the rise and low during the decay of U(t), demonstrating that the U-dot-dependence of f, not refractoriness, is essential for synchronization. Moreover, the bifurcation scenario is quantitatively described by a simple f(U,U-dot) relationship. These findings suggest f(U,U-dot) as the relevant model class for the investigation of neural synchronization phenomena in a noisy environment.
Feed forward control: An implementation at CIRFEL
Krishnaswamy, J.; Lehrman, I.S.; Hartley, R. [Northrop Grumman Advanced Technology and Development Center, Princeton, NJ (United States)] [and others
1995-12-31
An integral part of the Compact InfraRed Free Electron LASER (CIRFEL) is control of the phase and amplitude stability in the RF power system. We have implemented such a Feed Forward system using the LabView software package, by National Instruments. We will discuss implementation and performance data of the Feed Forward control of the RF power system at CIRFEL. We will also briefly discuss some conditions under which the problem is ill-conditioned, and what idealizations can be made to remedy these ill-conditioned systems. Using an arbitrary function generator, we generate a driving signal for a voltage-controlled attenuator at the input side of the RF system, and we monitor the RF voltage in cell I of the photocathode gun using a digital storage oscilliscope in averaging mode. The system is stable enough to use data from one shot to modify the inputs for future shots. After downloading the averaged data to a personal computer via a GPIB (IEEE 488) bus, we use a simple linear transformation on the difference waveform between the current shot and the target to produce a correction signal. This signal is added to the driving signal in the arbitrary function generator, and the process is repeated until we get the flatness we need in the output signals from cell 1. The system for phase control is similar, with a voltage-controlled phase shifter replacing the attenuator, and monitoring of the RF phase in cell I replacing the monitoring of RF voltage. By repeatedly alternating between correcting the RF voltage (equivalent to correcting the RF power) and RF phase in cell 1, we are able to achieve simultaneous phase variations of <{+-}1{degrees} and amplitude variations of <{+-}0.1% over a 3{mu}sec pulse.
Storage capacity and learning algorithms for two-layer neural networks
Engel, A.; Köhler, H. M.; Tschepke, F.; Vollmayr, H.; Zippelius, A.
1992-05-01
A two-layer feedforward network of McCulloch-Pitts neurons with N inputs and K hidden units is analyzed for N-->∞ and K finite with respect to its ability to implement p=αN random input-output relations. Special emphasis is put on the case where all hidden units are coupled to the output with the same strength (committee machine) and the receptive fields of the hidden units either enclose all input units (fully connected) or are nonoverlapping (tree structure). The storage capacity is determined generalizing Gardner's treatment [J. Phys. A 21, 257 (1988); Europhys. Lett. 4, 481 (1987)] of the single-layer perceptron. For the treelike architecture, a replica-symmetric calculation yields αc~ √K for a large number K of hidden units. This result violates an upper bound derived by Mitchison and Durbin [Biol. Cybern. 60, 345 (1989)]. One-step replica-symmetry breaking gives lower values of αc. In the fully connected committee machine there are in general correlations among different hidden units. As the limit of capacity is approached, the hidden units are anticorrelated: One hidden unit attempts to learn those patterns which have not been learned by the others. These correlations decrease as 1/K, so that for K-->∞ the capacity per synapse is the same as for the tree architecture, whereas for small K we find a considerable enhancement for the storage per synapse. Numerical simulations were performed to explicitly construct solutions for the tree as well as the fully connected architecture. A learning algorithm is suggested. It is based on the least-action algorithm, which is modified to take advantage of the two-layer structure. The numerical simulations yield capacities p that are slightly more than twice the number of degrees of freedom, while the fully connected net can store relatively more patterns than the tree. Various generalizations are discussed. Variable weights from hidden to output give the same results for the storage capacity as does the committee
A linear approach for sparse coding by a two-layer neural network
Montalto, Alessandro; Prevete, Roberto
2015-01-01
Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of these approaches require the repeated application of a learning process upon the presentation of unseen data input vectors, or else involve the use of large numbers of parameters and hyper-parameters, which must be chosen through cross-validation, thus increasing running time dramatically. In this paper, we propose and experimentally investigate a new approach for the purpose of overcoming limitations of both kinds. The proposed approach makes use of a linear auto-associative network (called SCNN) with just one hidden layer. The combination of this architecture with a specific error function to be minimized enables one to learn a linear encoder computing a sparse code which turns out to be as similar as possible to the sparse coding that one obtains by re-training the neura...
Optimize Short Term load Forcasting Anomalous Based Feed Forward Backpropagation
Mulyadi, Y.; Abdullah, A. G.; Rohmah, K. A.
2017-03-01
This paper contains the Short-Term Load Forecasting (STLF) using artificial neural network especially feed forward back propagation algorithm which is particularly optimized in order to getting a reduced error value result. Electrical load forecasting target is a holiday that hasn’t identical pattern and different from weekday’s pattern, in other words the pattern of holiday load is an anomalous. Under these conditions, the level of forecasting accuracy will be decrease. Hence we need a method that capable to reducing error value in anomalous load forecasting. Learning process of algorithm is supervised or controlled, then some parameters are arranged before performing computation process. Momentum constant a value is set at 0.8 which serve as a reference because it has the greatest converge tendency. Learning rate selection is made up to 2 decimal digits. In addition, hidden layer and input component are tested in several variation of number also. The test result leads to the conclusion that the number of hidden layer impact on the forecasting accuracy and test duration determined by the number of iterations when performing input data until it reaches the maximum of a parameter value.
Somatosensory integration controlled by dynamic thalamocortical feed-forward inhibition.
Gabernet, Laetitia; Jadhav, Shantanu P; Feldman, Daniel E; Carandini, Matteo; Scanziani, Massimo
2005-10-20
The temporal features of tactile stimuli are faithfully represented by the activity of neurons in the somatosensory cortex. However, the cellular mechanisms that enable cortical neurons to report accurate temporal information are not known. Here, we show that in the rodent barrel cortex, the temporal window for integration of thalamic inputs is under the control of thalamocortical feed-forward inhibition and can vary from 1 to 10 ms. A single thalamic fiber can trigger feed-forward inhibition and contacts both excitatory and inhibitory cortical neurons. The dynamics of feed-forward inhibition exceed those of each individual synapse in the circuit and are captured by a simple disynaptic model of the thalamocortical projection. The variations in the integration window produce changes in the temporal precision of cortical responses to whisker stimulation. Hence, feed-forward inhibitory circuits, classically known to sharpen spatial contrast of tactile inputs, also increase the temporal resolution in the somatosensory cortex.
Learning feed-forward multi-nets
Venema, RS; Spaanenburg, L; Kurkova,; Steele, NC; Neruda, R; Karny, M
2001-01-01
Multi-nets promise an improved performance over monolithic neural networks by virtue of their distributed implementation. This potential lacks popularity as, without precautions, the learning rate has to drop considerably to eliminate the occurrence of unlearning. This paper introduces extensions of
Development of a combined feed forward-feedback system for an electron Linac
Meier, E. [School of Physics, Monash University, Wellington Rd, Clayton VIC 3800 (Australia) and Australian Synchrotron, 800 Blackburn Rd, Clayton VIC 3168 (Australia); FERMI-Elettra, Sincrotrone Trieste, S.S. 14km 163.5 in AREA Science Park, 34012 Basovizza, Trieste (Italy)], E-mail: evelyne.meier@synchrotron.org.au; Biedron, S.G. [Department of Defense Project Office, Argonne National Laboratory, IL 60439 (United States); FERMI-Elettra, Sincrotrone Trieste, S.S. 14km 163.5 in AREA Science Park, 34012 Basovizza, Trieste (Italy)], E-mail: biedron@anl.gov; LeBlanc, G. [Australian Synchrotron, 800 Blackburn Rd, Clayton VIC 3168 (Australia)], E-mail: Greg.LeBlanc@synchrotron.org.au; Morgan, M.J. [School of Physics, Monash University, Wellington Rd, Clayton VIC 3800 (Australia)], E-mail: Michael.Morgan@sci.monash.edu.au; Wu, J. [LCLS, SLAC National Accelerator Laboratory, 2575 Sand Hill Rd, Menlo Park, CA 94025 (United States)], E-mail: jhwu@slac.stanford.edu
2009-10-11
This paper describes the results of an advanced control algorithm for the stabilization of electron beam energy in a Linac. The approach combines a conventional Proportional-Integral (PI) controller with a neural network (NNET) feed forward algorithm; it utilizes the robustness of PI control and the ability of a feed forward system in order to exert control over a wider range of frequencies. The NNET is trained to recognize jitter occurring in the phase and voltage of one of the klystrons, based on a record of these parameters, and predicts future energy deviations. A systematic approach is developed to determine the optimal NNET parameters that are then applied to the Australian Synchrotron Linac. The system's capability to fully cancel multi-frequency jitter is demonstrated. The NNET system is then augmented with the PI algorithm, and further jitter attenuation is achieved when the NNET is not operating optimally.
Introduction to Artificial Neural Networks
Larsen, Jan
1999-01-01
The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks.......The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks....
Improved Cuckoo Search Algorithm for Feed forward Neural Network Training
Ehsan Valian; Shahram Mohanna; Saeed Tavakoli
2011-01-01
The cuckoo search algorithm is a recently developed meta-heuristic optimization algorithm, which is suitable for solving optimization problems. To enhance the accuracy and convergence rate of this algorithm, an improved cuckoo search algorithm is proposed in this paper. Normally, the parameters of the cuckoo search are kept constant. This may lead to decreasing the efficiency of the algorithm. To cope with this issue, a proper strategy for tuning the cuckoo search parameters is pr...
Feed-forward mechanisms: addiction-like behavioral and molecular adaptations in overeating.
Alsiö, Johan; Olszewski, Pawel K; Levine, Allen S; Schiöth, Helgi B
2012-04-01
Food reward, not hunger, is the main driving force behind eating in the modern obesogenic environment. Palatable foods, generally calorie-dense and rich in sugar/fat, are thus readily overconsumed despite the resulting health consequences. Important advances have been made to explain mechanisms underlying excessive consumption as an immediate response to presentation of rewarding tastants. However, our understanding of long-term neural adaptations to food reward that oftentimes persist during even a prolonged absence of palatable food and contribute to the reinstatement of compulsive overeating of high-fat high-sugar diets, is much more limited. Here we discuss the evidence from animal and human studies for neural and molecular adaptations in both homeostatic and non-homeostatic appetite regulation that may underlie the formation of a "feed-forward" system, sensitive to palatable food and propelling the individual from a basic preference for palatable diets to food craving and compulsive, addiction-like eating behavior.
Quantum teleportation over 143 kilometres using active feed-forward.
Ma, Xiao-Song; Herbst, Thomas; Scheidl, Thomas; Wang, Daqing; Kropatschek, Sebastian; Naylor, William; Wittmann, Bernhard; Mech, Alexandra; Kofler, Johannes; Anisimova, Elena; Makarov, Vadim; Jennewein, Thomas; Ursin, Rupert; Zeilinger, Anton
2012-09-13
The quantum internet is predicted to be the next-generation information processing platform, promising secure communication and an exponential speed-up in distributed computation. The distribution of single qubits over large distances via quantum teleportation is a key ingredient for realizing such a global platform. By using quantum teleportation, unknown quantum states can be transferred over arbitrary distances to a party whose location is unknown. Since the first experimental demonstrations of quantum teleportation of independent external qubits, an internal qubit and squeezed states, researchers have progressively extended the communication distance. Usually this occurs without active feed-forward of the classical Bell-state measurement result, which is an essential ingredient in future applications such as communication between quantum computers. The benchmark for a global quantum internet is quantum teleportation of independent qubits over a free-space link whose attenuation corresponds to the path between a satellite and a ground station. Here we report such an experiment, using active feed-forward in real time. The experiment uses two free-space optical links, quantum and classical, over 143 kilometres between the two Canary Islands of La Palma and Tenerife. To achieve this, we combine advanced techniques involving a frequency-uncorrelated polarization-entangled photon pair source, ultra-low-noise single-photon detectors and entanglement-assisted clock synchronization. The average teleported state fidelity is well beyond the classical limit of two-thirds. Furthermore, we confirm the quality of the quantum teleportation procedure without feed-forward by complete quantum process tomography. Our experiment verifies the maturity and applicability of such technologies in real-world scenarios, in particular for future satellite-based quantum teleportation.
Faraggi, Eshel; Xue, Bin; Zhou, Yaoqi
2009-03-01
This article attempts to increase the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins through improved learning. Most methods developed for improving the backpropagation algorithm of artificial neural networks are limited to small neural networks. Here, we introduce a guided-learning method suitable for networks of any size. The method employs a part of the weights for guiding and the other part for training and optimization. We demonstrate this technique by predicting residue solvent accessibility and real-value backbone torsion angles of proteins. In this application, the guiding factor is designed to satisfy the intuitive condition that for most residues, the contribution of a residue to the structural properties of another residue is smaller for greater separation in the protein-sequence distance between the two residues. We show that the guided-learning method makes a 2-4% reduction in 10-fold cross-validated mean absolute errors (MAE) for predicting residue solvent accessibility and backbone torsion angles, regardless of the size of database, the number of hidden layers and the size of input windows. This together with introduction of two-layer neural network with a bipolar activation function leads to a new method that has a MAE of 0.11 for residue solvent accessibility, 36 degrees for psi, and 22 degrees for phi. The method is available as a Real-SPINE 3.0 server in http://sparks.informatics.iupui.edu.
Feed-forward segmentation of figure-ground and assignment of border-ownership.
Hans Supèr
Full Text Available Figure-ground is the segmentation of visual information into objects and their surrounding backgrounds. Two main processes herein are boundary assignment and surface segregation, which rely on the integration of global scene information. Recurrent processing either by intrinsic horizontal connections that connect surrounding neurons or by feedback projections from higher visual areas provide such information, and are considered to be the neural substrate for figure-ground segmentation. On the contrary, a role of feedforward projections in figure-ground segmentation is unknown. To have a better understanding of a role of feedforward connections in figure-ground organization, we constructed a feedforward spiking model using a biologically plausible neuron model. By means of surround inhibition our simple 3-layered model performs figure-ground segmentation and one-sided border-ownership coding. We propose that the visual system uses feed forward suppression for figure-ground segmentation and border-ownership assignment.
Optimizing information flow in small genetic networks. II. Feed-forward interactions.
Walczak, Aleksandra M; Tkacik, Gasper; Bialek, William
2010-04-01
Central to the functioning of a living cell is its ability to control the readout or expression of information encoded in the genome. In many cases, a single transcription factor protein activates or represses the expression of many genes. As the concentration of the transcription factor varies, the target genes thus undergo correlated changes, and this redundancy limits the ability of the cell to transmit information about input signals. We explore how interactions among the target genes can reduce this redundancy and optimize information transmission. Our discussion builds on recent work [Tkacik, Phys. Rev. E 80, 031920 (2009)], and there are connections to much earlier work on the role of lateral inhibition in enhancing the efficiency of information transmission in neural circuits; for simplicity we consider here the case where the interactions have a feed forward structure, with no loops. Even with this limitation, the networks that optimize information transmission have a structure reminiscent of the networks found in real biological systems.
Feed-forward regulation of phagocytosis by Entamoeba histolytica.
Sateriale, Adam; Vaithilingam, Archana; Donnelly, Liam; Miller, Peter; Huston, Christopher D
2012-12-01
The parasitic protozoan Entamoeba histolytica is aptly named for its capacity to destroy host tissue. When E. histolytica trophozoites invade the lamina propria of a host colon, extracellular matrices are degraded while host cells are killed and phagocytosed. The ability of E. histolytica to phagocytose host cells correlates with virulence in vivo. In order to better understand the mechanism of phagocytosis, we used an E. histolytica Affymetrix microarray chip to measure the total gene expression of phagocytic and nonphagocytic subpopulations. Using paramagnetic beads coated with a known host ligand that stimulates phagocytosis, phagocytic and nonphagocytic amoebae from a single culture were purified. Microarray analysis of the subpopulations identified 121 genes with >2-fold higher expression in phagocytic than in nonphagocytic amoebae. Functional annotation identified genes encoding proteins involved in actin binding and cytoskeletal organization as highly enriched gene clusters. Post hoc analyses of selected genes showed that the gene expression profile identified in the microarray experiment did not exist prior to cell sorting but rather was stimulated through phagocytosis. Further, these expression profiles correlated with an increase in phagocytic ability, as E. histolytica cultures exposed to an initial stimulus of phagocytosis showed increased phagocytic ability upon a second stimulus. To our knowledge, this is the first description of such feed-forward regulation of gene expression and phagocytic ability in a phagocyte.
Adaptive Feed-Forward Control of Low Frequency Interior Noise
Kletschkowski, Thomas
2012-01-01
This book presents a mechatronic approach to Active Noise Control (ANC). It describes the required elements of system theory, engineering acoustics, electroacoustics and adaptive signal processing in a comprehensive, consistent and systematic manner using a unified notation. Furthermore, it includes a design methodology for ANC-systems, explains its application and describes tools to be used for ANC-system design. From the research point of view, the book presents new approaches to sound source localization in weakly damped interiors. One is based on the inverse finite element method, the other is based on a sound intensity probe with an active free field. Furthermore, a prototype of an ANC-system able to reach the physical limits of local (feed-forward) ANC is described. This is one example for applied research in ANC-system design. Other examples are given for (i) local ANC in a semi-enclosed subspace of an aircraft cargo hold and (ii) for the combination of audio entertainment with ANC.
On Using a Support Vector Machine in Learning Feed-Forward Control
de Kruif, B.J.; de Vries, Theodorus J.A.
2001-01-01
For mechatronic motion systems, the performance increases significantly if, besides feedback control, also feed-forward control is used. This feed-forward part should contain the (stable part of the) inverse of the plant. This inverse is difficult to obtain if non-linear dynamics are present. To
On Using a Support Vector Machine in Learning Feed-Forward Control
Kruif, de Bas J.; Vries, de Theo J.A.
2001-01-01
For mechatronic motion systems, the performance increases significantly if, besides feedback control, also feed-forward control is used. This feed-forward part should contain the (stable part of the) inverse of the plant. This inverse is difficult to obtain if non-linear dynamics are present. To ove
Conrad, Finn; Zhou, Jianjun; Gabacik, Andrzej;
1998-01-01
Invited paper presents a new control algorithm based on feed-forward geometrical compensation strategy combined with adaptive feedback control.......Invited paper presents a new control algorithm based on feed-forward geometrical compensation strategy combined with adaptive feedback control....
Murphy, Karen; Barry, Shane
2016-01-01
Presentation feedback can be limited in its feed-forward value, as students do not have their actual presentation available for review whilst reflecting upon the feedback. This study reports on students' perceptions of the learning and feed-forward value of an oral presentation assessment. Students self-marked their performance immediately after…
Feed-forward motor control of ultrafast, ballistic movements.
Kagaya, K; Patek, S N
2016-02-01
To circumvent the limits of muscle, ultrafast movements achieve high power through the use of springs and latches. The time scale of these movements is too short for control through typical neuromuscular mechanisms, thus ultrafast movements are either invariant or controlled prior to movement. We tested whether mantis shrimp (Stomatopoda: Neogonodactylus bredini) vary their ultrafast smashing strikes and, if so, how this control is achieved prior to movement. We collected high-speed images of strike mechanics and electromyograms of the extensor and flexor muscles that control spring compression and latch release. During spring compression, lateral extensor and flexor units were co-activated. The strike initiated several milliseconds after the flexor units ceased, suggesting that flexor activity prevents spring release and determines the timing of strike initiation. We used linear mixed models and Akaike's information criterion to serially evaluate multiple hypotheses for control mechanisms. We found that variation in spring compression and strike angular velocity were statistically explained by spike activity of the extensor muscle. The results show that mantis shrimp can generate kinematically variable strikes and that their kinematics can be changed through adjustments to motor activity prior to the movement, thus supporting an upstream, central-nervous-system-based control of ultrafast movement. Based on these and other findings, we present a shishiodoshi model that illustrates alternative models of control in biological ballistic systems. The discovery of feed-forward control in mantis shrimp sets the stage for the assessment of targets, strategic variation in kinematics and the role of learning in ultrafast animals. © 2016. Published by The Company of Biologists Ltd.
Optimal Feed Forward MLPArchitecture for Off-Line Cursive Numeral Recognition
Vijaypal Singh Dhaka
2010-01-01
Full Text Available The purpose of this work is to analyze the performance of back-propagation feed-forward algorithm using various different activation functions for the neurons of hidden and output layer and varying the number of neurons in the hidden layer. For sample creation, 250 numerals were gathered form 35 people of different ages including male and female. After binarization, these numerals were clubbed together to form training patterns for the neural network. Network was trained to learn its behavior by adjusting the connection strengths at every iteration. The conjugate gradient descent of each presented training pattern was calculated to identify the minima on the error surface for each training pattern. Experiments were performed by selecting different combinations of two activation functions out of the three activation functions logsig, tansig and purelin for the neurons of the hidden and output layers and the results revealed that as the number of neurons in the hidden layer is increased, the network gets trained in small number of epochs and the percentage recognition accuracy of the neural network was observed to increase up to certain level and then it starts decreasing when number of hidden neurons exceeds a certain level.
Unlearning in feed-forward multi-nets
Spaanenburg, L; Kurkova,; Steele, NC; Neruda, R; Karny, M
2001-01-01
Multi-nets promise an improved performance over monolithic neural networks by virtue of their distributed implementation. Modular neural networks are multi-nets based on an judicious assembly of functionally different parts. This can be viewed as again a monolithic network, but with more complex neu
Sasse, Sarah K; Gerber, Anthony N
2015-01-01
Nuclear receptors (NRs) are widely targeted to treat a range of human diseases. Feed-forward loops are an ancient mechanism through which single cell organisms organize transcriptional programming and modulate gene expression dynamics, but they have not been systematically studied as a regulatory paradigm for NR-mediated transcriptional responses. Here, we provide an overview of the basic properties of feed-forward loops as predicted by mathematical models and validated experimentally in single cell organisms. We review existing evidence implicating feed-forward loops as important in controlling clinically relevant transcriptional responses to estrogens, progestins, and glucocorticoids, among other NR ligands. We propose that feed-forward transcriptional circuits are a major mechanism through which NRs integrate signals, exert temporal control over gene regulation, and compartmentalize client transcriptomes into discrete subunits. Implications for the design and function of novel selective NR ligands are discussed.
The role of feed-forward and feedback processes for closed-loop prosthesis control
Saunders Ian
2011-10-01
Full Text Available Abstract Background It is widely believed that both feed-forward and feed-back mechanisms are required for successful object manipulation. Open-loop upper-limb prosthesis wearers receive no tactile feedback, which may be the cause of their limited dexterity and compromised grip force control. In this paper we ask whether observed prosthesis control impairments are due to lack of feedback or due to inadequate feed-forward control. Methods Healthy subjects were fitted with a closed-loop robotic hand and instructed to grasp and lift objects of different weights as we recorded trajectories and force profiles. We conducted three experiments under different feed-forward and feed-back configurations to elucidate the role of tactile feedback (i in ideal conditions, (ii under sensory deprivation, and (iii under feed-forward uncertainty. Results (i We found that subjects formed economical grasps in ideal conditions. (ii To our surprise, this ability was preserved even when visual and tactile feedback were removed. (iii When we introduced uncertainty into the hand controller performance degraded significantly in the absence of either visual or tactile feedback. Greatest performance was achieved when both sources of feedback were present. Conclusions We have introduced a novel method to understand the cognitive processes underlying grasping and lifting. We have shown quantitatively that tactile feedback can significantly improve performance in the presence of feed-forward uncertainty. However, our results indicate that feed-forward and feed-back mechanisms serve complementary roles, suggesting that to improve on the state-of-the-art in prosthetic hands we must develop prostheses that empower users to correct for the inevitable uncertainty in their feed-forward control.
A dendritic lattice neural network for color image segmentation
Urcid, Gonzalo; Lara-Rodríguez, Luis David; López-Meléndez, Elizabeth
2015-09-01
A two-layer dendritic lattice neural network is proposed to segment color images in the Red-Green-Blue (RGB) color space. The two layer neural network is a fully interconnected feed forward net consisting of an input layer that receives color pixel values, an intermediate layer that computes pixel interdistances, and an output layer used to classify colors by hetero-association. The two-layer net is first initialized with a finite small subset of the colors present in the input image. These colors are obtained by means of an automatic clustering procedure such as k-means or fuzzy c-means. In the second stage, the color image is scanned on a pixel by pixel basis where each picture element is treated as a vector and feeded into the network. For illustration purposes we use public domain color images to show the performance of our proposed image segmentation technique.
Oscillations via Spike-Timing Dependent Plasticity in a Feed-Forward Model.
Yotam Luz
2016-04-01
Full Text Available Neuronal oscillatory activity has been reported in relation to a wide range of cognitive processes including the encoding of external stimuli, attention, and learning. Although the specific role of these oscillations has yet to be determined, it is clear that neuronal oscillations are abundant in the central nervous system. This raises the question of the origin of these oscillations: are the mechanisms for generating these oscillations genetically hard-wired or can they be acquired via a learning process? Here, we study the conditions under which oscillatory activity emerges through a process of spike timing dependent plasticity (STDP in a feed-forward architecture. First, we analyze the effect of oscillations on STDP-driven synaptic dynamics of a single synapse, and study how the parameters that characterize the STDP rule and the oscillations affect the resultant synaptic weight. Next, we analyze STDP-driven synaptic dynamics of a pre-synaptic population of neurons onto a single post-synaptic cell. The pre-synaptic neural population is assumed to be oscillating at the same frequency, albeit with different phases, such that the net activity of the pre-synaptic population is constant in time. Thus, in the homogeneous case in which all synapses are equal, the post-synaptic neuron receives constant input and hence does not oscillate. To investigate the transition to oscillatory activity, we develop a mean-field Fokker-Planck approximation of the synaptic dynamics. We analyze the conditions causing the homogeneous solution to lose its stability. The findings show that oscillatory activity appears through a mechanism of spontaneous symmetry breaking. However, in the general case the homogeneous solution is unstable, and the synaptic dynamics does not converge to a different fixed point, but rather to a limit cycle. We show how the temporal structure of the STDP rule determines the stability of the homogeneous solution and the drift velocity of the
Oscillations via Spike-Timing Dependent Plasticity in a Feed-Forward Model.
Luz, Yotam; Shamir, Maoz
2016-04-01
Neuronal oscillatory activity has been reported in relation to a wide range of cognitive processes including the encoding of external stimuli, attention, and learning. Although the specific role of these oscillations has yet to be determined, it is clear that neuronal oscillations are abundant in the central nervous system. This raises the question of the origin of these oscillations: are the mechanisms for generating these oscillations genetically hard-wired or can they be acquired via a learning process? Here, we study the conditions under which oscillatory activity emerges through a process of spike timing dependent plasticity (STDP) in a feed-forward architecture. First, we analyze the effect of oscillations on STDP-driven synaptic dynamics of a single synapse, and study how the parameters that characterize the STDP rule and the oscillations affect the resultant synaptic weight. Next, we analyze STDP-driven synaptic dynamics of a pre-synaptic population of neurons onto a single post-synaptic cell. The pre-synaptic neural population is assumed to be oscillating at the same frequency, albeit with different phases, such that the net activity of the pre-synaptic population is constant in time. Thus, in the homogeneous case in which all synapses are equal, the post-synaptic neuron receives constant input and hence does not oscillate. To investigate the transition to oscillatory activity, we develop a mean-field Fokker-Planck approximation of the synaptic dynamics. We analyze the conditions causing the homogeneous solution to lose its stability. The findings show that oscillatory activity appears through a mechanism of spontaneous symmetry breaking. However, in the general case the homogeneous solution is unstable, and the synaptic dynamics does not converge to a different fixed point, but rather to a limit cycle. We show how the temporal structure of the STDP rule determines the stability of the homogeneous solution and the drift velocity of the limit cycle.
Constructive neural network learning
Lin, Shaobo; Zeng, Jinshan; Zhang, Xiaoqin
2016-01-01
In this paper, we aim at developing scalable neural network-type learning systems. Motivated by the idea of "constructive neural networks" in approximation theory, we focus on "constructing" rather than "training" feed-forward neural networks (FNNs) for learning, and propose a novel FNNs learning system called the constructive feed-forward neural network (CFN). Theoretically, we prove that the proposed method not only overcomes the classical saturation problem for FNN approximation, but also ...
Second-Order Feed-Forward Renderingfor Specular and Glossy Reflections.
Wang, Lili; Xie, Naiwen; Ke, Wei; Popescu, Voicu
2014-09-01
The feed-forward pipeline based on projection followed by rasterization handles the rays that leave the eye efficiently: these first-order rays are modeled with a simple camera that projects geometry to screen. Second-order rays however, as, for example, those resulting from specular reflections, are challenging for the feed-forward approach. We propose an extension of the feed-forward pipeline to handle second-order rays resulting from specular and glossy reflections. The coherence of second-order rays is leveraged through clustering, the geometry reflected by a cluster is approximated with a depth image, and the color samples captured by the second-order rays of a cluster are computed by intersection with the depth image. We achieve quality specular and glossy reflections at interactive rates in fully dynamic scenes.
Concatenated beam splitters, optical feed-forward and the nonlinear sign gate
Jacobs, K; Jacobs, Kurt; Dowling, Jonathan P.
2006-01-01
We consider a nonlinear sign gate implemented using a sequence of two beam splitters, and consider the use of further sequences of beam splitters to implement feed-forward so as to correct an error resulting from the first beam splitter. We obtain similar results to Scheel et al. [Scheel et al., Phys. Rev. A 73, 034301 (2006)], in that we also find that our feed-forward procedure is only able to produce a very minor improvement in the success probability of the original gate.
Simple Digital Feed-Forward Circuit to Compensate for AOM Thermal Lensing
Hill, Joshua; Aman, James; Killian, Thomas; Neutral Experiment Team
2016-05-01
I demonstrate a simple digital feed-forward circuit which, when combined with two-frequency radio frequency (RF) electronics, maintains constant total RF power driving an acousto-optic modulator (AOM). Consistency in total power is desirable to mitigate thermal lensing effects that otherwise displace and misshape the laser beam when the primary frequency drive RF power is changed to, for example, alter the laser power in a diffracted beam. The Arduino-based feed-forward circuit is cost-effective, quick to implement, and easily modified.
Learning Processes of Layered Neural Networks
Fujiki, Sumiyoshi; FUJIKI, Nahomi, M.
1995-01-01
A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward neural network, and a learning equation similar to that of the Boltzmann machine algorithm is obtained. By applying a mean field approximation to the same stochastic feed-forward neural network, a deterministic analog feed-forward network is obtained and the back-propagation learning rule is re-derived.
Learning Algorithms of Multilayer Neural Networks
Fujiki, Sumiyoshi; FUJIKI, Nahomi, M.
1996-01-01
A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward multilayer neural network, with far interlayer synaptic connections, and we obtain a learning rule similar to that of the Boltzmann machine on the same multilayer structure. By applying a mean field approximation to the stochastic feed-forward neural network, the generalized error back-propagation learning rule is derived for a deterministic analog feed-forward multilayer network with the far interlay...
Nicola, Victor F.; Zaburnenko, Tatiana S.
2006-01-01
In this paper we propose a state-dependent importance sampling heuristic to estimate the probability of population overﬂow in feed-forward networks. This heuristic attempts to approximate the “optimal” state-dependent change of measure without the need for difficult analysis or costly optimization i
High-speed linear optics quantum computing using active feed-forward.
Prevedel, Robert; Walther, Philip; Tiefenbacher, Felix; Böhi, Pascal; Kaltenbaek, Rainer; Jennewein, Thomas; Zeilinger, Anton
2007-01-04
As information carriers in quantum computing, photonic qubits have the advantage of undergoing negligible decoherence. However, the absence of any significant photon-photon interaction is problematic for the realization of non-trivial two-qubit gates. One solution is to introduce an effective nonlinearity by measurements resulting in probabilistic gate operations. In one-way quantum computation, the random quantum measurement error can be overcome by applying a feed-forward technique, such that the future measurement basis depends on earlier measurement results. This technique is crucial for achieving deterministic quantum computation once a cluster state (the highly entangled multiparticle state on which one-way quantum computation is based) is prepared. Here we realize a concatenated scheme of measurement and active feed-forward in a one-way quantum computing experiment. We demonstrate that, for a perfect cluster state and no photon loss, our quantum computation scheme would operate with good fidelity and that our feed-forward components function with very high speed and low error for detected photons. With present technology, the individual computational step (in our case the individual feed-forward cycle) can be operated in less than 150 ns using electro-optical modulators. This is an important result for the future development of one-way quantum computers, whose large-scale implementation will depend on advances in the production and detection of the required highly entangled cluster states.
Liu Cheng, E-mail: liuch_2004@stu.xjtu.edu.c [School of Energy and Power Engineering, Xi' an Jiaotong University, Xi' an, Shaanxi 710049 (China); Zhao Fuyu; Hu Ping; Hou Suxia; Li Chong [School of Energy and Power Engineering, Xi' an Jiaotong University, Xi' an, Shaanxi 710049 (China)
2010-01-15
In this paper, a P controller with partial feed forward compensation and decoupling control for the steam generator water level is presented. While taking the steam flowrate as a disturbance to water level, the controller design can be completed in three stages. (1) Main circuit controller is designed without regard to disturbance. Since the transfer function of the steam generator model contains integrate element and differential element, the proportional (P) controller can selected as main circuit controller instead of PID controller for steam generator water level. (2) Partial feed forward compensation is introduced to remove the disturbance from the steam flowrate. If disregarding the differential element, the partial feed forward compensation's designing turns to be very simple. Partial feed forward compensation coefficient is set as reciprocal of P controller gain. (3) The coupling effects between the water level regulating and steam flowrate disturbance can be decreased by model reference decoupling control. The proposed methodology shows satisfactory transient responses, disturbance rejection and robustness.
Balancing feed-forward excitation and inhibition via Hebbian inhibitory synaptic plasticity.
Yotam Luz
2012-01-01
Full Text Available It has been suggested that excitatory and inhibitory inputs to cortical cells are balanced, and that this balance is important for the highly irregular firing observed in the cortex. There are two hypotheses as to the origin of this balance. One assumes that it results from a stable solution of the recurrent neuronal dynamics. This model can account for a balance of steady state excitation and inhibition without fine tuning of parameters, but not for transient inputs. The second hypothesis suggests that the feed forward excitatory and inhibitory inputs to a postsynaptic cell are already balanced. This latter hypothesis thus does account for the balance of transient inputs. However, it remains unclear what mechanism underlies the fine tuning required for balancing feed forward excitatory and inhibitory inputs. Here we investigated whether inhibitory synaptic plasticity is responsible for the balance of transient feed forward excitation and inhibition. We address this issue in the framework of a model characterizing the stochastic dynamics of temporally anti-symmetric Hebbian spike timing dependent plasticity of feed forward excitatory and inhibitory synaptic inputs to a single post-synaptic cell. Our analysis shows that inhibitory Hebbian plasticity generates 'negative feedback' that balances excitation and inhibition, which contrasts with the 'positive feedback' of excitatory Hebbian synaptic plasticity. As a result, this balance may increase the sensitivity of the learning dynamics to the correlation structure of the excitatory inputs.
Feed-Forward versus Feedback Inhibition in a Basic Olfactory Circuit.
Tiffany Kee
2015-10-01
Full Text Available Inhibitory interneurons play critical roles in shaping the firing patterns of principal neurons in many brain systems. Despite difference in the anatomy or functions of neuronal circuits containing inhibition, two basic motifs repeatedly emerge: feed-forward and feedback. In the locust, it was proposed that a subset of lateral horn interneurons (LHNs, provide feed-forward inhibition onto Kenyon cells (KCs to maintain their sparse firing--a property critical for olfactory learning and memory. But recently it was established that a single inhibitory cell, the giant GABAergic neuron (GGN, is the main and perhaps sole source of inhibition in the mushroom body, and that inhibition from this cell is mediated by a feedback (FB loop including KCs and the GGN. To clarify basic differences in the effects of feedback vs. feed-forward inhibition in circuit dynamics we here use a model of the locust olfactory system. We found both inhibitory motifs were able to maintain sparse KCs responses and provide optimal odor discrimination. However, we further found that only FB inhibition could create a phase response consistent with data recorded in vivo. These findings describe general rules for feed-forward versus feedback inhibition and suggest GGN is potentially capable of providing the primary source of inhibition to the KCs. A better understanding of how inhibitory motifs impact post-synaptic neuronal activity could be used to reveal unknown inhibitory structures within biological networks.
Proposed Feed Forward Correction for the CLIC Ring-To-Main-Linac Transfer Lines
Apsimon, Robert; Uythoven, Jan
2014-01-01
To achieve the design luminosity for the CLIC main beam an unprecedented degree of machine stability is required. Extremely stringent tolerances are placed on the damping ring extraction system in order to limit emittance growth along the ring-to-main-linac transfer line; particularly through the pre-linac betatron collimation system. In this paper we propose feed forward systems situated across the central arcs and turnaround loops of the transfer lines as an elegant solution to relax the damping ring extraction requirements as well as to significantly reduce emittance growth through the betatron collimation system. The optics for the beam position monitor and kicker regions are presented and the results of tracking simulations shown to verify the performance of the feed forward systems.
Feed-Forward Corrections for Tune and Chromaticity Injection Decay During 2015 LHC Operation
Solfaroli Camillocci, Matteo; Lamont, Mike; Schaumann, Michaela; Todesco, Ezio; Wenninger, Jorg
2016-01-01
After two years of shutdown, the Large Hadron Collider (LHC) has been operated in 2015 at 6.5 TeV, close to its designed energy. When the current is stable at low field, the harmonic components of the main circuits are subject to a dynamic variation induced by current redistribution on the superconducting cables. The Field Description of the LHC (FiDel) foresaw an increase of the decay at injection of tune (quadrupolar components) and chromaticity (sextupolar components) of about 50% with respect to LHC Run1 due to the higher operational current. This paper discusses the beam-based measurements of the decay during the injection plateau and the implementation and accuracy of the feed-forward corrections as present in 2015. Moreover, the observed tune shift proportional to the circulating beam intensity and it's foreseen feed-forward correction are covered.
Feed-forward inhibition: a novel cellular mechanism for the analgesic effect of substance P
Yoshimura Megumu
2005-11-01
Full Text Available Abstract Substance P (SP is a neuropeptide well known for its contribution to pain transmission in the spinal cord, however, less is known about the possible modulatory effects of SP. A new study by Gu and colleagues, published in Molecular Pain (2005, 1:20, describes its potential role in feed-forward inhibition in lamina V of the dorsal horn of the spinal cord. This inhibition seems to function through a direct excitation of GABAergic interneurons by substance P released from primary afferent fibers and has a distinct temporal phase of action from the well-described glutamate-dependent feed-forward inhibition. It is believed that through this inhibition, substance P can balance nociceptive output from the spinal cord.
Evidence Feed Forward Hidden Markov Model: A New Type Of Hidden Markov Model
Michael Del Rose
2011-01-01
Full Text Available The ability to predict the intentions of people based solely on their visual actions is a skill only performed by humans and animals. The intelligence of current computer algorithms has not reached this level of complexity, but there are several research efforts that are working towards it. With the number of classification algorithms available, it is hard to determine which algorithm works best for a particular situation. In classification of visual human intent data, Hidden Markov Models (HMM, and their variants, are leading candidates. The inability of HMMs to provide a probability in the observation to observation linkages is a big downfall in this classification technique. If a person is visually identifying an action of another person, they monitor patterns in the observations. By estimating the next observation, people have the ability to summarize the actions, and thus determine, with pretty good accuracy, the intention of the person performing the action. These visual cues and linkages are important in creating intelligent algorithms for determining human actions based on visual observations. The Evidence Feed Forward Hidden Markov Model is a newly developed algorithm which provides observation to observation linkages. The following research addresses the theory behind Evidence Feed Forward HMMs, provides mathematical proofs of their learning of these parameters to optimize the likelihood of observations with a Evidence Feed Forwards HMM, which is important in all computational intelligence algorithm, and gives comparative examples with standard HMMs in classification of both visual action data and measurement data; thus providing a strong base for Evidence Feed Forward HMMs in classification of many types of problems.
Feed-forward and feedback projections of midbrain reticular formation neurons in the cat
Eddie ePerkins
2014-01-01
Full Text Available Gaze changes involving the eyes and head are orchestrated by brainstem gaze centers found within the superior colliculus (SC, paramedian pontine reticular formation (PPRF, and medullary reticular formation (MdRF. The mesencephalic reticular formation (MRF also plays a role in gaze. It receives a major input from the ipsilateral SC and contains cells that fire in relation to gaze changes. Moreover, it provides a feedback projection to the SC and feed-forward projections to the PPRF and MdRF. We sought to determine whether these MRF feedback and feed-forward projections originate from the same or different neuronal populations by utilizing paired fluorescent retrograde tracers in cats. Specifically, we tested: 1. whether MRF neurons that control eye movements form a single population by injecting the SC and PPRF with different tracers, and 2. whether MRF neurons that control head movements form a single population by injecting the SC and MdRF with different tracers. In neither case were double labeled neurons observed, indicating that feedback and feed-forward projections originate from separate MRF populations. In both cases, the labeled reticulotectal and reticuloreticular neurons were distributed bilaterally in the MRF. However, neurons projecting to the MdRF were generally constrained to the medial half of the MRF, while those projecting to the PPRF, like MRF reticulotectal neurons, were spread throughout the mediolateral axis. Thus, the medial MRF may be specialized for control of head movements, with control of eye movements being more widespread in this structure.
Feed-forward Control Nursing Model in Expectant Treatment of Placenta Previa.
Zhu, Yanfei; Zhang, Shuxuan; Shan, Wenxian; Hu, Ming
2017-02-01
We studied the possible advantages of feed-forward control nursing model in the treatment of placenta previa. We enrolled 60 pregnant women who were receiving treatment for expectant placenta previa between January 2010 and January 2016 and randomly divided them into the control group and the observation group with 30 cases in each group. In the control group, we offered specialist nursing which included examination, body positioning, vaginal bleeding record, psychological consultation and medication observation. Feed-forward control nursing was applied in the observation group which included establishing feed-forward control nursing improvement team, conducting quality control of nursing defects and putting forward ideas for improvements and verifying improvement outcomes. The observation group got significantly higher success rate and lower complication rate compared with control group. Gestational age and fetal weights improved apparently in the observation group. When we compared the amount of postpartum bleeding and pregnancy bleeding in two groups we did not find any statistically significant difference (P>0.05). Patients' satisfaction rate toward our nursing services was much higher in the observation group and the rate of nursing errors was significantly lower in this group. All differences were statistically significant (Pplacenta previa can improve treatment success rate, decrease complications and upgrade nursing quality.
Feed-forward control of the flow over a backward-facing step
Juillet, Fabien; Schmid, Peter; McKeon, Beverley
2012-11-01
In this study, the control of incoming perturbations in convection-dominated flows is analyzed numerically and experimentally. For this purpose, multiple sensors and actuators are used. First, a model is built from input and output data sequences using a least-squares system identification. Then, a feed-forward Model Predicitive Controller (MPC) is designed. It appears that feed-forward control is particularly relevant when applied to convection-dominated flows. A very general and flexible formulation of the technique is introduced and validated on the flow over a backward-facing step. Although the objective sensors are localized on the walls, the impact of the control is more global and perturbations are also reduced in the middle of the channel. The coupling of system identification together with feed-forward control was found to be a flexible, efficient and experimentally feasible strategy. In particular, the successful numerical control is further supported by experimental results. Support from Ecole Polytechnique and the Partner University Fund (PUF) is gratefully acknowledged.
Global Feed-Forward Vibration Isolation in a km scale Interferometer
DeRosa, Ryan; Atkinson, Dani; Miao, Haixing; Frolov, Valery; Landry, Michael; Giaime, Joseph; Adhikari, Rana
2012-01-01
Using a network of seismometers and sets of optimal filters, we implemented a feed-forward control technique to minimize the seismic contribution to multiple interferometric degrees of freedom of the LIGO interferometers. The filters are constructed by using the Levinson-Durbin recursion relation to approximate the optimal Wiener filter. By reducing the RMS of the interferometer feedback signals below \\sim10 Hz, we have improved the stability and duty cycle of the joint network of gravitational wave detectors. By suppressing the large control forces and mirror motions, we have dramatically reduced the rate of non-Gaussian transients in the gravitational wave signal stream.
Compressive sensing reconstruction of feed-forward connectivity in pulse-coupled nonlinear networks
Barranca, Victor J.; Zhou, Douglas; Cai, David
2016-06-01
Utilizing the sparsity ubiquitous in real-world network connectivity, we develop a theoretical framework for efficiently reconstructing sparse feed-forward connections in a pulse-coupled nonlinear network through its output activities. Using only a small ensemble of random inputs, we solve this inverse problem through the compressive sensing theory based on a hidden linear structure intrinsic to the nonlinear network dynamics. The accuracy of the reconstruction is further verified by the fact that complex inputs can be well recovered using the reconstructed connectivity. We expect this Rapid Communication provides a new perspective for understanding the structure-function relationship as well as compressive sensing principle in nonlinear network dynamics.
Compressive sensing reconstruction of feed-forward connectivity in pulse-coupled nonlinear networks.
Barranca, Victor J; Zhou, Douglas; Cai, David
2016-06-01
Utilizing the sparsity ubiquitous in real-world network connectivity, we develop a theoretical framework for efficiently reconstructing sparse feed-forward connections in a pulse-coupled nonlinear network through its output activities. Using only a small ensemble of random inputs, we solve this inverse problem through the compressive sensing theory based on a hidden linear structure intrinsic to the nonlinear network dynamics. The accuracy of the reconstruction is further verified by the fact that complex inputs can be well recovered using the reconstructed connectivity. We expect this Rapid Communication provides a new perspective for understanding the structure-function relationship as well as compressive sensing principle in nonlinear network dynamics.
Voice Coil Motor Position Control Based on Feed-forward Fuzzy PID
尹峰松
2016-01-01
Conventional PID algorithm is unable to track the response with high frequency,and has obvious overshoot in some voice coil motor practical applications.So,combined with the fuzzy PID control theory,we can obtain the precise control by the method.Meanwhile,through the feed-forward control,the performance of quick response and dynamic tracking can be improved.Thus,this control method not only maintains the excellent performance of the controller,but also improves the stability of the system.
DESIGNING PHYSICAL EDUCATION LESSONS IN PRIMARY SCHOOL BY CONTENT TYPE FEED-FORWARD
Cojanu Florin
2010-06-01
Full Text Available In actual didactic design is need to anticipate problems that may arise during implementation of proposed interdisciplinary content in the physical education lesson in class, by projecting sequential forward type of content, there by ensuring quality and efficiency. Its necessary to include in the design content of physical education lessons in primary sequence type of feed-forward, to increase the quality and effectiveness of physical education lessons at the operational objectives achieved. To development modern didactics of physical education we can keep some purchases of traditionalteaching, but still with emphasis currently reconsidering its entire system on the content, forms, methods of education.
Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control †
René Felix Reinhart
2017-02-01
Full Text Available Feed-forward model-based control relies on models of the controlled plant, e.g., in robotics on accurate knowledge of manipulator kinematics or dynamics. However, mechanical and analytical models do not capture all aspects of a plant’s intrinsic properties and there remain unmodeled dynamics due to varying parameters, unmodeled friction or soft materials. In this context, machine learning is an alternative suitable technique to extract non-linear plant models from data. However, fully data-based models suffer from inaccuracies as well and are inefficient if they include learning of well known analytical models. This paper thus argues that feed-forward control based on hybrid models comprising an analytical model and a learned error model can significantly improve modeling accuracy. Hybrid modeling here serves the purpose to combine the best of the two modeling worlds. The hybrid modeling methodology is described and the approach is demonstrated for two typical problems in robotics, i.e., inverse kinematics control and computed torque control. The former is performed for a redundant soft robot and the latter for a rigid industrial robot with redundant degrees of freedom, where a complete analytical model is not available for any of the platforms.
Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control †.
Reinhart, René Felix; Shareef, Zeeshan; Steil, Jochen Jakob
2017-02-08
Feed-forward model-based control relies on models of the controlled plant, e.g., in robotics on accurate knowledge of manipulator kinematics or dynamics. However, mechanical and analytical models do not capture all aspects of a plant's intrinsic properties and there remain unmodeled dynamics due to varying parameters, unmodeled friction or soft materials. In this context, machine learning is an alternative suitable technique to extract non-linear plant models from data. However, fully data-based models suffer from inaccuracies as well and are inefficient if they include learning of well known analytical models. This paper thus argues that feed-forward control based on hybrid models comprising an analytical model and a learned error model can significantly improve modeling accuracy. Hybrid modeling here serves the purpose to combine the best of the two modeling worlds. The hybrid modeling methodology is described and the approach is demonstrated for two typical problems in robotics, i.e., inverse kinematics control and computed torque control. The former is performed for a redundant soft robot and the latter for a rigid industrial robot with redundant degrees of freedom, where a complete analytical model is not available for any of the platforms.
Top-level dynamics and the regulated gene response of feed-forward loop transcriptional motifs
Mayo, Michael; Abdelzaher, Ahmed; Perkins, Edward J.; Ghosh, Preetam
2014-09-01
Feed-forward loops are hierarchical three-node transcriptional subnetworks, wherein a top-level protein regulates the activity of a target gene via two paths: a direct-regulatory path, and an indirect route, whereby the top-level proteins act implicitly through an intermediate transcription factor. Using a transcriptional network of the model bacterium Escherichia coli, we confirmed that nearly all types of feed-forward loop were significantly overrepresented in the bacterial network. We then used mathematical modeling to study their dynamics by manipulating the rise times of the top-level protein concentration, termed the induction time, through alteration of the protein destruction rates. Rise times of the regulated proteins exhibited two qualitatively different regimes, depending on whether top-level inductions were "fast" or "slow." In the fast regime, rise times were nearly independent of rapid top-level inductions, indicative of biological robustness, and occurred when RNA production rate-limits the protein yield. Alternatively, the protein rise times were dependent upon slower top-level inductions, greater than approximately one bacterial cell cycle. An equation is given for this crossover, which depends upon three parameters of the direct-regulatory path: transcriptional cooperation at the DNA-binding site, a protein-DNA dissociation constant, and the relative magnitude of the top-level protien concentration.
Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control †
Reinhart, René Felix; Shareef, Zeeshan; Steil, Jochen Jakob
2017-01-01
Feed-forward model-based control relies on models of the controlled plant, e.g., in robotics on accurate knowledge of manipulator kinematics or dynamics. However, mechanical and analytical models do not capture all aspects of a plant’s intrinsic properties and there remain unmodeled dynamics due to varying parameters, unmodeled friction or soft materials. In this context, machine learning is an alternative suitable technique to extract non-linear plant models from data. However, fully data-based models suffer from inaccuracies as well and are inefficient if they include learning of well known analytical models. This paper thus argues that feed-forward control based on hybrid models comprising an analytical model and a learned error model can significantly improve modeling accuracy. Hybrid modeling here serves the purpose to combine the best of the two modeling worlds. The hybrid modeling methodology is described and the approach is demonstrated for two typical problems in robotics, i.e., inverse kinematics control and computed torque control. The former is performed for a redundant soft robot and the latter for a rigid industrial robot with redundant degrees of freedom, where a complete analytical model is not available for any of the platforms. PMID:28208697
Li, Zhifu; Hu, Yueming; Li, Di
2016-08-01
For a class of linear discrete-time uncertain systems, a feedback feed-forward iterative learning control (ILC) scheme is proposed, which is comprised of an iterative learning controller and two current iteration feedback controllers. The iterative learning controller is used to improve the performance along the iteration direction and the feedback controllers are used to improve the performance along the time direction. First of all, the uncertain feedback feed-forward ILC system is presented by an uncertain two-dimensional Roesser model system. Then, two robust control schemes are proposed. One can ensure that the feedback feed-forward ILC system is bounded-input bounded-output stable along time direction, and the other can ensure that the feedback feed-forward ILC system is asymptotically stable along time direction. Both schemes can guarantee the system is robust monotonically convergent along the iteration direction. Third, the robust convergent sufficient conditions are given, which contains a linear matrix inequality (LMI). Moreover, the LMI can be used to determine the gain matrix of the feedback feed-forward iterative learning controller. Finally, the simulation results are presented to demonstrate the effectiveness of the proposed schemes.
Scholbrock, A. K.; Fleming, P. A.; Fingersh, L. J.; Wright, A. D.; Schlipf, D.; Haizmann, F.; Belen, F.
2013-01-01
Wind turbines are complex, nonlinear, dynamic systems driven by aerodynamic, gravitational, centrifugal, and gyroscopic forces. The aerodynamics of wind turbines are nonlinear, unsteady, and complex. Turbine rotors are subjected to a chaotic three-dimensional (3-D) turbulent wind inflow field with imbedded coherent vortices that drive fatigue loads and reduce lifetime. In order to reduce cost of energy, future large multimegawatt turbines must be designed with lighter weight structures, using active controls to mitigate fatigue loads, maximize energy capture, and add active damping to maintain stability for these dynamically active structures operating in a complex environment. Researchers at the National Renewable Energy Laboratory (NREL) and University of Stuttgart are designing, implementing, and testing advanced feed-back and feed-forward controls in order to reduce the cost of energy for wind turbines.
Dwyer Cianciolo, Alicia M. (Editor)
2011-01-01
NASA senior management commissioned the Entry, Descent and Landing Systems Analysis (EDL-SA) Study in 2008 to identify and roadmap the Entry, Descent and Landing (EDL) technology investments that the agency needed to successfully land large payloads at Mars for both robotic and human-scale missions. Year 1 of the study focused on technologies required for Exploration-class missions to land payloads of 10 to 50 mt. Inflatable decelerators, rigid aeroshell and supersonic retro-propulsion emerged as the top candidate technologies. In Year 2 of the study, low TRL technologies identified in Year 1, inflatables aeroshells and supersonic retropropulsion, were combined to create a demonstration precursor robotic mission. This part of the EDL-SA Year 2 effort, called Exploration Feed Forward (EFF), took much of the systems analysis simulation and component model development from Year 1 to the next level of detail.
Sub-Shot-Noise Transmission Measurement Enabled by Active Feed-Forward of Heralded Single Photons
Sabines-Chesterking, J.; Whittaker, R.; Joshi, S. K.; Birchall, P. M.; Moreau, P. A.; McMillan, A.; Cable, H. V.; O'Brien, J. L.; Rarity, J. G.; Matthews, J. C. F.
2017-07-01
Harnessing the unique properties of quantum mechanics offers the possibility of delivering alternative technologies that can fundamentally outperform their classical counterparts. These technologies deliver advantages only when components operate with performance beyond specific thresholds. For optical quantum metrology, the biggest challenge that impacts on performance thresholds is optical loss. Here, we demonstrate how including an optical delay and an optical switch in a feed-forward configuration with a stable and efficient correlated photon-pair source reduces the detector efficiency required to enable quantum-enhanced sensing down to the detection level of single photons and without postselection. When the switch is active, we observe a factor of improvement in precision of 1.27 for transmission measurement on a per-input-photon basis compared to the performance of a laser emitting an ideal coherent state and measured with the same detection efficiency as our setup. When the switch is inoperative, we observe no quantum advantage.
Novel synchronous DPSK optical regenerator based on a feed-forward based carrier extraction scheme.
Ibrahim, Selwan K; Sygletos, Stylianos; Rafique, Danish; O'Dowd, John A; Weerasuriya, Ruwan; Ellis, Andrew D
2011-05-09
We experimentally demonstrate a novel synchronous 10.66 Gbit/s DPSK OEO regenerator which uses a feed-forward carrier extraction scheme with an injection-locked laser to synchronize the regenerated signal wavelength to the incoming signal wavelength. After injection-locking, a low-cost DFB laser used at the regenerator exhibited the same linewidth characteristics as the narrow line-width transmitter laser. The phase regeneration properties of the regenerator were evaluated by emulating random Gaussian phase noise applied to the DPSK signal before the regenerator using a phase modulator driven by an arbitrary waveform generator. The overall performance was evaluated in terms of electrical eye-diagrams, BER measurements, and constellation diagrams.
Overview of the NASA Entry, Descent and Landing Systems Analysis Exploration Feed-Forward Study
DwyerCianciolo, Alicia M.; Zang, Thomas A.; Sostaric, Ronald R.; McGuire, M. Kathy
2011-01-01
Technology required to land large payloads (20 to 50 mt) on Mars remains elusive. In an effort to identify the most viable investment path, NASA and others have been studying various concepts. One such study, the Entry, Descent and Landing Systems Analysis (EDLSA) Study [1] identified three potential options: the rigid aeroshell, the inflatable aeroshell and supersonic retropropulsion (SRP). In an effort to drive out additional levels of design detail, a smaller demonstrator, or exploration feed-forward (EFF), robotic mission was devised that utilized two of the three (inflatable aeroshell and SRP) high potential technologies in a configuration to demonstrate landing a two to four metric ton payload on Mars. This paper presents and overview of the maximum landed mass, inflatable aeroshell controllability and sensor suite capability assessments of the selected technologies and recommends specific technology areas for additional work.
Dwyer Ciancolo, Alicia M.; Davis, Jody L.; Engelund, Walter C.; Komar, D. R.; Queen, Eric M.; Samareh, Jamshid A.; Way, David W.; Zang, Thomas A.; Murch, Jeff G.; Krizan, Shawn A.; Olds, Aaron D.; Powell, Richard W.; Shidner, Jeremy D.; Kinney, Daivd J.; McGuire, M. Kathleen; Arnold, James O.; Covington, M. Alan; Sostaric, Ronald R.; Zumwalt, Carlie H.; Llama, Eduardo G.
2011-01-01
NASA senior management commissioned the Entry, Descent and Landing Systems Analysis (EDL-SA) Study in 2008 to identify and roadmap the Entry, Descent and Landing (EDL) technology investments that the agency needed to successfully land large payloads at Mars for both robotic and human-scale missions. Year 1 of the study focused on technologies required for Exploration-class missions to land payloads of 10 to 50 t. Inflatable decelerators, rigid aeroshell and supersonic retro-propulsion emerged as the top candidate technologies. In Year 2 of the study, low TRL technologies identified in Year 1, inflatables aeroshells and supersonic retropropulsion, were combined to create a demonstration precursor robotic mission. This part of the EDL-SA Year 2 effort, called Exploration Feed Forward (EFF), took much of the systems analysis simulation and component model development from Year 1 to the next level of detail.
Design of Phase Feed Forward System in CTF3 and Performance of Fast Beam Phase Monitors
Skowronski, P K; Ghigo, A; Marcellini, F; Burrows, PN; Christian, GB; Perry, C; Gerbershagen, A; Roberts, J; Ikarios, E
2013-01-01
The CLIC two beam acceleration technology requires a drive beam phase stability better than 0.3 deg rms at 12 GHz, corresponding to a timing stability below 50 fs rms. For this reason the CLIC design includes a phase stabilization feed-forward system. It relies on precise beam phase measurements and their subsequent correction in a chicane with the help of fast kickers. A prototype of such a system is being installed in the CLIC Test Facility CTF3. In this paper its design and implementation is described in detail. Additionally, the performance of the precision phase monitor prototypes installed at the end of the CTF3 linac, as measured with the drive beam, is presented.
Deterministic quantum teleportation with feed-forward in a solid state system.
Steffen, L; Salathe, Y; Oppliger, M; Kurpiers, P; Baur, M; Lang, C; Eichler, C; Puebla-Hellmann, G; Fedorov, A; Wallraff, A
2013-08-15
Engineered macroscopic quantum systems based on superconducting electronic circuits are attractive for experimentally exploring diverse questions in quantum information science. At the current state of the art, quantum bits (qubits) are fabricated, initialized, controlled, read out and coupled to each other in simple circuits. This enables the realization of basic logic gates, the creation of complex entangled states and the demonstration of algorithms or error correction. Using different variants of low-noise parametric amplifiers, dispersive quantum non-demolition single-shot readout of single-qubit states with high fidelity has enabled continuous and discrete feedback control of single qubits. Here we realize full deterministic quantum teleportation with feed-forward in a chip-based superconducting circuit architecture. We use a set of two parametric amplifiers for both joint two-qubit and individual qubit single-shot readout, combined with flexible real-time digital electronics. Our device uses a crossed quantum bus technology that allows us to create complex networks with arbitrary connecting topology in a planar architecture. The deterministic teleportation process succeeds with order unit probability for any input state, as we prepare maximally entangled two-qubit states as a resource and distinguish all Bell states in a single two-qubit measurement with high efficiency and high fidelity. We teleport quantum states between two macroscopic systems separated by 6 mm at a rate of 10(4) s(-1), exceeding other reported implementations. The low transmission loss of superconducting waveguides is likely to enable the range of this and other schemes to be extended to significantly larger distances, enabling tests of non-locality and the realization of elements for quantum communication at microwave frequencies. The demonstrated feed-forward may also find application in error correction schemes.
Wang, Haojie; Han, Minxiao; Yan, Wenli
2016-01-01
It is a common practice for storage batteries to be connected to DC microgrid buses through DC-DC converters for voltage support on islanded operation mode. A feed-forward control based dual-loop constant voltage PI control for three-branch interleaved DC-DC converters (TIDC) is proposed for stor......It is a common practice for storage batteries to be connected to DC microgrid buses through DC-DC converters for voltage support on islanded operation mode. A feed-forward control based dual-loop constant voltage PI control for three-branch interleaved DC-DC converters (TIDC) is proposed...... for storage batteries in DC microgrids. The working principle of TIDC is analyzed, and the factors influencing the response rate based on the dual-loop constant voltage control for TIDC are discussed, and then the method of feed-forward control for TIDC is studied to improve the response rate for load...
Haojie Wang
2016-07-01
Full Text Available It is a common practice for storage batteries to be connected to DC microgrid buses through DC-DC converters for voltage support on islanded operation mode. A feed-forward control based dual-loop constant voltage PI control for three-branch interleaved DC-DC converters (TIDC is proposed for storage batteries in DC microgrids. The working principle of TIDC is analyzed, and the factors influencing the response rate based on the dual-loop constant voltage control for TIDC are discussed, and then the method of feed-forward control for TIDC is studied to improve the response rate for load changing. A prototype of the TIDC is developed and an experimental platform is built. The experiment results show that DC bus voltage sags or swells caused by load changing can be reduced and the time for voltage recovery can be decreased significantly with the proposed feed-forward control.
Calderone, Luigi; Pinola, Licia; Varoli, Vincenzo
1992-04-01
The paper describes an analytical procedure to optimize the feed-forward compensation for any PWM dc/dc converters. The aims of achieving zero dc audiosusceptibility was found to be possible for the buck, buck-boost, Cuk, and SEPIC cells; for the boost converter, however, only nonoptimal compensation is feasible. Rules for the design of PWM controllers and procedures for the evaluation of the hardware-introduced errors are discussed. A PWM controller implementing the optimal feed-forward compensation for buck-boost, Cuk, and SEPIC cells is described and fully experimentally characterized.
Stability prediction of berm breakwater using neural network
Mandal, S.; Rao, S.; Manjunath, Y.R.
. In order to allow the network to learn both non-linear and linear relationships between input nodes and output nodes, multiple-layer networks are often used. Among many neural network architectures, the three layers feed forward backpropagation neural...
Development of an Accurate Feed-Forward Temperature Control Tankless Water Heater
David Yuill
2008-06-30
The following document is the final report for DE-FC26-05NT42327: Development of an Accurate Feed-Forward Temperature Control Tankless Water Heater. This work was carried out under a cooperative agreement from the Department of Energy's National Energy Technology Laboratory, with additional funding from Keltech, Inc. The objective of the project was to improve the temperature control performance of an electric tankless water heater (TWH). The reason for doing this is to minimize or eliminate one of the barriers to wider adoption of the TWH. TWH use less energy than typical (storage) water heaters because of the elimination of standby losses, so wider adoption will lead to reduced energy consumption. The project was carried out by Building Solutions, Inc. (BSI), a small business based in Omaha, Nebraska. BSI partnered with Keltech, Inc., a manufacturer of electric tankless water heaters based in Delton, Michigan. Additional work was carried out by the University of Nebraska and Mike Coward. A background study revealed several advantages and disadvantages to TWH. Besides using less energy than storage heaters, TWH provide an endless supply of hot water, have a longer life, use less floor space, can be used at point-of-use, and are suitable as boosters to enable alternative water heating technologies, such as solar or heat-pump water heaters. Their disadvantages are their higher cost, large instantaneous power requirement, and poor temperature control. A test method was developed to quantify performance under a representative range of disturbances to flow rate and inlet temperature. A device capable of conducting this test was designed and built. Some heaters currently on the market were tested, and were found to perform quite poorly. A new controller was designed using model predictive control (MPC). This control method required an accurate dynamic model to be created and required significant tuning to the controller before good control was achieved. The MPC
Ikeda, H.; Saigusa, T.; Kamei, J.; Koshikawa, N.; Cools, A.R.
2013-01-01
Central dopamine systems are key players in the cerebral organization of behavior and in various neurological and psychiatric diseases. We demonstrate the presence of a neurochemical feed-forward loop characterized by region-specific changes in dopamine efflux in serially connected striatal regions,
Comparisons of Feed-Forward and Multiple-Feedback Sigma-Delta Modulators for MEMS Accelerometers
Meimei Zhang
2016-01-01
Full Text Available This paper investigates two different architectures of a 5th order electro-mechanical sigma-delta modulator: a feed-forward (FF architecture and a multiple-feedback (MF architecture. And a comparison was performed in terms of stability and noise shaping ability, sensitivities to parameter variances due to fabrication tolerances and loop gain, and nonlinearity in feedback force. Both architectures were modeled in Simulink and investigated at system level. The results show that: a both architectures are stable and achieve the similar noise floor level of -170dB within 250Hz in the ideal condition; b both architectures have good ability in fabrication tolerance; c the performance of the MF architecture will degrade heavily with the loop gain decreasing and become unstable if the loop gain beyond one optimal value, while the FF architecture is insensitive; d the FF architecture controls the proof mass well and achieves better SNDR, whereas the MF has a 56dB degradation in consideration of nonlinearity in feedback force.
Estimated wind speed feed forward control for wind turbine operation optimisation
Van der Hooft, E.L.; Van Engelen, T.G. [ECN Wind Energy, Petten (Netherlands)
2004-11-01
For a pitch controlled variable speed wind turbine, a feed forward control structure based on the estimation of rotor averaged wind speed has been developed and analyzed. The additional control action will accelerate ordinary rotor speed feedback control to resist disturbances of wind speed turbulence and wind gusts. Wind speed estimation is based on reconstruction of aerodynamic torque from measurements and a priori knowledge of rotor behaviour. The theoretical base arises from the energy balance between captured aerodynamic energy from wind on the one hand and extracted electric energy (generator), stored kinetic energy (rotor inertia) and losses on the other hand. A tabular implementation for use in real-time control has been derived and evaluated by time domain simulations, stability analysis and parametric uncertainty studies. Without stability drawbacks, the proposed method has shown to be a powerful for reduction of rotor speed variations (30-40%) and wind gust suppression. Energy yield increase is feasible (0.9%) if temporarily torque excesses are not allowed.
Noise processing by microRNA-mediated circuits: The Incoherent Feed-Forward Loop, revisited
Silvia Grigolon
2016-04-01
Full Text Available The intrinsic stochasticity of gene expression is usually mitigated in higher eukaryotes by post-transcriptional regulation channels that stabilise the output layer, most notably protein levels. The discovery of small non-coding RNAs (miRNAs in specific motifs of the genetic regulatory network has led to identifying noise buffering as the possible key function they exert in regulation. Recent in vitro and in silico studies have corroborated this hypothesis. It is however also known that miRNA-mediated noise reduction is hampered by transcriptional bursting in simple topologies. Here, using stochastic simulations validated by analytical calculations based on van Kampen's expansion, we revisit the noise-buffering capacity of the miRNA-mediated Incoherent Feed Forward Loop (IFFL, a small module that is widespread in the gene regulatory networks of higher eukaryotes, in order to account for the effects of intermittency in the transcriptional activity of the modulator gene. We show that bursting considerably alters the circuit's ability to control static protein noise. By comparing with other regulatory architectures, we find that direct transcriptional regulation significantly outperforms the IFFL in a broad range of kinetic parameters. This suggests that, under pulsatile inputs, static noise reduction may be less important than dynamical aspects of noise and information processing in characterising the performance of regulatory elements.
A feed-forward loop coupling extracellular BMP transport and morphogenesis in Drosophila wing.
Shinya Matsuda
2013-03-01
Full Text Available A variety of extracellular factors regulate morphogenesis during development. However, coordination between extracellular signaling and dynamic morphogenesis is largely unexplored. We address the fundamental question by studying posterior crossvein (PCV development in Drosophila as a model, in which long-range BMP transport from the longitudinal veins plays a critical role during the pupal stages. Here, we show that RhoGAP Crossveinless-C (Cv-C is induced at the PCV primordial cells by BMP signaling and mediates PCV morphogenesis cell-autonomously by inactivating members of the Rho-type small GTPases. Intriguingly, we find that Cv-C is also required non-cell-autonomously for BMP transport into the PCV region, while a long-range BMP transport is guided toward ectopic wing vein regions by loss of the Rho-type small GTPases. We present evidence that low level of ß-integrin accumulation at the basal side of PCV epithelial cells regulated by Cv-C provides an optimal extracellular environment for guiding BMP transport. These data suggest that BMP transport and PCV morphogenesis are tightly coupled. Our study reveals a feed-forward mechanism that coordinates the spatial distribution of extracellular instructive cues and morphogenesis. The coupling mechanism may be widely utilized to achieve precise morphogenesis during development and homeostasis.
Feed-forward carrier phase recovery for offset-QAM Nyquist WDM transmission.
Tang, Haoyuan; Xiang, Meng; Fu, Songnian; Tang, Ming; Shum, Perry; Liu, Deming
2015-03-09
Due to the half symbol delay between in-phase and quadrature components for offset quadrature amplitude modulation (OQAM) signal, phase noise cannot only lead to constellation rotation but also introduce additional crosstalk. Therefore, OQAM signal has very poor tolerance to the laser linewidth. Here, we carry out a semi-analytical investigation of phase noise induced crosstalk during OQAM Nyquist WDM transmission, and find that the carrier phase recovery (CPR) has to be implemented prior to the inter-symbol-interference (ISI) equalization. Then, after a function separation of polarization de-multiplexing and ISI equalization, we propose a new DSP flow with a linewidth-tolerant blind feed-forward CPR scheme for OQAM signal. Its effectiveness is verified under the scenario of 5-channel 28-Gbaud polarization multiplexing (PM) OQAM Nyquist WDM systems. A tolerance of linewidth and symbol duration products of 6.5×10(-4) and 1.1×10(-4) is secured for 4-OQAM and 16-OQAM, respectively, given 1-dB required-OSNR penalty at BER = 10(-3).
ADAPTIVE FEED-FORWARD COMPENSATOR FOR HARMONIC CANCELLATION IN ELECTRO- HYDRAULIC SERVO SYSTEM
YAO Jianjun; WANG Liquan; JIANG Hongzhou; WU Zhenshun; HAN Junwei
2008-01-01
Since the dead zone phenomenon occurs in electro-hydraulic servo system, the output of the system corresponding to a sinusoidal input contains higher harmonic besides the fundamental input, which causes harmonic distortion of the output signal. The method for harmonic cancellation based on adaptive filter is proposed. The task is accomplished by generating reference signals with frequency that should be eliminated from the output. The reference inputs are weighted by the adaptive filter in such a way that it closely matches the harmonic. The output of the adaptive filter is a harmonic replica and is injected to the fundamental signal such that the output harmonic is cancelled leaving the desired signal alone, and the total harmonic distortion (THD) is greatly reduced. The weights of filter are adjusted on-line according to the control error by using least-mean-square (LMS) algorithm. Simulation results performed with a hydraulic system demonstrate the efficiency and validity of the proposed adaptive feed-forward compensator (AFC) control scheme.
Flatness-based model inverse for feed-forward braking control
de Vries, Edwin; Fehn, Achim; Rixen, Daniel
2010-12-01
For modern cars an increasing number of driver assistance systems have been developed. Some of these systems interfere/assist with the braking of a car. Here, a brake actuation algorithm for each individual wheel that can respond to both driver inputs and artificial vehicle deceleration set points is developed. The algorithm consists of a feed-forward control that ensures, within the modelled system plant, the optimal behaviour of the vehicle. For the quarter-car model with LuGre-tyre behavioural model, an inverse model can be derived using v x as the 'flat output', that is, the input for the inverse model. A number of time derivatives of the flat output are required to calculate the model input, brake torque. Polynomial trajectory planning provides the needed time derivatives of the deceleration request. The transition time of the planning can be adjusted to meet actuator constraints. It is shown that the output of the trajectory planning would ripple and introduce a time delay when a gradual continuous increase of deceleration is requested by the driver. Derivative filters are then considered: the Bessel filter provides the best symmetry in its step response. A filter of same order and with negative real-poles is also used, exhibiting no overshoot nor ringing. For these reasons, the 'real-poles' filter would be preferred over the Bessel filter. The half-car model can be used to predict the change in normal load on the front and rear axle due to the pitching of the vehicle. The anticipated dynamic variation of the wheel load can be included in the inverse model, even though it is based on a quarter-car. Brake force distribution proportional to normal load is established. It provides more natural and simpler equations than a fixed force ratio strategy.
A feed-forward controlled AC-DC boost converter for biomedical implants.
Jiang, Hao; Lan, Di; Lin, Dahsien; Zhang, Junmin; Liou, Shyshenq; Shahnasser, Hamid; Shen, Ming; Harrison, Michael; Roy, Shuvo
2012-01-01
Miniaturization is important to make implants clinic friendly. Wireless power transfer is an essential technology to miniaturize implants by reducing their battery size or completely eliminating their batteries. Traditionally, a pair of inductively-coupled coils operating at radio-frequency (RF) is employed to deliver electrical power wirelessly. In this approach, a rectifier is needed to convert the received RF power to a stable DC one. To achieve high efficiency, the induced voltage of the receiving coil must be much higher than the turn-on voltage of the rectifying diode (which could be an active circuit for low turn-on voltage) [1]. In order to have a high induced voltage, the size of the receiving coil often is significantly larger than rest of the implant. A rotating magnets based wireless power transfer has been demonstrated to deliver the same amount of power at much lower frequency (around 100 Hz) because of the superior magnetic strength produced by rare-earth magnets [2]. Taking the advantage of the low operating frequency, an innovative feed-forward controlled AC to DC boost converter has been demonstrated for the first time to accomplish the following two tasks simultaneously: (1) rectifying the AC power whose amplitude (500 mV) is less than the rectifier's turn-on voltage (1.44 V) and (2) boosting the DC output voltage to a much higher level (5 V). Within a range, the output DC voltage can be selected by the control circuit. The standard deviation of the output DC voltage is less than 2.1% of its mean. The measured load regulation is 0.4 V/kΩ. The estimated conversion efficiency excluding the power consumption of the control circuits reaches 75%. The converter in this paper has the potential to reduce the size of the receiving coil and yet achieve desirable DC output voltage for powering biomedical implants.
JadR*-mediated feed-forward regulation of cofactor supply in jadomycin biosynthesis.
Zhang, Yanyan; Pan, Guohui; Zou, Zhengzhong; Fan, Keqiang; Yang, Keqian; Tan, Huarong
2013-11-01
Jadomycin production is under complex regulation in Streptomyces venezuelae. Here, another cluster-situated regulator, JadR*, was shown to negatively regulate jadomycin biosynthesis by binding to four upstream regions of jadY, jadR1, jadI and jadE in jad gene cluster respectively. The transcriptional levels of four target genes of JadR* increased significantly in ΔjadR*, confirming that these genes were directly repressed by JadR*. Jadomycin B (JdB) and its biosynthetic intermediates 2,3-dehydro-UWM6 (DHU), dehydrorabelomycin (DHR) and jadomycin A (JdA) modulated the DNA-binding activities of JadR* on the jadY promoter, with DHR giving the strongest dissociation effects. Direct interactions between JadR* and these ligands were further demonstrated by surface plasmon resonance, which showed that DHR has the highest affinity for JadR*. However, only DHU and DHR could induce the expression of jadY and jadR* in vivo. JadY is the FMN/FAD reductase supplying cofactors FMNH₂/FADH₂ for JadG, an oxygenase, that catalyses the conversion of DHR to JdA. Therefore, our results revealed that JadR* and early pathway intermediates, particularly DHR, regulate cofactor supply by a convincing case of a feed-forward mechanism. Such delicate regulation of expression of jadY could ensure a timely supply of cofactors FMNH₂/FADH₂ for jadomycin biosynthesis, and avoid unnecessary consumption of NAD(P)H.
Gong, Ai-hua; Wei, Ping; Zhang, Sicong; Yao, Jun; Yuan, Ying; Zhou, Ai-dong; Lang, Frederick F.; Heimberger, Amy B.; Rao, Ganesh; Huang, Suyun
2015-01-01
The growth factor PDGF controls the development of glioblastoma (GBM) but its contribution to the function of GBM stem-like cells (GSC) has been little studied. Here we report that the transcription factor FoxM1 promotes PDGFA-STAT3 signaling to drive GSC self-renewal and tumorigenicity. In GBM we found a positive correlation between expression of FoxM1 and PDGF-A. In GSC and mouse neural stem cells, FoxM1 bound to the PDGF-A promoter to upregulate PDGF-A expression, acting to maintain the stem-like qualities of GSC in part through this mechanism. Analysis of the human cancer genomic database TCGA revealed that GBM express higher levels of STAT3, a PDGF-A effector signaling molecule, as compared with normal brain. FoxM1 regulated STAT3 transcription through interactions with the β-catenin/TCF4 complex. FoxM1 deficiency inhibited PDGF-A and STAT3 expression in neural stem cells and GSC, abolishing their stem-like and tumorigenic properties. Further mechanistic investigations defined a FoxM1-PDGFA-STAT3 feed-forward pathway that was sufficient to confer stem-like properties to glioma cells. Collectively, our findings showed how FoxM1 activates expression of PDGF-A and STAT3 in a pathway required to maintain the self-renewal and tumorigenicity of glioma stem-like cells. PMID:25832656
Latha. S. C
2014-11-01
Full Text Available The portable devices development of semiconductor manufacturing technology, conversion efficiency, power consumption, and the size of devices have become the most important design criteria of switching power converters. For portable applications better conveniences extension of battery life and improves the conversion efficiency of power converters .It is essential to develop accurate switching power converters, which can reduce more wasted power energy. The proposed topology can achieve faster transient responses when the supply voltages are changed for the converter by making use of the feed forward network .With mode select circuit the conduction & switching losses are reduced the positive buck–boost converter operate in buck, buck–boost, or boost converter. By adding feed-forward techniques, the proposed converter can improve transient response when the supply voltages are changed. The designing, modeling & experimental results were verified in MATLAB/ Simulink. The fuzzy logic controller is used as controller.
Lintz, M.; Phung, D. H.; Coulon, J.-P.; Faure, B.; Lévèque, T.
2017-02-01
We have achieved distributed feedback laser diode line narrowing by simultaneously acting on the diode current via a feed-back loop and on an external electrooptic phase modulator in feed-forward actuator. This configuration turns out to be very efficient in reaching large bandwidth in the phase correction: up to 15 MHz with commercial laser control units. About 98% of the laser power undergoes narrowing. The full width at half maximum of the narrowed optical spectrum is of less than 4 kHz. This configuration appears to be very convenient as the delay in the feed-forward control electronics is easily compensated for by a 20 m optical fiber roll.
Daniela Albanesi
2013-01-01
Full Text Available The biosynthesis of membrane lipids is an essential pathway for virtually all bacteria. Despite its potential importance for the development of novel antibiotics, little is known about the underlying signaling mechanisms that allow bacteria to control their membrane lipid composition within narrow limits. Recent studies disclosed an elaborate feed-forward system that senses the levels of malonyl-CoA and modulates the transcription of genes that mediate fatty acid and phospholipid synthesis in many Gram-positive bacteria including several human pathogens. A key component of this network is FapR, a transcriptional regulator that binds malonyl-CoA, but whose mode of action remains enigmatic. We report here the crystal structures of FapR from Staphylococcus aureus (SaFapR in three relevant states of its regulation cycle. The repressor-DNA complex reveals that the operator binds two SaFapR homodimers with different affinities, involving sequence-specific contacts from the helix-turn-helix motifs to the major and minor grooves of DNA. In contrast with the elongated conformation observed for the DNA-bound FapR homodimer, binding of malonyl-CoA stabilizes a different, more compact, quaternary arrangement of the repressor, in which the two DNA-binding domains are attached to either side of the central thioesterase-like domain, resulting in a non-productive overall conformation that precludes DNA binding. The structural transition between the DNA-bound and malonyl-CoA-bound states of SaFapR involves substantial changes and large (>30 Å inter-domain movements; however, both conformational states can be populated by the ligand-free repressor species, as confirmed by the structure of SaFapR in two distinct crystal forms. Disruption of the ability of SaFapR to monitor malonyl-CoA compromises cell growth, revealing the essentiality of membrane lipid homeostasis for S. aureus survival and uncovering novel opportunities for the development of antibiotics
Albanesi, Daniela; Reh, Georgina; Guerin, Marcelo E; Schaeffer, Francis; Debarbouille, Michel; Buschiazzo, Alejandro; Schujman, Gustavo E; de Mendoza, Diego; Alzari, Pedro M
2013-01-01
The biosynthesis of membrane lipids is an essential pathway for virtually all bacteria. Despite its potential importance for the development of novel antibiotics, little is known about the underlying signaling mechanisms that allow bacteria to control their membrane lipid composition within narrow limits. Recent studies disclosed an elaborate feed-forward system that senses the levels of malonyl-CoA and modulates the transcription of genes that mediate fatty acid and phospholipid synthesis in many Gram-positive bacteria including several human pathogens. A key component of this network is FapR, a transcriptional regulator that binds malonyl-CoA, but whose mode of action remains enigmatic. We report here the crystal structures of FapR from Staphylococcus aureus (SaFapR) in three relevant states of its regulation cycle. The repressor-DNA complex reveals that the operator binds two SaFapR homodimers with different affinities, involving sequence-specific contacts from the helix-turn-helix motifs to the major and minor grooves of DNA. In contrast with the elongated conformation observed for the DNA-bound FapR homodimer, binding of malonyl-CoA stabilizes a different, more compact, quaternary arrangement of the repressor, in which the two DNA-binding domains are attached to either side of the central thioesterase-like domain, resulting in a non-productive overall conformation that precludes DNA binding. The structural transition between the DNA-bound and malonyl-CoA-bound states of SaFapR involves substantial changes and large (>30 Å) inter-domain movements; however, both conformational states can be populated by the ligand-free repressor species, as confirmed by the structure of SaFapR in two distinct crystal forms. Disruption of the ability of SaFapR to monitor malonyl-CoA compromises cell growth, revealing the essentiality of membrane lipid homeostasis for S. aureus survival and uncovering novel opportunities for the development of antibiotics against this major human
Feed-forward active contour analysis for improved brachial artery reactivity testing.
Pugliese, Daniel N; Sehgal, Chandra M; Sultan, Laith R; Reamer, Courtney B; Mohler, Emile R
2016-08-01
The object of this study was to utilize a novel feed-forward active contour (FFAC) algorithm to find a reproducible technique for analysis of brachial artery reactivity. Flow-mediated dilation (FMD) is an important marker of vascular endothelial function but has not been adopted for widespread clinical use given its technical limitations, including inter-observer variability and differences in technique across clinical sites. We developed a novel FFAC algorithm with the goal of validating a more reliable standard. Forty-six healthy volunteers underwent FMD measurement according to the standard technique. Ultrasound videos lasting 5-10 seconds each were obtained pre-cuff inflation and at minutes 1 through 5 post-cuff deflation in longitudinal and transverse views. Automated segmentation using the FFAC algorithm with initial boundary definition from three different observers was used to analyze the images to measure diameter/cross-sectional area over the cardiac cycle. The %FMD was calculated for average, minimum, and maximum diameters/areas. Using the FFAC algorithm, the population-specific coefficient of variation (CV) at end-diastole was 3.24% for transverse compared to 9.96% for longitudinal measurements; the subject-specific CV was 15.03% compared to 57.41%, respectively. For longitudinal measurements made via the conventional method, the population-specific CV was 4.77% and subject-specific CV was 117.79%. The intraclass correlation coefficient (ICC) for transverse measurements was 0.97 (95% CI: 0.95-0.98) compared to 0.90 (95% CI: 0.84-0.94) for longitudinal measurements with FFAC and 0.72 (95% CI: 0.51-0.84) for conventional measurements. In conclusion, transverse views using the novel FFAC method provide less inter-observer variability than traditional longitudinal views. Improved reproducibility may allow adoption of FMD testing in a clinical setting. The FFAC algorithm is a robust technique that should be evaluated further for its ability to replace the
Training two-layered feedforward networks with variable projection method.
Kim, C T; Lee, J J
2008-02-01
The variable projection (VP) method for separable nonlinear least squares (SNLLS) is presented and incorporated into the Levenberg-Marquardt optimization algorithm for training two-layered feedforward neural networks. It is shown that the Jacobian of variable projected networks can be computed by simple modification of the backpropagation algorithm. The suggested algorithm is efficient compared to conventional techniques such as conventional Levenberg-Marquardt algorithm (LMA), hybrid gradient algorithm (HGA), and extreme learning machine (ELM).
Park Giseo
2016-01-01
Full Text Available Electro-Mechanical Brake (EMB is expected to be one of the future brake system. Feedback controller with sensor measuring is commonly used for control of EMB. However, this controller has some issues like delayed response and extra cost about sensor installation. In this paper, Feed-forward controller in EMB is proposed for solving these problems of feedback control. Also, it is very necessary to describe dynamical phenomenon of friction in actual EMB system. The actual EMB system shows stick-slip friction of mechanical parts which is difficult to model and apply to design of controller. This research is focused on exquisitely describing this stick-slip friction. In order to do this, the experiment about EMB is proceeded in the open loop system with the motor current command and data from the experiment is used for identification of model parameters during stiction. Then, parameters during slip is estimated in the closed loop system. Finally, developed friction model of EMB is proposed and it is utilized for design of feed-forward controller. Matlab Simulink is used for design of EMB simulation model and EMB test bench is utilized for experiment. Performance of proposed control system is compared with that of feedback control system.
Simulation of Wave Forces on A Semi-Circular Breakwater Using Multilayer Feed Forward Network
徐杰; 陶建华
2003-01-01
In this paper, the Artificial Neural Network (ANN) is used to study the wave forces on a semi-circular breakwater. The process of establishing the network model for a specific physical problem is presented. Networks with double implicit layers have been studied by numerical experiments. 117 sets of experimental data are used to train and test the ANN. According to the results of ANN simulation, this method is proved to have good precision compared with experimental and numerical results.
Dunne, F.; Simley, E.; Pao, L.Y.
2011-10-01
This report examines the accuracy of measurements that rely on Doppler LIDAR systems to determine their applicability to wind turbine feed-forward control systems and discusses feed-forward control system designs that use preview wind measurements. Light Detection and Ranging (LIDAR) systems are able to measure the speed of incoming wind before it interacts with a wind turbine rotor. These preview wind measurements can be used in feed-forward control systems designed to reduce turbine loads. However, the degree to which such preview-based control techniques can reduce loads by reacting to turbulence depends on how accurately the incoming wind field can be measured. The first half of this report examines the accuracy of different measurement scenarios that rely on coherent continuous-wave or pulsed Doppler LIDAR systems to determine their applicability to feed-forward control. In particular, the impacts of measurement range and angular offset from the wind direction are studied for various wind conditions. A realistic case involving a scanning LIDAR unit mounted in the spinner of a wind turbine is studied in depth with emphasis on choices for scan radius and preview distance. The effects of turbulence parameters on measurement accuracy are studied as well. Continuous-wave and pulsed LIDAR models based on typical commercially available units were used in the studies present in this report. The second half of this report discusses feed-forward control system designs that use preview wind measurements. Combined feedback/feed-forward blade pitch control is compared to industry standard feedback control when simulated in realistic turbulent above-rated winds. The feed-forward controllers are designed to reduce fatigue loads, increasing turbine lifetime and therefore reducing the cost of energy. Three feed-forward designs are studied: non-causal series expansion, Preview Control, and optimized FIR filter. The input to the feed-forward controller is a measurement of
FPGA Implementation of Feed-Forward MLP Neural Networks%前向MLP网络的FPGA实现
都军伟; 王永纲; 杨阳; 李凯
2010-01-01
分别采用CORDIC(Coordinate rotation digital computer)算法和分布式算法实现多层感知器网络的传输函数计算和输入与权重乘积和计算,通过模块复用的方法构造了一个用于函数逼近的、无需乘法器的神经网络,并在NoisⅡ开发平台上测试了该网络的性能.该网络每17个时钟周期输出一个数据,占用FPGA的7781个LE(Logic element)和8976 bit存储器,具有良好的扩展性.
Liu, W; Ratnaweera, H
2016-01-01
Coagulant dosing control in drinking and wastewater treatment plants (WWTPs) is often limited to flow proportional concepts. The advanced multi-parameter-based dosing control systems have significantly reduced coagulant consumption and improved outlet qualities. Due to the long retention time in separation stages, these models are mostly based on feed-forward (FF) models. This paper demonstrates the improvement of such models with feed-back (FB) concepts with simplifications, making it possible to use even in systems with long separation stages. Full-scale case studies from a drinking water treatment plant and a WWTP are presented. The model qualities were improved by the dosage adjustment of the FB model, ranging from 66% to 197% of the FF model. Hence, the outlet qualities became more stable and coagulant consumption was further reduced in the range of 3.7%-15.5%.
Viollet, Stéphane; Zeil, Jochen
2013-04-01
Flying insects keep their visual system horizontally aligned, suggesting that gaze stabilization is a crucial first step in flight control. Unlike flies, hymenopteran insects such as bees and wasps do not have halteres that provide fast, feed-forward angular rate information to stabilize head orientation in the presence of body rotations. We tested whether hymenopteran insects use inertial (mechanosensory) information to control head orientation from other sources, such as the wings, by applying periodic roll perturbations to male Polistes humilis wasps flying in tether under different visual conditions indoors and in natural outdoor conditions. We oscillated the thorax of the insects with frequency-modulated sinusoids (chirps) with frequencies increasing from 0.2 to 2 Hz at a maximal amplitude of 50 deg peak-to-peak and maximal angular velocity of ±245 deg s(-1). We found that head roll stabilization is best outdoors, but completely absent in uniform visual conditions and in darkness. Step responses confirm that compensatory head roll movements are purely visually driven. Modelling step responses indicates that head roll stabilization is achieved by merging information on head angular velocity, presumably provided by motion-sensitive neurons and information on head orientation, presumably provided by light level integration across the compound eyes and/or ocelli (dorsal light response). Body roll in free flight reaches amplitudes of ±40 deg and angular velocities greater than 1000 deg s(-1), while head orientation remains horizontal for most of the time to within ±10 deg. In free flight, we did not find a delay between spontaneous body roll and compensatory head movements, and suggest that this is evidence for the contribution of a feed-forward control to head stabilization.
Spatial frequency domain spectroscopy of two layer media
Yudovsky, Dmitry; Durkin, Anthony J.
2011-10-01
Monitoring of tissue blood volume and oxygen saturation using biomedical optics techniques has the potential to inform the assessment of tissue health, healing, and dysfunction. These quantities are typically estimated from the contribution of oxyhemoglobin and deoxyhemoglobin to the absorption spectrum of the dermis. However, estimation of blood related absorption in superficial tissue such as the skin can be confounded by the strong absorption of melanin in the epidermis. Furthermore, epidermal thickness and pigmentation varies with anatomic location, race, gender, and degree of disease progression. This study describes a technique for decoupling the effect of melanin absorption in the epidermis from blood absorption in the dermis for a large range of skin types and thicknesses. An artificial neural network was used to map input optical properties to spatial frequency domain diffuse reflectance of two layer media. Then, iterative fitting was used to determine the optical properties from simulated spatial frequency domain diffuse reflectance. Additionally, an artificial neural network was trained to directly map spatial frequency domain reflectance to sets of optical properties of a two layer medium, thus bypassing the need for iteration. In both cases, the optical thickness of the epidermis and absorption and reduced scattering coefficients of the dermis were determined independently. The accuracy and efficiency of the iterative fitting approach was compared with the direct neural network inversion.
neural network based model o work based model of an industrial oil ...
eobe
Marquardt. Marquardt Back Propagation Algorithm ..... Ioan I. et al “The Optimization of Feed Forward. Neural Networks ... Controller Design of an Industrial Oil-Fired Boiler. Plant” ... Mechanical Engineering Purdue University, 2006. [38].
Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
Kheradpisheh, Saeed Reza; Ghodrati, Masoud; Ganjtabesh, Mohammad; Masquelier, Timothée
2016-09-01
Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human visual system: both use restricted receptive fields, and a hierarchy of layers which progressively extract more and more abstracted features. Yet it is unknown whether DCNNs match human performance at the task of view-invariant object recognition, whether they make similar errors and use similar representations for this task, and whether the answers depend on the magnitude of the viewpoint variations. To investigate these issues, we benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking. Unlike in all previous DCNN studies, we carefully controlled the magnitude of the viewpoint variations to demonstrate that shallow nets can outperform deep nets and humans when variations are weak. When facing larger variations, however, more layers were needed to match human performance and error distributions, and to have representations that are consistent with human behavior. A very deep net with 18 layers even outperformed humans at the highest variation level, using the most human-like representations.
Feed forward and feedback control for over-ground locomotion in anaesthetized cats
Mazurek, K. A.; Holinski, B. J.; Everaert, D. G.; Stein, R. B.; Etienne-Cummings, R.; Mushahwar, V. K.
2012-04-01
The biological central pattern generator (CPG) integrates open and closed loop control to produce over-ground walking. The goal of this study was to develop a physiologically based algorithm capable of mimicking the biological system to control multiple joints in the lower extremities for producing over-ground walking. The algorithm used state-based models of the step cycle each of which produced different stimulation patterns. Two configurations were implemented to restore over-ground walking in five adult anaesthetized cats using intramuscular stimulation (IMS) of the main hip, knee and ankle flexor and extensor muscles in the hind limbs. An open loop controller relied only on intrinsic timing while a hybrid-CPG controller added sensory feedback from force plates (representing limb loading), and accelerometers and gyroscopes (representing limb position). Stimulation applied to hind limb muscles caused extension or flexion in the hips, knees and ankles. A total of 113 walking trials were obtained across all experiments. Of these, 74 were successful in which the cats traversed 75% of the 3.5 m over-ground walkway. In these trials, the average peak step length decreased from 24.9 ± 8.4 to 21.8 ± 7.5 (normalized units) and the median number of steps per trial increased from 7 (Q1 = 6, Q3 = 9) to 9 (8, 11) with the hybrid-CPG controller. Moreover, within these trials, the hybrid-CPG controller produced more successful steps (step length ≤ 20 cm ground reaction force ≥ 12.5% body weight) than the open loop controller: 372 of 544 steps (68%) versus 65 of 134 steps (49%), respectively. This supports our previous preliminary findings, and affirms that physiologically based hybrid-CPG approaches produce more successful stepping than open loop controllers. The algorithm provides the foundation for a neural prosthetic controller and a framework to implement more detailed control of locomotion in the future.
Application of Neural Networks for Energy Reconstruction
Damgov, Jordan
2002-01-01
The possibility to use Neural Networks for reconstruction ofthe energy deposited in the calorimetry system of the CMS detector is investigated. It is shown that using feed-forward neural network, good linearity, Gaussian energy distribution and good energy resolution can be achieved. Significant improvement of the energy resolution and linearity is reached in comparison with other weighting methods for energy reconstruction.
Two-Layer Quantum Key Distribution
Ramos, Rubens Viana
2012-01-01
Recently a new quantum key distribution protocol using coherent and thermal states was proposed. In this work this kind of two-layer QKD protocol is formalized and its security against the most common attacks, including external control and Trojan horse attacks, is discussed.
RA Acts in a Coherent Feed-Forward Mechanism with Tbx5 to Control Limb Bud Induction and Initiation
Nishimoto, Satoko; Wilde, Susan M.; Wood, Sophie; Logan, Malcolm P.O.
2015-01-01
Summary The retinoic acid (RA)- and β-catenin-signaling pathways regulate limb bud induction and initiation; however, their mechanisms of action are not understood and have been disputed. We demonstrate that both pathways are essential and that RA and β-catenin/TCF/LEF signaling act cooperatively with Hox gene inputs to directly regulate Tbx5 expression. Furthermore, in contrast to previous models, we show that Tbx5 and Tbx4 expression in forelimb and hindlimb, respectively, are not sufficient for limb outgrowth and that input from RA is required. Collectively, our data indicate that RA signaling and Tbx genes act in a coherent feed-forward loop to regulate Fgf10 expression and, as a result, establish a positive feedback loop of FGF signaling between the limb mesenchyme and ectoderm. Our results incorporate RA-, β-catenin/TCF/LEF-, and FGF-signaling pathways into a regulatory network acting to recruit cells of the embryo flank to become limb precursors. PMID:26212321
RA Acts in a Coherent Feed-Forward Mechanism with Tbx5 to Control Limb Bud Induction and Initiation
Satoko Nishimoto
2015-08-01
Full Text Available The retinoic acid (RA- and β-catenin-signaling pathways regulate limb bud induction and initiation; however, their mechanisms of action are not understood and have been disputed. We demonstrate that both pathways are essential and that RA and β-catenin/TCF/LEF signaling act cooperatively with Hox gene inputs to directly regulate Tbx5 expression. Furthermore, in contrast to previous models, we show that Tbx5 and Tbx4 expression in forelimb and hindlimb, respectively, are not sufficient for limb outgrowth and that input from RA is required. Collectively, our data indicate that RA signaling and Tbx genes act in a coherent feed-forward loop to regulate Fgf10 expression and, as a result, establish a positive feedback loop of FGF signaling between the limb mesenchyme and ectoderm. Our results incorporate RA-, β-catenin/TCF/LEF-, and FGF-signaling pathways into a regulatory network acting to recruit cells of the embryo flank to become limb precursors.
Smith, G. A.; Meyer, G.
1984-01-01
A full-flight-envelope automatic trajectory control system concept is being investigated at Ames Research Center. This concept was developed for advanced aircraft configurations with severe nonlinear characteristics. A feature of the system is an inverse of the complete nonlinear aircraft model as part of the feed-forward control path. Simulation and flight tests have been reported at previous Digital Avionics Systems conferences. A new method for the continuous real-time inversion of the aircraft model using a Newton-Raphson trim algorithm instead of the original inverse table look-up procedure has been developed. The results of a simulation study of a vertical attitude takeoff and landing aircraft using the new inversion technique are presented. Maneuvers were successfully carried out in all directions in the vertical-attitude hover mode. Transition runs from conventional flight through the region of lift-curve-slope reversal at an angle of attack of about 32 deg and to hover at zero speed in the vertical attitude showed satisfactory transient response. Simulations were also conducted in conventional flight at high subsonic speed in steep climb and with turns up to 4 g. Successful flight tests of the system with the new model-inversion technique in a UH-1H helicopter have recently been carried out.
Chen, Xing; Lu, Jinlong; Cui, Yifan; Zhang, Jian; Lu, Xing; Tian, Xusheng; Ci, Cheng; Liu, Bo; Wu, Hong; Tang, Tingsong; Shi, Kebin; Zhang, Zhigang
2015-12-22
Precision time synchronization between two remote sites is desired in many applications such as global positioning satellite systems, long-baseline interferometry, coherent radar detection and fundamental physics constant measurements. The recently developed frequency dissemination technologies based on optical fiber link have improved the transfer instability to the level of 10(-19)/day at remote location. Therefore it is possible to keep clock oscillation at remote locations continuously corrected, or to reproduce a "virtual" clock on the remote location. However the initial alignment and the correction of 1 pps timing signal from time to time are still required, besides the highly stabilized clock frequency transfer between distant locations. Here we demonstrate a time synchronization based on an ultra-stable frequency transfer system via 120-km commercial fiber link by transferring an optical frequency comb. Both the phase noise compensation in frequency dissemination and temporal basis alignment in time synchronization were implemented by a feed-forward digital compensation (FFDC) technique. The fractional frequency instability was measured to be 6.18 × 10(-20) at 2000 s. The timing deviation of time synchronization was measured to be 0.6 ps in 1500 s. This technique also can be applied in multi-node fiber network topology.
Chen, Xing; Lu, Jinlong; Cui, Yifan; Zhang, Jian; Lu, Xing; Tian, Xusheng; Ci, Cheng; Liu, Bo; Wu, Hong; Tang, Tingsong; Shi, Kebin; Zhang, Zhigang
2015-12-01
Precision time synchronization between two remote sites is desired in many applications such as global positioning satellite systems, long-baseline interferometry, coherent radar detection and fundamental physics constant measurements. The recently developed frequency dissemination technologies based on optical fiber link have improved the transfer instability to the level of 10-19/day at remote location. Therefore it is possible to keep clock oscillation at remote locations continuously corrected, or to reproduce a “virtual” clock on the remote location. However the initial alignment and the correction of 1 pps timing signal from time to time are still required, besides the highly stabilized clock frequency transfer between distant locations. Here we demonstrate a time synchronization based on an ultra-stable frequency transfer system via 120-km commercial fiber link by transferring an optical frequency comb. Both the phase noise compensation in frequency dissemination and temporal basis alignment in time synchronization were implemented by a feed-forward digital compensation (FFDC) technique. The fractional frequency instability was measured to be 6.18 × 10-20 at 2000 s. The timing deviation of time synchronization was measured to be 0.6 ps in 1500 s. This technique also can be applied in multi-node fiber network topology.
Artificial Neural Networks for Diagnosis of Kidney Stones Disease
Koushal Kumar
2012-07-01
Full Text Available Artificial Neural networks are often used as a powerful discriminating classifier for tasks in medical diagnosis for early detection of diseases. They have several advantages over parametric classifiers such as discriminate analysis. The objective of this paper is to diagnose kidney stone disease by using three different neural network algorithms which have different architecture and characteristics. The aim of this work is to compare the performance of all three neural networks on the basis of its accuracy, time taken to build model, and training data set size. We will use Learning vector quantization (LVQ, two layers feed forward perceptron trained with back propagation training algorithm and Radial basis function (RBF networks for diagnosis of kidney stone disease. In this work we used Waikato Environment for Knowledge Analysis (WEKA version 3.7.5 as simulation tool which is an open source tool. The data set we used for diagnosis is real world data with 1000 instances and 8 attributes. In the end part we check the performance comparison of different algorithms to propose the best algorithm for kidney stone diagnosis. So this will helps in early identification of kidney stone in patients and reduces the diagnosis time.
Pradhan, Ranjan K; Feigl, Eric O; Gorman, Mark W; Brengelmann, George L; Beard, Daniel A
2016-06-01
A control system model was developed to analyze data on in vivo coronary blood flow regulation and to probe how different mechanisms work together to control coronary flow from rest to exercise, and under a variety of experimental conditions, including cardiac pacing and with changes in coronary arterial pressure (autoregulation). In the model coronary flow is determined by the combined action of a feedback pathway signal that is determined by the level of plasma ATP in coronary venous blood, an adrenergic open-loop (feed-forward) signal that increases with exercise, and a contribution of pressure-mediated myogenic control. The model was identified based on data from exercise experiments where myocardial oxygen extraction, coronary flow, cardiac interstitial norepinephrine concentration, and arterial and coronary venous plasma ATP concentrations were measured during control and during adrenergic and purinergic receptor blockade conditions. The identified model was used to quantify the relative contributions of open-loop and feedback pathways and to illustrate the degree of redundancy in the control of coronary flow. The results indicate that the adrenergic open-loop control component is responsible for most of the increase in coronary blood flow that occurs during high levels of exercise. However, the adenine nucleotide-mediated metabolic feedback control component is essential. The model was evaluated by predicting coronary flow in cardiac pacing and autoregulation experiments with reasonable fits to the data. The analysis shows that a model in which coronary venous plasma adenine nucleotides are a signal in local metabolic feedback control of coronary flow is consistent with the available data.
Application of neural networks in coastal engineering - An overview
Mandal, S.; Patil, S.G.; Manjunatha, Y.R.; Hegde, A.V.
prediction, wave tranquility studies and near shore morphology are highlighted in this paper. 2 Feed forward neural network A neural network model is interconnected by several neurons. Generally, neuron model consists of three layers namely input layer.... Three-layered feed forward neural network INPUT LAYER HIDDEN LAYER OUTPUT LAYER WEIGHTS BIAS SINGLE NEURON NODE 2 0 )( 2 1 ∑ = −= N k kkp tOE (3) ko M i rKjk bzTwxy +×= ∑ −1 )()( ∑ − +×= D i jiiji bxwz 1 (1) (2) (4) ∑ = = P p p E p E 1 1...
Boundness of a Neural Network Weights Using the Notion of a Limit of a Sequence
Hazem Migdady
2014-06-01
Full Text Available feed forward neural network with backpropagation learning algorithm is considered as a black box learning classifier since there is no certain interpretation or nticipation of the behavior of a neural network weights. The weights of a neural network ar e considered as the learning tool of the classifier, and the learning task is performed by the repetition modification of those weights. This modification is performed using the delta rule which is mainly usedin the gradient descent technique. In this article a proof is provided that helps to understand and explain the behavior of the weights in a feed forward neural network with backpropagation learning algorithm. Also, it illustrates why a feed forward neural network is not always guaranteed to converge in a global minimum. Moreover, the proof shows that the weights in t he neural network are upper bounded (i.e. they do not approach infinity.
Boundness of a Neural Network Weights Using the Notion of a Limit of a Sequence
Hazem Migdady
2014-05-01
Full Text Available feed forward neural network with backpropagation learning algorithm is considered as a black box learning classifier since there is no certain interpretation or anticipation of the behavior of a neural network weights. The weights of a neural network are considered as the learning tool of the classifier, and the learning task is performed by the repetition modification of those weights. This modification is performed using the delta rule which is mainly used in the gradient descent technique. In this article a proof is provided that helps to understand and explain the behavior of the weights in a feed forward neural network with backpropagation learning algorithm. Also, it illustrates why a feed forward neural network is not always guaranteed to converge in a global minimum. Moreover, the proof shows that the weights in the neural network are upper bounded (i.e. they do not approach infinity.
Myriam Zecca
Full Text Available During development, the Drosophila wing primordium undergoes a dramatic increase in cell number and mass under the control of the long-range morphogens Wingless (Wg, a Wnt and Decapentaplegic (Dpp, a BMP. This process depends in part on the capacity of wing cells to recruit neighboring, non-wing cells into the wing primordium. Wing cells are defined by activity of the selector gene vestigial (vg and recruitment entails the production of a vg-dependent "feed-forward signal" that acts together with morphogen to induce vg expression in neighboring non-wing cells. Here, we identify the protocadherins Fat (Ft and Dachsous (Ds, the Warts-Hippo tumor suppressor pathway, and the transcriptional co-activator Yorkie (Yki, a YES associated protein, or YAP as components of the feed-forward signaling mechanism, and we show how this mechanism promotes wing growth in response to Wg. We find that vg generates the feed-forward signal by creating a steep differential in Ft-Ds signaling between wing and non-wing cells. This differential down-regulates Warts-Hippo pathway activity in non-wing cells, leading to a burst of Yki activity and the induction of vg in response to Wg. We posit that Wg propels wing growth at least in part by fueling a wave front of Ft-Ds signaling that propagates vg expression from one cell to the next.
Iwamoto, S.; Yamamoto, Y. [Kyushu University, Fukuoka (Japan); Ogawa, Y. [Kyushu University, Fukuoka (Japan). Faculty of Engineering
1998-06-01
Development has been demanded on a maneuvering motion control system with fine and high accuracy as a navigation aiding system for ship operators. In order to use practically the learning feed-forward control system which has been proposed by the authors, a target value follow-up control system was experimented first by using an actual ship. The experiment revealed that the result of simulation derived at the control system design phase agreed well both qualitatively and quantitatively with the result of the actual ship experiment. Performance of the learning feed-forward control system in the actual ship can be estimated sufficiently from the simulation result. A learning feed-forward control system for follow-up control to desired value (LFFCD) as the base of the learning feed-forward control system can be practically used sufficiently because of the following reasons: high-accuracy control which cannot be obtained by feedback control is possible; the system can be adapted well to non-linearity such as large angle turning because of its learning function; and a case of estimation error in ship body characteristics can also be responded by the learning function. 6 refs., 14 figs., 1 tab.
Tutorial on neural network applications in high energy physics: A 1992 perspective
Denby, B.
1992-04-01
Feed forward and recurrent neural networks are introduced and related to standard data analysis tools. Tips are given on applications of neural nets to various areas of high energy physics. A review of applications within high energy physics and a summary of neural net hardware status are given.
Neural Classifier Construction using Regularization, Pruning
Hintz-Madsen, Mads; Hansen, Lars Kai; Larsen, Jan;
1998-01-01
In this paper we propose a method for construction of feed-forward neural classifiers based on regularization and adaptive architectures. Using a penalized maximum likelihood scheme, we derive a modified form of the entropic error measure and an algebraic estimate of the test error. In conjunction...
Chaotic behavior of a layered neural network
Derrida, B.; Meir, R.
1988-09-15
We consider the evolution of configurations in a layered feed-forward neural network. Exact expressions for the evolution of the distance between two configurations are obtained in the thermodynamic limit. Our results show that the distance between two arbitrarily close configurations always increases, implying chaotic behavior, even in the phase of good retrieval.
Estimation of concrete compressive strength using artificial neural network
Kostić, Srđan; Vasović, Dejan
2015-01-01
In present paper, concrete compressive strength is evaluated using back propagation feed-forward artificial neural network. Training of neural network is performed using Levenberg-Marquardt learning algorithm for four architectures of artificial neural networks, one, three, eight and twelve nodes in a hidden layer in order to avoid the occurrence of overfitting. Training, validation and testing of neural network is conducted for 75 concrete samples with distinct w/c ratio and amount of superp...
Trinh, Hung-Cuong; Le, Duc-Hau; Kwon, Yung-Keun
2014-01-01
It has been a challenge in systems biology to unravel relationships between structural properties and dynamic behaviors of biological networks. A Cytoscape plugin named NetDS was recently proposed to analyze the robustness-related dynamics and feed-forward/feedback loop structures of biological networks. Despite such a useful function, limitations on the network size that can be analyzed exist due to high computational costs. In addition, the plugin cannot verify an intrinsic property which can be induced by an observed result because it has no function to simulate the observation on a large number of random networks. To overcome these limitations, we have developed a novel software tool, PANET. First, the time-consuming parts of NetDS were redesigned to be processed in parallel using the OpenCL library. This approach utilizes the full computing power of multi-core central processing units and graphics processing units. Eventually, this made it possible to investigate a large-scale network such as a human signaling network with 1,609 nodes and 5,063 links. We also developed a new function to perform a batch-mode simulation where it generates a lot of random networks and conducts robustness calculations and feed-forward/feedback loop examinations of them. This helps us to determine if the findings in real biological networks are valid in arbitrary random networks or not. We tested our plugin in two case studies based on two large-scale signaling networks and found interesting results regarding relationships between coherently coupled feed-forward/feedback loops and robustness. In addition, we verified whether or not those findings are consistently conserved in random networks through batch-mode simulations. Taken together, our plugin is expected to effectively investigate various relationships between dynamics and structural properties in large-scale networks. Our software tool, user manual and example datasets are freely available at http://panet-csc.sourceforge.net/.
Hung-Cuong Trinh
Full Text Available It has been a challenge in systems biology to unravel relationships between structural properties and dynamic behaviors of biological networks. A Cytoscape plugin named NetDS was recently proposed to analyze the robustness-related dynamics and feed-forward/feedback loop structures of biological networks. Despite such a useful function, limitations on the network size that can be analyzed exist due to high computational costs. In addition, the plugin cannot verify an intrinsic property which can be induced by an observed result because it has no function to simulate the observation on a large number of random networks. To overcome these limitations, we have developed a novel software tool, PANET. First, the time-consuming parts of NetDS were redesigned to be processed in parallel using the OpenCL library. This approach utilizes the full computing power of multi-core central processing units and graphics processing units. Eventually, this made it possible to investigate a large-scale network such as a human signaling network with 1,609 nodes and 5,063 links. We also developed a new function to perform a batch-mode simulation where it generates a lot of random networks and conducts robustness calculations and feed-forward/feedback loop examinations of them. This helps us to determine if the findings in real biological networks are valid in arbitrary random networks or not. We tested our plugin in two case studies based on two large-scale signaling networks and found interesting results regarding relationships between coherently coupled feed-forward/feedback loops and robustness. In addition, we verified whether or not those findings are consistently conserved in random networks through batch-mode simulations. Taken together, our plugin is expected to effectively investigate various relationships between dynamics and structural properties in large-scale networks. Our software tool, user manual and example datasets are freely available at http://panet-csc.sourceforge.net/.
In vivo spatial frequency domain spectroscopy of two layer media
Yudovsky, Dmitry; Nguyen, John Quan M.; Durkin, Anthony J.
2012-10-01
Monitoring of tissue blood volume and local oxygen saturation can inform the assessment of tissue health, healing, and dysfunction. These quantities can be estimated from the contribution of oxyhemoglobin and deoxyhemoglobin to the absorption spectrum of the dermis. However, estimation of blood related absorption in skin can be confounded by the strong absorption of melanin in the epidermis and epidermal thickness and pigmentation varies with anatomic location, race, gender, and degree of disease progression. Therefore, a method is desired that decouples the effect of melanin absorption in the epidermis from blood absorption in the dermis for a large range of skin types and thicknesses. A previously developed inverse method based on a neural network forward model was applied to simulated spatial frequency domain reflectance of skin for multiple wavelengths in the near infrared. It is demonstrated that the optical thickness of the epidermis and absorption and reduced scattering coefficients of the dermis can be determined independently and with minimal coupling. Then, the same inverse method was applied to reflectance measurements from a tissue simulating phantom and in vivo human skin. Oxygen saturation and total hemoglobin concentrations were estimated from the volar forearms of weakly and strongly pigmented subjects using a standard homogeneous model and the present two layer model.
Grandjean, Geoffrey; de Jong, Petrus R; James, Brian P; Koh, Mei Yee; Lemos, Robert; Kingston, John; Aleshin, Alexander; Bankston, Laurie A; Miller, Claudia P; Cho, Eun Jeong; Edupuganti, Ramakrishna; Devkota, Ashwini; Stancu, Gabriel; Liddington, Robert C; Dalby, Kevin N; Powis, Garth
2016-07-15
The hypoxia-inducible transcription factor HIF1α drives expression of many glycolytic enzymes. Here, we show that hypoxic glycolysis, in turn, increases HIF1α transcriptional activity and stimulates tumor growth, revealing a novel feed-forward mechanism of glycolysis-HIF1α signaling. Negative regulation of HIF1α by AMPK1 is bypassed in hypoxic cells, due to ATP elevation by increased glycolysis, thereby preventing phosphorylation and inactivation of the HIF1α transcriptional coactivator p300. Notably, of the HIF1α-activated glycolytic enzymes we evaluated by gene silencing, aldolase A (ALDOA) blockade produced the most robust decrease in glycolysis, HIF-1 activity, and cancer cell proliferation. Furthermore, either RNAi-mediated silencing of ALDOA or systemic treatment with a specific small-molecule inhibitor of aldolase A was sufficient to increase overall survival in a xenograft model of metastatic breast cancer. In establishing a novel glycolysis-HIF-1α feed-forward mechanism in hypoxic tumor cells, our results also provide a preclinical rationale to develop aldolase A inhibitors as a generalized strategy to treat intractable hypoxic cancer cells found widely in most solid tumors. Cancer Res; 76(14); 4259-69. ©2016 AACR.
Kuttykrishnan, Sooraj; Sabina, Jeffrey; Langton, Laura; Johnston, Mark; Brent, Michael R.
The ability to design and engineer organisms demands the ability to predict kinetic responses of novel regulatory networks built from well-characterized biological components. Surprisingly, few validated kinetic models of complex regulatory networks have been derived by combining models of the network components. A major bottleneck in producing such models is the difficulty of measuring in vivo rate constants for components of complex networks. We demonstrate that a simple, genetic approach to measuring rate constants in vivo produces an accurate kinetic model of the complex network that Saccharomyces cerevisiae employs to regulate the expression of genes encoding glucose transporters. The model predicts a transient pulse of transcription of HXT4 (but not HXT2 or HXT3) in response to addition of a small amount of glucose to cells, an outcome we observed experimentally. Our model also provides a mechanistic explanation for this result: HXT24 are governed by a type 2, incoherent feed forward regulatory loop involving the Rgt1 and Mig2 transcriptional repressors. The efficiency with which Rgt1 and Mig2 repress expression of each HXT gene determines which of them have a pulse of transcription in response to glucose. Finally, the model correctly predicts how lesions in the feed forward loop change the kinetics of induction of HXT4 expression.
Smith, G. A.; Meyer, G.; Nordstrom, M.
1986-01-01
A new automatic flight control system concept suitable for aircraft with highly nonlinear aerodynamic and propulsion characteristics and which must operate over a wide flight envelope was investigated. This exact model follower inverts a complete nonlinear model of the aircraft as part of the feed-forward path. The inversion is accomplished by a Newton-Raphson trim of the model at each digital computer cycle time of 0.05 seconds. The combination of the inverse model and the actual aircraft in the feed-forward path alloys the translational and rotational regulators in the feedback path to be easily designed by linear methods. An explanation of the model inversion procedure is presented. An extensive set of simulation data for essentially the full flight envelope for a vertical attitude takeoff and landing aircraft (VATOL) is presented. These data demonstrate the successful, smooth, and precise control that can be achieved with this concept. The trajectory includes conventional flight from 200 to 900 ft/sec with path accelerations and decelerations, altitude changes of over 6000 ft and 2g and 3g turns. Vertical attitude maneuvering as a tail sitter along all axes is demonstrated. A transition trajectory from 200 ft/sec in conventional flight to stationary hover in the vertical attitude includes satisfactory operation through lift-cure slope reversal as attitude goes from horizontal to vertical at constant altitude. A vertical attitude takeoff from stationary hover to conventional flight is also demonstrated.
Interfacial Stability in a Two-Layer Benard Problem.
1985-04-01
STABILITY IN A TWO-LAYER BENARD PROBLEM Yuriko Renardy Technical Summary Report #2814 April 1985 I cti- Work Unit Number 2 - Physical Mathematics...34•"• -••’-’• ^ ••’••• VI , •• W -•- • •- ’•"• INTERFACIAL STABILITY IN A TWO-LAYER BENARD PROBLEM Yuriko Renardy I. INTRODUCTION Two layers of fluids are...Subtltl») INTERFACIAL STABILITY IN A TWO-LAYER BENARD PROBLEM 7. AUTMORf.; Yuriko Renardy »• PERFORMING ORGANIZATION NAME AND ADDRESS
Jet analysis by neural networks in high energy hadron-hadron collisions
De Felice, P; Pasquariello, G; De Felice, P; Nardulli, G; Pasquariello, G
1995-01-01
We study the possibility to employ neural networks to simulate jet clustering procedures in high energy hadron-hadron collisions. We concentrate our analysis on the Fermilab Tevatron energy and on the k_\\bot algorithm. We consider both supervised multilayer feed-forward network trained by the backpropagation algorithm and unsupervised learning, where the neural network autonomously organizes the events in clusters.
Suppressing Halo-chaos for Intense Ion Beamby Neural Network Adaptation Control Strategy
FANGJin-qing; LUOXiao-shu; WENGJia-qiang; ZHULun-wu
2003-01-01
Neural network has some advantages of adaptation, learn-self, self-organization and suitable for high-dimension for various applications in many fields, especially among them the feed-forward back-propagating neural network self-adaptation method is suitable for control of nonlinear systems.
用于本构模型的新的神经网络%NEW NEURAL NETWORK FOR CONSTITU- TIVE MODELING
赵启林; 王思敬; 金广谦
2003-01-01
In this paper,a new neural network is developed to connect FE analysis with the feed-forward neural network. With this new neural network,the constitutive model of material may be determined from the information of nodal's force and displacement. In this methodology,the stage which takes long time to obtain stress and strain by FE analysis is prevented.
Yan, Ming; Li, Wenxue; Yang, Kangwen; Zhou, Hui; Shen, Xuling; Zhou, Qian; Ru, Qitian; Bai, Dongbi; Zeng, Heping
2012-05-01
We report on a simple scheme to precisely control carrier-envelope phase of a nonlinear-polarization-rotation mode-locked self-started Yb-fiber laser system with an average output power of ∼7 W and a pulse width of 130 fs. The offset frequency was locked to the repetition rate of ∼64.5 MHz with a relative linewidth of ∼1.4 MHz by using a self-referenced feed-forward scheme based on an acousto-optic frequency shifter. The phase noise and timing jitter were calculated to be 370 mrad and 120 as, respectively.
Prediction of littoral drift with artificial neural networks
Singh, A.K.; Deo, M.C.; SanilKumar, V.
of the rate of sand drift has still remained as a problem. The current study addresses this issue through the use of artificial neural networks (ANN). Feed forward networks were developed to predict the sand drift from a variety of causative variables...
Armstrong, Caren; Szabadics, János; Tamás, Gábor; Soltesz, Ivan
2011-06-01
Feed-forward inhibition from molecular layer interneurons onto granule cells (GCs) in the dentate gyrus is thought to have major effects regulating entorhinal-hippocampal interactions, but the precise identity, properties, and functional connectivity of the GABAergic cells in the molecular layer are not well understood. We used single and paired intracellular patch clamp recordings from post-hoc-identified cells in acute rat hippocampal slices and identified a subpopulation of molecular layer interneurons that expressed immunocytochemical markers present in members of the neurogliaform cell (NGFC) class. Single NGFCs displayed small dendritic trees, and their characteristically dense axonal arborizations covered significant portions of the outer and middle one-thirds of the molecular layer, with frequent axonal projections across the fissure into the CA1 and subicular regions. Typical NGFCs exhibited a late firing pattern with a ramp in membrane potential prior to firing action potentials, and single spikes in NGFCs evoked biphasic, prolonged GABA(A) and GABA(B) postsynaptic responses in GCs. In addition to providing dendritic GABAergic inputs to GCs, NGFCs also formed chemical synapses and gap junctions with various molecular layer interneurons, including other NGFCs. NGFCs received low-frequency spontaneous synaptic events, and stimulation of perforant path fibers revealed direct, facilitating synaptic inputs from the entorhinal cortex. Taken together, these results indicate that NGFCs form an integral part of the local molecular layer microcircuitry generating feed-forward inhibition and provide a direct GABAergic pathway linking the dentate gyrus to the CA1 and subicular regions through the hippocampal fissure.
Christian Puller
Full Text Available The functional roles and synaptic features of horizontal cells in the mammalian retina are still controversial. Evidence exists for feedback signaling from horizontal cells to cones and feed-forward signaling from horizontal cells to bipolar cells, but the details of the latter remain elusive. Here, immunohistochemistry and confocal microscopy were used to analyze the expression patterns of the SNARE protein syntaxin-4, the GABA receptor subunits α1 and ρ, and the cation-chloride cotransporters NKCC and KCC2 in the outer plexiform layer of primate retina. In macaque retina, as observed previously in other species, syntaxin-4 was expressed on dendrites and axon terminals of horizontal cells at cone pedicles and rod spherules. At cones, syntaxin-4 appeared densely clustered in two bands, at horizontal cell dendritic tips and at the level of desmosome-like junctions. Interestingly, in the lower band where horizontal cells may synapse directly onto bipolar cells, syntaxin-4 was highly enriched beneath short-wavelength sensitive (S cones and colocalized with calbindin, a marker for HII horizontal cells. The enrichment at S-cones was not observed in either mouse or ground squirrel. Furthermore, high amounts of both GABA receptor and cation-chloride cotransporter subunits were found beneath primate S-cones. Finally, while syntaxin-4 was expressed by both HI and HII horizontal cell types, the intense clustering and colocalization with calbindin at S-cones indicated an enhanced expression in HII cells. Taken together, GABA receptors beneath cone pedicles, chloride transporters, and syntaxin-4 are putative constituents of a synaptic set of proteins which would be required for a GABA-mediated feed-forward pathway via horizontal cells carrying signals directly from cones to bipolar cells.
Friard Olivier
2010-08-01
Full Text Available Abstract Background Transcription Factors (TFs and microRNAs (miRNAs are key players for gene expression regulation in higher eukaryotes. In the last years, a large amount of bioinformatic studies were devoted to the elucidation of transcriptional and post-transcriptional (mostly miRNA-mediated regulatory interactions, but little is known about the interplay between them. Description Here we describe a dynamic web-accessible database, CircuitsDB, supporting a genome-wide transcriptional and post-transcriptional regulatory network integration, for the human and mouse genomes, based on a bioinformatic sequence-analysis approach. In particular, CircuitsDB is currently focused on the study of mixed miRNA/TF Feed-Forward regulatory Loops (FFLs, i.e. elementary circuits in which a master TF regulates an miRNA and together with it a set of Joint Target protein-coding genes. The database was constructed using an ab-initio oligo analysis procedure for the identification of the transcriptional and post-transcriptional interactions. Several external sources of information were then pooled together to obtain the functional annotation of the proposed interactions. Results for human and mouse genomes are presented in an integrated web tool, that allows users to explore the circuits, investigate their sequence and functional properties and thus suggest possible biological experiments. Conclusions We present CircuitsDB, a web-server devoted to the study of human and mouse mixed miRNA/TF Feed-Forward regulatory circuits, freely available at: http://biocluster.di.unito.it/circuits/
Theoretical Permeability of Two-layered Nonwoven Geotextiles
LIU Li-fang; CHU Cai-yuan
2006-01-01
The two-layered nonwoven geotextile, which consists of a layer constructed with fine fibers for providing optimal filtration characteristics and another layer constructed with coarse fibers for providing the required mechanical properties, is desirable for drainage and filtration system.Based on Darcy's law and drag force theory, a mathematical model on vertical permeability coefficient of two-layered nonwoven geotextile is estabilished. Comparison with experimental results shows that the present model possesses 83.6% accuracy for needle-punched two-layered nonwoven geotextiles. And experimental results also show that with the increasing of needle density the vertical permeability coefficient of two-layered nonwoven geotextiless firstly decreases and then increases, reaching the smallest value at 470 p/cm2.
Sha, Daohang
2010-01-01
Back-propagation with gradient method is the most popular learning algorithm for feed-forward neural networks. However, it is critical to determine a proper fixed learning rate for the algorithm. In this paper, an optimized recursive algorithm is presented for online learning based on matrix operation and optimization methods analytically, which can avoid the trouble to select a proper learning rate for the gradient method. The proof of weak convergence of the proposed algorithm also is given. Although this approach is proposed for three-layer, feed-forward neural networks, it could be extended to multiple layer feed-forward neural networks. The effectiveness of the proposed algorithms applied to the identification of behavior of a two-input and two-output non-linear dynamic system is demonstrated by simulation experiments.
K. Duraiswamy
2012-01-01
Full Text Available The moving object or vehicle location prediction based on their spatial and temporal information is an important task in many applications. Different methods were utilized for performing the vehicle movement detection and prediction process. In such works, there is a lack of analysis in predicting the vehicles location in current as well as in future. Moreover, such methods compute the vehicles movement by finding the topological relationships among trajectories and locations, whereas the representative GPS points are determined by the 30 m circular window. Due to this process, the performance of the method is degraded because such 30 m circular window is selected by calculating the error range in the given input image and such error range may vary from image to image. To reduce the drawback presented in the existing method, in this study a heuristic moving vehicle location prediction algorithm is proposed. The proposed heuristic algorithm mainly comprises two techniques namely, optimization GA algorithm and FFBNN. In this proposed technique, initially the vehicles frequent paths are collected by monitoring all the vehicles movement in a specific period. Among the frequent paths, the vehicles optimal paths are computed by the GA algorithm. The selected optimal paths for each vehicle are utilized to train the FFBNN. The well trained FFBNN is then utilized to find the vehicle movement from the current location. By combining the proposed heuristic algorithm with GA and FFBNN, the vehicles location is predicted efficiently. The implementation result shows the effectiveness of the proposed heuristic algorithm in predicting the vehicles future location from the current location. The performance of the heuristic algorithm is evaluated by comparing the result with the RBF classifier. The comparison result shows our proposed technique acquires an accurate vehicle location prediction ratio than the RBF prediction ratio, in terms of accuracy.
2014-03-27
security-conference/. [Accessed 10 January 2014]. [3] "The Economic Impact of Cybercrime and Cyber Espionage," 2013. [4] "Department of Homeland...Technology in Automation, Control and Intelligent Systems (CYBER), Bangkok , 2012. [38] M. Panda and M. R. Patra, "Network Intrusion Detection
Temporal solar irradiance variability analysis using neural networks
Tebabal, Ambelu; Damtie, Baylie; Nigussie, Melessew
A feed-forward neural network which can account for nonlinear relationship was used to model total solar irradiance (TSI). A single layer feed-forward neural network with Levenberg-marquardt back-propagation algorithm have been implemented for modeling daily total solar irradiance from daily photometric sunspot index, and core-to-wing ratio of Mg II index data. In order to obtain the optimum neural network for TSI modeling, the root mean square error (RMSE) and mean absolute error (MAE) have been taken into account. The modeled and measured TSI have the correlation coefficient of about R=0.97. The neural networks (NNs) model output indicates that reconstructed TSI from solar proxies (photometric sunspot index and Mg II) can explain 94% of the variance of TSI. This modeled TSI using NNs further strengthens the view that surface magnetism indeed plays a dominant role in modulating solar irradiance.
Viscardi Massimo
2016-12-01
Full Text Available Successful implementation of an active vibration control system is strictly correlated to the exact knowledge of the dynamic behavior of the system, of the excitation level and spectra and of the sensor and actuator’s specification. Only the correct management of these aspects may guarantee the correct choice of the control strategy and the relative performance. Within this paper, some preliminary activities aimed at the creation of a structurally simple, cheap and easily replaceable active control systems for metal panels are discussed. The final future aim is to control and to reduce noise, produced by vibrations of metal panels of the body of a car. The paper is focused on two points. The first one is the realization of an electronic circuit for Synchronized Shunted Switch Architecture (SSSA with the right dimensioning of the components to control the proposed test article, represented by a rectangular aluminum plate. The second one is a preliminary experimental study on the test article, in controlled laboratory conditions, to compare performances of two possible control approach: SSSA and a feed-forward control approach. This comparison would contribute to the future choice of the most suitable control architecture for the specific attenuation of structure-born noise related to an automotive floor structure under deterministic (engine and road-tyre interaction and stochastic (road-tyre interaction and aerodynamic forcing actions.
Cátia Vieira
2014-01-01
Full Text Available Purinergic signalling is remarkably plastic during gastrointestinal inflammation. Thus, selective drugs targeting the “purinome” may be helpful for inflammatory gastrointestinal diseases. The myenteric neuromuscular transmission of healthy individuals is fine-tuned and controlled by adenosine acting on A2A excitatory receptors. Here, we investigated the neuromodulatory role of adenosine in TNBS-inflamed longitudinal muscle-myenteric plexus of the rat ileum. Seven-day postinflammation ileitis lacks adenosine neuromodulation, which may contribute to acceleration of gastrointestinal transit. The loss of adenosine neuromodulation results from deficient accumulation of the nucleoside at the myenteric synapse despite the fact that the increases in ATP release were observed. Disparity between ATP outflow and adenosine deficit in postinflammatory ileitis is ascribed to feed-forward inhibition of ecto-5′-nucleotidase/CD73 by high extracellular ATP and/or ADP. Redistribution of NTPDase2, but not of NTPDase3, from ganglion cell bodies to myenteric nerve terminals leads to preferential ADP accumulation from released ATP, thus contributing to the prolonged inhibition of muscle-bound ecto-5′-nucleotidase/CD73 and to the delay of adenosine formation at the inflamed neuromuscular synapse. On the other hand, depression of endogenous adenosine accumulation may also occur due to enhancement of adenosine deaminase activity. Both membrane-bound and soluble forms of ecto-5′-nucleotidase/CD73 and adenosine deaminase were detected in the inflamed myenteric plexus. These findings provide novel therapeutic targets for inflammatory gut motility disorders.
Permutation parity machines for neural cryptography.
Reyes, Oscar Mauricio; Zimmermann, Karl-Heinz
2010-06-01
Recently, synchronization was proved for permutation parity machines, multilayer feed-forward neural networks proposed as a binary variant of the tree parity machines. This ability was already used in the case of tree parity machines to introduce a key-exchange protocol. In this paper, a protocol based on permutation parity machines is proposed and its performance against common attacks (simple, geometric, majority and genetic) is studied.
Improved efficient routing strategy on two-layer complex networks
Ma, Jinlong; Han, Weizhan; Guo, Qing; Zhang, Shuai; Wang, Junfang; Wang, Zhihao
2016-10-01
The traffic dynamics of multi-layer networks has become a hot research topic since many networks are comprised of two or more layers of subnetworks. Due to its low traffic capacity, the traditional shortest path routing (SPR) protocol is susceptible to congestion on two-layer complex networks. In this paper, we propose an efficient routing strategy named improved global awareness routing (IGAR) strategy which is based on the betweenness centrality of nodes in the two layers. With the proposed strategy, the routing paths can bypass hub nodes of both layers to enhance the transport efficiency. Simulation results show that the IGAR strategy can bring much better traffic capacity than the SPR and the global awareness routing (GAR) strategies. Because of the significantly improved traffic performance, this study is helpful to alleviate congestion of the two-layer complex networks.
An integrated architecture of adaptive neural network control for dynamic systems
Ke, Liu; Tokar, R.; Mcvey, B.
1994-07-01
In this study, an integrated neural network control architecture for nonlinear dynamic systems is presented. Most of the recent emphasis in the neural network control field has no error feedback as the control input which rises the adaptation problem. The integrated architecture in this paper combines feed forward control and error feedback adaptive control using neural networks. The paper reveals the different internal functionality of these two kinds of neural network controllers for certain input styles, e.g., state feedback and error feedback. Feed forward neural network controllers with state feedback establish fixed control mappings which can not adapt when model uncertainties present. With error feedbacks, neural network controllers learn the slopes or the gains respecting to the error feedbacks, which are error driven adaptive control systems. The results demonstrate that the two kinds of control scheme can be combined to realize their individual advantages. Testing with disturbances added to the plant shows good tracking and adaptation.
Genetic algorithm for neural networks optimization
Setyawati, Bina R.; Creese, Robert C.; Sahirman, Sidharta
2004-11-01
This paper examines the forecasting performance of multi-layer feed forward neural networks in modeling a particular foreign exchange rates, i.e. Japanese Yen/US Dollar. The effects of two learning methods, Back Propagation and Genetic Algorithm, in which the neural network topology and other parameters fixed, were investigated. The early results indicate that the application of this hybrid system seems to be well suited for the forecasting of foreign exchange rates. The Neural Networks and Genetic Algorithm were programmed using MATLAB«.
Role of neural networks in the search of the Higgs boson at LHC
Maggipinto, T.; Nardulli, G.; Dusini, S.; Ferrari, F.; Lazzizzera, I.; Sidoti, A.; Sartori, A.; Tecchiolli, G. P.
1997-02-01
We show that neural network classifiers can be helpful to discriminate Higgs production from background at LHC in the Higgs mass range MH ~ 200 GeV. We employ a common feed-forward neural network trained by the backpropagation algorithm for off-line analysis and the neural chip Totem, trained by the Reactive Tabu Search algorithm, which could be used for on-line analysis.
Synchronization of Stochastic Two-Layer Geophysical Flows
HAN Yongqian
2011-01-01
In this paper, the two-layer quasigeostrophic flow model under stochastic wind forcing is considered. It is shown that when the layer depth or density difference across the layers tends to zero, the dynamics on both layers synchronizes to an averaged geophysical flow model.
Linear waves in two-layer fluids over periodic bottoms
Yu, J.; Maas, L.R.M.
2016-01-01
A new, exact Floquet theory is presented for linear waves in two-layer fluidsover a periodic bottom of arbitrary shape and amplitude. A method of conformaltransformation is adapted. The solutions are given, in essentially analytical form, forthe dispersion relation between wave frequency and general
Linear waves in two-layer fluids over periodic bottoms
Yu, Jie; Maas, L.R.M.
2016-01-01
A new, exact Floquet theory is presented for linear waves in two-layer fluids over a periodic bottom of arbitrary shape and amplitude. A method of conformal transformation is adapted. The solutions are given, in essentially analytical form, for the dispersion relation between wave frequency and gene
Multiobjective training of artificial neural networks for rainfall-runoff modeling
De Vos, N.J.; Rientjes, T.H.M.
2008-01-01
This paper presents results on the application of various optimization algorithms for the training of artificial neural network rainfall-runoff models. Multilayered feed-forward networks for forecasting discharge from two mesoscale catchments in different climatic regions have been developed for thi
Bhowmik, Subrata; Weber, Felix; Høgsberg, Jan Becker
2013-01-01
This paper presents a systematic design and training procedure for the feed-forward backpropagation neural network (NN) modeling of both forward and inverse behavior of a rotary magnetorheological (MR) damper based on experimental data. For the forward damper model, with damper force as output an...
Multiobjective training of artificial neural networks for rainfall-runoff modeling
De Vos, N.J.; Rientjes, T.H.M.
2008-01-01
This paper presents results on the application of various optimization algorithms for the training of artificial neural network rainfall-runoff models. Multilayered feed-forward networks for forecasting discharge from two mesoscale catchments in different climatic regions have been developed for
Alexander Krajete
2016-08-01
Full Text Available Recently, interests for new biofuel generations allowing conversion of gaseous substrate(s to gaseous product(s arose for power to gas and waste to value applications. An example is biological methane production process (BMPP with Methanothermobacter marburgensis. The latter, can convert carbon dioxide (CO2 and hydrogen (H2, having different origins and purities, to methane (CH4, water and biomass. However, these gas converting bioprocesses are tendentiously gas limited processes and the specific methane productivity per biomass amount (qCH4 tends to be low. Therefore, this contribution proposes a workflow for the development of a feed forward strategy to control biomass, growth (rx and qCH4 in a continuous gas limited BMPP. The proposed workflow starts with a design of experiment (DoE to optimize media composition and search for a liquid based limitation to control selectively growth. From the DoE it came out that controlling biomass growth was possible independently of the dilution and gassing rate applied while not affecting methane evolution rates (MERs. This was done by shifting the process from a natural gas limited state to a controlled liquid limited growth. The latter allowed exploiting the maximum biocatalytic activity for methane formation of Methanothermobacter marburgensis. An increase of qCH4 from 42 to 129 mmolCH4 g−1 h−1 was achieved by applying a liquid limitation compare with the reference state. Finally, a verification experiment was done to verify the feeding strategy transferability to a different process configuration. This evidenced the ratio of the fed KH2PO4 to rx (R(FKH2PO4/rx has an appropriate parameter for scaling feeds in a continuous gas limited BMPP. In the verification experiment CH4 was produced in a single bioreactor step at a methane evolution rate (MER of 132 mmolCH4*L−1*h−1 at a CH4 purity of 93 [Vol.%].
Chen Peng
Full Text Available BACKGROUND: As one of the most common types of co-regulatory motifs, feed-forward loops (FFLs control many cell functions and play an important role in human cancers. Therefore, it is crucial to reconstruct and analyze cancer-related FFLs that are controlled by transcription factor (TF and microRNA (miRNA simultaneously, in order to find out how miRNAs and TFs cooperate with each other in cancer cells and how they contribute to carcinogenesis. Current FFL studies rely on predicted regulation information and therefore suffer the false positive issue in prediction results. More critically, FFLs generated by existing approaches cannot represent the dynamic and conditional regulation relationship under different experimental conditions. METHODOLOGY/PRINCIPAL FINDINGS: In this study, we proposed a novel filter-wrapper feature selection method to accurately identify co-regulatory mechanism by incorporating prior information from predicted regulatory interactions with parallel miRNA/mRNA expression datasets. By applying this method, we reconstructed 208 and 110 TF-miRNA co-regulatory FFLs from human pan-cancer and prostate datasets, respectively. Further analysis of these cancer-related FFLs showed that the top-ranking TF STAT3 and miRNA hsa-let-7e are key regulators implicated in human cancers, which have regulated targets significantly enriched in cellular process regulations and signaling pathways that are involved in carcinogenesis. CONCLUSIONS/SIGNIFICANCE: In this study, we introduced an efficient computational approach to reconstruct co-regulatory FFLs by accurately identifying gene co-regulatory interactions. The strength of the proposed feature selection method lies in the fact it can precisely filter out false positives in predicted regulatory interactions by quantitatively modeling the complex co-regulation of target genes mediated by TFs and miRNAs simultaneously. Moreover, the proposed feature selection method can be generally applied to
Muraoka, Ryo; Nakanishi, Tetsuya
2017-02-01
A feedback control of the spill structure for the slow beam extraction from the medical synchrotron using a fast quadruple and radio frequency (RF)-knockout (QAR method) is studied to obtain the designed spill structure. In addition the feed-forward control is used so that the feedback control is performed effectively. In this extraction method, the spill of several ms are extracted continuously with an interval time of less than 1 ms. Beam simulation showed that a flat spill structure was effectively obtained with feed-forward and feedback control system as well as a step-wise structure which is useful for the shortening of an irradiation time in a spot scanning operation. The effect of current ripples from main quadruple magnet's power supplies could be also reduced with the feedback control application.
Pattern Synchronization in a Two-Layer Neuronal Network
SUN Xiao-Juan; LU Qi-Shao
2009-01-01
Pattern synchronization in a two-layer neuronal network is studied.For a single-layer network of Rulkov map neurons,there are three kinds of patterns induced by noise.Additive noise can induce ordered patterns at some intermediate noise intensities in a resonant way;however,for small and large noise intensities there exist excitable patterns and disordered patterns,respectively.For a neuronal network coupled by two single-layer networks with noise intensity differences between layers,we find that the two-layer network can achieve synchrony as the interlayer coupling strength increases.The synchronous states strongly depend on the interlayer coupling strength and the noise intensity difference between layers.
TWO-LAYER MODEL DESCRIPTION OF POLYMER THIN FILM DYNAMICS
Dong-dong Peng; Ran-xing Nancy Li; Chi-hang Lam; Ophelia K.C.Tsui
2013-01-01
Experiments in the past two decades have shown that the glass transition temperature of polymer films can become noticeably different from that of the bulk when the film thickness is decreased below ca.100 nm.It is broadly believed that these observations are caused by a nanometer interfacial layer with dynamics faster or slower than that of the bulk.In this paper,we examine how this idea may be realized by using a two-layer model assuming a hydrodynamic coupling between the interfacial layer and the remaining,bulk-like layer in the film.Illustrative examples will be given showing how the two-layer model is applied to the viscosity measurements of polystyrene and polymethylmethacrylate films supported by silicon oxide,where divergent thickness dependences are observed.
Electromagnetic Scattering in a Two-layered Medium
FENG LI-XIN; LI YUAN; Ma Fu-ming
2011-01-01
The object of this paper is to investigate the three-dimensional electro-magnetic scattering problems in a two-layered background medium.These problems have an important application in today's technology,such as to detect objects that are buried in soil.Here,we model both the exterior impedance problem and the inhomogeneous medium problem in R3.We establish uniqueness and existence for the solution of the two scattering problems,respectively.
Modeling Broadband Microwave Structures by Artificial Neural Networks
V. Otevrel
2004-06-01
Full Text Available The paper describes the exploitation of feed-forward neural networksand recurrent neural networks for replacing full-wave numerical modelsof microwave structures in complex microwave design tools. Building aneural model, attention is turned to the modeling accuracy and to theefficiency of building a model. Dealing with the accuracy, we describea method of increasing it by successive completing a training set.Neural models are mutually compared in order to highlight theiradvantages and disadvantages. As a reference model for comparisons,approximations based on standard cubic splines are used. Neural modelsare used to replace both the time-domain numeric models and thefrequency-domain ones.
A neural network-based optimal spatial filter design method for motor imagery classification.
Ayhan Yuksel
Full Text Available In this study, a novel spatial filter design method is introduced. Spatial filtering is an important processing step for feature extraction in motor imagery-based brain-computer interfaces. This paper introduces a new motor imagery signal classification method combined with spatial filter optimization. We simultaneously train the spatial filter and the classifier using a neural network approach. The proposed spatial filter network (SFN is composed of two layers: a spatial filtering layer and a classifier layer. These two layers are linked to each other with non-linear mapping functions. The proposed method addresses two shortcomings of the common spatial patterns (CSP algorithm. First, CSP aims to maximize the between-classes variance while ignoring the minimization of within-classes variances. Consequently, the features obtained using the CSP method may have large within-classes variances. Second, the maximizing optimization function of CSP increases the classification accuracy indirectly because an independent classifier is used after the CSP method. With SFN, we aimed to maximize the between-classes variance while minimizing within-classes variances and simultaneously optimizing the spatial filter and the classifier. To classify motor imagery EEG signals, we modified the well-known feed-forward structure and derived forward and backward equations that correspond to the proposed structure. We tested our algorithm on simple toy data. Then, we compared the SFN with conventional CSP and its multi-class version, called one-versus-rest CSP, on two data sets from BCI competition III. The evaluation results demonstrate that SFN is a good alternative for classifying motor imagery EEG signals with increased classification accuracy.
Neural Networks in Control Applications
Sørensen, O.
The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all...... in a recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...
Systolic implementation of neural networks
De Groot, A.J.; Parker, S.R.
1989-01-01
The backpropagation algorithm for error gradient calculations in multilayer, feed-forward neural networks is derived in matrix form involving inner and outer products. It is demonstrated that these calculations can be carried out efficiently using systolic processing techniques, particularly using the SPRINT, a 64-element systolic processor developed at Lawrence Livermore National Laboratory. This machine contains one million synapses, and forward-propagates 12 million connections per second, using 100 watts of power. When executing the algorithm, each SPRINT processor performs useful work 97% of the time. The theory and applications are confirmed by some nontrivial examples involving seismic signal recognition. 4 refs., 7 figs.
Chen, Chau-Kuang
2010-01-01
Artificial Neural Network (ANN) and Support Vector Machine (SVM) approaches have been on the cutting edge of science and technology for pattern recognition and data classification. In the ANN model, classification accuracy can be achieved by using the feed-forward of inputs, back-propagation of errors, and the adjustment of connection weights. In…
Tidal modulation of two-layer hydraulic exchange flows
L. M. Frankcombe
2006-11-01
Full Text Available Time-dependent, two layer hydraulic exchange flow is studied using an idealised shallow water model. It is found that barotropic time-dependent perturbations, representing tidal forcing, increase the baroclinic exchange flux above the steady hydraulic limit, with flux increasing monotonically with tidal amplitude (measured either by height or flux amplitude over a tidal period. Exchange flux also depends on the non-dimensional tidal period, γ, which was introduced by Helfrich (1995. Resonance complicates the relationship between exchange flux and height amplitude, but, when tidal strength is characterised by flux amplitude, exchange flux is a monotonic function of γ.
Baroclinic instability in the two-layer model. Interpretations
Egger, Joseph [Meteorological Inst., Univ. of Munich (Germany)
2009-10-15
Two new interpretations of the wellknown instability criterion of the two-layer model of baroclinic instability are given whereby also a slight generalization of this model is introduced by admitting an interface on top with a reduced gravity g. It is found that instability sets in when the horizontal potential temperature advection by the barotropic mode becomes more important than the vertical temperature advection due to this mode. The second interpretation is based on potential vorticity (PV) thinking. Instability implies a dominance of the vertical PV coupling coefficient compared to horizontal mean state PV advection generated at the same level. The interface damps with decreasing g. (orig.)
Interference testing of a two-layer commingled reservoir
Onur, M.; Reynolds, A.C. (Tulsa Univ., OK (USA))
1989-12-01
A two-well system in an infinite-acting, commingled, two-layer reservoir is considered. One well, the active well, is produced at a constant total rate, and the second well, the observation well, is shut in at all times. An analytical solution in Laplace space is presented, and the parametric groups that uniquely determine the pressure and rate solutions are identified. Results regarding crossflow through the observation well are presented. Conditions under which the line-source solution can be used to analyze observations-well pressure data are delineated.
Prato, Carlo Giacomo; Gitelman, Victoria; Bekhor, Shlomo
2011-01-01
on 1,793 fatal traffic accidents occurred during the period between 2003 and 2006 and applies Kohonen and feed-forward back-propagation neural networks with the objective of extracting from the data typical patterns and relevant factors. Kohonen neural networks reveal five compelling accident patterns....... Feed-forward back-propagation neural networks indicate that sociodemographic characteristics of drivers and victims, accident location, and period of the day are extremely relevant factors. Accident patterns suggest that countermeasures are necessary for identified problems concerning mainly vulnerable...... road users such as pedestrians, cyclists, motorcyclists and young drivers. A “safe-system” integrating a system approach for the design of countermeasures and a monitoring process of performance indicators might address the priorities highlighted by the neural networks....
Nonlinear topographic effects in two-layer flows
Peter George Baines
2016-02-01
Full Text Available We consider the nature of non-linear flow of a two-layer fluid with a rigid lid over a long obstacle, such that the flow may be assumed to be hydrostatic. Such flows can generate hydraulic jumps upstream, and the model uses a new model of internal hydraulic jumps, which results in corrections to flows that have been computed using earlier models of jumps that are now known to be incorrect. The model covers the whole range of ratios of the densities of the two fluids, and is not restricted to the Boussinesq limit. The results are presented in terms of flow types in various regions of a Froude number-obstacle height (F0 – Hm diagram, in which the Froude number F0 is based on the initial flow conditions. When compared with single-layer flow, and some previous results with two layers, some surprising and novel patterns emerge on these diagrams. Specifically, in parts of the diagram where the flow may be supercritical (F0 > 1, there are regions where hysteresis may occur, implying that the flow may have two and sometimes three multiple flow states for the same conditions (i.e. values of F0 and Hm.
Two-Layer Elastographic 3-D Traction Force Microscopy
Álvarez-González, Begoña; Zhang, Shun; Gómez-González, Manuel; Meili, Ruedi; Firtel, Richard A.; Lasheras, Juan C.; Del Álamo, Juan C.
2017-01-01
Cellular traction force microscopy (TFM) requires knowledge of the mechanical properties of the substratum where the cells adhere to calculate cell-generated forces from measurements of substratum deformation. Polymer-based hydrogels are broadly used for TFM due to their linearly elastic behavior in the range of measured deformations. However, the calculated stresses, particularly their spatial patterns, can be highly sensitive to the substratum’s Poisson’s ratio. We present two-layer elastographic TFM (2LETFM), a method that allows for simultaneously measuring the Poisson’s ratio of the substratum while also determining the cell-generated forces. The new method exploits the analytical solution of the elastostatic equation and deformation measurements from two layers of the substratum. We perform an in silico analysis of 2LETFM concluding that this technique is robust with respect to TFM experimental parameters, and remains accurate even for noisy measurement data. We also provide experimental proof of principle of 2LETFM by simultaneously measuring the stresses exerted by migrating Physarum amoeboae on the surface of polyacrylamide substrata, and the Poisson’s ratio of the substrata. The 2LETFM method could be generalized to concurrently determine the mechanical properties and cell-generated forces in more physiologically relevant extracellular environments, opening new possibilities to study cell-matrix interactions.
Two-layer networked learning control using self-learning fuzzy control algorithms
2007-01-01
Since the existing single-layer networked control systems have some inherent limitations and cannot effectively handle the problems associated with unreliable networks, a novel two-layer networked learning control system (NLCS) is proposed in this paper. Its lower layer has a number of local controllers that are operated independently, and its upper layer has a learning agent that communicates with the independent local controllers in the lower layer. To implement such a system, a packet-discard strategy is firstly developed to deal with network-induced delay and data packet loss. A cubic spline interpolator is then employed to compensate the lost data. Finally, the output of the learning agent based on a novel radial basis function neural network (RBFNN) is used to update the parameters of fuzzy controllers. A nonlinear heating, ventilation and air-conditioning (HVAC) system is used to demonstrate the feasibility and effectiveness of the proposed system.
Analysis and optimization of gas-centrifugal separation of uranium isotopes by neural networks
Migliavacca S.C.P.
2002-01-01
Full Text Available Neural networks are an attractive alternative for modeling complex problems with too many difficulties to be solved by a phenomenological model. A feed-forward neural network was used to model a gas-centrifugal separation of uranium isotopes. The prediction showed good agreement with the experimental data. An optimization study was carried out. The optimal operational condition was tested by a new experiment and a difference of less than 1% was found.
Successful prediction of horse racing results using a neural network
Allinson, N. M.; Merritt, D.
1991-01-01
Most application work within neural computing continues to employ multi-layer perceptrons (MLP). Though many variations of the fully interconnected feed-forward MLP, and even more variations of the back propagation learning rule, exist; the first section of the paper attempts to highlight several properties of these standard networks. The second section outlines an application-namely the prediction of horse racing results
刘萍; 王民权; 王劲
2013-01-01
CNC servo system has time delay in machine process of high-speed and high-precision which would cause form error because of deviation between instruction and real trajectory. Feed-forward control was introduced into servo system of CNC machine. Through theoretical analysis, it is shown that the form error can be effectively reduced by adopting proper feed-forward controller. CNC machine test results show; by adjusting the speed feed-forward coefficient, the speed loop gain can be improved, the form error due to changing acceleration is reduced, so surface quality and form precision are increased. Further the precision of CNC machine tools is improved.%针对高速高精加工过程中,因数控伺服系统时滞而导致的指令轨迹与实际轨迹存在偏差、进而导致形状误差的问题,将前馈控制引入数控机床伺服系统.通过理论分析可知:选用适当的前馈控制器,可以有效减小形状误差.数控机床测试结果表明:通过调整速度前馈系数,可以提高速度环的增益,从而减小因加速度变化引起的形状误差,改善表面精度和加工形状精度,进而提高CNC机床的加工精度.
Design and analysis of two-layer anonymous communication system
WANG Wei-ping; WANG Jian-xin
2007-01-01
A new architecture for scalable anonymous communication system(SACS) was proposed. The users were divided into several subgroups managed by different sub-blenders, and all sub-blenders were managed by the main-blender using two layers management scheme. The identity information of members are distributed on different sub-blenders, which makes each member keep much less information and network overload greatly reduce. The anonymity and the overhead of the new scheme were analyzed and compared with that of Crowds, which shows the cost of storage and network overhead for the new scheme largely decreases while the anonymity is little degraded. The experiment results also show that the new system architecture is well scalable. The ratio of management cost of SACS to that of Crowds is about 1:25 while the value of P(I|H1+) only increases by 0.001-0.020, which shows that SACS keeps almost the same anonymity with Crowds.
Control on a 2-D Wing Flutter Using an AdaptiveNonlinear Neural Controller
Hayder S. Abd Al-Amir
2011-01-01
Full Text Available An adaptive nonlinear neural controller to reduce the nonlinear flutter in 2-D wing is proposed in the paper. The nonlinearities in the system come from the quasi steady aerodynamic model and torsional spring in pitch direction. Time domain simulations are used to examine the dynamic aero elastic instabilities of the system (e.g. the onset of flutter and limit cycle oscillation, LCO. The structure of the controller consists of two models :the modified Elman neural network (MENN and the feed forward multi-layer Perceptron (MLP. The MENN model is trained with off-line and on-line stages to guarantee that the outputs of the model accurately represent the plunge and pitch motion of the wing and this neural model acts as the identifier. The feed forward neural controller is trained off-line and adaptive weights are implemented on-line to find the flap angles, which controls the plunge and pitch motion of the wing. The general back propagation algorithm is used to learn the feed forward neural controller and the neural identifier. The simulation results show the effectiveness of the proposed control algorithm; this is demonstrated by the minimized tracking error to zero approximation with very acceptable settling time even with the existence of bounded external disturbances.
An Improved Back Propagation Neural Network Algorithm on Classification Problems
Nawi, Nazri Mohd; Ransing, R. S.; Salleh, Mohd Najib Mohd; Ghazali, Rozaida; Hamid, Norhamreeza Abdul
The back propagation algorithm is one the most popular algorithms to train feed forward neural networks. However, the convergence of this algorithm is slow, it is mainly because of gradient descent algorithm. Previous research demonstrated that in 'feed forward' algorithm, the slope of the activation function is directly influenced by a parameter referred to as 'gain'. This research proposed an algorithm for improving the performance of the back propagation algorithm by introducing the adaptive gain of the activation function. The gain values change adaptively for each node. The influence of the adaptive gain on the learning ability of a neural network is analysed. Multi layer feed forward neural networks have been assessed. Physical interpretation of the relationship between the gain value and the learning rate and weight values is given. The efficiency of the proposed algorithm is compared with conventional Gradient Descent Method and verified by means of simulation on four classification problems. In learning the patterns, the simulations result demonstrate that the proposed method converged faster on Wisconsin breast cancer with an improvement ratio of nearly 2.8, 1.76 on diabetes problem, 65% better on thyroid data sets and 97% faster on IRIS classification problem. The results clearly show that the proposed algorithm significantly improves the learning speed of the conventional back-propagation algorithm.
NEURAL NETWORK TRAINING WITH PARALLEL PARTICLE SWARM OPTIMIZER
无
2006-01-01
Feed forward neural net works such as multi-layer perceptron,radial basis function neural net-works,have been widely applied to classification,function approxi mation and data mining.Evolu-tionary computation has been explored to train neu-ral net works as a very promising and competitive al-ternative learning method,because it has potentialto produce global mini mum in the weight space.Recently,an emerging evolutionary computationtechnique,Particle Swar m Opti mization(PSO)be-comes a hot topic because of i...
A Fuzzy-Neural Network Control of Nonlinear Dynamic Systems
无
2000-01-01
In this paper,an adaptive dynamic control scheme based on a fuzzy neural network is presented,that presents utilizes both feed-forward and feedback controller elements.The former of the two elements comprises a neural network with both identification and control role,and the latter is a fuzzy neural algorithm,which is introduced to provide additional control enhancement.The feedforward controller provides only coarse control,whereas the feedback oontroller can generate on-line conditional proposition rule automatically to improve the overall control action.These properties make the design very versatile and applicable to a range of industrial applications.
谢钟翔; 成佳庆; 张立勋; 张振峰
2013-01-01
为解决扁式布袋除尘器中脉冲喷吹对工艺风力除尘系统管道的负压造成的定时扰动问题，提出一种基于 T-S模糊模型的模糊控制结合脉冲喷吹和压力波动前馈的混合前馈控制方法。从山东和其他一些地方的集中工艺风力系统生产环境中的运行效果可以看出，它有效地减弱了脉冲喷吹对于管道负压造成的扰动，简化了控制，具有良好的稳定性和鲁棒性。%A mixed feed-forward control method based on T-S fuzzy model combined with pulse jet and pressure fluctuation feed-forward is proposed to decrease the timing disturbance on the negative pressure of wind dust removal pipeline caused by pulse jet in flat bag dedusting system. The proposed method is applied in the practical production environments with concentrated wind power processes in Shandong and other provinces. The operation results indicate that, it can effectively weaken the disturbance on pipeline negative pressure caused by pulse jet, and simplify the control with good stability and robustness.
Designing Two-Layer Optical Networks with Statistical Multiplexing
Addis, B.; Capone, A.; Carello, G.; Malucelli, F.; Fumagalli, M.; Pedrin Elli, E.
The possibility of adding multi-protocol label switching (MPLS) support to transport networks is considered an important opportunity by telecom carriers that want to add packet services and applications to their networks. However, the question that arises is whether it is suitable to have MPLS nodes just at the edge of the network to collect packet traffic from users, or also to introduce MPLS facilities on a subset of the core nodes in order to exploit packet switching flexibility and multiplexing, thus providing induction of a better bandwidth allocation. In this article, we address this complex decisional problem with the support of a mathematical programming approach. We consider two-layer networks where MPLS is overlaid on top of transport networks-synchronous digital hierarchy (SDH) or wavelength division multiplexing (WDM)-depending on the required link speed. The discussions' decisions take into account the trade-off between the cost of adding MPLS support in the core nodes and the savings in the link bandwidth allocation due to the statistical multiplexing and the traffic grooming effects induced by MPLS nodes. The traffic matrix specifies for each point-to-point request a pair of values: a mean traffic value and an additional one. Using this traffic model, the effect of statistical multiplexing on a link allows the allocation of a capacity equal to the sum of all the mean values of the traffic demands routed on the link and only the highest additional one. The proposed approach is suitable to solve real instances in reasonable time.
Wind Resource Assessment and Forecast Planning with Neural Networks
Nicolus K. Rotich
2014-06-01
Full Text Available In this paper we built three types of artificial neural networks, namely: Feed forward networks, Elman networks and Cascade forward networks, for forecasting wind speeds and directions. A similar network topology was used for all the forecast horizons, regardless of the model type. All the models were then trained with real data of collected wind speeds and directions over a period of two years in the municipal of Puumala, Finland. Up to 70th percentile of the data was used for training, validation and testing, while 71–85th percentile was presented to the trained models for validation. The model outputs were then compared to the last 15% of the original data, by measuring the statistical errors between them. The feed forward networks returned the lowest errors for wind speeds. Cascade forward networks gave the lowest errors for wind directions; Elman networks returned the lowest errors when used for short term forecasting.
TIME SERIES FORECASTING USING NEURAL NETWORKS
BOGDAN OANCEA
2013-05-01
Full Text Available Recent studies have shown the classification and prediction power of the Neural Networks. It has been demonstrated that a NN can approximate any continuous function. Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. Neural Networks have the advantage that can approximate nonlinear functions. In this paper we compared the performances of different feed forward and recurrent neural networks and training algorithms for predicting the exchange rate EUR/RON and USD/RON. We used data series with daily exchange rates starting from 2005 until 2013.
Hardware implementation of stochastic spiking neural networks.
Rosselló, Josep L; Canals, Vincent; Morro, Antoni; Oliver, Antoni
2012-08-01
Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bio-inspired nature and by a higher computational capacity with respect to other neural models. In real biological neurons, stochastic processes represent an important mechanism of neural behavior and are responsible of its special arithmetic capabilities. In this work we present a simple hardware implementation of spiking neurons that considers this probabilistic nature. The advantage of the proposed implementation is that it is fully digital and therefore can be massively implemented in Field Programmable Gate Arrays. The high computational capabilities of the proposed model are demonstrated by the study of both feed-forward and recurrent networks that are able to implement high-speed signal filtering and to solve complex systems of linear equations.
Sondhiya, Deepak Kumar; Gwal, Ashok Kumar; Verma, Shivali; Kasde, Satish Kumar
Abstract: In this paper, a wavelet-based neural network system for the detection and identification of four types of VLF whistler’s transients (i.e. dispersive, diffuse, spiky and multipath) is implemented and tested. The discrete wavelet transform (DWT) technique is integrated with the feed forward neural network (FFNN) model to construct the identifier. First, the multi-resolution analysis (MRA) technique of DWT and the Parseval’s theorem are employed to extract the characteristics features of the transients at different resolution levels. Second, the FFNN identifies these extracted features to identify the transients according to the features extracted. The proposed methodology can reduce a great quantity of the features of transients without losing its original property; less memory space and computing time are required. Various transient events are tested; the results show that the identifier can detect whistler transients efficiently. Keywords: Discrete wavelets transform, Multi-resolution analysis, Parseval’s theorem and Feed forward neural network
Yasir Hassan Ali
2015-01-01
Full Text Available The thickness of an oil film lubricant can contribute to less gear tooth wear and surface failure. The purpose of this research is to use artificial neural network (ANN computational modelling to correlate spur gear data from acoustic emissions, lubricant temperature, and specific film thickness (λ. The approach is using an algorithm to monitor the oil film thickness and to detect which lubrication regime the gearbox is running either hydrodynamic, elastohydrodynamic, or boundary. This monitoring can aid identification of fault development. Feed-forward and recurrent Elman neural network algorithms were used to develop ANN models, which are subjected to training, testing, and validation process. The Levenberg-Marquardt back-propagation algorithm was applied to reduce errors. Log-sigmoid and Purelin were identified as suitable transfer functions for hidden and output nodes. The methods used in this paper shows accurate predictions from ANN and the feed-forward network performance is superior to the Elman neural network.
Multimodality image registration and fusion using neural network
Mostafa G Mostafa; Aly A Farag; Edward Essock
2003-01-01
Multimodality image registration and fusion are essential steps in building 3-D models from remotesensing data. We present in this paper a neural network technique for the registration and fusion of multimodali-ty remote sensing data for the reconstruction of 3-D models of terrain regions. A FeedForward neural network isused to fuse the intensity data sets with the spatial data set after learning its geometry. Results on real data arepresented. Human performance evaluation is assessed on several perceptual tests in order to evaluate the fusionresults.
Dynamic Pricing in Electronic Commerce Using Neural Network
Ghose, Tapu Kumar; Tran, Thomas T.
In this paper, we propose an approach where feed-forward neural network is used for dynamically calculating a competitive price of a product in order to maximize sellers’ revenue. In the approach we considered that along with product price other attributes such as product quality, delivery time, after sales service and seller’s reputation contribute in consumers purchase decision. We showed that once the sellers, by using their limited prior knowledge, set an initial price of a product our model adjusts the price automatically with the help of neural network so that sellers’ revenue is maximized.
Modeling, Optimization and simulation of Rotary Furnace using Artificial Neural Network
Dr. R, K. Jain,
2011-04-01
Full Text Available This paper deals with modeling and simulation of LDO fired rotary furnace using feed forward modeling method of artificial neural network (ANN.The authors conducted experimental investigations onfuel consumption in a rotary furnace in an industry. It was observed that 6% oxygen enrichment of the air preheated up to 4600C simultaneously with reduction of air volume to 75% of its theoretical requirement lowered the specific fuel consumption to 0.260 lit/kg..The compact heat exchanger with 533 fins was used for preheating the air. Accordingly the emission level was also considerably reduced. The feed forward modeling method of artificial neural network contained in MAT LAB software was used for modeling andoptimization of specific fuel consumption. The percentage variation, between actual experimental data and same data when simulated is +1.730%, and other feasible simulated datas is +6.192%,-3.038%,-5.692%,and+0.115%which is fairly acceptable.
Fuel economy and torque tracking in camless engines through optimization of neural networks
Ashhab, Moh' d Sami S. [Department of Mechanical Engineering, The Hashemite University, Zarqa 13115 (Jordan)
2008-02-15
The feed forward controller of a camless internal combustion engine is modeled by inverting a multi-input multi-output feed forward artificial neural network (ANN) model of the engine. The engine outputs, pumping loss and cylinder air charge, are related to the inputs, intake valve lift and closing timing, by the artificial neural network model, which is trained with historical input-output data. The controller selects the intake valve lift and closing timing that will mimimize the pumping loss and achieve engine torque tracking. Lower pumping loss means better fuel economy, whereas engine torque tracking guarantees the driver's torque demand. The inversion of the ANN is performed with the complex method constrained optimization. How the camless engine inverse controller can be augmented with adaptive techniques to maintain accuracy even when the engine parts degrade is discussed. The simulation results demonstrate the effectiveness of the developed camless engine controller. (author)
Khaled Mammar; Abdelkader Chaker
2012-01-01
The paper is focused especially on presenting possibilities of applying artificial neural networks at creating the optimal model PEM fuel cell. Various ANN approaches have been tested; the back-propagation feed-forward networks show satisfactory performance with regard to cell voltage prediction. The model is then used in a power system for residential application. This models include an ANN fuel cell stack model, reformer model and DC/AC inverter model. Furthermore a neural network (NNTC) an...
DeepNet: An Ultrafast Neural Learning Code for Seismic Imaging
Barhen, J.; Protopopescu, V.; Reister, D.
1999-07-10
A feed-forward multilayer neural net is trained to learn the correspondence between seismic data and well logs. The introduction of a virtual input layer, connected to the nominal input layer through a special nonlinear transfer function, enables ultrafast (single iteration), near-optimal training of the net using numerical algebraic techniques. A unique computer code, named DeepNet, has been developed, that has achieved, in actual field demonstrations, results unattainable to date with industry standard tools.
CHEN Xi; ZHAO Guo-zhu
2005-01-01
In the paper, an artificial neural network (ANN) method is put forward to optimize melting temperature control, which reveals the nonlinear relationships of tank melting temperature disturbances with secondary wind flow and fuel pressure, implements dynamic feed-forward complementation and dynamic correctional ratio between air and fuel in the main control system. The application to Anhui Fuyang Glass Factory improved the control character of the melting temperature greatly.
A Comparison between Neural Networks and Traditional Forecasting Methods: A Case Study
C. A. Mitrea
2009-10-01
Full Text Available Forecasting accuracy drives the performance of inventory management. This study is to investigate and compare different forecasting methods like Moving Average (MA and Autoregressive Integrated Moving Average (ARIMA with Neural Networks (NN models as Feed-forward NN and Nonlinear Autoregressive network with eXogenous inputs (NARX. Data used to forecast is acquired from inventory database of Panasonic Refrigeration Devices Company located in Singapore. Results have shown that forecasting with NN offers better performance in comparison with traditional methods.
Time-Delay Neural Network for Smart MIMO Channel Estimation in Downlink 4G-LTE-Advance System
Nirmalkumar S. Reshamwala; Pooja S. Suratia; Satish K. Shah
2014-01-01
Long-Term Evolution (LTE) is the next generation of current mobile telecommunication networks. LTE has a new ﬂat radio-network architecture and signiﬁcant increase in spectrum efficiency. In this paper, main focus on throughput performance analysis of robust MIMO channel estimators for Downlink Long Term Evolution-Advance (DL LTE-A)-4G system using three Artificial Neural Networks: Feed-forward neural network (FFNN), Cascade-forward neural network (CFNN) and Time-Delay neural network (TDNN) a...
Meier, E.; Morgan, M. J.; Biedron, S. G.; LeBlanc, G.; Wu, J. (OTD-ESE); (Monash Univ.); (Australian Synchrotron Project); (SLAC National Accelerator Lab.)
2009-01-01
This paper describes the implementation of a neural network hybrid controller for energy stabilization at the Australian Synchrotron Linac. The structure of the controller consists of a neural network (NNET) feed forward control, augmented by a conventional Proportional-Integral (PI) feedback controller to ensure stability of the system. The system is provided with past states of the machine in order to predict its future state, and therefore apply appropriate feed forward control. The NNET is able to cancel multiple frequency jitter in real-time. When it is not performing optimally due to jitter changes, the system can successfully be augmented by the PI controller to attenuate the remaining perturbations. With a view to control the energy and bunch length at the FERMI{at}Elettra Free Electron Laser (FEL), the present study considers a neural network hybrid feed forward-feedback type of control to rectify limitations related to feedback systems, such as poor response for high jitter frequencies or limited bandwidth, while ensuring robustness of control. The Australian Synchrotron Linac is equipped with a beam position monitor (BPM), that was provided by Sincrotrone Trieste from a former transport line thus allowing energy measurements and energy control experiments. The present study will consequently focus on correcting energy jitter induced by variations in klystron phase and voltage.
Kannada character recognition system using neural network
Kumar, Suresh D. S.; Kamalapuram, Srinivasa K.; Kumar, Ajay B. R.
2013-03-01
Handwriting recognition has been one of the active and challenging research areas in the field of pattern recognition. It has numerous applications which include, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. As there is no sufficient number of works on Indian language character recognition especially Kannada script among 15 major scripts in India. In this paper an attempt is made to recognize handwritten Kannada characters using Feed Forward neural networks. A handwritten Kannada character is resized into 20x30 Pixel. The resized character is used for training the neural network. Once the training process is completed the same character is given as input to the neural network with different set of neurons in hidden layer and their recognition accuracy rate for different Kannada characters has been calculated and compared. The results show that the proposed system yields good recognition accuracy rates comparable to that of other handwritten character recognition systems.
Determining the input dimension of a neural network for nonlinear time series prediction
张胜; 刘红星; 高敦堂; 都思丹
2003-01-01
Determining the input dimension of a feed-forward neural network for nonlinear time series prediction plays an important role in the modelling.The paper first summarizes the current methods for determining the input dimension of the neural network.Then inspired by the fact that the correlation dimension of a nonlinear dynamic system is the mostimportant feature of it,the paper presents a new idea that the input dimension of the neural network for nonlinear time series prediction can be taken as an integer just greater than or equal to the correlation dimension.Finally,some wlidation examples and results are given.
Detection of Denial of Service Attacks against Domain Name System Using Neural Networks
Mohd Fadlee A. Rasid
2009-11-01
Full Text Available In this paper we introduce an intrusion detection system for Denial of Service (DoS attacks against Domain Name System (DNS. Our system architecture consists of two most important parts: a statistical preprocessor and a neural network classifier. The preprocessor extracts required statistical features in a short-time frame from traffic received by the target name server. We compared three different neural networks for detecting and classifying different types of DoS attacks. The proposed system is evaluated in a simulated network and showed that the best performed neural network is a feed-forward backpropagation with an accuracy of 99%.
Reflected light intensity profile of two-layer tissues: phantom experiments.
Ankri, Rinat; Taitelbaum, Haim; Fixler, Dror
2011-08-01
Experimental measurements of the reflected light intensity from two-layer phantoms are presented. We report, for the first time, an experimental observation of a typical reflected light intensity behavior for the two-layer structure characterized by two different slopes in the reflected light profile of the irradiated tissue. The point in which the first slope changes to the second slope, named as the crossover point, depends on the upper layer thickness as well as on the ratio between the absorption coefficients of the two layers. Since similar experiments from one-layer phantoms present a monotonic decay behavior, the existence and the location of the crossover point can be used as a diagnostic fingerprint for two-layer tissue structures. This pertains to two layers with greater absorptivity in the upper layer, which is the typical biological case in tissues like skin.
Cabrelli, C; Molter, U; Shonkwiler, R
2000-01-01
A sufficient condition that a region be classifiable by a two-layer feedforward neural net (a two-layer perceptron) using threshold activation functions is that either it be a convex polytope or that intersected with the complement of a convex polytope in its interior, or that intersected with the complement of a convex polytope in its interior or ... recursively. These have been called convex recursive deletion (CoRD) regions.We give a simple algorithm for finding the weights and thresholds in both layers for a feedforward net that implements such a region. The results of this work help in understanding the relationship between the decision region of a perceptron and its corresponding geometry in input space. Our construction extends in a simple way to the case that the decision region is the disjoint union of CoRD regions (requiring three layers). Therefore this work also helps in understanding how many neurons are needed in the second layer of a general three-layer network. In the event that the decision region of a network is known and is the union of CoRD regions, our results enable the calculation of the weights and thresholds of the implementing network directly and rapidly without the need for thousands of backpropagation iterations.
Reliability analysis of C-130 turboprop engine components using artificial neural network
Qattan, Nizar A.
In this study, we predict the failure rate of Lockheed C-130 Engine Turbine. More than thirty years of local operational field data were used for failure rate prediction and validation. The Weibull regression model and the Artificial Neural Network model including (feed-forward back-propagation, radial basis neural network, and multilayer perceptron neural network model); will be utilized to perform this study. For this purpose, the thesis will be divided into five major parts. First part deals with Weibull regression model to predict the turbine general failure rate, and the rate of failures that require overhaul maintenance. The second part will cover the Artificial Neural Network (ANN) model utilizing the feed-forward back-propagation algorithm as a learning rule. The MATLAB package will be used in order to build and design a code to simulate the given data, the inputs to the neural network are the independent variables, the output is the general failure rate of the turbine, and the failures which required overhaul maintenance. In the third part we predict the general failure rate of the turbine and the failures which require overhaul maintenance, using radial basis neural network model on MATLAB tool box. In the fourth part we compare the predictions of the feed-forward back-propagation model, with that of Weibull regression model, and radial basis neural network model. The results show that the failure rate predicted by the feed-forward back-propagation artificial neural network model is closer in agreement with radial basis neural network model compared with the actual field-data, than the failure rate predicted by the Weibull model. By the end of the study, we forecast the general failure rate of the Lockheed C-130 Engine Turbine, the failures which required overhaul maintenance and six categorical failures using multilayer perceptron neural network (MLP) model on DTREG commercial software. The results also give an insight into the reliability of the engine
2010-01-01
Back-propagation with gradient method is the most popular learning algorithm for feed-forward neural networks. However, it is critical to determine a proper fixed learning rate for the algorithm. In this paper, an optimized recursive algorithm is presented for online learning based on matrix operation and optimization methods analytically, which can avoid the trouble to select a proper learning rate for the gradient method. The proof of weak convergence of the proposed algorithm also is given...
A case for spiking neural network simulation based on configurable multiple-FPGA systems.
Yang, Shufan; Wu, Qiang; Li, Renfa
2011-09-01
Recent neuropsychological research has begun to reveal that neurons encode information in the timing of spikes. Spiking neural network simulations are a flexible and powerful method for investigating the behaviour of neuronal systems. Simulation of the spiking neural networks in software is unable to rapidly generate output spikes in large-scale of neural network. An alternative approach, hardware implementation of such system, provides the possibility to generate independent spikes precisely and simultaneously output spike waves in real time, under the premise that spiking neural network can take full advantage of hardware inherent parallelism. We introduce a configurable FPGA-oriented hardware platform for spiking neural network simulation in this work. We aim to use this platform to combine the speed of dedicated hardware with the programmability of software so that it might allow neuroscientists to put together sophisticated computation experiments of their own model. A feed-forward hierarchy network is developed as a case study to describe the operation of biological neural systems (such as orientation selectivity of visual cortex) and computational models of such systems. This model demonstrates how a feed-forward neural network constructs the circuitry required for orientation selectivity and provides platform for reaching a deeper understanding of the primate visual system. In the future, larger scale models based on this framework can be used to replicate the actual architecture in visual cortex, leading to more detailed predictions and insights into visual perception phenomenon.
A survey on RBF Neural Network for Intrusion Detection System
Henali Sheth
2014-12-01
Full Text Available Network security is a hot burning issue nowadays. With the help of technology advancement intruders or hackers are adopting new methods to create different attacks in order to harm network security. Intrusion detection system (IDS is a kind of security software which inspects all incoming and outgoing network traffic and it will generate alerts if any attack or unusual behavior is found in a network. Various approaches are used for IDS such as data mining, neural network, genetic and statistical approach. Among this Neural Network is more suitable approach for IDS. This paper describes RBF neural network approach for Intrusion detection system. RBF is a feed forward and supervise technique of neural network.RBF approach has good classification ability but its performance depends on its parameters. Based on survey we find that RBF approach has some short comings. In order to overcome this we need to do proper optimization of RBF parameters.
Relational Neural Evolution Approach to Bank Failure Prediction
Abudu, Bolanle; Markose, Sheri
2007-12-01
Relational neural networks as a concept offers a unique opportunity for improving classification accuracy by exploiting relational structure in data. The premise is that a relational classification technique, which uses information implicit in relationships, should classify more accurately than techniques that only examine objects in isolation. In this paper, we study the use of relational neural networks for predicting bank failure. Alongside classical financial ratios normally used as predictor variables, we introduced new relational variables for the network. The relational neural network structure, specified as a combination of feed forward and recurrent neural networks, is determined by bank data through neuro-evolution. We discuss empirical results comparing performance of the relational approach to standard propositional methods used for bank failure prediction.
System Identification, Prediction, Simulation and Control with Neural Networks
Sørensen, O.
1997-01-01
The intention of this paper is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: 1) Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. 2) Amongst numerous training algorithms, only the Recursive Prediction Error Method using...... a Gauss-Newton search direction is applied. 3) Amongst numerous model types, often met in control applications, only the Non-linear ARMAX (NARMAX) model, representing input/output description, is examined. A simulated example confirms that a neural network has the potential to perform excellent System...
ECO INVESTMENT PROJECT MANAGEMENT THROUGH TIME APPLYING ARTIFICIAL NEURAL NETWORKS
Tamara Gvozdenović
2007-06-01
Full Text Available he concept of project management expresses an indispensable approach to investment projects. Time is often the most important factor in these projects. The artificial neural network is the paradigm of data processing, which is inspired by the one used by the biological brain, and it is used in numerous, different fields, among which is the project management. This research is oriented to application of artificial neural networks in managing time of investment project. The artificial neural networks are used to define the optimistic, the most probable and the pessimistic time in PERT method. The program package Matlab: Neural Network Toolbox is used in data simulation. The feed-forward back propagation network is chosen.
a Heterosynaptic Learning Rule for Neural Networks
Emmert-Streib, Frank
In this article we introduce a novel stochastic Hebb-like learning rule for neural networks that is neurobiologically motivated. This learning rule combines features of unsupervised (Hebbian) and supervised (reinforcement) learning and is stochastic with respect to the selection of the time points when a synapse is modified. Moreover, the learning rule does not only affect the synapse between pre- and postsynaptic neuron, which is called homosynaptic plasticity, but effects also further remote synapses of the pre- and postsynaptic neuron. This more complex form of synaptic plasticity has recently come under investigations in neurobiology and is called heterosynaptic plasticity. We demonstrate that this learning rule is useful in training neural networks by learning parity functions including the exclusive-or (XOR) mapping in a multilayer feed-forward network. We find, that our stochastic learning rule works well, even in the presence of noise. Importantly, the mean learning time increases with the number of patterns to be learned polynomially, indicating efficient learning.
Vertex Reconstructing Neural Network at the ZEUS Central Tracking Detector
Dror, G; Dror, Gideon; Etzion, Erez
2001-01-01
An unconventional solution for finding the location of event creation is presented. It is based on two feed-forward neural networks with fixed architecture, whose parameters are chosen so as to reach a high accuracy. The interaction point location is a parameter that can be used to select events of interest from the very high rate of events created at the current experiments in High Energy Physics. The system suggested here is tested on simulated data sets of the ZEUS Central Tracking Detector, and is shown to perform better than conventional algorithms.
Microstructural characterization of materials by neural network technique
Barat, P. [Variable Energy Cyclotron Centre, 1/AF Bidhan Nagar, Kolkata 700064 (India); Chatterjee, A., E-mail: arnomitra@veccal.ernet.i [Variable Energy Cyclotron Centre, 1/AF Bidhan Nagar, Kolkata 700064 (India); Mukherjee, P.; Gayathri, N. [Variable Energy Cyclotron Centre, 1/AF Bidhan Nagar, Kolkata 700064 (India); Jayakumar, T.; Raj, Baldev [Indira Gandhi Centre for Atomic Research, Kalpakkam 603102 (India)
2010-11-15
Ultrasonic signals received by pulse echo technique from plane parallel Zircaloy 2 samples of fixed thickness and of three different microstructures, were subjected to signal analysis, as conventional parameters like velocity and attenuation could not reliably discriminate them. The signals, obtained from these samples, were first sampled and digitized. Modified Karhunen Loeve Transform was used to reduce their dimensionality. A multilayered feed forward Artificial Neural Network was trained using a few signals in their reduced domain from the three different microstructures. The rest of the signals from the three samples with different microstructures were classified satisfactorily using this network.
Investigations of Two-Layer Earth Parameters at Low Voltage: Measurements and Calculations
E. Ramdan; N. M. Nor; K. Ramar
2009-01-01
Problem statement: The two-layer soil model at low magnitude voltage is assumed to be accurate for the measurement and calculation of the earth resistance of a combined grid-multiple rods electrode...
许波桅; 杨勇生; 杨斌; 李军军
2015-01-01
为兼顾供应链系统的弹性和运作成本，提出三前馈自动渠道的、基于库存和定购的生产控制系统(Triple feed-forward automatic pipeline, inventory and order-based production control system, TFF-APIOBPCS)。在自动渠道的、基于库存和定购的生产控制系统模型中，增加一阶微分前馈环节，以部分抵消需求波动对库存的影响。在零稳态误差情况下针对生产控制系统的不同极点分布，分析一阶微分前馈环节的参数与供应链弹性的关系。综合考虑库存成本及生产调节成本，构造供应链系统的运作成本模型。通过阶跃需求、随机需求下的供应链系统仿真，评估一阶前馈环节参数对供应链弹性及运作成本的影响，验证三前馈自动渠道的、基于库存和定购的生产控制系统的有效性。结果表明，针对不同波动程度的需求，合理设置一阶微分前馈环节的参数，可以获得弹性与运作成本的良好均衡。%In order to trade off between supply chain resilience and operational cost, a sort of triple feed-forward automatic pipeline, inventory and order-based production control system(TFF-APIOBPCS) is presented. A first order differential feedforward unit, introduced to production control model APIOBPCS, enables the model to mitigate the impact of fluctuations in demand on actual inventory. Aiming at different pole distribution of the production control system, analysis of the relationship between the parameters of first order differential feedforward and resilience are conducted under zero steady-state error. Supply chain operational cost model is constructed by comprehensive consideration of inventory cost and production regulation cost. Supply chain system simulations with a unit step signal and a stochastic signal as the customer demand evaluate the effect of the first order differential feedforward parameters on supply chain resilience and operational cost, and reveal the
Diagonal Based Feature Extraction for Handwritten Alphabets Recognition System using Neural Network
Pradeep, J; Himavathi, S; 10.5121/ijcsit.2011.3103
2011-01-01
An off-line handwritten alphabetical character recognition system using multilayer feed forward neural network is described in the paper. A new method, called, diagonal based feature extraction is introduced for extracting the features of the handwritten alphabets. Fifty data sets, each containing 26 alphabets written by various people, are used for training the neural network and 570 different handwritten alphabetical characters are used for testing. The proposed recognition system performs quite well yielding higher levels of recognition accuracy compared to the systems employing the conventional horizontal and vertical methods of feature extraction. This system will be suitable for converting handwritten documents into structural text form and recognizing handwritten names.
Kadowaki, Taro; Nagayama, Ryuta; Georg, Jens; Nishiyama, Yoshitaka; Wilde, Annegret; Hess, Wolfgang R; Hihara, Yukako
2016-04-01
Since cyanobacteria need to decrease PSI content to avoid absorption of excess light energy, down-regulation of PSI gene expression is one of the key characteristics of the high-light (HL) acclimation response. The transcriptional regulator RpaB and the small RNA PsrR1 (photosynthesis regulatory RNA1) have been suggested to be the two most critical factors for this response in Synechocystis sp. PCC 6803. In this study, we found that the HLR1 DNA-binding motif, the recognition sequence for RpaB, is highly conserved in the core promoter region of the psrR1 gene among cyanobacterial species. Gel mobility shift assay revealed that RpaB binds to the HLR1 sequence of psrR1 in vitro. RNA gel blot analysis together with chromatin affinity purification (ChAP) analysis suggested that PSI genes are activated and the psrR1 gene is repressed by the binding of RpaB under low-light (LL) conditions. A decrease in DNA binding affinity of RpaB occurs within 5 min after the shift from LL to HL conditions, leading to the prompt decrease in PSI promoter activity together with derepression of psrR1 gene expression. Accumulating PsrR1 molecules then prevent translation from pre-existing PSI transcripts. By this dual repression at transcriptional and post-transcriptional levels, rapid and strict down-regulation of PSI expression under HL is secured. Our findings suggest that RpaB and PsrR1 constitute a feed-forward loop for the regulation of PSI gene expression to achieve a rapid acclimation response to the damaging HL conditions.
Implementation of neural network for color properties of polycarbonates
Saeed, U.; Ahmad, S.; Alsadi, J.; Ross, D.; Rizvi, G.
2014-05-01
In present paper, the applicability of artificial neural networks (ANN) is investigated for color properties of plastics. The neural networks toolbox of Matlab 6.5 is used to develop and test the ANN model on a personal computer. An optimal design is completed for 10, 12, 14,16,18 & 20 hidden neurons on single hidden layer with five different algorithms: batch gradient descent (GD), batch variable learning rate (GDX), resilient back-propagation (RP), scaled conjugate gradient (SCG), levenberg-marquardt (LM) in the feed forward back-propagation neural network model. The training data for ANN is obtained from experimental measurements. There were twenty two inputs including resins, additives & pigments while three tristimulus color values L*, a* and b* were used as output layer. Statistical analysis in terms of Root-Mean-Squared (RMS), absolute fraction of variance (R squared), as well as mean square error is used to investigate the performance of ANN. LM algorithm with fourteen neurons on hidden layer in Feed Forward Back-Propagation of ANN model has shown best result in the present study. The degree of accuracy of the ANN model in reduction of errors is proven acceptable in all statistical analysis and shown in results. However, it was concluded that ANN provides a feasible method in error reduction in specific color tristimulus values.
Process analysis of two-layered tube hydroforming with analytical and experimental verification
Seyedkashi, S. M. Hossein [The University of Birjand, Birjand (Iran, Islamic Republic of); Panahizadeh R, Valiollah [Shahid Rajaee Teacher Training University, Tehran (Iran, Islamic Republic of); Xu, Haibin; Kim, Sang Yun; Moon, Young Hoon [Pusan National University, Busan (Korea, Republic of)
2013-01-15
Two-layered tubular joints are suitable for special applications. Designing and manufacturing of two layered components require enough knowledge about the tube material behavior during the hydroforming process. In this paper, hydroforming of two-layered tubes is investigated analytically, and the results are verified experimentally. The aim of this study is to derive an analytical model which can be used in the process design. Fundamental equations are written for both of the outer and inner tubes, and the total forming pressure is obtained from these equations. Hydroforming experiments are carried out on two different combinations of materials for inner and outer tubes; case 1: copper/aluminum and case 2: carbon steel/stainless steel. It is observed that experimental results are in good agreement with the theoretical model obtained for estimation of forming pressure able to avoid wrinkling.
Lie symmetry analysis and exact solutions of the quasigeostrophic two-layer problem
Bihlo, Alexander; Popovych, Roman O.
2011-03-01
The quasigeostrophic two-layer model is of superior interest in dynamic meteorology since it is one of the easiest ways to study baroclinic processes in geophysical fluid dynamics. The complete set of point symmetries of the two-layer equations is determined. An optimal set of one- and two-dimensional inequivalent subalgebras of the maximal Lie invariance algebra is constructed. On the basis of these subalgebras, we exhaustively carry out group-invariant reduction and compute various classes of exact solutions. Wherever possible, reference to the physical meaning of the exact solutions is given. In particular, the well-known baroclinic Rossby wave solutions in the two-layer model are rediscovered.
Wetzel, Alfredo N; Cerovecki, Ivana; Hendershott, Myrl C; Karsten, Richard H; Miller, Peter D
2013-01-01
In this study the influence of stratification on surface tidal elevations in a two-layer analytical model is examined. The model assumes linearized, non-rotating, shallow-water dynamics in one dimension with astronomical forcing and allows for arbitrary topography. Both large scale (barotropic) and small scale (baroclinic) components of the surface tidal elevation are shown to be affected by stratification. It is also shown that the topography and basin boundaries affect the sensitivity of the barotropic surface tide to stratification significantly. In a companion paper it is shown that the barotropic tide in two-layer numerical models run in realistic global domains differs from its value in one-layer numerical models by amounts qualitatively consistent with analytic predictions from this paper. The analytical model also roughly predicts the sensitivity to perturbations in stratification in the two-layer domain model. Taken together, this paper and the companion paper therefore provide a framework to underst...
Wave scattering by undulating bed topography in a two-layer ocean
P. MAITI; B. N. MANDAL; U. BASU
2009-01-01
The problem of wave scattering by undulating bed topography in a two-layer ocean is investigated on the basis of linear theory. In a two-layer fluid with the upper layer having a free surface, there exist two modes of waves propagating at both the free surface of the upper layer and the interface between the two layers. Due to a wave train of a particular mode incident on an obstacle which is bottom-standing on the lower layer, reflected and transmitted waves of both modes are created by the obstacle. For small undulations on the bottom of the lower layer, a perturbation method is employed to obtain first-order reflection and transmission coefficients of both modes for incident wave trains of again both modes in terms of integrals involving the bed-shape function. For sinusoidal undulations, numerical results are presented graphically to illustrate the energy transfer between the waves of different modes by the undulating bed.
THE WAVE-MAKING CHARACTERISTICS OF A MOVING BODY IN A TWO-LAYER FLUID
ZHU Wei
2005-01-01
The Wave-making characteristics of a moving body in a two-layer fluid with free surface is investigated numerically and experimentally. The numerical analysis is based on the modified layered boundary integral equation system. The wave characteristics on the free surface and interface generated by a moving sphere and an ellipsoid is numerically simulated in both finite depth and infinite depth of lower layer model. The numerical results of the sphere are compared with the analytical results for a dipole with the same velocity in a two-layer fluid of finite depth. The dependence of the wave systems and structures on the characteristic quantities is discussed. Three kinds of measurement techniques are used in model experiments on the internal waves generated by a sphere advancing in a two-layer fluid. The effects of the varying velocity and stratification on the wavelength, wave amplitudes and the maximum half angles of internal waves are analyzed qualitatively.
Band splitting and relative spin alignment in two-layer systems
Ovchinnikov, A A
2002-01-01
It is shown that the single-particle spectra of the low Hubbard zone in the two-layer correlated 2D-systems sharply differ in the case of different relative alignment of the layers spin systems. The behavior of the two-layer splitting in the Bi sub 2 Sr sub 2 CaCu sub 2 O sub 8 sub + subdelta gives all reasons for the hypothesis on the possible rearrangement of the F sub z -> AF sub z alignment configuration, occurring simultaneously with the superconducting transition. The effects of the spin alignment on the magnetic excitations spectrum, as the way for studying the spin structure of the two-layer systems, are discussed by the example of homogenous solutions for the effective spin models
Ultrasound evaluation of the cesarean scar: comparison between one- and two layer uterotomy closure
Glavind, Julie; Madsen, Lene Duch; Uldbjerg, Niels
Objectives: To compare the residual myometrial thickness and the size of the cesarean scar defect after one- and two layer uterotomy closure. Methods: From July 2010 a continuous two-layer uterotomy closure technique replaced a continuous one-layer technique after cesarean delivery...... at the Department of Obstetrics and Gynecology at Aarhus University Hospital. A total of 149 consecutively invited women (68 women with one-layer and 81 women with two-layer closure) had their cesarean scar examined with 2D transvaginal sonography (TVS) 6-16 months post partum. Inclusion criteria were non......-pregnant women with one previous elective cesarean, no post-partum uterine infection or uterine re-operation, and no type 1 diabetes. Scar defect width, depth, and residual myometrial thickness were measured on the sagittal plane, and scar defect length was measured on the transverse plane. Results: The median...
Dan MA
2014-01-01
A two-layer switching architecture and a two-layer switching rule for stabilization of switched linear control systems are proposed, under which the mismatched switching between switched systems and their candidate hybrid controllers can be allowed. In the low layer, a state-dependent switching rule with a dwell time constraint to exponentially stabilize switched linear systems is given;in the high layer, supervisory conditions on the mismatched switching frequency and the mismatched switching ratio are presented, under which the closed-loop switched system is still exponentially stable in case of the candidate controller switches delay with respect to the subsystems. Different from the traditional switching rule, the two-layer switching architecture and switching rule have robustness, which in some extend permit mismatched switching between switched subsystems and their candidate controllers.
Random Boundary Simulation of Pumping Groundwater on Two-layer Soft Soil Structure with Porous Media
无
2002-01-01
Based on random theory,fluid dynamics,porous media and soil mechanics,the porosity and random characteristic of the two-layer soft soil in Wuhan region were studied in this paper.The random seepage coefficient on the two-layer soft soil was analyzed,and the seepage model and its random distribution function were given.The groundwater flow differential equations related to the two layer soft soil structure were also established.The evaluation procedure of effect boundary on the pumping water in deep foundation pit was put forward.Moreover,with an engineering example,the probability distribution on random boundary prediction for pumping water of foundation pit was computed.
Protein fold recognition with a two-layer method based on SVM-SA, WP-NN and C4.5 (TLM-SNC).
Zangooei, Mohammad Hossein; Jalili, Saeed
2013-01-01
The structural knowledge of protein is crucial in understanding its biological role. An effort is made to assign a fold to a given protein in a protein fold recognition problem. A computational Two-Layer Method (TLM) based on the Support Vector Machine (SVM), the Neural Network (NN) and the Decision Tree (C4.5) has been developed in this study for the assignment of a protein sequence to a folding class in SCOP. Prediction accuracy is measured on a dataset and the accuracy of the proposed method is very promising in comparison with other classification methods.
Transient stability Assessment using Artificial Neural Network Considering Fault Location
P.K.Olulope
2010-06-01
Full Text Available This paper describes the capability of artificial neural network for predicting the critical clearing time of power system. It combines the advantages of time domain integration schemes with artificial neural network for real time transient stability assessment. The training of ANN is done using selected features as input and critical fault clearing time (CCT as desire target. A single contingency was applied and the target CCT was found using time domain simulation. Multi layer feed forward neural network trained with Levenberg Marquardt (LM back propagation algorithm is used to provide the estimated CCT. The effectiveness of ANN, the method is demonstrated on single machine infinite bus system (SMIB. The simulation shows that ANN can provide fast and accurate mapping which makes it applicable to real time scenario.
Neural networks for predicting breeding values and genetic gains
Gabi Nunes Silva
2014-12-01
Full Text Available Analysis using Artificial Neural Networks has been described as an approach in the decision-making process that, although incipient, has been reported as presenting high potential for use in animal and plant breeding. In this study, we introduce the procedure of using the expanded data set for training the network. Wealso proposed using statistical parameters to estimate the breeding value of genotypes in simulated scenarios, in addition to the mean phenotypic value in a feed-forward back propagation multilayer perceptron network. After evaluating artificial neural network configurations, our results showed its superiority to estimates based on linear models, as well as its applicability in the genetic value prediction process. The results further indicated the good generalization performance of the neural network model in several additional validation experiments.
Short Term Load Forecast Using Wavelet Neural Network
Gui Min; Rong Fei; Luo An
2005-01-01
This paper presents a wavelet neural network (WNN) model combining wavelet transform and artificial neural networks for short term load forecast (STLF). Both historical load and temperature data having important impacts on load level were used in the proposed forecasting model. The model used the three-layer feed forward network trained by the error back-propagation algorithm. To enhance the forecasting accuracy by neural networks, wavelet multi-resolution analysis method was introduced to pre-process these data and reconstruct the predicted output. The proposed model has been evaluated with actual data of electricity load and temperature of Hunan Province. The simulation results show that the model is capable of providing a reasonable forecasting accuracy in STLF.
Earth slope reliability analysis under seismic loadings using neural network
PENG Huai-sheng; DENG Jian; GU De-sheng
2005-01-01
A new method was proposed to cope with the earth slope reliability problem under seismic loadings. The algorithm integrates the concepts of artificial neural network, the first order second moment reliability method and the deterministic stability analysis method of earth slope. The performance function and its derivatives in slope stability analysis under seismic loadings were approximated by a trained multi-layer feed-forward neural network with differentiable transfer functions. The statistical moments calculated from the performance function values and the corresponding gradients using neural network were then used in the first order second moment method for the calculation of the reliability index in slope safety analysis. Two earth slope examples were presented for illustrating the applicability of the proposed approach. The new method is effective in slope reliability analysis. And it has potential application to other reliability problems of complicated engineering structure with a considerably large number of random variables.
Lie symmetry analysis and exact solutions of the quasi-geostrophic two-layer problem
Bihlo, Alexander
2010-01-01
The quasi-geostrophic two-layer model is of superior interest in dynamic meteorology since it is one of the easiest ways to study baroclinic processes in geophysical fluid dynamics. The complete set of point symmetries of the two-layer equations is determined. An optimal set of one- and two-dimensional inequivalent subalgebras of the maximum Lie invariance algebra is constructed. On the basis of these subalgebras we exhaustively carry out group-invariant reduction and compute various classes of exact solutions. Where possible, reference to the physical meaning of the exact solutions is given.
Free surface simulation of a two-layer fluid by boundary element method
Weoncheol Koo
2010-09-01
Full Text Available A two-layer fluid with free surface is simulated in the time domain by a two-dimensional potential-based Numerical Wave Tank (NWT. The developed NWT is based on the boundary element method and a leap-frog time integration scheme. A whole domain scheme including interaction terms between two layers is applied to solve the boundary integral equation. The time histories of surface elevations on both fluid layers in the respective wave modes are verified with analytic results. The amplitude ratios of upper to lower elevation for various density ratios and water depths are also compared.
The Generalized Energy Equation and Instability in the Two-layer Barotropic Vortex
无
2007-01-01
The linear two-layer barotropic primitive equations in cylindrical coordinates are used to derive a generalized energy equation, which is subsequently applied to explain the instability of the spiral wave in the model. In the two-layer model, there are not only the generalized barotropic instability and the super highspeed instability, but also some other new instabilities, which fall into the range of the Kelvin-Helmholtz instability and the generalized baroclinic instability, when the upper and lower basic flows are different.They are perhaps the mechanisms of the generation of spiral cloud bands in tropical cyclones as well.
许丽丽; 宁提纲; 李晶; 裴丽; 油海东; 陈宏尧; 张婵
2013-01-01
光载无线通信(ROF)技术是通信业宽带化和无线化的产物,该技术将光纤通信技术与毫米波通信技术进行融合,具有广阔的应用前景.目前世界众多国家在60 GHz毫米波频段相继划出免许可连续频谱,这使得60 GHz毫米波无线通信成为近距离无线通信领域的研究热点之一.为了降低ROF系统的成本,提高系统的性能,提出了一种改进的基于前向调制(FFM)技术生成60 GHz毫米波方案,分析了系统各光电器件的工作原理,仿真了不同的参量设置对系统性能的影响曲线.该方案结合了前向调制技术和光波分复用技术的优点,简化了整个系统的复杂程度,降低了ROF系统的造价成本,同时减小了误码率,提高了系统的性能.%A radio over fiber (ROF) system is a product of the broad band and wireless in the communication industry. It combines the optical fiber communication technology and millimeter-wave communication technology, and has a broad application prospect. At present many countries mark off unlicensed continuous-frequency spectra in 60 GHz millimeter wave frequency band, which makes 60 GHz millimeter-wave wireless communication become one of the hot researches in the field of close wireless communication. In order to reduce the cost of a ROF system and improve its performance, an improved 60 GHz millimeter-wave generator based on feed-forward modulation (FFM) technique is proposed. The principle of the photoelectric device is analysed and the effect of different parameters setting in the performance of the system curve is simulated. The scheme combines with the advantages of forward modulation technology and light wavelength division multiplexing technology. It simplifies the complexity of the system, reduces the cost of the ROF system, reduces the error rate and improves the performance of the whole system.
A hardware implementation of artificial neural networks using field programmable gate arrays
Won, E.
2007-11-01
An artificial neural network algorithm is implemented using a low-cost field programmable gate array hardware. One hidden layer is used in the feed-forward neural network structure in order to discriminate one class of patterns from the other class in real time. In this work, the training of the network is performed in the off-line computing environment and the results of the training are configured to the hardware in order to minimize the latency of the neural computation. With five 8-bit input patterns, six hidden nodes, and one 8-bit output, the implemented hardware neural network makes decisions on a set of input patterns in 11 clock cycles, or less than 200 ns with a 60 MHz clock. The result from the hardware neural computation is well predictable based on the off-line computation. This implementation may be used in level 1 hardware triggers in high energy physics experiments.
PERFORMANCE COMPARISON FOR INTRUSION DETECTION SYSTEM USING NEURAL NETWORK WITH KDD DATASET
S. Devaraju
2014-04-01
Full Text Available Intrusion Detection Systems are challenging task for finding the user as normal user or attack user in any organizational information systems or IT Industry. The Intrusion Detection System is an effective method to deal with the kinds of problem in networks. Different classifiers are used to detect the different kinds of attacks in networks. In this paper, the performance of intrusion detection is compared with various neural network classifiers. In the proposed research the four types of classifiers used are Feed Forward Neural Network (FFNN, Generalized Regression Neural Network (GRNN, Probabilistic Neural Network (PNN and Radial Basis Neural Network (RBNN. The performance of the full featured KDD Cup 1999 dataset is compared with that of the reduced featured KDD Cup 1999 dataset. The MATLAB software is used to train and test the dataset and the efficiency and False Alarm Rate is measured. It is proved that the reduced dataset is performing better than the full featured dataset.
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.
Forecasting the Tehran Stock Market by Artificial Neural Network
Reza Aghababaeyan
2011-09-01
Full Text Available One of the most important problems in modern finance is finding efficient ways to summarize and visualize the stock market data to give individuals or institutions useful information about the market behavior for investment decisions. The enormous amount of valuable data generated by the stock market has attracted researchers to explore this problem domain using different methodologies. Potential significant benefits of solving these problems motivated extensive research for years. In this paper, computational data mining methodology was used to predict seven major stock market indexes. Two learning algorithms including Linear Regression and Neural Network Standard feed-forward back prop (FFB were tested and compared. The models were trained from four years of historical data from March 2007 to February 2011 in order to predict the major stock prices indexes in the Iran (Tehran Stock Exchange. The performance of these prediction models was evaluated using two widely used statistical metrics. We can show that using Neural Network Standard feed-forward back prop (FFB algorithm resulted in better prediction accuracy. In addition, traditional knowledge shows that a longer training period with more training data could help to build a more accurate prediction model. However, as the stock market in Iran has been highly fluctuating in the past two years, this paper shows that data collected from a closer and shorter period could help to reduce the prediction error for such highly speculated fast changing environment.
A two-layered approach to recognize high-level human activities
N. Hu; G. Englebienne; B. Kröse
2014-01-01
Automated human activity recognition is an essential task for Human Robot Interaction (HRI). A successful activity recognition system enables an assistant robot to provide precise services. In this paper, we present a two-layered approach that can recognize sub-level activities and high-level activi
Novel procedure to compute a contact zone magnitude of vibrations of two-layered uncoupled plates
Awrejcewicz J.
2005-01-01
Full Text Available A novel iteration procedure for dynamical problems, where in each time step, a contacting plates' zone is improved, is proposed. Therefore, a zone and magnitude of a contact load are also improved. Investigations of boundary conditions' influence on externally driven vibrations of uncoupled two-layer plates, where for each of the layers, the Kirchhoff hypothesis holds, are carried out.
Franken, Michel; Stramigioli, Stefano; Misra, Sarthak; Secchi, Cristian; Macchelli, Alessandro
2011-01-01
In this paper, a two-layer approach is presented to guarantee the stable behavior of bilateral telemanipulation sys- tems in the presence of time-varying destabilizing factors such as hard contacts, relaxed user grasps, stiff control settings, and/or communication delays. The approach splits the con
Coupling of Flexural and Longitudinal Damped Vibration in a Two-Layered Beam
F. Pourroy
1998-01-01
Full Text Available In dynamics, the effect of varying the constitutive materials’ thickness of a two-layered beam is investigated. Resonance frequencies and damping variations are determined. It is shown that for specific thicknesses the coupling of longitudinal and flexural vibrations influences the global modal damping ratio significantly.
Two-layer sheet of gelatin: A new topical hemostatic agent.
Takagi, Toshitaka; Tsujimoto, Hiroyuki; Torii, Hiroko; Ozamoto, Yuki; Hagiwara, Akeo
2016-11-02
Uncontrolled surgical bleeding is associated with increased morbidity, mortality, and hospital cost. Topical hemostatic agents available today have problems controlling hemostatic effects; furthermore, their handling is difficult and they are unsafe. We devised a new hemostatic agent comprising gelatin sponge and film designed to be applied to the bleeding site, thereby creating a topical hemostatic agent made of gelatin alone. The gelatin was prepared by alkali treatment to eliminate viral activity. Hemostatic effects, surgical handling, and tissue reactions of the materials, namely a two-layer sheet of gelatin, TachoSil, and gelatin sponge, were evaluated using 21 dogs' spleens. The two-layer gelatin sheet and gelatin sponge exhibited superior hemostatic effects (100% hemostasis completed) compared with TachoSil (0-17% hemostasis). The gelatin matrix immediately absorbed blood flowing from wounds and activated the autologous components in the absorbed blood that promoted coagulation at the bleeding site. The two-layer gelatin sheet had the best surgical handling among the evaluated materials. Materials made of gelatin were associated with fewer inflammatory reactions compared with materials of TachoSil. The two-layer sheet of gelatin is a useful topical agent because of its superior hemostatic effects and usability, and is associated with a lower risk of transmitting diseases and inflammatory reactions. Copyright © 2016. Published by Elsevier Taiwan.
Single-layer versus two-layer stamps for reduced pressure thermal nanoimprint
Papenheim, Marc; Dhima, Khalid; Wang, Si; Steinberg, Christian; Scheer, Hella-Christin
2015-11-01
Low-pressure imprint is interesting to avoid stamp deformation, stamp failure as well as polymer recovery. When large-area stamps are prepared with a stepping procedure, low pressure is required to optimize the stitching. However, with low-pressure imprint, conformal contact between stamp and substrate is critical. Admittedly, the imprint pressure required for conformal contact depends on the stamp material and its thickness. To get an idea to which extent the imprint pressure can be reduced with a flexible stamp, we compared different stamp materials and stamp architectures, single-layer stamps and two-layer stamps. The two-layer stamps are replica stamps, where the structures were replicated in a thin layer of OrmoStamp, fixed by a backplane. On the background of plate theory, we deduce the pressure reduction compared to a Si stamp by calculating the respective pressure ratio, independent from geometries. In addition, temperature-induced issues are addressed which are of relevance for a thermal imprint process. These issues are related to the mismatch between the thermal expansion coefficients of the stamp and the substrate, and in case of a two-layer stamp, to the mismatch between the backplane material and the top layer. The latter results in temperature-induced stamp bending. On the basis of simple analytical calculations, the potential of single-layer stamps and two-layer stamps with respect to thermal imprint at reduced pressure is discussed and guidelines are provided to assess the imprint situation when replica stamps are used for imprint. The results demonstrate the attractiveness of two-layer stamps for reduced pressure nanoimprint, even in a temperature-based process.
Kazantsev, Victor; Pimashkin, Alexey
2007-09-01
We propose two-layer architecture of associative memory oscillatory network with directional interlayer connectivity. The network is capable to store information in the form of phase-locked (in-phase and antiphase) oscillatory patterns. The first (input) layer takes an input pattern to be recognized and their units are unidirectionally connected with all units of the second (control) layer. The connection strengths are weighted using the Hebbian rule. The output (retrieved) patterns appear as forced-phase locked states of the control layer. The conditions are found and analytically expressed for pattern retrieval in response on incoming stimulus. It is shown that the system is capable to recover patterns with a certain level of distortions or noises in their profiles. The architecture is implemented with the Kuramoto phase model and using synaptically coupled neural oscillators with spikes. It is found that the spiking model is capable to retrieve patterns using the spiking phase that translates memorized patterns into the spiking phase shifts at different time scales.
IMPLEMENTATION OF ARTIFICIAL NEURAL NETWORK FOR FACE RECOGNITION USING GABOR FEATURE EXTRACTION
Muthukannan K
2013-11-01
Full Text Available Face detection and recognition is the first step for many applications in various fields such as identification and is used as a key to enter into the various electronic devices, video surveillance, and human computer interface and image database management. This paper focuses on feature extraction in an image using Gabor filter and the extracted image feature vector is then given as an input to the neural network. The neural network is trained with the input data. The Gabor wavelet concentrates on the important components of the face including eye, mouth, nose, cheeks. The main requirement of this technique is the threshold, which gives privileged sensitivity. The threshold values are the feature vectors taken from the faces. These feature vectors are given into the feed forward neural network to train the network. Using the feed forward neural network as a classifier, the recognized and unrecognized faces are classified. This classifier attains a higher face deduction rate. By training more input vectors the system proves to be effective. The effectiveness of the proposed method is demonstrated by the experimental results.
Waves induced by a submerged moving dipole in a two-layer fluid of finite depth
Gang Wei; Dongqiang Lu; Shiqiang Dai
2005-01-01
The waves induced by a moving dipole in a twofluid system are analytically and experimentally investigated.The velocity potential of a dipole moving horizontally in the lower layer of a two-layer fluid with finite depth is derived by superposing Green's functions of sources (or sinks). The far-field waves are studied by using the method of stationary phase. The effects of two resulting modes, i.e. the surfaceand internal-wave modes, on both the surface divergence field and the interfacial elevation are analyzed. A laboratory study on the internal waves generated by a moving sphere in a two-layer fluid is conducted in a towing tank under the same conditions as in the theoretical approach. The qualitative consistency between the present theory and the laboratory study is examined and confirmed.
Analysis of Two-Layered Random Interfaces for Two Dimensional Widom-Rowlinson's Model
Jun Wang
2011-01-01
Full Text Available The statistical behaviors of two-layered random-phase interfaces in two-dimensional Widom-Rowlinson's model are investigated. The phase interfaces separate two coexisting phases of the lattice Widom-Rowlinson model; when the chemical potential μ of the model is large enough, the convergence of the probability distributions which describe the fluctuations of the phase interfaces is studied. In this paper, the backbones of interfaces are introduced in the model, and the corresponding polymer chains and cluster expansions are developed and analyzed for the polymer weights. And the existence of the free energy for two-layered random-phase interfaces of the two-dimensional Widom-Rowlinson model is given.
Nonlinear dynamics at the interface of two-layer stratified flows over pronounced obstacles
Cabeza, C; Bove, I; Freire, D; Marti, Arturo C; Sarasua, L G; Usera, G; Montagne, R; Araújo, M
2008-01-01
The flow of a two--layer stratified fluid over an abrupt topographic obstacle, simulating relevant situations in oceanographic problems, is investigated numerically and experimentally in a simplified two--dimensional situation. Experimental results and numerical simulations are presented at low Froude numbers in a two-layer stratified flow and for two abrupt obstacles, semi--cylindrical and prismatic. We find four different regimes of the flow immediately past the obstacles: sub-critical (I), internal hydraulic jump (II), Kelvin-Helmholtz at the interface (III) and shedding of billows (IV). The critical condition for delimiting the experiments is obtained using the hydraulic theory. Moreover, the dependence of the critical Froude number on the geometry of the obstacle are investigated. The transition from regime III to regime IV is explained with a theoretical stability analysis. The results from the stability analysis are confirmed with the DPIV measurements. In regime (IV), when the velocity upstream is lar...
Nonstationary Axisymmetric Temperature Field in a Two-Layer Slab Under Mixed Heating Conditions
Turchin, I. N.; Timar, I.; Kolodii, Yu. A.
2015-09-01
With the use of the Laguerre and Hankel integral transforms, the solution of a two-dimensional initial-boundary-value heat conduction problem for a two-layer slab under mixed boundary conditions is constructed: one of the surfaces is heated by a heat flux distributed axisymmetrically in a circle of radius R and is cooled by the Newton law outside this circle. The solution of the problem is reduced to a sequence of infinite quasi-regular systems of algebraic equations. The results of numerical analysis of the temperature field in the two-layer slab made from an aluminum alloy and ceramicsare presented depending on the relative geometric properties of the components and cooling intensity.
A Two-layer Model for the Simulation of the VARTM Process with Resin Distribution Layer
Young, Wen-Bin
2013-12-01
Vacuum assisted resin transfer molding (VARTM) is one of the important processes to fabricate high performance composites. In this process, resin is drawn into the mold to impregnate the fiber reinforcement to a form composite. A resin distribution layer with high permeability was often introduced on top of the fiber reinforcement to accelerate the filling speed. Due to the difference of the flow resistance in the resin distribution layer and the reinforcement as well as the resulting through thickness transverse flow, the filling flow field is intrinsically three-dimensional. This study developed a two-layer model with two-dimensional formulation to simulate the filling flow of the VARTM process with a resin distribution layer. Two-dimensional flow was considered in each layer and a transverse flow in the thickness direction was estimated between the two layers. Thermal analysis including the transverse convection was also performed to better simulate the temperature distribution.
Estimation of apparent soil resistivity for two-layer soil structure
Nassereddine, M.; Rizk, J.; Nagrial, M.; Hellany, A. [School of Computing, Engineering and Mathematics, University of Western Sydney (Australia)
2013-07-01
High voltage (HV) earthing design is one of the key elements when it comes to safety compliance of a system. High voltage infrastructure exposes workers and people to unsafe conditions. The soil structure plays a vital role in determining the allowable and actual step/touch voltage. This paper presents vital information when working with two-layer soil structure. It shows the process as to when it is acceptable to use a single layer instead of a two-layer structure. It also discusses the simplification of the soil structure approach depending on the reflection coefficient. It introduces the reflection coefficient K interval which determines if single layer approach is acceptable. Multiple case studies are presented to address the new approach and its accuracy.
TAILING WAVETRAIN GENERATION IN PRECURSOR SOLITON GENERATION IN TWO-LAYER FLOW
Xu Zhaoting; Xu Hao; Samuel Shan-pu Shen
2000-01-01
A theory of tailing wavetrain generation for the precursor soliton generation in two-layer flow is presented by using averaged KdV equations(AKdV),which are derived by the authors in terms of Whitham's method of averaging[1,2].From the AKdV equations,group velocities of the tailing wavetrain generation are obtained by means of generating conditions of the tailing wavetrains,furthermore an analytical solution of the tailing wavetrain generation is found theoretically.A comparison between the theoretical and numerical results is carried out in the present paper,which shows that the theoretical results are in good agreement with the numerical ones,obtained from the fKdV equation in two-layer flow with the depth of unity in the rest.
Cournil, Michel; Herri, Jean-Michel
2002-01-01
6 pages; This paper proposes to re-visit the problem of gas-liquid crystallization in the framework of a two-layer model and with the help of data coming from experiments on methane hydrate crystallization in a semi-batch reactor. Preliminary quantitative discussion of the order of magnitude of different effects makes possible realistic simplifications in the theoretical models. In particular, the role of the interfacial film is clearly defined. As previous authors did, we use a formulation i...
Naruse, Makoto; Ishii, Satoshi; Drezet, Aurélien; Huant, Serge; Hoga, Morihisa; Ohyagi, Yasuyuki; Matsumoto, Tsutomu; Tate, Naoya; Ohtsu, Motoichi
2014-01-01
We theoretically demonstrate direction-dependent polarization conversion efficiency, yielding unidirectional light transmission, through a two-layer nanostructure by using the angular spectrum representation of optical near-fields. The theory provides results that are consistent with electromagnetic numerical simulations. This study reveals that optical near-field interactions among nanostructured matter can provide unique optical properties, such as the unidirectionality observed here, and offers fundamental guiding principles for understanding and engineering nanostructures for realizing novel functionalities.
Two-layer cold storage method for pancreas and islet cell transplantation
Yasuhiro; Fujino
2010-01-01
The two-layer cold storage method (TLM) was f irst reported in 1988, consisting of a perfluorochemical (PFC) and initially Euro-Collins' solution, which was later replaced by University of Wisconsin solution (UW). PFC is a biologically inert liquid and acts as an oxygen-supplying agent. A pancreas preserved using the TLM is oxygenated through the PFC and substrates are supplied by the UW solution. This allows the pancreas preserved using the TLM to generate adenosine triphosphate during storage, prolonging ...
SH-TM mathematical analogy for the two-layer case. A magnetotellurics application
J. Carcione; F. Poletto
2017-01-01
The same mathematical formalism of the wave equation can be used to describe anelastic and electromagnetic wave propagation. In this work, we obtain the mathematical analogy for the reflection/refraction (transmission) problem of two layers, considering the presence of anisotropy and attenuation -- viscosity in the viscoelastic case and resistivity in the electromagnetic case. The analogy is illustrated for SH (shear-horizontally polarised) and TM (transverse-magnetic) waves. In particular, w...
On Theory of Dispersive Transport in a Two-Layer Polymer Structure
Sibatov, R. T.; Morozova, E. V.
2016-09-01
Dispersive transport of charge carriers in a two-layer polymer structure is modeled on the basis of the integrodifferential equation of hereditary diffusion. The model of multiple trapping in a bilayer is generalized to the case of an arbitrary density of localized states. With the help of an efficient Monte Carlo algorithm, curves of the transient current are calculated and their features are explained within the framework of a stochastic interpretation of the process.
On two-layer models and the similarity functions for the PBL
Brown, R. A.
1982-01-01
An operational Planetary Boundary Layer model which employs similarity principles and two-layer patching to provide state-of-the-art parameterization for the PBL flow is used to study the popularly used similarity functions, A and B. The expected trends with stratification are shown. The effects of baroclinicity, secondary flow, humidity, latitude, surface roughness variation and choice of characteristic height scale are discussed.
Two-layer cold storage method for pancreas and islet cell transplantation
Fujino, Yasuhiro
2010-01-01
The two-layer cold storage method (TLM) was first reported in 1988, consisting of a perfluorochemical (PFC) and initially Euro-Collins’ solution, which was later replaced by University of Wisconsin solution (UW). PFC is a biologically inert liquid and acts as an oxygen-supplying agent. A pancreas preserved using the TLM is oxygenated through the PFC and substrates are supplied by the UW solution. This allows the pancreas preserved using the TLM to generate adenosine triphosphate during storag...
A Two Layer Approach to the Computability and Complexity of Real Functions
Lambov, Branimir Zdravkov
2003-01-01
We present a new model for computability and complexity of real functions together with an implementation that it based on it. The model uses a two-layer approach in which low-type basic objects perform the computation of a real function, but, whenever needed, can be complemented with higher type...... in computable analysis, while the efficiency of the implementation is not compromised by the need to create and maintain higher-type objects....
Lukić, M.; Ćojbašić, Ž.; Rabasović, M. D.; Markushev, D. D.; Todorović, D. M.
2013-09-01
This paper concerns with the possibilities of computational intelligence application for simultaneous determination of the laser beam spatial profile and vibrational-to-translational relaxation time of the polyatomic molecules in gases by pulsed photoacoustics. Results regarding the application of neural computing through the use of feed-forward multilayer perception networks are presented. Feed-forward multilayer perception networks are trained in an offline batch training regime to estimate simultaneously, and in real-time, the laser beam spatial profile (profile shape class) and the vibrational-to-translational relaxation time from given (theoretical) photoacoustic signals. The proposed method significantly shortens the time required for the simultaneous determination of the laser beam spatial profile and relaxation time and has the advantage of accurately calculating the aforementioned quantities.
Wang, Gang; Wu, Nanhua; Chen, Jionghua; Wang, Jinjian; Shao, Jingling; Zhu, Xiaolei; Lu, Xiaohua; Guo, Lucun
2016-11-01
The thermodynamic and kinetic behaviors of gold nanoparticles confined between two-layer graphene nanosheets (two-layer-GNSs) are examined and investigated during heating and cooling processes via molecular dynamics (MD) simulation technique. An EAM potential is applied to represent the gold-gold interactions while a Lennard-Jones (L-J) potential is used to describe the gold-GNS interactions. The MD melting temperature of 1345 K for bulk gold is close to the experimental value (1337 K), confirming that the EAM potential used to describe gold-gold interactions is reliable. On the other hand, the melting temperatures of gold clusters supported on graphite bilayer are corrected to the corresponding experimental values by adjusting the εAu-C value. Therefore, the subsequent results from current work are reliable. The gold nanoparticles confined within two-layer GNSs exhibit face center cubic structures, which is similar to those of free gold clusters and bulk gold. The melting points, heats of fusion, and heat capacities of the confined gold nanoparticles are predicted based on the plots of total energies against temperature. The density distribution perpendicular to GNS suggests that the freezing of confined gold nanoparticles starts from outermost layers. The confined gold clusters exhibit layering phenomenon even in liquid state. The transition of order-disorder in each layer is an essential characteristic in structure for the freezing phase transition of the confined gold clusters. Additionally, some vital kinetic data are obtained in terms of classical nucleation theory.
Long-term persistence of oil from the Exxon Valdez spill in two-layer beaches
Li, Hailong; Boufadel, Michel C.
2010-02-01
Oil spilled from the tanker Exxon Valdez in 1989 (refs 1, 2) persists in the subsurface of gravel beaches in Prince William Sound, Alaska. The contamination includes considerable amounts of chemicals that are harmful to the local fauna. However, remediation of the beaches was stopped in 1992, because it was assumed that the disappearance rate of oil was large enough to ensure a complete removal of oil within a few years. Here we present field data and numerical simulations of a two-layered beach with a small freshwater recharge in the contaminated area, where a high-permeability upper layer is underlain by a low-permeability lower layer. We find that the upper layer temporarily stored the oil, while it slowly and continuously filled the lower layer wherever the water table dropped below the interface of the two layers, as a result of low freshwater recharge from the land. Once the oil entered the lower layer, it became entrapped by capillary forces and persisted there in nearly anoxic conditions that are a result of the tidal hydraulics in the two-layered beaches. We suggest that similar dynamics could operate on tidal gravel beaches around the world, which are particularly common in mid- and high-latitude regions, with implications for locating spilled oil and for its biological remediation.
Steady internal waves in an exponentially stratified two-layer fluid
Makarenko, Nikolay; Maltseva, Janna; Ivanova, Kseniya
2016-04-01
The problem on internal waves in a weakly stratified two-layered fluid is studied analytically. We suppose that the fluid possess exponential stratification in both the layers, and the fluid density has discontinuity jump at the interface. By that, we take into account the influence of weak continuous stratification outside of sharp pycnocline. The model equation of strongly nonlinear interfacial waves propagating along the pycnocline is considered. This equation extends approximate models [1-3] suggested for a two-layer fluid with one homogeneous layer. The derivation method uses asymptotic analysis of fully nonlinear Euler equations. The perturbation scheme involves the long wave procedure with a pair of the Boussinesq parameters. First of these parameters characterizes small density slope outside of pycnocline and the second one defines small density jump at the interface. Parametric range of solitary wave solutions is characterized, including extreme regimes such as plateau-shape solitary waves. This work was supported by RFBR (grant No 15-01-03942). References [1] N. Makarenko, J. Maltseva. Asymptotic models of internal stationary waves, J. Appl. Mech. Techn. Phys, 2008, 49(4), 646-654. [2] N. Makarenko, J. Maltseva. Phase velocity spectrum of internal waves in a weakly-stratified two-layer fluid, Fluid Dynamics, 2009, 44(2), 278-294. [3] N. Makarenko, J. Maltseva. An analytical model of large amplitude internal solitary waves, Extreme Ocean Waves, 2nd ed. Springer 2015, E.Pelinovsky and C.Kharif (Eds), 191-201.
A two-layer flow model to represent ice-ocean interactions beneath Antarctic ice shelves
Lee, V.; Payne, A. J.; Gregory, J. M.
2011-01-01
We develop a two-dimensional two-layer flow model that can calculate melt rates beneath ice shelves from ocean temperature and salinity fields at the shelf front. The cavity motion is split into two layers where the upper plume layer represents buoyant meltwater-rich water rising along the underside of the ice to the shelf front, while the lower layer represents the ambient water connected to the open ocean circulating beneath the plume. Conservation of momentum has been reduced to a frictional geostrophic balance, which when linearized provides algebraic equations for the plume velocity. The turbulent exchange of heat and salt between the two layers is modelled through an entrainment rate which is directed into the faster flowing layer. The numerical model is tested using an idealized geometry based on the dimensions of Pine Island Ice Shelf. We find that the spatial distribution of melt rates is fairly robust. The rates are at least 2.5 times higher than the mean in fast flowing regions corresponding to the steepest section of the underside of the ice shelf close to the grounding line and to the converged geostrophic flow along the rigid lateral boundary. Precise values depend on a combination of entrainment and plume drag coefficients. The flow of the ambient is slow and the spread of ocean scalar properties is dominated by diffusion.
A two-layer flow model to represent ice-ocean interactions beneath Antarctic ice shelves
V. Lee
2011-01-01
Full Text Available We develop a two-dimensional two-layer flow model that can calculate melt rates beneath ice shelves from ocean temperature and salinity fields at the shelf front. The cavity motion is split into two layers where the upper plume layer represents buoyant meltwater-rich water rising along the underside of the ice to the shelf front, while the lower layer represents the ambient water connected to the open ocean circulating beneath the plume. Conservation of momentum has been reduced to a frictional geostrophic balance, which when linearized provides algebraic equations for the plume velocity. The turbulent exchange of heat and salt between the two layers is modelled through an entrainment rate which is directed into the faster flowing layer.
The numerical model is tested using an idealized geometry based on the dimensions of Pine Island Ice Shelf. We find that the spatial distribution of melt rates is fairly robust. The rates are at least 2.5 times higher than the mean in fast flowing regions corresponding to the steepest section of the underside of the ice shelf close to the grounding line and to the converged geostrophic flow along the rigid lateral boundary. Precise values depend on a combination of entrainment and plume drag coefficients. The flow of the ambient is slow and the spread of ocean scalar properties is dominated by diffusion.
A two-layer optimization model for high-speed railway line planning
Li WANG; Li-min JIA; Yong QIN; Jie XU; Wen-ring MO
2011-01-01
Line planning is the first important strategic element in the railway operation planning process,which will directly affect the successive planning to determine the efficiency of the whole railway system.A two-layer optimization model is proposed within a simulation framework to deal with the high-speed railway (HSR) line planning problem.In the model,the top layer aims at achieving an optimal stop-schedule set with the service frequencies,and is formulated as a nonlinear program,solved by genetic algorithm.The objective of top layer is to minimize the total operation cost and unserved passenger volume.Given a specific stop-schedule,the bottom layer focuses on weighted passenger flow assignment,formulated as a mixed integer program with the objective of maximizing the served passenger volume and minimizing the total travel time for all passengers.The case study on Taiwan HSR shows that the proposed two-layer model is better than the existing techniques.In addition,this model is also illustrated with the Beijing-Shanghai HSR in China.The result shows that the two-layer optimization model can reduce computation complexity and that an optimal set of stop-schedules can always be generated with less calculation time.
Diffraction of Water Waves by A Vertically Floating Cylinder in A Two-Layer Fluid
无
2008-01-01
In this paper, the diffraction of water waves by a vertically floating cylinder in a two-layer luid of a finite depth is studied. Analytical expressions for the hydrodynamic loads on the vertically floating cylinder are obtained by use of the method of eigenfunction expansions. The hydrodynamic loads on the vertically floating cylinder in a two-layer fluid include not only the surge, heave and pitch exciting forces due to the incident wave of the surface-wave mode, but also those due to the incident wave of the internal-wave mode. This is different from the case of a homogenous fluid. Some given examples show that, for a two-layer fluid system with a small density difference, the hydrodynamic loads for the surface-wave mode do not differ significantly from those due to surface waves in a single-layer fluid, but the hydrodynamic loads for the internal-wave mode are important over a wide range of frequencies. Moreover, also considered are the free surface and interface elevations generated by the diffraction wave due to the incident wave of the surface-wave and internal-wave modes, and transfer of energy between modes.
Input data preprocessing method for exchange rate forecasting via neural network
Antić Dragan S.
2014-01-01
Full Text Available The aim of this paper is to present a method for neural network input parameters selection and preprocessing. The purpose of this network is to forecast foreign exchange rates using artificial intelligence. Two data sets are formed for two different economic systems. Each system is represented by six categories with 70 economic parameters which are used in the analysis. Reduction of these parameters within each category was performed by using the principal component analysis method. Component interdependencies are established and relations between them are formed. Newly formed relations were used to create input vectors of a neural network. The multilayer feed forward neural network is formed and trained using batch training. Finally, simulation results are presented and it is concluded that input data preparation method is an effective way for preprocessing neural network data. [Projekat Ministarstva nauke Republike Srbije, br.TR 35005, br. III 43007 i br. III 44006
Jamil, Majid; Sharma, Sanjeev Kumar; Singh, Rajveer
2015-01-01
This paper focuses on the detection and classification of the faults on electrical power transmission line using artificial neural networks. The three phase currents and voltages of one end are taken as inputs in the proposed scheme. The feed forward neural network along with back propagation algorithm has been employed for detection and classification of the fault for analysis of each of the three phases involved in the process. A detailed analysis with varying number of hidden layers has been performed to validate the choice of the neural network. The simulation results concluded that the present method based on the neural network is efficient in detecting and classifying the faults on transmission lines with satisfactory performances. The different faults are simulated with different parameters to check the versatility of the method. The proposed method can be extended to the Distribution network of the Power System. The various simulations and analysis of signals is done in the MATLAB(®) environment.
Kalman filtering for neural prediction of response spectra from mining tremors
Krok, A.; Waszczyszyn, Z. [Cracow University of Technology, Krakow (Poland)
2007-08-15
Acceleration response spectra (ARS) for mining tremors in the Upper Silesian Coalfield, Poland are generated using neural networks trained by means of Kalman filtering. The target ARS were computed on the base of measured accelerograms. It was proved that the standard feed-forward, layered neural network, trained by the DEFK (decoupled extended Kalman filter) algorithm is numerically much less efficient than the standard recurrent NN learnt by Recurrent DEKF, cf. (Haykin S, (editor). Kalman filtering and neural networks. New York: John Wiley & Sons; 2001). It is also shown that the studied KF algorithms are better than the traditional Resilient-Propagation learning method. The improvement of the training process and neural prediction due to introduction of an autoregressive input is also discussed in the paper.
Psychological Processing in Chronic Pain: A Neural Systems Approach
Simons, Laura; Elman, Igor; Borsook, David
2014-01-01
Our understanding of chronic pain involves complex brain circuits that include sensory, emotional, cognitive and interoceptive processing. The feed-forward interactions between physical (e.g., trauma) and emotional pain and the consequences of altered psychological status on the expression of pain have made the evaluation and treatment of chronic pain a challenge in the clinic. By understanding the neural circuits involved in psychological processes, a mechanistic approach to the implementation of psychology-based treatments may be better understood. In this review we evaluate some of the principle processes that may be altered as a consequence of chronic pain in the context of localized and integrated neural networks. These changes are ongoing, vary in their magnitude, and their hierarchical manifestations, and may be temporally and sequentially altered by treatments, and all contribute to an overall pain phenotype. Furthermore, we link altered psychological processes to specific evidence-based treatments to put forth a model of pain neuroscience psychology. PMID:24374383
Neural Network Control of a Magnetically Suspended Rotor System
Choi, Benjamin B.
1998-01-01
Magnetic bearings offer significant advantages because they do not come into contact with other parts during operation, which can reduce maintenance. Higher speeds, no friction, no lubrication, weight reduction, precise position control, and active damping make them far superior to conventional contact bearings. However, there are technical barriers that limit the application of this technology in industry. One of them is the need for a nonlinear controller that can overcome the system nonlinearity and uncertainty inherent in magnetic bearings. At the NASA Lewis Research Center, a neural network was selected as a nonlinear controller because it generates a neural model without any detailed information regarding the internal working of the magnetic bearing system. It can be used even for systems that are too complex for an accurate system model to be derived. A feed-forward architecture with a back-propagation learning algorithm was selected because of its proven performance, accuracy, and relatively easy implementation.
An Artificial Neural Network for Data Forecasting Purposes
Catalina Lucia COCIANU
2015-01-01
Full Text Available Considering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN in solving the forecast task in the most general case, when the time series are non-stationary. We used a feed-forward neural architecture: the nonlinear autoregressive network with exogenous inputs. The network training function used to update the weight and bias parameters corresponds to gradient descent with adaptive learning rate variant of the backpropagation algorithm. The results obtained using this technique are compared with the ones resulted from some ARIMA models. We used the mean square error (MSE measure to evaluate the performances of these two models. The comparative analysis leads to the conclusion that the proposed model can be successfully applied to forecast the financial data.
Using Feature Weights to Improve Performance of Neural Networks
Iqbal, Ridwan Al
2011-01-01
Different features have different relevance to a particular learning problem. Some features are less relevant; while some very important. Instead of selecting the most relevant features using feature selection, an algorithm can be given this knowledge of feature importance based on expert opinion or prior learning. Learning can be faster and more accurate if learners take feature importance into account. Correlation aided Neural Networks (CANN) is presented which is such an algorithm. CANN treats feature importance as the correlation coefficient between the target attribute and the features. CANN modifies normal feed-forward Neural Network to fit both correlation values and training data. Empirical evaluation shows that CANN is faster and more accurate than applying the two step approach of feature selection and then using normal learning algorithms.
APPLIED CRYPTOGRAPHY IN PASSWORD ENCRYPTION USING NEURAL NETWORKS
Venkata Karthik Gullapalli
2015-09-01
Full Text Available Today the world depends on computers and information systems for processing information in various fields. These systems must be developed in such a way that they are less vulnerable to attacks and more reliable and secured. These systems are more vulnerable to technical issues and many cases of data trawling have been reported as a result of password breaches. Encryption and decryption plays a major role in the modern era as the rate of data flow increased tremendously. Social networking sites such as Facebook and Google stores the most important and private data of people electronically in the servers. Artificial intelligence took over many functions of computer systems in different fields including data security. Neural networks process information with care and certainty like human mind does. This paper proposes a methodology to implement encryption and decryption using the feed forward neural networks and to improve the security of information systems.
Neural network surface acoustic wave RF signal processor for digital modulation recognition.
Kavalov, Dimitar; Kalinin, Victor
2002-09-01
An architecture of a surface acoustic wave (SAW) processor based on an artificial neural network is proposed for an automatic recognition of different types of digital passband modulation. Three feed-forward networks are trained to recognize filtered and unfiltered binary phase shift keying (BPSK) and quadrature phase shift keying (QPSK) signals, as well as unfiltered BPSK, QPSK, and 16 quadrature amplitude (16QAM) signals. Performance of the processor in the presence of additive white Gaussian noise (AWGN) is simulated. The influence of second-order effects in SAW devices, phase, and amplitude errors on the performance of the processor also is studied.
Artificial Neural Network Model for Predicting Ultimate Tensile Capacity of Adhesive Anchors
XU Bo; WU Zhi-min; SONG Zhi-fei
2007-01-01
To predict the tensile capacity of adhesive anchors, a multilayered feed-forward neural network trained with the backpropagation algorithm is constructed. The ANN model have 5 inputs, including the compressive strength of concrete, tensile strength of concrete, anchor diameter, hole diameter, embedment of anchors, and ultimate load. The predictions obtained from the trained ANN show a good agreement with the experiments. Meanwhile, the predicted ultinate tensile capacity of anchors is close to the one calculated from the strength formula of the combined cone-bond failure model.
Time-of-flight discrimination between gamma-rays and neutrons by neural networks
2012-01-01
In gamma-ray spectroscopy, a number of neutrons are emitted from the nuclei together with the gamma-rays and these neutrons influence gamma-ray spectra. An obvious method of separating between neutrons and gamma-rays is based on the time-of-flight (tof) technique. This work aims obtaining tof distributions of gamma-rays and neutrons by using feed-forward artificial neural network (ANN). It was shown that, ANN can correctly classify gamma-ray and neutron events. Testing of trained networks on ...
A Neural Network Based Recognition and Classification of Commonly Used Indian Non Leafy Vegetables
Ajit Danti
2014-09-01
Full Text Available A methodology to characterize the commonly used Indian non-leafy vegetables’ images is developed. From the captured images of Indian non-leafy vegetables, color components, namely, RGB and HSV features are extracted, analyzed and classified. A feed forward backpropagation artificial neural network (BPNN is used for the classification. The results show that it has good robustness and a very high success rate in the range of 96-100% for eight types of vegetables. The work finds usefulness in developing recognition system for super market, automatic vending, packing and grading of vegetables, food preparation and Agriculture Produce Market Committee (APMC.
ESTIMATION OF PV MODULE SURFACE TEMPERATURE USING ARTIFICIAL NEURAL NETWORKS
Can Coskun
2016-12-01
Full Text Available This study aimed to use the artificial neural network (ANN method to estimate the surface temperature of a photovoltaic (PV panel. Using the experimentally obtained PV data, the accuracy of the ANN model was evaluated. To train the artificial neural network (ANN, outer temperature solar radiation and wind speed values were inputs and surface temperature was an output. The ANN was used to estimate PV panel surface temperature. Using the Levenberg-Marquardt (LM algorithm the feed forward artificial neural network was trained. Two back propagation type ANN algorithms were used and their performance was compared with the estimate from the LM algorithm. To train the artificial neural network, experimental data were used for two thirds with the remaining third used for testing. Additionally scaled conjugate gradient (SCG back propagation and resilient back propagation (RB type ANN algorithms were used for comparison with the LM algorithm. The performances of these three types of artificial neural network were compared and mean error rates of between 0.005962 and 0.012177% were obtained. The best estimate was produced by the LM algorithm. Estimation of PV surface temperature with artificial neural networks provides better results than conventional correlation methods. This study showed that artificial neural networks may be effectively used to estimate PV surface temperature.
FINITE ELEMENT FOR STRESS-STRAIN STATE MODELING OF TWO-LAYERED AXIALLY SYMMETRIC SHELLS
K. S. Kurochka
2015-07-01
Full Text Available Subject of Research. Computation of composite material designs requires application of numerical methods. The finiteelement method usage is connected with surface approximation problems. Application of volumetric and laminar elements leads to systems with large sizes and a great amount of computation. The objective of this paper is to present an equivalent two-layer mathematical model for evaluation of displacements and stresses of cross-ply laminated cone shells subjected to uniformly distributed load. An axially symmetric element for shell problems is described. Method. Axially symmetric finite element is proposed to be applied in calculations with use of correlation for the inner work of each layer separately. It gives the possibility to take into account geometric and physical nonlinearities and non-uniformity in the layers of the shell. Discrete mathematical model is created on the base of the finite-element method with the use of possible motions principle and Kirchhoff–Love assumptions. Hermite element is chosen as a finite one. Cone shell deflection is considered as the quantity sought for. Main Results. One-layered and two-layered cone shells have been considered for proposed mathematical model verification with known analytical and numerical analytical solutions, respectively. The axial displacements of the two-layered cone are measured with an error not exceeding 5.4 % for the number of finite elements equal to 30. The proposed mathematical model requires fewer nodes to define the finite element meshing of the system and much less computation time. Thereby time for finding solution decreases considerably. Practical Relevance. Proposed model is applicable for computation of multilayered designs under axially symmetric loads: composite high-pressure bottles, cylinder shaped fiberglass pipes, reservoirs for explosives and flammable materials, oil and gas storage tanks.
PECULIARITIES OF LAMB WAVE PROPAGATION THROUGH TWO-LAYERED THIN PLATE MATERIALS
A. R. Baev
2008-01-01
Full Text Available Peculiarities of the plate wave propagation through two-layered thin plate have been analyzed and formulas for velocity determination of the quickest plate mode have been proposed. The ascertained interaction makes it possible to determine coating layer thickness in accordance with the given and known elastic parameters of contacting materials. On the basis of the developed methodology experiments have been carried out that revealed qualitative and quantitative correspondence between theoretical and experimental data. The paper shows a principle possibility for assessment of material separation surface by time propagation data of the investigated mode .
Determination of homeostatic elastic moduli in two layers of the esophagus
Gregersen, Hans; Liao, Donghua; Fung, Yuan Cheng
2008-01-01
for determination of incremental moduli in circumferential, axial, and cross directions in the two layers. The experiments are inflation, axial stretching, circumferential bending, and axial bending. The analysis takes advantage of knowing the esophageal zero-stress state (an open sector with an opening angle of 59......The function of the esophagus is mechanical. To understand the function, it is necessary to know how the stress and strain in the esophagus can be computed, and how to determine the stress-strain relationship of the wall materials. The present article is devoted to the issue of determining...
YANG; Ning(杨宁); CHEN; Zhining; (陈志宁); WANG; Yunyi; (王蕴仪); Chia; M.; Y.; W.
2003-01-01
This paper presents a novel two-layer electromagnetic bandgap (EBG) structure. The studies on the characteristics of the cell are carried out numerically and experimentally. A lumped-LC equivalent circuit extracted from the numerical simulation is used to model the bandgap characteristics of the proposed EBG structure. The influences of geometric parameters on the operation frequency and equivalent LC parameters are discussed. A meander line high performance bandstop filter and a notch type duplexer are designed and measured. These EBG structures are shown to have potential applications in microwave and RF systems.
A Two-Layered Model for Dynamic Supply Chain Management Considering Transportation Constraint
Tanimizu, Yoshitaka; Harada, Kana; Ozawa, Chisato; Iwamura, Koji; Sugimura, Nobuhiro
This research proposes a two-layered model for dynamic supply chain management considering transportation constraint. The model provides a method for suppliers to estimate suitable prices and delivery times of products based on not only production schedules but also transportation plans in consideration of constraints about shipping times and loading capacities for transportation. A prototype of dynamic supply chain simulation system was developed and some computational experiments were carried out in order to verify the effectiveness of the model. The prototype system is available to determine suitable shipping times and loading capacities of transportation vehicles.
Flows induced by sorption on fibrous material in a two-layer oil-water system
Chaplina, T. O.; Chashechkin, Yu. D.; Stepanova, E. V.
2016-09-01
The processes of sorption on fibrous materials in the open elliptic cell filled with a two-layer oil-water liquid at rest are investigated experimentally. When the sorption efficiency dependent on the type of material proves to be reasonably high, large-scale flows are formed in the liquid. In this case, the uniformity of distribution of oil is violated and the free surface of the water is partially restored. The trajectories of motion of individual oil droplets on a released water surface are tracked, and the transfer rates are calculated in various phases of the process.
SH-TM mathematical analogy for the two-layer case. A magnetotellurics application
J. Carcione
2017-02-01
Full Text Available The same mathematical formalism of the wave equation can be used to describe anelastic and electromagnetic wave propagation. In this work, we obtain the mathematical analogy for the reflection/refraction (transmission problem of two layers, considering the presence of anisotropy and attenuation -- viscosity in the viscoelastic case and resistivity in the electromagnetic case. The analogy is illustrated for SH (shear-horizontally polarised and TM (transverse-magnetic waves. In particular, we illustrate examples related to the magnetotelluric method applied to geothermal systems and consider the effects of anisotropy. The solution is tested with the classical solution for stratified isotropic media.
Solitary SH waves in two-layered traction-free plates
Djeran-Maigre, Irini; Kuznetsov, Sergey
2008-01-01
A solitary wave, resembling a soliton wave, is observed when analyzing the linear problem of polarized shear (SH) surface acoustic waves propagating in elastic orthotropic two-layered traction-free plates. The analysis is performed by applying a special complex formalism and the Modified Transfer Matrix (MTM) method. Conditions for the existence of solitary SH waves are obtained. Analytical expressions for the phase speed of the solitary wave are derived. To cite this article: I. Djeran-Maigre, S. Kuznetsov, C. R. Mecanique 336 (2008).
和立新; 朱立新
2014-01-01
Based on the three-layer cultural structure theory, the authors expatiated on the cultural attribute of movement skills, and analyzed the sign of missing of some cultural constituent elements in the process of teaching and learning, ex-plained the function of feed forward control according to the characteristics of movement skills showed at various stages, put forward the principles to be followed in using cultural form as feed forward information for movement skill learning:learning migration theory and knowledge structure integrity, analyzed the characteristics of implementation of the method of comprehension teaching, and explained it by taking shot put movement skill learning for example.%依文化三层次结构论，阐述了动作技能的文化属性，并解析了传习过程中部分文化构成要素的遗失现象；结合动作技能形成的特点，对前馈控制作用进行说明，提出以文化形态作为动作技能学习前馈信息遵循的原理：学习迁移理论、知识结构的完整性；分析领会教学法的实施特点，并以推铅球动作技能学习为例说明。
Cehelsky, Priscilla; Tung, Ka Kit
1987-01-01
Previous results based on low- and intermediate-order truncations of the two-layer model suggest the existence of multiple equilibria and/or multiple weather regimes for the extratropical large-scale flow. The importance of the transient waves in the synoptic scales in organizing the large-scale flow and in the maintenance of weather regimes was emphasized. The result shows that multiple equilibria/weather regimes that are present in lower-order models examined disappear when a sufficient number of modes are kept in the spectral expansion of the solution to the governing partial differential equations. Much of the chaotic behavior of the large-scale flow that is present in intermediate-order models is now found to be spurious. Physical reasons for the drastic modification are offered. A peculiarity in the formulation of most existing two-layer models is noted that also tends to exaggerate the importance of baroclinic processes and increase the degree of unpredictability of the large-scale flow.
Photoacoustic investigation of the effective diffusivity of two-layer semiconductors
Medina, J; Gurevich, Yu. G; Logvinov G, N; Rodriguez, P; Gonzalez de la Cruz, G. [Instituto Mexicano del Petroleo, Mexico, D.F. (Mexico)
2001-08-01
In this work, the problem of the effective thermal diffusivity of two-layer systems is investigated using the photoacoustic spectroscopy. The experimental results are examined in terms of the effective thermal parameters of the composite system determined from an homogeneous material which produces the same physical response under an external perturbation in the detector device. It is shown, that the effective thermal conductivity is not symmetric under exchange of the two layers of the composite; i.e., the effective thermal parameters depend upon which layer is illuminated in the photoacoustic experiments. Particular emphasis is given to the characterization of the interface thermal conductivity between the layer-system. [Spanish] En el presente trabajo se utiliza la espectroscopia fotoacustica para medir la difusividad termica de un sistema de dos capas. Los resultados experimentales son analizados en terminos de los parametros termicos efectivos determinados a partir de un material homogeneo, el cual produce la misma respuesta fisica bajo una perturbacion externa. Se puso particular enfasis en la caracterizacion de los efectos de interfase en el flujo de calor en el sistema de dos capas. Los resultados experimentales se comparan con el modelo teorico propuesto en este trabajo.
Modelling of fast jet formation under explosion collision of two-layer alumina/copper tubes
I Balagansky
2017-09-01
Full Text Available Under explosion collapse of two-layer tubes with an outer layer of high-modulus ceramics and an inner layer of copper, formation of a fast and dense copper jet is plausible. We have performed a numerical simulation of the explosion collapse of a two-layer alumina/copper tube using ANSYS AUTODYN software. The simulation was performed in a 2D-axis symmetry posting on an Eulerian mesh of 3900x1200 cells. The simulation results indicate two separate stages of the tube collapse process: the nonstationary and the stationary stage. At the initial stage, a non-stationary fragmented jet is moving with the velocity of leading elements up to 30 km/s. The collapse velocity of the tube to the symmetry axis is about 2 km/s, and the pressure in the contact zone exceeds 700 GPa. During the stationary stage, a dense jet is forming with the velocity of 20 km/s. Temperature of the dense jet is about 2000 K, jet failure occurs when the value of effective plastic deformation reaches 30.
Validation of the Two-Layer Model for Correcting Clear Sky Reflectance Near Clouds
Wen, Guoyong; Marshak, Alexander; Evans, K. Frank; Vamal, Tamas
2014-01-01
A two-layer model was developed in our earlier studies to estimate the clear sky reflectance enhancement near clouds. This simple model accounts for the radiative interaction between boundary layer clouds and molecular layer above, the major contribution to the reflectance enhancement near clouds for short wavelengths. We use LES/SHDOM simulated 3D radiation fields to valid the two-layer model for reflectance enhancement at 0.47 micrometer. We find: (a) The simple model captures the viewing angle dependence of the reflectance enhancement near cloud, suggesting the physics of this model is correct; and (b) The magnitude of the 2-layer modeled enhancement agree reasonably well with the "truth" with some expected underestimation. We further extend our model to include cloud-surface interaction using the Poisson model for broken clouds. We found that including cloud-surface interaction improves the correction, though it can introduced some over corrections for large cloud albedo, large cloud optical depth, large cloud fraction, large cloud aspect ratio. This over correction can be reduced by excluding scenes (10 km x 10km) with large cloud fraction for which the Poisson model is not designed for. Further research is underway to account for the contribution of cloud-aerosol radiative interaction to the enhancement.
Risks of an epidemic in a two-layered railway-local area traveling network
Ruan, Zhongyuan; Hui, Pakming; Lin, Haiqing; Liu, Zonghua
2013-01-01
In view of the huge investments into the construction of high speed rails systems in USA, Japan, and China, we present a two-layer traveling network model to study the risks that the railway network poses in case of an epidemic outbreak. The model consists of two layers with one layer representing the railway network and the other representing the local-area transportation subnetworks. To reveal the underlying mechanism, we also study a simplified model that focuses on how a major railway affects an epidemic. We assume that the individuals, when they travel, take on the shortest path to the destination and become non-travelers upon arrival. When an infection process co-evolves with the traveling dynamics, the railway serves to gather a crowd, transmit the disease, and spread infected agents to local area subnetworks. The railway leads to a faster initial increase in infected agents and a higher steady state infection, and thus poses risks; and frequent traveling leads to a more severe infection. These features revealed in simulations are in agreement with analytic results of a simplified version of the model.
Traffic dynamics on two-layer complex networks with limited delivering capacity
Ma, Jinlong; Han, Weizhan; Guo, Qing; Wang, Zhenyong
2016-08-01
The traffic dynamics of multi-layer networks has attracted a great deal of interest since many real networks are comprised of two or more layers of subnetworks. Due to its low traffic capacity, the average delivery capacity allocation strategy is susceptible to congestion with the wildly used shortest path routing protocol on two-layer complex networks. In this paper, we introduce a delivery capacity allocation strategy into the traffic dynamics on two-layer complex networks and focus on its effect on the traffic capacity measured by the critical point Rc of phase transition from free flow to congestion. When the total nodes delivering capacity is fixed, the delivering capacity of each node in physical layer is assigned to the degree distributions of both the physical and logical layers. Simulation results show that the proposed strategy can bring much better traffic capacity than that with the average delivery capacity allocation strategy. Because of the significantly improved traffic performance, this work may be useful for optimal design of networked traffic dynamics.
Investigations of Two-Layer Earth Parameters at Low Voltage: Measurements and Calculations
E. Ramdan
2009-01-01
Full Text Available Problem statement: The two-layer soil model at low magnitude voltage is assumed to be accurate for the measurement and calculation of the earth resistance of a combined grid-multiple rods electrode. The aim of this study is to measure and calculate the earth resistance of a combined grid-multiple rods electrode buried in a two-layer soil and to confirm the simplicity and accuracy of the used formula. Approach: Soil resistivity was measured using Wenner four point method. Advanced earth resistivity measurement interpretation techniques which include graphical curve matching based on master curves and an advanced computer program based on a genetic algorithm are used in this study. Results: Based on the resistivity data, the earth resistance value was calculated using the formulas obtained from the literature. Measurements of the earth resistance of the earthing system were also conducted using the fall of potential method. Conclusion/Recommendations: A very good agreement was obtained between the measured and calculated earth resistance values. This research is the first time ever conducted where the measured earth resistance values are compared directly with the calculated earth values.
李新政; 白占国; 李燕; 贺亚峰; 赵昆
2015-01-01
The resonance interaction between two modes is investigated using a two-layer coupled Brusselator model. When two different wavelength modes satisfy resonance conditions, new modes will appear, and a variety of superlattice patterns can be obtained in a short wavelength mode subsystem. We find that even though the wavenumbers of two Turing modes are fixed, the parameter changes have infl uences on wave intensity and pattern selection. When a hexagon pattern occurs in the short wavelength mode layer and a stripe pattern appears in the long wavelength mode layer, the Hopf instability may happen in a nonlinearly coupled model, and twinkling-eye hexagon and travelling hexagon patterns will be obtained. The symmetries of patterns resulting from the coupled modes may be different from those of their parents, such as the cluster hexagon pattern and square pattern. With the increase of perturbation and coupling intensity, the nonlinear system will con-vert between a static pattern and a dynamic pattern when the Turing instability and Hopf instability happen in the nonlinear system. Besides the wavenumber ratio and intensity ratio of the two different wavelength Turing modes, perturbation and coupling intensity play an important role in the pattern formation and selection. According to the simulation results, we find that two modes with different symmetries can also be in the spatial resonance under certain conditions, and complex patterns appear in the two-layer coupled reaction diffusion systems.
Two-Layer Tight Frame Sparsifying Model for Compressed Sensing Magnetic Resonance Imaging
Peng, Xi; Dong, Pei
2016-01-01
Compressed sensing magnetic resonance imaging (CSMRI) employs image sparsity to reconstruct MR images from incoherently undersampled K-space data. Existing CSMRI approaches have exploited analysis transform, synthesis dictionary, and their variants to trigger image sparsity. Nevertheless, the accuracy, efficiency, or acceleration rate of existing CSMRI methods can still be improved due to either lack of adaptability, high complexity of the training, or insufficient sparsity promotion. To properly balance the three factors, this paper proposes a two-layer tight frame sparsifying (TRIMS) model for CSMRI by sparsifying the image with a product of a fixed tight frame and an adaptively learned tight frame. The two-layer sparsifying and adaptive learning nature of TRIMS has enabled accurate MR reconstruction from highly undersampled data with efficiency. To solve the reconstruction problem, a three-level Bregman numerical algorithm is developed. The proposed approach has been compared to three state-of-the-art methods over scanned physical phantom and in vivo MR datasets and encouraging performances have been achieved. PMID:27747226
Analysis and Control of Two-Layer Frenkel-Kontorova Model
TANG Wen-Yan; QU Zhi-Hua; GUO Yi
2011-01-01
A one-dimensional two-layer Frenkel-Kontorova model is studied.Firstly,a feedback tracking control law is given.Then,the boundedness result for the error states of single particles of the model is derived using the Lyapunov Method.Especially,the motion of single particles can be approximated analytically for the case of sufficiently large targeted velocity.Simulations illustrate the accuracy of the derived results.Recently,the Frenkel-Kontorova (FK) model,which describes a chain of classical particles interacting with its nearest neighbors and subjected to a periodic one-site potential,has become a useful tool to study nanotribology.[1-6] There are several generalizations of the FK model that have been introduced with the hope of understanding friction dynamics at nanoscale.These models include a manylayer model with harmonic interactions,the FrenkelKontorova-Tomlinson model (FKT) and the singlelayer model with harmonic interactions.%A one-dimensional two-layer Frenkel-Kontorova model is studied. Firstly, a feedback tracking control law is given. Then, the boundedness result for the error states of single particles of the model is derived using the Lyapunov Method. Especially, the motion of single particles can be approximated analytically for the case of sufficiently large targeted velocity. Simulations illustrate the accuracy of the derived results.
Reverse-feeding effect of epidemic by propagators in two-layered networks
Dayu, Wu; Yanping, Zhao; Muhua, Zheng; Jie, Zhou; Zonghua, Liu
2016-02-01
Epidemic spreading has been studied for a long time and is currently focused on the spreading of multiple pathogens, especially in multiplex networks. However, little attention has been paid to the case where the mutual influence between different pathogens comes from a fraction of epidemic propagators, such as bisexual people in two separated groups of heterosexual and homosexual people. We here study this topic by presenting a network model of two layers connected by impulsive links, in contrast to the persistent links in each layer. We let each layer have a distinct pathogen and their interactive infection is implemented by a fraction of propagators jumping between the corresponding pairs of nodes in the two layers. By this model we show that (i) the propagators take the key role to transmit pathogens from one layer to the other, which significantly influences the stabilized epidemics; (ii) the epidemic thresholds will be changed by the propagators; and (iii) a reverse-feeding effect can be expected when the infective rate is smaller than its threshold of isolated spreading. A theoretical analysis is presented to explain the numerical results. Project supported by the National Natural Science Foundation of China (Grant Nos. 11135001, 11375066, and 11405059) and the National Basic Key Program of China (Grant No. 2013CB834100).
NUMERICAL SIMULATION OF HEAD-CUT WITH A TWO-LAYERED BED
无
2005-01-01
Gully erosion is one of the main causes of top soil loss, land deterioration and sources of sediment deposition in streams. Headcut often occurs in the gully erosion process when erodability of the soil layers varies, and the gully cuts through a hard layer at a point. A scouring hole appears downstream of the head cut which migrates upstream due to strong erosion in the scour hole. This paper presents numerical analyses of turbulent flow and sediment transport processes of a head-cut associated with a two-layer soil stratigraphic formation. The flow in the scour hole is three-dimensional induced by the water jet from the brink of the top layer; the sediment transport model considers sediment entrainment by the impinging jet, erosion underneath the hard layer and the retreat of the brink of the hard layer. The 3D flow simulation in the scour hole and the scouring process was verified with physical model data. The two-layer head cut migration is simulated with different flow and soil parameters, the trends of the simulated results reasonably revealed contributions of these parameters to the scouring and migration process.
Two-layer wireless distributed sensor/control network based on RF
Feng, Li; Lin, Yuchi; Zhou, Jingjing; Dong, Guimei; Xia, Guisuo
2006-11-01
A project of embedded Wireless Distributed Sensor/Control Network (WDSCN) based on RF is presented after analyzing the disadvantages of traditional measure and control system. Because of high-cost and complexity, such wireless techniques as Bluetooth and WiFi can't meet the needs of WDSCN. The two-layer WDSCN is designed based on RF technique, which operates in the ISM free frequency channel with low power and high transmission speed. Also the network is low cost, portable and moveable, integrated with the technologies of computer network, sensor, microprocessor and wireless communications. The two-layer network topology is selected in the system; a simple but efficient self-organization net protocol is designed to fit the periodic data collection, event-driven and store-and-forward. Furthermore, adaptive frequency hopping technique is adopted for anti-jamming apparently. The problems about power reduction and synchronization of data in wireless system are solved efficiently. Based on the discussion above, a measure and control network is set up to control such typical instruments and sensors as temperature sensor and signal converter, collect data, and monitor environmental parameters around. This system works well in different rooms. Experiment results show that the system provides an efficient solution to WDSCN through wireless links, with high efficiency, low power, high stability, flexibility and wide working range.
Xi, Jun; Xue, Yujing; Xu, Yinxiang; Shen, Yuhong
2013-11-01
In this study, the ultrahigh pressure extraction of green tea polyphenols was modeled and optimized by a three-layer artificial neural network. A feed-forward neural network trained with an error back-propagation algorithm was used to evaluate the effects of pressure, liquid/solid ratio and ethanol concentration on the total phenolic content of green tea extracts. The neural network coupled with genetic algorithms was also used to optimize the conditions needed to obtain the highest yield of tea polyphenols. The obtained optimal architecture of artificial neural network model involved a feed-forward neural network with three input neurons, one hidden layer with eight neurons and one output layer including single neuron. The trained network gave the minimum value in the MSE of 0.03 and the maximum value in the R(2) of 0.9571, which implied a good agreement between the predicted value and the actual value, and confirmed a good generalization of the network. Based on the combination of neural network and genetic algorithms, the optimum extraction conditions for the highest yield of green tea polyphenols were determined as follows: 498.8 MPa for pressure, 20.8 mL/g for liquid/solid ratio and 53.6% for ethanol concentration. The total phenolic content of the actual measurement under the optimum predicated extraction conditions was 582.4 ± 0.63 mg/g DW, which was well matched with the predicted value (597.2mg/g DW). This suggests that the artificial neural network model described in this work is an efficient quantitative tool to predict the extraction efficiency of green tea polyphenols. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.
Wu Jian; Murphy, Martin J. [Department of Radiation Oncology, Virginia Commonwealth University, Richmond, Virginia 23298 (United States)
2010-11-15
Purpose: To develop a neural network based registration quality evaluator (RQE) that can identify unsuccessful 3D/3D image registrations for the head-and-neck patient setup in radiotherapy. Methods: A two-layer feed-forward neural network was used as a RQE to classify 3D/3D rigid registration solutions as successful or unsuccessful based on the features of the similarity surface near the point-of-solution. The supervised training and test data sets were generated by rigidly registering daily cone-beam CTs to the treatment planning fan-beam CTs of six patients with head-and-neck tumors. Two different similarity metrics (mutual information and mean-squared intensity difference) and two different types of image content (entire image versus bony landmarks) were used. The best solution for each registration pair was selected from 50 optimizing attempts that differed only by the initial transformation parameters. The distance from each individual solution to the best solution in the normalized parametrical space was compared to a user-defined error threshold to determine whether that solution was successful or not. The supervised training was then used to train the RQE. The performance of the RQE was evaluated using the test data set that consisted of registration results that were not used in training. Results: The RQE constructed using the mutual information had very good performance when tested using the test data sets, yielding the sensitivity, the specificity, the positive predictive value, and the negative predictive value in the ranges of 0.960-1.000, 0.993-1.000, 0.983-1.000, and 0.909-1.000, respectively. Adding a RQE into a conventional 3D/3D image registration system incurs only about 10%-20% increase of the overall processing time. Conclusions: The authors' patient study has demonstrated very good performance of the proposed RQE when used with the mutual information in identifying unsuccessful 3D/3D registrations for daily patient setup. The classifier
Neural networks in windprofiler data processing
Weber, H.; Richner, H.; Kretzschmar, R.; Ruffieux, D.
2003-04-01
Wind profilers are basically Doppler radars yielding 3-dimensional wind profiles that are deduced from the Doppler shift caused by turbulent elements in the atmosphere. These signals can be contaminated by other airborne elements such as birds or hydrometeors. Using a feed-forward neural network with one hidden layer and one output unit, birds and hydrometeors can be successfully identified in non-averaged single spectra; theses are subsequently removed in the wind computation. An infrared camera was used to identify birds in one of the beams of the wind profiler. After training the network with about 6000 contaminated data sets, it was able to identify contaminated data in a test data set with a reliability of 96 percent. The assumption was made that the neural network parameters obtained in the beam for which bird data was collected can be transferred to the other beams (at least three beams are needed for computing wind vectors). Comparing the evolution of a wind field with and without the neural network shows a significant improvement of wind data quality. Current work concentrates on training the network also for hydrometeors. It is hoped that the instrument's capability can thus be expanded to measure not only correct winds, but also observe bird migration, estimate precipitation and -- by combining precipitation information with vertical velocity measurement -- the monitoring of the height of the melting layer.
A Global Model of $\\beta^-$-Decay Half-Lives Using Neural Networks
Costiris, N; Gernoth, K A; Mavrommatis, E
2007-01-01
Statistical modeling of nuclear data using artificial neural networks (ANNs) and, more recently, support vector machines (SVMs), is providing novel approaches to systematics that are complementary to phenomenological and semi-microscopic theories. We present a global model of $\\beta^-$-decay halflives of the class of nuclei that decay 100% by $\\beta^-$ mode in their ground states. A fully-connected multilayered feed forward network has been trained using the Levenberg-Marquardt algorithm, Bayesian regularization, and cross-validation. The halflife estimates generated by the model are discussed and compared with the available experimental data, with previous results obtained with neural networks, and with estimates coming from traditional global nuclear models. Predictions of the new neural-network model are given for nuclei far from stability, with particular attention to those involved in r-process nucleosynthesis. This study demonstrates that in the framework of the $\\beta^-$-decay problem considered here, ...
S. Ramasundaram
2013-02-01
Full Text Available Prediction of compressive strength of concrete is very useful for economic constructions. The compressive strength can be estimated after 28 days of casting the specimen cubes or may be predictedbased on the quantum and quality of ingredients used in making the concrete. When the first one requires a 28-day time, the second one does have problem of accuracy. Hence, a hybrid model is proposed in which the concrete cube is cured using the microwave based accelerated curing procedure and the early strength is used to predict the 28-day strength. Feed-forward neural network model was used to predict compressive strength of the concrete after the microwave curing to ascertain the predictability of neural network models. The results indicate that the neural network models have a good scope for further study and implementations.
Visually-salient contour detection using a V1 neural model with horizontal connections
Loxley, P N
2011-01-01
A convolution model which accounts for neural activity dynamics in the primary visual cortex is derived and used to detect visually salient contours in images. Image inputs to the model are modulated by long-range horizontal connections, allowing contextual effects in the image to determine visual saliency, i.e. line segments arranged in a closed contour elicit a larger neural response than line segments forming background clutter. The model is tested on 3 types of contour, including a line, a circular closed contour, and a non-circular closed contour. Using a modified association field to describe horizontal connections the model is found to perform well for different parameter values. For each type of contour a different facilitation mechanism is found. Operating as a feed-forward network, the model assigns saliency by increasing the neural activity of line segments facilitated by the horizontal connections. Alternatively, operating as a feedback network, the model can achieve further improvement over sever...
Artificial neural networks for modeling time series of beach litter in the southern North Sea.
Schulz, Marcus; Matthies, Michael
2014-07-01
In European marine waters, existing monitoring programs of beach litter need to be improved concerning litter items used as indicators of pollution levels, efficiency, and effectiveness. In order to ease and focus future monitoring of beach litter on few important litter items, feed-forward neural networks consisting of three layers were developed to relate single litter items to general categories of marine litter. The neural networks developed were applied to seven beaches in the southern North Sea and modeled time series of five general categories of marine litter, such as litter from fishing, shipping, and tourism. Results of regression analyses show that general categories were predicted significantly moderately to well. Measured and modeled data were in the same order of magnitude, and minima and maxima overlapped well. Neural networks were found to be eligible tools to deliver reliable predictions of marine litter with low computational effort and little input of information. Copyright © 2014 Elsevier Ltd. All rights reserved.
CONTROL OF NONLINEAR PROCESS USING NEURAL NETWORK BASED MODEL PREDICTIVE CONTROL
Dr.A.TRIVEDI
2011-04-01
Full Text Available This paper presents a Neural Network based Model Predictive Control (NNMPC strategy to control nonlinear process. Multilayer Perceptron Neural Network (MLP is chosen to represent a Nonlinear Auto Regressive with eXogenous signal (NARX model of a nonlinear system. NARX dynamic model is based on feed-forward architecture and offers good approximation capabilities along with robustness and accuracy. Based on the identified neural model, a generalized predictive control (GPC algorithm is implemented to control the composition in acontinuous stirred tank reactor (CSTR, whose parameters are optimally determined by solving quadratic performance index using well known Levenberg-Marquardt and Quasi-Newton algorithm. NNMPC is tuned by selecting few horizon parameters and weighting factor. The tracking performance of the NNMPC is tested using different amplitude function as a reference signal on CSTR application. Also the robustness and performance is tested in the presence of disturbance on random reference signal.
Neera Saxena
2011-07-01
Full Text Available This paper presents an ensemble of neo-cognitron neural network base classifiers to enhance the accuracy of the system, along the experimental results. The method offers lesser computational preprocessing in comparison to other ensemble techniques as it ex-preempts feature extraction process before feeding the data into base classifiers. This is achieved by the basic nature of neo-cognitron, it is a multilayer feed-forward neural network. Ensemble of such base classifiers gives class labels for each pattern that in turn is combined to give the final class label for that pattern. The purpose of this paper is not only to exemplify learning behaviour of neo-cognitron as base classifiers, but also to purport better fashion to combine neural network based ensemble classifiers.
Bayesian Regularization in a Neural Network Model to Estimate Lines of Code Using Function Points
K. K. Aggarwal
2005-01-01
Full Text Available It is a well known fact that at the beginning of any project, the software industry needs to know, how much will it cost to develop and what would be the time required ? . This paper examines the potential of using a neural network model for estimating the lines of code, once the functional requirements are known. Using the International Software Benchmarking Standards Group (ISBSG Repository Data (release 9 for the experiment, this paper examines the performance of back propagation feed forward neural network to estimate the Source Lines of Code. Multiple training algorithms are used in the experiments. Results demonstrate that the neural network models trained using Bayesian Regularization provide the best results and are suitable for this purpose.
Prediction of operational parameters effect on coal flotation using artificial neural network
E. Jorjani; Sh. Mesroghli; S. Chehreh Chelgani
2008-01-01
Artificial neural network procedures were used to predict the combustible value (i.e. 100-Ash) and combustible recovery of coal flotation concentrate in different operational conditions. The pulp density, pH, rotation rate, coal particle size, dosage of collector, frother and conditioner were used as inputs to the network. Feed-forward artificial neural networks with 5-30-2-1 and 7-10-3-1 arrangements were capable to estimate the combustible value and combustible recovery of coal flotation concentrate respectively as the outputs. Quite satisfactory correlations of 1 and 0.91 in training and testing stages for combustible value and of 1 and 0.95 in training and testing stages for combustible recovery prediction were achieved. The proposed neural network models can be used to determine the most advantageous operational conditions for the expected concentrate assay and recovery in the coal flotation process.
Çebi, A.; Akdoğan, E.; Celen, A.; Dalkilic, A. S.
2017-02-01
An artificial neural network (ANN) model of friction factor in smooth and microfin tubes under heating, cooling and isothermal conditions was developed in this study. Data used in ANN was taken from a vertically positioned heat exchanger experimental setup. Multi-layered feed-forward neural network with backpropagation algorithm, radial basis function networks and hybrid PSO-neural network algorithm were applied to the database. Inputs were the ratio of cross sectional flow area to hydraulic diameter, experimental condition number depending on isothermal, heating, or cooling conditions and mass flow rate while the friction factor was the output of the constructed system. It was observed that such neural network based system could effectively predict the friction factor values of the flows regardless of their tube types. A dependency analysis to determine the strongest parameter that affected the network and database was also performed and tube geometry was found to be the strongest parameter of all as a result of analysis.
Çebi, A.; Akdoğan, E.; Celen, A.; Dalkilic, A. S.
2016-06-01
An artificial neural network (ANN) model of friction factor in smooth and microfin tubes under heating, cooling and isothermal conditions was developed in this study. Data used in ANN was taken from a vertically positioned heat exchanger experimental setup. Multi-layered feed-forward neural network with backpropagation algorithm, radial basis function networks and hybrid PSO-neural network algorithm were applied to the database. Inputs were the ratio of cross sectional flow area to hydraulic diameter, experimental condition number depending on isothermal, heating, or cooling conditions and mass flow rate while the friction factor was the output of the constructed system. It was observed that such neural network based system could effectively predict the friction factor values of the flows regardless of their tube types. A dependency analysis to determine the strongest parameter that affected the network and database was also performed and tube geometry was found to be the strongest parameter of all as a result of analysis.
Wave turbulence in a two-layer fluid: coupling between free surface and interface waves
Issenmann, Bruno; Falcon, Eric
2016-01-01
We experimentally study gravity-capillary wave turbulence on the interface between two immiscible fluids of close density with free upper surface. We locally measure the wave height at the interface between both fluids by means of a highly sensitive laser Doppler vibrometer. We show that the inertial range of the capillary wave turbulence regime is significantly extended when the upper fluid depth is increased: The crossover frequency between the gravity and capillary wave turbulence regimes is found to decrease whereas the dissipative cut-off frequency of the spectrum is found to increase. We explain most of these observations by the progressive decoupling between waves propagating at the interface and the ones at the free surface, using the full dispersion relation of gravity-capillary waves in a two-layer fluid of finite depths.s.
Spin-3/2 Ising model AFM/AFM two-layer lattice with crystal field
Erhan Albayrak; Ali Yigit
2009-01-01
The spin-3/2 Ising model is investigated for the case of antiferromagnetic (AFM/AFM) interactions on the two-layer Bethe lattice by using the exact recursion relations in the pairwise approach for given coordination numbers q = 3, 4 and 6 when the layers are under the influences of equal external magnetic and equal crystal fields. The ground state, (GS) phase diagrams are obtained on the different planes in detail and then the temperature-dependent phase diagrams of the system are calculated accordingly. It is observed that the system presents both second- and first-order phase transitions for all q, therefore, tricritical points. It is also found that the system exhibits double-critical end points and isolated points. The model aiso presents two Néel temperatures, T_N, and the existence of which leads to the reentrant behaviour.
Two-layer interfacial flows beyond the Boussinesq approximation: a Hamiltonian approach
Camassa, R.; Falqui, G.; Ortenzi, G.
2017-02-01
The theory of integrable systems of Hamiltonian PDEs and their near-integrable deformations is used to study evolution equations resulting from vertical-averages of the Euler system for two-layer stratified flows in an infinite two-dimensional channel. The Hamiltonian structure of the averaged equations is obtained directly from that of the Euler equations through the process of Hamiltonian reduction. Long-wave asymptotics together with the Boussinesq approximation of neglecting the fluids’ inertia is then applied to reduce the leading order vertically averaged equations to the shallow-water Airy system, albeit in a non-trivial way. The full non-Boussinesq system for the dispersionless limit can then be viewed as a deformation of this well known equation. In a perturbative study of this deformation, a family of approximate constants of the motion are explicitly constructed and used to find local solutions of the evolution equations by means of hodograph-like formulae.
Central-Upwind Schemes for Two-Layer Shallow Water Equations
Kurganov, Alexander
2009-01-01
We derive a second-order semidiscrete central-upwind scheme for one- and two-dimensional systems of two-layer shallow water equations. We prove that the presented scheme is well-balanced in the sense that stationary steady-state solutions are exactly preserved by the scheme and positivity preserving; that is, the depth of each fluid layer is guaranteed to be nonnegative. We also propose a new technique for the treatment of the nonconservative products describing the momentum exchange between the layers. The performance of the proposed method is illustrated on a number of numerical examples, in which we successfully capture (quasi) steady-state solutions and propagating interfaces. © 2009 Society for Industrial and Applied Mathematics.
Khalil, Mohammed S; Kurniawan, Fajri; Khan, Muhammad Khurram; Alginahi, Yasser M
2014-01-01
This paper presents a novel watermarking method to facilitate the authentication and detection of the image forgery on the Quran images. Two layers of embedding scheme on wavelet and spatial domain are introduced to enhance the sensitivity of fragile watermarking and defend the attacks. Discrete wavelet transforms are applied to decompose the host image into wavelet prior to embedding the watermark in the wavelet domain. The watermarked wavelet coefficient is inverted back to spatial domain then the least significant bits is utilized to hide another watermark. A chaotic map is utilized to blur the watermark to make it secure against the local attack. The proposed method allows high watermark payloads, while preserving good image quality. Experiment results confirm that the proposed methods are fragile and have superior tampering detection even though the tampered area is very small.
Transient response of a vertical electric dipole (VED) on a two-layer medium
Poh, S. Y.; Kong, J. A.
The transient electromagnetic radiation by a vertical electric dipole on a two-layer medium is analyzed using the double deformation technique, which is a modal technique based on identification of singularities in the complex frequency and wavenumber planes. Previous application of the double deformation technique to the solution of this problem is incomplete in the early time response. In this paper it is shown that the existence of a pole locus on the negative imaginary frequency axis, which dominates the early time response, proves crucial in obtaining the solution for all times. A variety of combinations of parameters are used to illustrate the double deformation technique, and results will be compared with those obtained via explicit inversion, and a single deformation method.
Two-Layer Coding Rate Optimization in Relay-Aided Systems
Sun, Fan
2011-01-01
We consider a three-node transmission system, where a source node conveys a data block to a destination node with the help of a half-duplex decode and-forward (DF) relay node. The whole data block is transmitted as a sequence of packets. For reliable transmission in the three-node system, a two......-layer coding scheme is proposed, where physical layer channel coding is utilized within each packet for error-correction and random network coding is applied on top of channel coding for network error-control. There is a natural tradeoff between the physical layer coding rate and the network coding rate given...... requirement. Numerical results are also provided to show the optimized physical layer coding and network coding rate pairs in different system scenarios....
The peak effect (PE) region of the antiferromagnetic two layer Ising nanographene
Şarlı, Numan, E-mail: numansarli82@gmail.com [Institute of Science, Erciyes University, 38039 Kayseri (Turkey); Akbudak, Salih [Department of Physics, Adiyaman University, 02100 Adiyaman (Turkey); Department of Nanotechnology and Nanomedicine, Hacettepe University, 06800 Ankara (Turkey); Ellialtıoğlu, Mehmet Recai [Department of Physics Engineering, Hacettepe University, 06800 Ankara (Turkey)
2014-11-01
In this work, the magnetic properties of the ferromagnetic and antiferromagnetic two layer spin-1/2 Ising nanographene systems are investigated within the effective field theory. We find that the magnetizations and the hysteresis behaviors of the central graphene atoms are similar to those of the edge graphene atoms in the ferromagnetic case. But, they are quite different in the antiferromagnetic case. The antiferromagnetic central graphene atoms exhibit type II superconductivity and they have triple hysteresis loop. The peak effect (PE) region is observed on the hysteresis curves of the antiferromagnetic Ising nanographene system. Therefore, we suggest that there is a strong relationship between the antiferromagnetism and the peak effect. Our results are in agreement with some experimental works in recent literature.
STRESS ANALYSIS AND BURST PRESSURE DETERMINATION OF TWO LAYER COMPOUND PRESSURE VESSEL
HARERAM LOHAR
2013-02-01
Full Text Available Multilayer pressure vessel is designed to work under high-pressure condition. This paper introduces the stress analysis and the burst pressure calculation of a two-layer shrink fitted pressure vessel. In the shrink-fitting problems, considering long hollow cylinders, the plane strain hypothesis can be regarded as more natural. Generally hoops stress distribution is non-linear and sharply reduced toward the outer surface. By shrink fitting concentric shells towards the inner shells are placed in residual compression so that the initial compressive hoop stress must be relieved by internal pressure before hoop tensile stress are developed. Therefore the maximum hoop stress will be reduced, resulting more burst pressure. The analytical results of stress distribution and burst pressure is calculated and validated by ANSYS Workbench results.
Testing the Two-Layer Model for Correcting Clear Sky Reflectance near Clouds
Wen, Guoyong; Marshak, Alexander; Evans, Frank; Varnai, Tamas; Levy, Rob
2015-01-01
A two-layer model (2LM) was developed in our earlier studies to estimate the clear sky reflectance enhancement due to cloud-molecular radiative interaction at MODIS at 0.47 micrometers. Recently, we extended the model to include cloud-surface and cloud-aerosol radiative interactions. We use the LES/SHDOM simulated 3D true radiation fields to test the 2LM for reflectance enhancement at 0.47 micrometers. We find: The simple model captures the viewing angle dependence of the reflectance enhancement near cloud, suggesting the physics of this model is correct; the cloud-molecular interaction alone accounts for 70 percent of the enhancement; the cloud-surface interaction accounts for 16 percent of the enhancement; the cloud-aerosol interaction accounts for an additional 13 percent of the enhancement. We conclude that the 2LM is simple to apply and unbiased.
Study of electronic and optical properties of two-layered hydrogenated aluminum nitrate nanosheet
Faghihzadeh, Somayeh; Shahtahmasebi, Nasser; Rezaee Roknabadi, Mahmood
2017-09-01
First principle calculations based on density functional theory using GW approximation and two particle Bethe-Salpeter equation with electron-hole effect were performed to investigate electronic structure and optical properties of two-layered hydrogenated AlN. According to many body green function due to decrease in dimension and considering electron-electron effect, direct (indirect) band gap change from 2 (1.01) eV to 4.83 (3.62) eV. The first peak in imaginary part of dielectric function was observed in parallel direction to a plane obtaining 3.4 was achieved by bound exciton states possess 1.39 eV. The first absorption peak was seen in two parallel and perpendicular directions to a plane which are in UV region.
Initial stresses in two-layer metal domes due to imperfections of their production and assemblage
Lebed Evgeniy Vasil’evich
2015-04-01
Full Text Available The process of construction of two-layer metal domes is analyzed to illustrate the causes of initial stresses in the bars of their frames. It has been noticed that it is impossible to build such structures with ideal geometric parameters because of imperfections caused by objective reasons. These imperfections cause difficulties in the process of connection of the elements in the joints. The paper demonstrates the necessity of fitting operations during assemblage that involve force fitting and yield initial stresses due to imperfections. The authors propose a special method of computer modeling of enforced elimination of possible imperfections caused by assemblage process and further confirm the method by an analysis of a concrete metal dome.
Analysis of data recorded by the LCTPC equipped with a two layer GEM-system
Ljunggren, M
2012-01-01
wire based readout. The prototype TPC is placed in a 1 Tesla magnet at DESY and tested using an electron beam. Analyses of data taken during two different measurement series, in 2009 and 2010, are presented here. The TPC was instrumented with a two layer GEM system and read out using modified electronics from the ALICE experiment, including the programmable charge sensitive preamp-shaper PCA16. The PCA16 chip has a number of programmable parameters which allows studies to determine the settings optimal to the final TPC. Here, the impact of the shaping time on the space resolution in the drift direction was studied. It was found that a shaping time of 60 ns is the b...
INFLUENCE OF TEMPERATURE ON BEHAVIOR OF THE INTERFACIAL CRACK BETWEEN THE TWO LAYERS
Jelena M Djoković
2010-01-01
Full Text Available In this paper is considered a problem of the semi-infinite crack at the interface between the two elastic isotropic layers in conditions of the environmental temperature change. The energy release rate needed for the crack growth along the interface was determined, for the case when the two-layered sample is cooled from the temperature of the layers joining down to the room temperature. It was noticed that the energy release rate increases with the temperature difference increase. In the paper is also presented the distribution of stresses in layers as a function of the temperature and the layers' thickness variations. Analysis is limited to the case when the bimaterial sample is exposed to uniform temperature.
High Performance Hybrid Two Layer Router Architecture for FPGAs Using Network On Chip
Ezhumalai, P; Arun, C; Sakthivel, P; Sridharan, D
2010-01-01
Networks on Chip is a recent solution paradigm adopted to increase the performance of Multicore designs. The key idea is to interconnect various computation modules (IP cores) in a network fashion and transport packets simultaneously across them, thereby gaining performance. In addition to improving performance by having multiple packets in flight, NoCs also present a host of other advantages including scalability, power efficiency, and component reuse through modular design. This work focuses on design and development of high performance communication architectures for FPGAs using NoCs Once completely developed, the above methodology could be used to augment the current FPGA design flow for implementing multicore SoC applications. We design and implement an NoC framework for FPGAs, MultiClock OnChip Network for Reconfigurable Systems (MoCReS). We propose a novel microarchitecture for a hybrid two layer router that supports both packetswitched communications, across its local and directional ports, as well as...
The fuzzy coat of pathological human Tau fibrils is a two-layered polyelectrolyte brush.
Wegmann, Susanne; Medalsy, Izhar D; Mandelkow, Eckhard; Müller, Daniel J
2013-01-22
The structure and properties of amyloid-like Tau fibrils accumulating in neurodegenerative diseases have been debated for decades. Although the core of Tau fibrils assembles from short β-strands, the properties of the much longer unstructured Tau domains protruding from the fibril core remain largely obscure. Applying immunogold transmission EM, and force-volume atomic force microscopy (AFM), we imaged human Tau fibrils at high resolution and simultaneously mapped their mechanical and adhesive properties. Tau fibrils showed a ≈ 16-nm-thick fuzzy coat that resembles a two-layered polyelectrolyte brush, which is formed by the unstructured short C-terminal and long N-terminal Tau domains. The mechanical and adhesive properties of the fuzzy coat are modulated by electrolytes and pH, and thus by the cellular environment. These unique properties of the fuzzy coat help in understanding how Tau fibrils disturb cellular interactions and accumulate in neurofibrillary tangles.
Sparse/DCT (S/DCT) two-layered representation of prediction residuals for video coding.
Kang, Je-Won; Gabbouj, Moncef; Kuo, C-C Jay
2013-07-01
In this paper, we propose a cascaded sparse/DCT (S/DCT) two-layer representation of prediction residuals, and implement this idea on top of the state-of-the-art high efficiency video coding (HEVC) standard. First, a dictionary is adaptively trained to contain featured patterns of residual signals so that a high portion of energy in a structured residual can be efficiently coded via sparse coding. It is observed that the sparse representation alone is less effective in the R-D performance due to the side information overhead at higher bit rates. To overcome this problem, the DCT representation is cascaded at the second stage. It is applied to the remaining signal to improve coding efficiency. The two representations successfully complement each other. It is demonstrated by experimental results that the proposed algorithm outperforms the HEVC reference codec HM5.0 in the Common Test Condition.
Development of an algebraic stress/two-layer model for calculating thrust chamber flow fields
Chen, C. P.; Shang, H. M.; Huang, J.
1993-01-01
Following the consensus of a workshop in Turbulence Modeling for Liquid Rocket Thrust Chambers, the current effort was undertaken to study the effects of second-order closure on the predictions of thermochemical flow fields. To reduce the instability and computational intensity of the full second-order Reynolds Stress Model, an Algebraic Stress Model (ASM) coupled with a two-layer near wall treatment was developed. Various test problems, including the compressible boundary layer with adiabatic and cooled walls, recirculating flows, swirling flows and the entire SSME nozzle flow were studied to assess the performance of the current model. Detailed calculations for the SSME exit wall flow around the nozzle manifold were executed. As to the overall flow predictions, the ASM removes another assumption for appropriate comparison with experimental data, to account for the non-isotropic turbulence effects.
Cumulative second-harmonic generation of Lamb waves propagating in a two-layered solid plate
Xiang Yan-Xun; Deng Ming-Xi
2008-01-01
The physical process of cumulative second-harmonic generation of Lamb waves propagating in a two-layered solid plate is presented by using the second-order perturbation and the technique of nonlinear reflection of acoustic waves at an interface.In general,the cumulative second-harmonic generation of a dispersive guided wave propagation does not occur.However,the present paper shows that the second-harmonic of Lamb wave propagation arising from the nonlinear interaction of the partial bulk acoustic waves and the restriction of the three boundaries of the solid plates does have a cumulative growth effect if some conditions are satisfied.Through boundary condition and initial condition of excitation,the analytical expression of cumulative second-harmonic of Lamb waves propagation is determined.Numerical results show the cumulative effect of Lamb waves on second-harmonic field patterns.
Convergent flow in a two-layer system and mountain building
Perazzo, Carlos Alberto
2009-01-01
With the purpose of modelling the process of mountain building, we investigate the evolution of the ridge produced by the convergent motion of a system consisting of two layers of liquids that differ in density and viscosity to simulate the crust and the upper mantle that form a lithospheric plate. We assume that the motion is driven by basal traction. Assuming isostasy, we derive a nonlinear differential equation for the evolution of the thickness of the crust. We solve this equation numerically to obtain the profile of the range. We find an approximate self-similar solution that describes reasonably well the process and predicts simple scaling laws for the height and width of the range as well as the shape of the transversal profile. We compare the theoretical results with the profiles of real mountain belts and find and excellent agreement.
TWO-LAYER SECURE PREVENTION MECHANISM FOR REDUCING E-COMMERCE SECURITY RISKS
Sen-Tarng Lai
2015-12-01
Full Text Available E-commerce is an important information system in the network and digital age. However, the network intrusion, malicious users, virus attack and system security vulnerabilities have continued to threaten the operation of the e-commerce, making e-commerce security encounter serious test. How to improve ecommerce security has become a topic worthy of further exploration. Combining routine security test and security event detection procedures, this paper proposes the Two-Layer Secure Prevention Mechanism (TLSPM. Applying TLSPM, routine security test procedure can identify security vulnerability and defect, and develop repair operations. Security event detection procedure can timely detect security event, and assist follow repair. TLSPM can enhance the e-commerce security and effectively reduce the security risk of e-commerce critical data and asset.
Calculation of AC loss in two-layer superconducting cable with equal currents in the layers
Erdogan, Muzaffer
2016-12-01
A new method for calculating AC loss of two-layer SC power transmission cables using the commercial software Comsol Multiphysics, relying on the approach of the equal partition of current between the layers is proposed. Applying the method to calculate the AC-loss in a cable composed of two coaxial cylindrical SC tubes, the results are in good agreement with the analytical ones of duoblock model. Applying the method to calculate the AC-losses of a cable composed of a cylindrical copper former, surrounded by two coaxial cylindrical layers of superconducting tapes embedded in an insulating medium with tape-on-tape and tape-on-gap configurations are compared. A good agreement between the duoblock model and the numerical results for the tape-on-gap cable is observed.
2-DE combined with two-layer feature selection accurately establishes the origin of oolong tea.
Chien, Han-Ju; Chu, Yen-Wei; Chen, Chi-Wei; Juang, Yu-Min; Chien, Min-Wei; Liu, Chih-Wei; Wu, Chia-Chang; Tzen, Jason T C; Lai, Chien-Chen
2016-11-15
Taiwan is known for its high quality oolong tea. Because of high consumer demand, some tea manufactures mix lower quality leaves with genuine Taiwan oolong tea in order to increase profits. Robust scientific methods are, therefore, needed to verify the origin and quality of tea leaves. In this study, we investigated whether two-dimensional gel electrophoresis (2-DE) and nanoscale liquid chromatography/tandem mass spectroscopy (nano-LC/MS/MS) coupled with a two-layer feature selection mechanism comprising information gain attribute evaluation (IGAE) and support vector machine feature selection (SVM-FS) are useful in identifying characteristic proteins that can be used as markers of the original source of oolong tea. Samples in this study included oolong tea leaves from 23 different sources. We found that our method had an accuracy of 95.5% in correctly identifying the origin of the leaves. Overall, our method is a novel approach for determining the origin of oolong tea leaves.
A Two-Layer Mathematical Modelling of Drug Delivery to Biological Tissues
Chakravarty, Koyel
2016-01-01
Local drug delivery has received much recognition in recent years, yet it is still unpredictable how drug efficacy depends on physicochemical properties and delivery kinetics. The purpose of the current study is to provide a useful mathematical model for drug release from a drug delivery device and consecutive drug transport in biological tissue, thereby aiding the development of new therapeutic drug by a systemic approach. In order to study the complete process, a two-layer spatio-temporal model depicting drug transport between the coupled media is presented. Drug release is described by considering solubilisation dynamics of drug particle, diffusion of the solubilised drug through porous matrix and also some other processes like reversible dissociation / recrystallization, drug particle-receptor binding and internalization phenomena. The model has led to a system of partial differential equations describing the important properties of drug kinetics. This model contributes towards the perception of the roles...
Some considerations on numerical schemes for treating hyperbolicity issues in two-layer models
Sarno, L.; Carravetta, A.; Martino, R.; Papa, M. N.; Tai, Y.-C.
2017-02-01
Multi-layer depth-averaged models are widely employed in various hydraulic engineering applications. Yet, such models are not strictly hyperbolic. Their equation systems typically lose hyperbolicity when the relative velocities between layers become too large, which is associated with Kelvin-Helmholtz instabilities involving turbulent momentum exchanges between the layers. Focusing on the two-layer case, we present a numerical improvement that locally avoids the loss of hyperbolicity. The proposed modification introduces an additional momentum exchange between layers, whose value is iteratively calculated to be strictly sufficient to keep the system hyperbolic. The approach can be easily implemented in any finite volume scheme and there is no limitation concerning the density ratio between layers. Numerical examples, employing both HLL-type and Roe-type approximate Riemann solvers, are reported to validate the method and its key features.
Artery buckling analysis using a two-layered wall model with collagen dispersion.
Mottahedi, Mohammad; Han, Hai-Chao
2016-07-01
Artery buckling has been proposed as a possible cause for artery tortuosity associated with various vascular diseases. Since microstructure of arterial wall changes with aging and diseases, it is essential to establish the relationship between microscopic wall structure and artery buckling behavior. The objective of this study was to developed arterial buckling equations to incorporate the two-layered wall structure with dispersed collagen fiber distribution. Seven porcine carotid arteries were tested for buckling to determine their critical buckling pressures at different axial stretch ratios. The mechanical properties of these intact arteries and their intima-media layer were determined via pressurized inflation test. Collagen alignment was measured from histological sections and modeled by a modified von-Mises distribution. Buckling equations were developed accordingly using microstructure-motivated strain energy function. Our results demonstrated that collagen fibers disperse around two mean orientations symmetrically to the circumferential direction (39.02°±3.04°) in the adventitia layer; while aligning closely in the circumferential direction (2.06°±3.88°) in the media layer. The microstructure based two-layered model with collagen fiber dispersion described the buckling behavior of arteries well with the model predicted critical pressures match well with the experimental measurement. Parametric studies showed that with increasing fiber dispersion parameter, the predicted critical buckling pressure increases. These results validate the microstructure-based model equations for artery buckling and set a base for further studies to predict the stability of arteries due to microstructural changes associated with vascular diseases and aging.
Quantification of the specific yield in a two-layer hard-rock aquifer model
Durand, Véronique; Léonardi, Véronique; de Marsily, Ghislain; Lachassagne, Patrick
2017-08-01
Hard rock aquifers (HRA) have long been considered to be two-layer systems, with a mostly capacitive layer just below the surface, the saprolite layer, and a mainly transmissive layer underneath, the fractured layer. Although this hydrogeological conceptual model is widely accepted today within the scientific community, it is difficult to quantify the respective storage properties of each layer with an equivalent porous medium model. Based on an HRA field site, this paper attempts to quantify in a distinct manner the respective values of the specific yield (Sy) in the saprolite and the fractured layer, with the help of a deterministic hydrogeological model. The study site is the Plancoët migmatitic aquifer located in north-western Brittany, France, with piezometric data from 36 observation wells surveyed every two weeks for eight years. Whereas most of the piezometers (26) are located where the water table lies within the saprolite, thus representing the specific yield of the unconfined layer (Sy1), 10 of them are representative of the unconfined fractured layer (Sy2), due to their position where the saprolite is eroded or unsaturated. The two-layer model, based on field observations of the layer geometry, runs with the MODFLOW code. 81 values of the Sy1/Sy2 parameter sets were tested manually, as an inverse calibration was not able to calibrate these parameters. In order to calibrate the storage properties, a new quality-of-fit criterion called ;AdVar; was also developed, equal to the mean squared deviation of the seasonal piezometric amplitude variation. Contrary to the variance, AdVar is able to select the best values for the specific yield in each layer. It is demonstrated that the saprolite layer is about 2.5 times more capacitive than the fractured layer, with Sy1 = 10% (7% < Sy1 < 15%) against Sy2 = 2% (1% < Sy2 < 3%), in this particular example.
Inertial/GPS Integrated Geolocation System for Detection and Recovery of Buried Munitions
2011-07-01
RN) (Haykin, 1999). Demuth and Beale (2004) showed that the two-layer feed-forward network (first layer is sigmoid and second is linear) can be...Secretary of Defense for Acquisition, Technology, and Logistics, Washington, D.C. 20301-3140, December 2003. Demuth , H. and Beale, M. (2004): Neural
Khanmohammadi, Mohammadreza; Garmarudi, Amir Bagheri; Rouchi, Mohammad Babaei; Khoddami, Nafiseh
2011-01-01
A method has been established for simultaneous determination of sodium sulfate, sodium carbonate, and sodium tripolyphosphate in detergent washing powder samples based on attenuated total reflectance Fourier transform IR spectrometry in the mid-IR spectral region (800-1550 cm(-1)). Genetic algorithm (GA) wavelength selection followed by feed forward back-propagation artificial neural network (BP-ANN) was the chemometric approach. Root mean square error of prediction for BP-ANN and GA-BP-ANN was 0.0051 and 0.0048, respectively. The proposed method is simple, with no tedious pretreatment step, for simultaneous determination of the above-mentioned components in commercial washing powder samples.
The Use of Neural Network Technology to Model Swimming Performance
Silva, António José; Costa, Aldo Manuel; Oliveira, Paulo Moura; Reis, Victor Machado; Saavedra, José; Perl, Jurgen; Rouboa, Abel; Marinho, Daniel Almeida
2007-01-01
The aims of the present study were: to identify the factors which are able to explain the performance in the 200 meters individual medley and 400 meters front crawl events in young swimmers, to model the performance in those events using non-linear mathematic methods through artificial neural networks (multi-layer perceptrons) and to assess the neural network models precision to predict the performance. A sample of 138 young swimmers (65 males and 73 females) of national level was submitted to a test battery comprising four different domains: kinanthropometric evaluation, dry land functional evaluation (strength and flexibility), swimming functional evaluation (hydrodynamics, hydrostatic and bioenergetics characteristics) and swimming technique evaluation. To establish a profile of the young swimmer non-linear combinations between preponderant variables for each gender and swim performance in the 200 meters medley and 400 meters font crawl events were developed. For this purpose a feed forward neural network was used (Multilayer Perceptron) with three neurons in a single hidden layer. The prognosis precision of the model (error lower than 0.8% between true and estimated performances) is supported by recent evidence. Therefore, we consider that the neural network tool can be a good approach in the resolution of complex problems such as performance modeling and the talent identification in swimming and, possibly, in a wide variety of sports. Key pointsThe non-linear analysis resulting from the use of feed forward neural network allowed us the development of four performance models.The mean difference between the true and estimated results performed by each one of the four neural network models constructed was low.The neural network tool can be a good approach in the resolution of the performance modeling as an alternative to the standard statistical models that presume well-defined distributions and independence among all inputs.The use of neural networks for sports
Yilbas, Bekir Sami; Kumar, Aditya; Bhushan, Bharat
2014-01-01
Single- and two-layer coatings were deposited onto carbon steel using a high-velocity oxy-fuel deposition gun. The two-layer coating consisted of a top layer of tungsten carbide cobalt/nickel alloy blend that provides wear resistance and a bottom layer of iron/molybdenum blend that provides corrosion resistance. The morphological changes in the single- and two-layer coatings were examined using scanning electron microscopy. The residual stresses formed on the surface of various coatings were determined from x-ray diffraction data. Nanomechanical properties were measured using the nanoindentation technique. Microhardness and fracture toughness were measured incorporating the microindentation tests. Macrowear and macrofriction characteristics were measured using the pin-on-disk testing apparatus. The goal of this study was to ensure that the mechanical properties, friction, and wear resistance of the two-layer coating are similar to that of the single-layer coating.
A novel nature inspired firefly algorithm with higher order neural network: Performance analysis
Janmenjoy Nayak
2016-03-01
Full Text Available The applications of both Feed Forward Neural network and Multilayer perceptron are very diverse and saturated. But the linear threshold unit of feed forward networks causes fast learning with limited capabilities, while due to multilayering, the back propagation of errors exhibits slow training speed in MLP. So, a higher order network can be constructed by correlating between the input variables to perform nonlinear mapping using the single layer of input units for overcoming the above drawbacks. In this paper, a Firefly based higher order neural network has been proposed for data classification for maintaining fast learning and avoids the exponential increase of processing units. A vast literature survey has been conducted to review the state of the art of the previous developed models. The performance of the proposed method has been tested with various benchmark datasets from UCI machine learning repository and compared with the performance of other established models. Experimental results imply that the proposed method is fast, steady, reliable and provides better classification accuracy than others.
Neural networks within multi-core optic fibers.
Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael
2016-07-07
Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.
Mandarin Chinese Tone Recognition with an Artificial Neural Network
XU Li; ZHANG Wenle; ZHOU Ning; LEE Chaoyang; LI Yongxin; CHEN Xiuwu; ZHAO Xiaoyan
2006-01-01
Mandarin Chinese tone patterns vary in one of the four ways, i.e, (1) high level; (2) rising; (3) low falling and rising; and (4) high falling. The present study is to examine the efficacy of an artificial neural network in recognizing these tone patterns. Speech data were recorded from 12 children (3-6 years of age) and 15 adults. All subjects were native Mandarin Chinese speakers. The fundamental frequencies (FO) of each monosyllabic word of the speech data were extracted with an autocorrelation method. The pitch data(i.e., the FO contours) were the inputs to a feed-forward backpropagation artificial neural network. The number of inputs to the neural network varied from 1 to 16 and the hidden layer of the network contained neurons that varied from 1 to 16 in number. The output of the network consisted of four neurons representing the four tone patterns of Mandarin Chinese. After being trained with the Levenberg-Marquardt optimization, the neural network was able to successfully classify the tone patterns with an accuracy of about 90% correct for speech samples from both adults and children. The artificial neural network may provide an objective and effective way of assessing tone production in prelingually-deafened children who have received cochlear implants.
Neural networks within multi-core optic fibers
Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael
2016-07-01
Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.
王金平; 许建平; 兰燕妮; 徐杨军
2012-01-01
针对恒定导通时间（COT）控制开关变换器的开关频率随输入电压变动而变化的缺点,本文提出了一种基于输入电压前馈补偿的恒定导通时间（IVFC-COT）控制技术,通过引入输入电压前馈环路,使恒定导通时间与输入电压成反比,从而消除输入电压波动对开关频率的影响。IVFC-COT控制在继承COT控制环路设计简单,无需误差放大器及其相应的补偿网络,瞬态响应速度快等优点的基础上,使开关频率在输入电压或负载波动时保持恒定。仿真及实验结果验证了IVFC-COT控制技术的可行性。%In order to make the switching frequency of constant on-time（COT）control technique immunity to the variation of input voltage, input voltage feed-forward compensated COT （IVFC-COT） control technique is proposed in this paper. By introducing input voltage feed-forward compensation, the on time is inverse proportion to the input voltage, and the effect of input voltage variation on switching frequency is eliminated. Similar to COT control technique, IVFC-COT also has simple control loop and fast transient response, moreover, error amplifier and its corresponding compensation network are not needed. In addition, it can make the switching frequency independent of the variation of input voltage and load. Simulation and experimental results are verified the validity of the proposed IVFC-COT control technique.
Optical measurements of absorption changes in two-layered diffusive media
Fabbri, Francesco [Department of Biomedical Engineering, Bioengineering Center, Tufts University, 4 Colby Street, Medford, MA 02155 (United States); Sassaroli, Angelo [Department of Biomedical Engineering, Bioengineering Center, Tufts University, 4 Colby Street, Medford, MA 02155 (United States); Henry, Michael E [McLean Hospital and Department of Psychiatry, Harvard Medical School, 115 Mill Street, Belmont, MA 02478 (United States); Fantini, Sergio [Department of Biomedical Engineering, Bioengineering Center, Tufts University, 4 Colby Street, Medford, MA 02155 (United States)
2004-04-07
We have used Monte Carlo simulations for a two-layered diffusive medium to investigate the effect of a superficial layer on the measurement of absorption variations from optical diffuse reflectance data processed by using: (a) a multidistance, frequency-domain method based on diffusion theory for a semi-infinite homogeneous medium; (b) a differential-pathlength-factor method based on a modified Lambert-Beer law for a homogeneous medium and (c) a two-distance, partial-pathlength method based on a modified Lambert-Beer law for a two-layered medium. Methods (a) and (b) lead to a single value for the absorption variation, whereas method (c) yields absorption variations for each layer. In the simulations, the optical coefficients of the medium were representative of those of biological tissue in the near-infrared. The thickness of the first layer was in the range 0.3-1.4 cm, and the source-detector distances were in the range 1-5 cm, which is typical of near-infrared diffuse reflectance measurements in tissue. The simulations have shown that (1) method (a) is mostly sensitive to absorption changes in the underlying layer, provided that the thickness of the superficial layer is {approx}0.6 cm or less; (2) method (b) is significantly affected by absorption changes in the superficial layer and (3) method (c) yields the absorption changes for both layers with a relatively good accuracy of {approx}4% for the superficial layer and {approx}10% for the underlying layer (provided that the absorption changes are less than 20-30% of the baseline value). We have applied all three methods of data analysis to near-infrared data collected on the forehead of a human subject during electroconvulsive therapy. Our results suggest that the multidistance method (a) and the two-distance partial-pathlength method (c) may better decouple the contributions to the optical signals that originate in deeper tissue (brain) from those that originate in more superficial tissue layers.
Meetei Mayek Unicode Modeling Using Swarm Intelligence and Neural Networks
Wahengbam Kanan Kumar
2014-04-01
Full Text Available The Different techniques have evolved for better optical character recognition for many scripts, yet very little literature has been found for Meetei Mayek script. The current paper exhibits a new approach to model and simulate handwritten Meetei mayek script by using advanced segmentation tools and recognition algorithms. Preprocessing of the acquired images is needed before segmentation and recognition steps; segmentation is done by using PSOFCM segmentation, while multilayer feed forward neural network with back propagation learning is used for the recognition purpose. It may be noted that PSOFCM segmentation proved useful for MRI image processing in our previous paper, the same technique is used for enhancing the characters. The detailed procedures along with the results are discussed in the sections shown below
A Neural Network Approach for GMA Butt Joint Welding
Christensen, Kim Hardam; Sørensen, Torben
2003-01-01
squares has been used with the back-propagation algorithm for training the network, while a Bayesian regularization technique has been successfully applied for minimizing the risk of inexpedient over-training. Finally, a predictive closed-loop control strategy based on a so-called single-neuron self......This paper describes the application of the neural network technology for gas metal arc welding (GMAW) control. A system has been developed for modeling and online adjustment of welding parameters, appropriate to guarantee a certain degree of quality in the field of butt joint welding with full...... penetration, when the gap width is varying during the welding process. The process modeling to facilitate the mapping from joint geometry and reference weld quality to significant welding parameters has been based on a multi-layer feed-forward network. The Levenberg-Marquardt algorithm for non-linear least...
Strawberry Maturity Neural Network Detectng System Based on Genetic Algorithm
Xu, Liming
The quick and non-detective detection of agriculture product is one of the measures to increase the precision and productivity of harvesting and grading. Having analyzed H frequency of different maturities in different light intensities, the results show that H frequency for the same maturity has little influence in different light intensities; Under the same light intensity, three strawberry maturities are changing in order. After having confirmed the H frequency section to distinguish the different strawberry maturity, the triplelayer feed-forward neural network system to detect strawberry maturity was designed by using genetic algorithm. The test results show that the detecting precision ratio is 91.7%, it takes 160ms to distinguish one strawberry. Therefore, the online non-detective detecting the strawberry maturity could be realized.
Analyzing rocket plume spectral data with neural networks
Whitaker, Kevin W.; Krishnakumar, K. S.; Benzing, Daniel A.
1995-01-01
The Optical Plume Anomaly Detection (OPAD) system is under development to provide early-warning failure detection in support of ground-level testing of the Space Shuttle Main Engine (SSME). Failure detection is to be achieved through the acquisition of spectrally resolved plume emissions and subsequent identification of abnormal levels indicative of engine corrosion or component failure. Two computer codes (one linear and the other non-linear) are used by the OPAD system to iteratively determine specific element concentrations in the SSME plume, given emission intensity and wavelength information. Since this analysis is extremely labor intensive, a study was initiated to develop neural networks that would model the 'inverse' of these computer codes. Optimally connected feed-forward networks with imperceptible prediction error have been developed for each element modeled by the linear code, SPECTRA4. Radial basis function networks were developed for the non-linear code, SPECTRA5, and predict combustion temperature in addition to element concentrations.
Analyzing rocket plume spectral data with neural networks
Whitaker, K.W.; Krishnakumar, K.S.; Benzing, D.A.
1995-09-01
The Optical Plume Anomaly Detection (OPAD) system is under development to provide early-warning failure detection in support of ground-level testing of the Space Shuttle Main Engine (SSME). Failure detection is to be achieved through the acquisition of spectrally resolved plume emissions and subsequent identification of abnormal levels indicative of engine corrosion or component failure. Two computer codes (one linear and the other non-linear) are used by the OPAD system to iteratively determine specific element concentrations in the SSME plume, given emission intensity and wavelength information. Since this analysis is extremely labor intensive, a study was initiated to develop neural networks that would model the `inverse` of these computer codes. Optimally connected feed-forward networks with imperceptible prediction error have been developed for each element modeled by the linear code, SPECTRA4. Radial basis function networks were developed for the non-linear code, SPECTRA5, and predict combustion temperature in addition to element concentrations.
WLAN indoor location method based on artificial neural network
Zhou Mu; Sun Ying; Xu Yubin; Deng Zhian; Meng Weixiao
2010-01-01
WLAN indoor location method based on artificial neural network (ANN) is analyzed.A three layer feed-forward ANN model offers the benefits of reducing time cost of the layout of an indoor location system, saving storage cost of the radio map establishment and enhancing real-time capacity in the on-line phase.According to the analysis of SNR distributions of recorded beacon signal samples and discussion about the multi-mode phenomenon, the one map method is proposed for the purpose of simplifying ANN input values and increasing location performances.Based on the simulations and comparison analysis with other two typical indoor location methods, K-nearest neighbor (KNN) and probability, the feasibility and effectiveness of ANN-based indoor location method are verified with average location error of 2.37m and location accuracy of 78.6% in 3m.
Analyzing rocket plume spectral data with neural networks
Whitaker, Kevin W.; Krishnakumar, K. S.; Benzing, Daniel A.
The Optical Plume Anomaly Detection (OPAD) system is under development to provide early-warning failure detection in support of ground-level testing of the Space Shuttle Main Engine (SSME). Failure detection is to be achieved through the acquisition of spectrally resolved plume emissions and subsequent identification of abnormal levels indicative of engine corrosion or component failure. Two computer codes (one linear and the other non-linear) are used by the OPAD system to iteratively determine specific element concentrations in the SSME plume, given emission intensity and wavelength information. Since this analysis is extremely labor intensive, a study was initiated to develop neural networks that would model the 'inverse' of these computer codes. Optimally connected feed-forward networks with imperceptible prediction error have been developed for each element modeled by the linear code, SPECTRA4. Radial basis function networks were developed for the non-linear code, SPECTRA5, and predict combustion temperature in addition to element concentrations.
Backpropagation Artificial Neural Network To Detect Hyperthermic Seizures In Rats
Rakesh Kumar Sinha
2003-02-01
Full Text Available A three-layered feed-forward back-propagation Artificial Neural Network was used to classify the seizure episodes in rats. Seizure patterns were induced by subjecting anesthetized rats to a Biological Oxygen Demand incubator at 45-47ºC for 30 to 60 minutes. Selected fast Fourier transform data of one second epochs of electroencephalogram were used to train and test the network for the classification of seizure and normal patterns. The results indicate that the present network with the architecture of 40-12-1 (input-hidden-output nodes agrees with manual scoring of seizure and normal patterns with a high recognition rate of 98.6%.
Thermal properties of composite two-layer systems with a fractal inclusion structure
Reyes-Salgado, J. J.; Dossetti, V.; Bonilla-Capilla, B.; Carrillo, J. L.
2015-01-01
In this work, we study the thermal transport properties of platelike composite two-layer samples made of polyester resin and magnetite inclusions. By means of photoacoustic spectroscopy and thermal relaxation, their effective thermal diffusivity and conductivity were experimentally measured. The composite layers were prepared under the action of a static magnetic field, resulting in anisotropic (fractal) inclusion structures with the formation of chain-like magnetite aggregates parallel to the faces of the layers. In one kind of the bilayers, a composite layer was formed on top of a resin layer while their relative thickness was varied. These samples can be described by known models. In contrast, bilayers with the same concentration of inclusions and the same thickness on both sides, where only the angle between their inclusion structures was systematically varied, show a nontrivial behaviour of their thermal conductivity as a function of this angle. Through a multifractal and lacunarity analysis, we explain the observed thermal response in terms of the complexity of the interface between the layers.
Two layer asymptotic model for the wave propagation in the presence of vorticity
Kazakova, M. Yu; Noble, P.
2016-06-01
In the present study, we consider the system of two layers of the immiscible constant density fluids which are modeled by the full Euler equations. The domain of the flow is infinite in the horizontal directions and delimited above by a free surface. Bottom topography is taken into account. This is a simple model of the wave propagation in the ocean where the upper layer corresponds to the (thin) layer of fluid above the thermocline whereas the lower layer is under the thermocline. Though even this simple framework is computationally too expensive and mathematically too complicated to describe efficiently propagation of waves in the ocean. Modeling assumption such as shallowness, vanishing vorticity and hydrostatic pressure are usually made to get the bi-layer shallow water models that are mathematically more manageable. Though, they cannot describe correctly the propagation of both internal and free surface waves and dispersive/non hydrostatic must be added. Our goal is to consider the regime of medium to large vorticities in shallow water flow. We present the derivation of the model for internal and surface wave propagation in the case of constant and general vorticities in each layer. The model reduces to the classical Green-Naghdi equations in the case of vanishing vorticities.
Two-layer interfacial flows beyond the Boussinesq approximation: a Hamiltonian approach
Camassa, R; Ortenzi, G
2015-01-01
The theory of integrable systems of Hamiltonian PDEs and their near-integrable deformations is used to study evolution equations resulting from vertical-averages of the Euler system for two-layer stratified flows in an infinite 2D channel. The Hamiltonian structure of the averaged equations is obtained directly from that of the Euler equations through the process of Hamiltonian reduction. Long-wave asymptotics together with the Boussinesq approximation of neglecting the fluids' inertia is then applied to reduce the leading order vertically averaged equations to the shallow-water Airy system, and thence, in a non-trivial way, to the dispersionless non-linear Schr\\"odinger equation. The full non-Boussinesq system for the dispersionless limit can then be viewed as a deformation of this well known equation. In a perturbative study of this deformation, it is shown that at first order the deformed system possesses an infinite sequence of constants of the motion, thus casting this system within the framework of comp...
Method of the Moulding Sands Binding Power Assessment in Two-Layer Moulds Systems
M. Holtzer
2014-07-01
Full Text Available More and more foundry plants applying moulding sands with water-glass or its substitutes for obtaining the high-quality casting surface at the smallest costs, consider the possibility of implementing two-layer moulds, in which e.g. the facing sand is a sand with an organic binder (no-bake type and the backing sand is a sand with inorganic binder. Both kinds of sands must have the same chemical reaction. The most often applied system is the moulding sand on the water-glass or geopolymer bases - as the backing sand and the moulding sand from the group of self-hardening sands with a resol resin - as the facing sand. Investigations were performed for the system: moulding sand with inorganic GEOPOL binder or moulding sand with water glass (as a backing sand and moulding sand, no-bake type, with a resol resin originated from various producers: Rezolit AM, Estrofen, Avenol NB 700 (as a facing sand. The LUZ apparatus, produced by Multiserw Morek, was adapted for investigations. A special partition with cuts was mounted in the attachment for making test specimens for measuring the tensile strength. This partition allowed a simultaneous compaction of two kinds of moulding sands. After 24 hours of hardening the highest values were obtained for the system: Geopol binder - Avenol resin.
Display of the β-effect in the Black Sea Two-Layer Model
A.A. Pavlushin
2016-10-01
Full Text Available The research is a continuation of a series of numerical experiments on modeling formation of wind currents and eddies in the Black Sea within the framework of a two-layer eddy-resolving model. The main attention is focused on studying the β-effect role. The stationary cyclonic wind is used as an external forcing and the bottom topography is not considered. It is shown that at the β-effect being taken into account, the Rossby waves propagating from east to west are observed both during the currents’ formation and at the statistical equilibrium mode when the mesoscale eddies are formed. In the integral flows’ field the waves are visually manifested in a form of the alternate large-scale cyclonic gyres and zones in which the meso-scale anti-cyclones are formed. This spatial pattern constantly propagates to the west that differs from the results of calculations using the constant Coriolis parameter when the spatially alternate cyclonic and anti-cyclonic vortices are formed, but hold a quasi-stationary position. The waves with the parameters of the Rossby wave first barotropic mode for the closed basin are most clearly pronounced. Interaction of the Rossby waves with large-scale circulation results in intensification of the of the currents’ hydrodynamic instability and in formation of the mesoscale eddies. Significant decrease of kinetic and available potential energy as compared to the values obtained at the constant Coriolis parameter is also a consequence of the eddy formation intensification.
Inferring topologies via driving-based generalized synchronization of two-layer networks
Wang, Yingfei; Wu, Xiaoqun; Feng, Hui; Lu, Jun-an; Xu, Yuhua
2016-05-01
The interaction topology among the constituents of a complex network plays a crucial role in the network’s evolutionary mechanisms and functional behaviors. However, some network topologies are usually unknown or uncertain. Meanwhile, coupling delays are ubiquitous in various man-made and natural networks. Hence, it is necessary to gain knowledge of the whole or partial topology of a complex dynamical network by taking into consideration communication delay. In this paper, topology identification of complex dynamical networks is investigated via generalized synchronization of a two-layer network. Particularly, based on the LaSalle-type invariance principle of stochastic differential delay equations, an adaptive control technique is proposed by constructing an auxiliary layer and designing proper control input and updating laws so that the unknown topology can be recovered upon successful generalized synchronization. Numerical simulations are provided to illustrate the effectiveness of the proposed method. The technique provides a certain theoretical basis for topology inference of complex networks. In particular, when the considered network is composed of systems with high-dimension or complicated dynamics, a simpler response layer can be constructed, which is conducive to circuit design. Moreover, it is practical to take into consideration perturbations caused by control input. Finally, the method is applicable to infer topology of a subnetwork embedded within a complex system and locate hidden sources. We hope the results can provide basic insight into further research endeavors on understanding practical and economical topology inference of networks.
Extreme events statistics in a two-layer quasi-geostrophic atmospheric model
Galfi, Vera Melinda; Bodai, Tamas; Lucarini, Valerio
2016-04-01
Extreme events statistics provides a theoretical framework to analyze and predict extreme events based on the convergence of the distribution of the extremes to some limiting distribution. In this work we analyze the convergence of the distribution of extreme events to the Generalized Extreme Value (GEV) distribution and to the Generalized Pareto Distribution (GPD), using a two-layer quasi-geostrophic atmospheric model, and compare our results with theoretical findings from the field of extreme value theory for dynamical systems. We study the behavior of the GEV shape parameter by increasing the block size and of the GPD shape parameter by increasing the threshold, and compare the inferred parameters with a theoretical shape parameter that depends only on the geometrical properties of the attractor. The main objective is to find out whether this theoretical shape parameter can be used to evaluate extreme event analysis based on model output. For this, we perform very long simulations. We run our system with two different levels of forcing determined by two different meridional temperature gradients, one inducing a medium level of chaos and the other one a high level of chaos. We analyze in both cases extremes of energy variables.
Deposition, Heat Treatment And Characterization of Two Layer Bioactive Coatings on Cylindrical PEEK.
Durham, John W; Rabiei, Afsaneh
2016-09-15
Polyether ether ketone (PEEK) rods were coated via ion beam asssited deposition (IBAD) at room temperature. The coating consists of a two-layer design of yttria-stabilized zirconia (YSZ) as a heat-protection layer, and hydroxyapatite (HA) as a top layer to increase bioactivity. A rotating substrate holder was designed to deposit an even coating on the cylindrical surface of PEEK rods; the uniformity is verified by cross-sectional measurements using scanning electron microscopy (SEM). Deposition is followed by heat treatment of the coating using microwave annealing and autoclaving. Transmission electron microscopy (TEM) showed a dense, uniform columnar grain structure in the YSZ layer that is well bonded to the PEEK substrate, while the calcium phosphate layer was amorphous and pore-free in its as-deposited state. Subsequent heat treatment via microwave energy introduced HA crystallization in the calcium phosphate layer and additional autoclaving further expanded the crystallization of the HA layer. Chemical composition evaluation of the coating indicated the Ca/P ratios of the HA layer to be near that of stoichiometric HA, with minor variations through the HA layer thickness. The adhesion strength of as-deposited HA/YSZ coatings on smooth, polished PEEK surfaces was mostly unaffected by microwave heat treatment, but decreased with additional autoclave treatment. Increasing surface roughness showed improvement of bond strength.
A novel approach to ECG classification based upon two-layered HMMs in body sensor networks.
Liang, Wei; Zhang, Yinlong; Tan, Jindong; Li, Yang
2014-03-27
This paper presents a novel approach to ECG signal filtering and classification. Unlike the traditional techniques which aim at collecting and processing the ECG signals with the patient being still, lying in bed in hospitals, our proposed algorithm is intentionally designed for monitoring and classifying the patient's ECG signals in the free-living environment. The patients are equipped with wearable ambulatory devices the whole day, which facilitates the real-time heart attack detection. In ECG preprocessing, an integral-coefficient-band-stop (ICBS) filter is applied, which omits time-consuming floating-point computations. In addition, two-layered Hidden Markov Models (HMMs) are applied to achieve ECG feature extraction and classification. The periodic ECG waveforms are segmented into ISO intervals, P subwave, QRS complex and T subwave respectively in the first HMM layer where expert-annotation assisted Baum-Welch algorithm is utilized in HMM modeling. Then the corresponding interval features are selected and applied to categorize the ECG into normal type or abnormal type (PVC, APC) in the second HMM layer. For verifying the effectiveness of our algorithm on abnormal signal detection, we have developed an ECG body sensor network (BSN) platform, whereby real-time ECG signals are collected, transmitted, displayed and the corresponding classification outcomes are deduced and shown on the BSN screen.
Dynamics and flow-coupling in two-layer turbulent thermal convection
Xie, Yi-Chao
2015-01-01
We present an experimental investigation of the dynamics and flow-coupling of convective turbulent flows in a cylindrical Rayleigh-Benard convection cell with two immiscible fluids, water and fluorinert FC-77 electronic liquid (FC77). It is found that one large-scale circulation (LSC) roll exists in each of the fluid layers, and that their circulation planes have two preferred azimuthal orientations separated by $\\sim\\pi$. A surprising finding of the study is that cessations/reversals of the LSC in FC77 of the two-layer system occur much more frequently than they do in single-layer turbulent RBC, and that a cessation is most likely to result in a flow reversal of the LSC, which is in sharp contrast with the uniform distribution of the orientational angular change of the LSC before and after cessations in single-layer turbulent RBC. This implies that the dynamics governing cessations and reversals in the two systems are very different. Two coupling modes, thermal coupling (flow directions of the two LSCs are o...
MHD two-layered unsteady fluid flow and heat transfer through a horizontal channel between
Raju T. Linga
2014-02-01
Full Text Available An unsteady magnetohydrodynamic (MHD two-layered fluids flow and heat transfer in a horizontal channel between two parallel plates in the presence of an applied magnetic and electric field is investigated, when the whole system is rotated about an axis perpendicular to the flow. The flow is driven by a constant uniform pressure gradient in the channel bounded by two parallel insulating plates, when both fluids are considered as electrically conducting, incompressible with variable properties, viz. different viscosities, thermal and electrical conductivities. The transport properties of the two fluids are taken to be constant and the bounding plates are maintained at constant and equal temperatures. The governing partial differential equations are then reduced to the ordinary linear differential equations using two-term series. Closed form solutions for primary and secondary velocity, also temperature distributions are obtained in both the fluid regions of the channel. Profiles of these solutions are plotted to discuss the effects of the flow and heat transfer characteristics, and their dependence on the governing parameters involved, such as the Hartmann number, rotation parameter, ratios of the viscosities, heights, electrical and thermal conductivities
A Two-Layer Method for Sedentary Behaviors Classification Using Smartphone and Bluetooth Beacons.
Cerón, Jesús D; López, Diego M; Hofmann, Christian
2017-01-01
Among the factors that outline the health of populations, person's lifestyle is the more important one. This work focuses on the caracterization and prevention of sedentary lifestyles. A sedentary behavior is defined as "any waking behavior characterized by an energy expenditure of 1.5 METs (Metabolic Equivalent) or less while in a sitting or reclining posture". To propose a method for sedentary behaviors classification using a smartphone and Bluetooth beacons considering different types of classification models: personal, hybrid or impersonal. Following the CRISP-DM methodology, a method based on a two-layer approach for the classification of sedentary behaviors is proposed. Using data collected from a smartphones' accelerometer, gyroscope and barometer; the first layer classifies between performing a sedentary behavior and not. The second layer of the method classifies the specific sedentary activity performed using only the smartphone's accelerometer and barometer data, but adding indoor location data, using Bluetooth Low Energy (BLE) beacons. To improve the precision of the classification, both layers implemented the Random Forest algorithm and the personal model. This study presents the first available method for the automatic classification of specific sedentary behaviors. The layered classification approach has the potential to improve processing, memory and energy consumption of mobile devices and wearables used.
Long-time Behavior of a Two-layer Model of Baroclinic Quasi-geostrophic Turbulence
Farhat, Aseel; Titi, Edriss S; Ziane, Mohammed
2012-01-01
We study a viscous two-layer quasi-geostrophic beta-plane model that is forced by imposition of a spatially uniform vertical shear in the eastward (zonal) component of the layer flows, or equivalently a spatially uniform north-south temperature gradient. We prove that the model is linearly unstable, but that non-linear solutions are bounded in time by a bound which is independent of the initial data and is determined only by the physical parameters of the model. We further prove, using arguments first presented in the study of the Kuramoto-Sivashinsky equation, the existence of an absorbing ball in appropriate function spaces, and in fact the existence of a compact finite-dimensional attractor, and provide upper bounds for the fractal and Hausdorff dimensions of the attractor. Finally, we show the existence of an inertial manifold for the dynamical system generated by the model's solution operator. Our results provide rigorous justification for observations made by Panetta based on long-time numerical integra...
A two-layer $\\alpha\\omega$ dynamo model, and its implications for 1-D dynamos
Roald, C B
1999-01-01
I will discuss an attempt at representing an interface dynamo in a simplified, essentially 1D framework. The operation of the dynamo is broken up into two 1D layers, one containing the $\\alpha$ effect and the other containing the $\\omega$ effect, and these two layers are allowed to communicate with each other by the simplest possible representation of diffusion, an analogue of Newton's law of cooling. Dynamical back-reaction of the magnetic field on them with diagrams I computed for a comparable purely 1D model. The bifurcation structure shows remarkable similarity, but a couple of subtle changes imply dramatically different physical behaviour for the model. In particular, the solar-like dynamo mode found in the 1-layer model is not stable in the 2-layer version; instead there is an (apparent) homoclinic bifurcation and a sequence of periodic, quasiperiodic, and chaotic modes. I argue that the fragility of these models makes them effectively useless as predictors or interpreters of more complex dynamos.
Two-Layer Linear MPC Approach Aimed at Walking Beam Billets Reheating Furnace Optimization
Silvia Maria Zanoli
2017-01-01
Full Text Available In this paper, the problem of the control and optimization of a walking beam billets reheating furnace located in an Italian steel plant is analyzed. An ad hoc Advanced Process Control framework has been developed, based on a two-layer linear Model Predictive Control architecture. This control block optimizes the steady and transient states of the considered process. Two main problems have been addressed. First, in order to manage all process conditions, a tailored module defines the process variables set to be included in the control problem. In particular, a unified approach for the selection on the control inputs to be used for control objectives related to the process outputs is guaranteed. The impact of the proposed method on the controller formulation is also detailed. Second, an innovative mathematical approach for stoichiometric ratios constraints handling has been proposed, together with their introduction in the controller optimization problems. The designed control system has been installed on a real plant, replacing operators’ mental model in the conduction of local PID controllers. After two years from the first startup, a strong energy efficiency improvement has been observed.
de Graaf, Inge E. M.; van Beek, Rens L. P. H.; Gleeson, Tom; Moosdorf, Nils; Schmitz, Oliver; Sutanudjaja, Edwin H.; Bierkens, Marc F. P.
2017-04-01
Groundwater is the world's largest accessible source of freshwater to satisfy human water needs. Moreover, groundwater buffers variable precipitation rates over time, thereby effectively sustaining river flows in times of droughts and evaporation in areas with shallow water tables. In this study, building on previous work, we simulate groundwater head fluctuations and groundwater storage changes in both confined and unconfined aquifer systems using a global-scale high-resolution (5‧) groundwater model by deriving new estimates of the distribution and thickness of confining layers. Inclusion of confined aquifer systems (estimated 6-20% of the total aquifer area) improves estimates of timing and amplitude of groundwater head fluctuations and changes groundwater flow paths and groundwater-surface water interaction rates. Groundwater flow paths within confining layers are shorter than paths in the underlying aquifer, while flows within the confined aquifer can get disconnected from the local drainage system due to the low conductivity of the confining layer. Lateral groundwater flows between basins are significant in the model, especially for areas with (partially) confined aquifers were long flow paths crossing catchment boundaries are simulated, thereby supporting water budgets of neighboring catchments or aquifer systems. The developed two-layer transient groundwater model is used to identify hot-spots of groundwater depletion. Global groundwater depletion is estimated as 7013 km3 (137 km3y-1) over 1960-2010, which is consistent with estimates of previous studies.
A Novel Approach to ECG Classification Based upon Two-Layered HMMs in Body Sensor Networks
Wei Liang
2014-03-01
Full Text Available This paper presents a novel approach to ECG signal filtering and classification. Unlike the traditional techniques which aim at collecting and processing the ECG signals with the patient being still, lying in bed in hospitals, our proposed algorithm is intentionally designed for monitoring and classifying the patient’s ECG signals in the free-living environment. The patients are equipped with wearable ambulatory devices the whole day, which facilitates the real-time heart attack detection. In ECG preprocessing, an integral-coefficient-band-stop (ICBS filter is applied, which omits time-consuming floating-point computations. In addition, two-layered Hidden Markov Models (HMMs are applied to achieve ECG feature extraction and classification. The periodic ECG waveforms are segmented into ISO intervals, P subwave, QRS complex and T subwave respectively in the first HMM layer where expert-annotation assisted Baum-Welch algorithm is utilized in HMM modeling. Then the corresponding interval features are selected and applied to categorize the ECG into normal type or abnormal type (PVC, APC in the second HMM layer. For verifying the effectiveness of our algorithm on abnormal signal detection, we have developed an ECG body sensor network (BSN platform, whereby real-time ECG signals are collected, transmitted, displayed and the corresponding classification outcomes are deduced and shown on the BSN screen.
Convergence of Extreme Value Statistics in a Two-Layer Quasi-Geostrophic Atmospheric Model
Vera Melinda Gálfi
2017-01-01
Full Text Available We search for the signature of universal properties of extreme events, theoretically predicted for Axiom A flows, in a chaotic and high-dimensional dynamical system. We study the convergence of GEV (Generalized Extreme Value and GP (Generalized Pareto shape parameter estimates to the theoretical value, which is expressed in terms of the partial information dimensions of the attractor. We consider a two-layer quasi-geostrophic atmospheric model of the mid-latitudes, adopt two levels of forcing, and analyse the extremes of different types of physical observables (local energy, zonally averaged energy, and globally averaged energy. We find good agreement in the shape parameter estimates with the theory only in the case of more intense forcing, corresponding to a strong chaotic behaviour, for some observables (the local energy at every latitude. Due to the limited (though very large data size and to the presence of serial correlations, it is difficult to obtain robust statistics of extremes in the case of the other observables. In the case of weak forcing, which leads to weaker chaotic conditions with regime behaviour, we find, unsurprisingly, worse agreement with the theory developed for Axiom A flows.
Critical properties of XY model on two-layer Villain-ferromagnetic lattice
Wang Yi; R. Quartu; Liu Xiao-Yan; Han Ru-Qi; Horiguchi Tsuyoshi
2004-01-01
We investigate phase transitions of the XY model on a two-layer square lattice which consists of a Villain plane(J) and a ferromagnetic plane (I), using Monte Carlo simulations and a histogram method. Depending on the values of interaction parameters (I, J), the system presents three phases: namely, a Kosterlitz-Thouless (KT) phase in which the two planes are critical for I predominant over J, a chiral phase in which the two planes have a chiral order for J predominant over I and a new phase in which only the Villain plane has a chiral order and the ferromagnetic plane is paramagnetic with a small value of chirality. We clarify the nature of phase transitions by using a finite size scaling method. We find three different kinds of transitions according to the values of (I, J): the KT transition, the Ising transition and an XY-Ising transition with v = 0.849(3). It turns out that the Ising or XY-Ising transition is associated with the disappearance of the chiral order in the Villain plane.
Powerful Amplification Cascades of FRET-Based Two-Layer Nonenzymatic Nucleic Acid Circuits.
Quan, Ke; Huang, Jin; Yang, Xiaohai; Yang, Yanjing; Ying, Le; Wang, He; Xie, Nuli; Ou, Min; Wang, Kemin
2016-06-07
Nucleic acid circuits have played important roles in biological engineering and have increasingly attracted researchers' attention. They are primarily based on nucleic acid hybridizations and strand displacement reactions between nucleic acid probes of different lengths. Signal amplification schemes that do not rely on protein enzyme show great potential in analytical applications. While the single amplification circuit often achieves linear amplification that may not meet the need for detection of target in a very small amount, it is very necessary to construct cascade circuits that allow for larger amplification of inputs. Herein, we have successfully engineered powerful amplification cascades of FRET-based two-layer nonenzymatic nucleic acid circuits, in which the outputs of catalyzed hairpin assembly (CHA) activate hybridization chain reactions (HCR) circuits to induce repeated hybridization, allowing real-time monitoring of self-assembly process by FRET signal. The cascades can yield 50000-fold signal amplification with the help of the well-designed and high-quality nucleic acid circuit amplifiers. Subsequently, with coupling of structure-switching aptamer, as low as 200 pM adenosine is detected in buffer, as well as in human serum. To our knowledge, we have for the first time realized real-time monitoring adaptation of HCR to CHA circuits and achieved amplified detection of nucleic acids and small molecules with relatively high sensitivity.
Nirmalkumar S. Reshamwala
2014-02-01
Full Text Available Long-Term Evolution (LTE is the next generation of current mobile telecommunication networks. LTE has a ?at radio-network architecture and signi?cant increase in spectrum efficiency, throughput and user capacity. In this paper, performance analysis of robust channel estimators for Downlink Long Term Evolution-Advanced (DL LTE-A system using three Artificial Neural Networks: Feed-forward neural network (FFNN, Cascade-forward neural network (CFNN and Layered Recurrent Neural Network (LRN are trained separately using Back-Propagation Algorithm and also ANN is trained by Genetic Algorithm (GA. The methods use the information got by the received reference symbols to estimate the total frequency response of the channel in two important phases. In the first phase, the proposed ANN based method learns to adapt to the channel variations, and in the second phase it estimates the channel matrix to improve performance of LTE. The performance of the estimation methods is evaluated by simulations in Vienna LTE-A DL Link Level Simulator in MATLAB software. Performance of the proposed channel estimator, ANN trained by Genetic Algorithm (ANN-GA is compared with traditional Least Square (LS algorithm and ANN based other estimator like Feed-forward neural network, Layered Recurrent Neural Network and Cascade-forward neural network for Closed Loop Spatial Multiplexing (CLSM-Single User Multi-input Multi-output (MIMO-2×2 and 4×4 in terms of throughput. Simulation result shows proposed ANN-GA gives better performance than other ANN based estimations methods and LS.
D Coordinate Transformation Using Artificial Neural Networks
Konakoglu, B.; Cakır, L.; Gökalp, E.
2016-10-01
Two coordinate systems used in Turkey, namely the ED50 (European Datum 1950) and ITRF96 (International Terrestrial Reference Frame 1996) coordinate systems. In most cases, it is necessary to conduct transformation from one coordinate system to another. The artificial neural network (ANN) is a new method for coordinate transformation. One of the biggest advantages of the ANN is that it can determine the relationship between two coordinate systems without a mathematical model. The aim of this study was to investigate the performances of three different ANN models (Feed Forward Back Propagation (FFBP), Cascade Forward Back Propagation (CFBP) and Radial Basis Function Neural Network (RBFNN)) with regard to 2D coordinate transformation. To do this, three data sets were used for the same study area, the city of Trabzon. The coordinates of data sets were measured in the ED50 and ITRF96 coordinate systems by using RTK-GPS technique. Performance of each transformation method was investigated by using the coordinate differences between the known and estimated coordinates. The results showed that the ANN algorithms can be used for 2D coordinate transformation in cases where optimum model parameters are selected.
Pruning Neural Networks with Distribution Estimation Algorithms
Cantu-Paz, E
2003-01-15
This paper describes the application of four evolutionary algorithms to the pruning of neural networks used in classification problems. Besides of a simple genetic algorithm (GA), the paper considers three distribution estimation algorithms (DEAs): a compact GA, an extended compact GA, and the Bayesian Optimization Algorithm. The objective is to determine if the DEAs present advantages over the simple GA in terms of accuracy or speed in this problem. The experiments used a feed forward neural network trained with standard back propagation and public-domain and artificial data sets. The pruned networks seemed to have better or equal accuracy than the original fully-connected networks. Only in a few cases, pruning resulted in less accurate networks. We found few differences in the accuracy of the networks pruned by the four EAs, but found important differences in the execution time. The results suggest that a simple GA with a small population might be the best algorithm for pruning networks on the data sets we tested.
Pustovalov, V. K.; Astafyeva, L. G.; Zharov, V. P.
2013-12-01
Modeling of nonlinear dependences of optical properties of spherical two-layered gold core and some material shell nanoparticles (NPs) placed in water on parameters of core and shell was carried out on the basis of the extended Mie theory. Efficiency cross-sections of absorption, scattering and extinction of radiation with wavelength 532 nm by core-shell NPs in the ranges of core radii r00=5-40 nm and of relative NP radii r1/r00=1-8 were calculated (r1-radius of two-layered nanoparticle). Shell materials were used with optical indexes in the ranges of refraction n1=0.2-1.5 and absorption k1=0-3.5 for the presentation of optical properties of wide classes of shell materials (including dielectrics, metals, polymers, vapor shell around gold core). Results show nonlinear dependences of optical properties of two-layered NPs on optical indexes of shell material, core r00 and relative NP r1/r00 radii. Regions with sharp decrease and increase of absorption, scattering and extinction efficiency cross-sections with changing of core and shell parameters were investigated. These dependences should be taken into account for applications of two-layered NPs in laser nanomedicine and optical diagnostics of tissues. The results can be used for experimental investigation of shell formation on NP core and optical determination of geometrical parameters of core and shell of two-layered NPs.
THE SEMI-GEOSTROPHIC ADAPTATION PROCESS WITH TWO-LAYER BAROCLINIC MODEL IN LOW LATITUDE ATMOSPHERE
无
2000-01-01
In this paper, the adaptation process in low latitude atmosphere is discussed by means of a two-layer baroclinic model on the equator β plane, showing that the adaptation process in low latitude is mainly dominated by the internal inertial gravity waves. The initial ageostrophic energy is dispersed by the internal inertial gravity waves, and as a result, the geostrophic motion is obtained in zonal direction while the ageostrophic motion maintains in meridional direction, which can be called semi-geostrophic balance in barotropic model as well as semi-thermal-wind balance in baroclinic model. The vertical motion is determined both by the distribution of the initial vertical motion and that of the initial vertical motion tendency, but it is unrelated to the initial potential vorticity. Finally, the motion tends to be horizontal. The discussion of the physical mechanism of the semi-thermal-wind balance in low latitude atmosphere shows that the achievement of the semi-thermal-wind balance is due to the adjustment between the stream field and the temperature field through the horizontal convergence and divergence which is related to the vertical motion excited by the internal inertial gravity waves. The terminal adaptation state obtained shows that the adaptation direction between the mean temperature field and the shear flow field is determined by the ratio of the scale of the initial ageostrophic disturbance to the scale of one character scale related to the baroclinic Rossby radius of deformation. The shear stream field adapts to the mean temperature field when the ratio is greater than 1, and the mean temperature field adapts to the shear stream field when the ratio is smaller than 1.
Aitova, E. V.; Bratsun, D. A.; Kostarev, K. G.; Mizev, A. I.; Mosheva, E. A.
2016-12-01
The development of convective instability in a two-layer system of miscible fluids placed in a narrow vertical gap has been studied theoretically and experimentally. The upper and lower layers are formed with aqueous solutions of acid and base, respectively. When the layers are brought into contact, the frontal neutralization reaction begins. We have found experimentally a new type of convective instability, which is characterized by the spatial localization and the periodicity of the structure observed for the first time in the miscible systems. We have tested a number of different acid-base systems and have found a similar patterning there. In our opinion, it may indicate that the discovered effect is of a general nature and should be taken into account in reaction-diffusion-convection problems as another tool with which the reaction can govern the movement of the reacting fluids. We have shown that, at least in one case (aqueous solutions of nitric acid and sodium hydroxide), a new type of instability called as the concentration-dependent diffusion convection is responsible for the onset of the fluid flow. It arises when the diffusion coefficients of species are different and depend on their concentrations. This type of instability can be attributed to a variety of double-diffusion convection. A mathematical model of the new phenomenon has been developed using the system of reaction-diffusion-convection equations written in the Hele-Shaw approximation. It is shown that the instability can be reproduced in the numerical experiment if only one takes into account the concentration dependence of the diffusion coefficients of the reagents. The dynamics of the base state, its linear stability and nonlinear development of the instability are presented. It is also shown that by varying the concentration of acid in the upper layer one can achieve the occurrence of chemo-convective solitary cell in the bulk of an almost immobile fluid. Good agreement between the
Global chaotization of fluid particle trajectories in a sheared two-layer two-vortex flow
Ryzhov, Evgeny A., E-mail: ryzhovea@poi.dvo.ru [Pacific Oceanological Institute of FEB RAS, 43, Baltiyskaya Street, Vladivostok 690041 (Russian Federation); Koshel, Konstantin V., E-mail: kvkoshel@poi.dvo.ru [Pacific Oceanological Institute of FEB RAS, 43, Baltiyskaya Street, Vladivostok 690041 (Russian Federation); Far Eastern Federal University, 8, Sukhanova Street, Vladivostok 690950 (Russian Federation)
2015-10-15
In a two-layer quasi-geostrophic approximation, we study the irregular dynamics of fluid particles arising due to two interacting point vortices embedded in a deformation flow consisting of shear and rotational components. The two vortices are arranged within the bottom layer, but an emphasis is on the upper-layer fluid particle motion. Vortices moving in one layer induce stirring of passive scalars in the other layer. This is of interest since point vortices induce singular velocity fields in the layer they belong to; however, in the other layer, they induce regular velocity fields that generally result in a change in passive particle stirring. If the vortices are located at stagnation points, there are three different types of the fluid flow. We examine how properties of each flow configuration are modified if the vortices are displaced from the stagnation points and thus circulate in the immediate vicinity of these points. To that end, an analysis of the steady-state configurations is presented with an emphasis on the frequencies of fluid particle oscillations about the elliptic stagnation points. Asymptotic relations for the vortex and fluid particle zero–oscillation frequencies are derived in the vicinity of the corresponding elliptic points. By comparing the frequencies of fluid particles with the ones of the vortices, relations between the parameters that lead to enhanced stirring of fluid particles are established. It is also demonstrated that, if the central critical point is elliptic, then the fluid particle trajectories in its immediate vicinity are mostly stable making it harder for the vortex perturbation to induce stirring. Change in the type of the central point to a hyperbolic one enhances drastically the size of the chaotic dynamics region. Conditions on the type of the central critical point also ensue from the derived asymptotic relations.
Lukas Falat
2014-01-01
Full Text Available In this paper, authors apply feed-forward artificial neural network (ANN of RBF type into the process of modelling and forecasting the future value of USD/CAD time series. Authors test the customized version of the RBF and add the evolutionary approach into it. They also combine the standard algorithm for adapting weights in neural network with an unsupervised clustering algorithm called K-means. Finally, authors suggest the new hybrid model as a combination of a standard ANN and a moving average for error modeling that is used to enhance the outputs of the network using the error part of the original RBF. Using high-frequency data, they examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, authors perform the comparative out-of-sample analysis of the suggested hybrid model with statistical models and the standard neural network.
B. Mondal
2015-06-01
Full Text Available Artificial Neural Network (ANN based pattern recognition technique is used for ensuring the reliable evaluation of responses from an array of Zinc Oxide (ZnO based sensors comprising of pure ZnO nano-rods and composites of ZnO–SnO2. All the sensors were fabricated in the lab. The paper first reports the development of an artificial neural network based model for successfully recognizing different concentration of hydrogen, methane and carbon mono-oxide. Feed forward back propagation neural network was used for the classification of the gases at critical concentrations. The optimized ANN algorithm is then embedded in the microcontroller based circuit and finally verified under lab conditions.
ZHANG; Renhua; SUN; Xiaomin; WANG; Weimin; XU; Jinping; ZH
2005-01-01
Based on the improved interaction mechanism of two-layer model, this paper proposed Pixel Component Arranging and Comparing Algorithm (PCACA) and theoretically positioning algorithm, estimated the true temperature of mixed pixel in four extreme points in combination with the measurements of dry and wet points in calibration fields and improved the reliability of positioning dry and wet line. A new two-layer energy-separation algorithm was proposed,which was simple and direct without resistance network parameters for each pixel. We also proposed a new thought about the effect of advection. The albedo of mixed pixel was also separated with PCACA. In combination with two-layer energy-separation algorithm, the net radiation of mixed pixel was separated to overcome the uncertainty of conventional energy-separation algorithm using Beer's Law. Through the validation of retrieval result, this method is proved to be feasible and operational. At the same time, the uncertainty of this algorithm was objectively analyzed.
A Deep Web Query Interfaces Classification Method Based on RBF Neural Network
YUAN Fang; ZHAO Yao; ZHOU Xu
2007-01-01
This paper proposes a new approach for classification for query interfaces of Deep Web, which extracts features from the form's text data on the query interfaces, assisted with the synonym library, and uses radial basic function neural network (RBFNN) algorithm to classify the query interfaces. The applied RBFNN is a kind of effective feed-forward artificial neural network, which has a simple networking structure but features with strength of excellent nonlinear approximation, fast convergence and global convergence. A TEL_8 query interfaces' data set from UIUC on-line database is used in our experiments, which consists of 477 query interfaces in 8 typical domains. Experimental results proved that the proposed approach can efficiently classify the query interfaces with an accuracy of 95.67%.
S.Praveena
2015-06-01
Full Text Available This paper presents a hybrid clustering algorithm and feed-forward neural network classifier for land-cover mapping of trees, shade, building and road. It starts with the single step preprocessing procedure to make the image suitable for segmentation. The pre-processed image is segmented using the hybrid genetic-Artificial Bee Colony(ABC algorithm that is developed by hybridizing the ABC and FCM to obtain the effective segmentation in satellite image and classified using neural network . The performance of the proposed hybrid algorithm is compared with the algorithms like, k-means, Fuzzy C means(FCM, Moving K-means, Artificial Bee Colony(ABC algorithm, ABC-GA algorithm, Moving KFCM and KFCM algorithm.
Kolla, Sri R; Altman, Shawn D
2007-04-01
This paper presents results from the implementation and testing of a PC based monitoring and fault identification scheme for a three-phase induction motor using artificial neural networks (ANNs). To accomplish the task, a hardware system is designed and built to acquire three-phase voltages and currents from a 1/3 HP squirrel-cage, three-phase induction motor. A software program is written to read the voltages and currents, which are first used to train a feed-forward neural network structure using the JavaNNS program. The trained network is placed in a LabVIEW based program formula node that monitors the voltages and currents online and displays the fault conditions and turns the motor off. The complete system is successfully tested in real time by creating different faults on the motor.
Eswari J, Satya; Chandrakar, Neha [National Institute of Technology Raipur, Raipur (India)
2016-04-15
Artificial neural networks (ANNs) can be used to develop a technique to classify lymph node negative breast cancer that is prone to distant metastases based on gene expression signatures. The neural network used is a multilayered feed forward network that employs back propagation algorithm. Once trained with DNA microarraybased gene expression profiles of genes that were predictive of distant metastasis recurrence of lymph node negative breast cancer, the ANNs became capable of correctly classifying all samples and recognizing the genes most appropriate to the classification. To test the ability of the trained ANN models in recognizing lymph node negative breast cancer, we analyzed additional idle samples that were not used beforehand for the training procedure and obtained the correctly classified result in the validation set. For more substantial result, bootstrapping of training and testing dataset was performed as external validation. This study illustrates the potential application of ANN for breast tumor diagnosis and the identification of candidate targets in patients for therapy.
Daniel Madan Raja S,
2011-02-01
Full Text Available In this paper we are trying to classify a war scene from the natural scene. For this purpose two set of image categories are taken viz., opencountry & war tank. By using Invariant Moments and Gray LevelCo-occurrence Matrix (GLCM, features are extracted from the images. The extracted features are trained and tested with Artificial Neural Networks (ANN using feed forward back propagation algorithm. The comparative results are proving efficiency of Artificial Neural Networks towards war scene classification problems by using Gray Level Co-occurrence Matrix (GLCM feature extraction method. It can be concluded that the proposed work significantly and directly contributes to scene classification and its new applications. The complete work is experimented in Matlab 7.6.0 using real world dataset.
Fuzzy Optimization of an Elevator Mechanism Applying the Genetic Algorithm and Neural Networks
无
2005-01-01
Considering the indefinite character of the value of design parameters and being satisfied with load-bearing capacity and stiffness, the fuzzy optimization mathematical model is set up to minimize the volume of tooth corona of a worm gear in an elevator mechanism. The method of second-class comprehensive evaluation was used based on the optimal level cut set, thus the optimal level value of every fuzzy constraint can be attained; the fuzzy optimization is transformed into the usual optimization.The Fast Back Propagation of the neural networks algorithm are adopted to train feed-forward networks so as to fit a relative coefficient. Then the fitness function with penalty terms is built by a penalty strategy, a neural networks program is recalled, and solver functions of the Genetic Algorithm Toolbox of Matlab software are adopted to solve the optimization model.
Maulidah, Rifa'atul; Purqon, Acep
2016-08-01
Mendong (Fimbristylis globulosa) has a potentially industrial application. We investigate a predictive model for heat and mass transfer in drying kinetics during drying a Mendong. We experimentally dry the Mendong by using a microwave oven. In this study, we analyze three mathematical equations and feed forward neural network (FNN) with back propagation to describe the drying behavior of Mendong. Our results show that the experimental data and the artificial neural network model has a good agreement and better than a mathematical equation approach. The best FNN for the prediction is 3-20-1-1 structure with Levenberg- Marquardt training function. This drying kinetics modeling is potentially applied to determine the optimal parameters during mendong drying and to estimate and control of drying process.
SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
Graff, Philip; Hobson, Michael P; Lasenby, Anthony N
2013-01-01
We present the first public release of our generic neural network training algorithm, called SKYNET. This efficient and robust machine-learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as regression, classification, density estimation, clustering and dimensionality reduction. SKYNET uses a powerful 'pre-training' method, to obtain a set of network parameters close to the true global maximum of the training objective function, followed by further optimisation using an automatically-regularised variant of Newton's method; the latter uses second-order derivative information to improve convergence, but without the need to evaluate or store the full Hessian matrix, by using a fast approximate method to calculate Hessian-vector products. This combination of methods allows for the training of complicated networks that are difficult to optimise using standard backpropagation techniques....
Sunday Olusanya Olatunji
2013-10-01
Full Text Available In this work, a new identification model, based on extreme learning machine (ELM, to better identify Erythemato – Squamous skin diseases have been proposed and implemented and the results compared to that of the classical artificial neural network (ANN. ELMs provide solutions to single- and multi- hidden layer feed-forward neural networks. ELMs can achieve high learning speed, good generalization performance, and ease of implementation. Experimental results indicated that ELM outperformed the classical ANN in all fronts both for the training and testing cases. The effect of varying size of training and testing set on the performance of classifiers were also investigated in this study. The proposed classifier demonstrated to be a viable tool in this germane field of medical diagnosis as indicated by its high accuracy and consistency of result.
Manipulator inverse kinematics control based on particle swarm optimization neural network
Wen, Xiulan; Sheng, Danghong; Guo, Jing
2008-10-01
The inverse kinematics control of a robotic manipulator requires solving non-linear equations having transcendental functions and involving time-consuming calculations. Particle Swarm Optimization (PSO), which is based on the behaviour of insect swarms and exploits the solution space by taking into account the experience of the single particle as well as that of the entire swarm, is similar to the genetic algorithm (GA) in that it performs a structured randomized search of an unknown parameter space by manipulating a population of parameter estimates to converge on a suitable solution. In this paper, PSO is firstly proposed to optimize feed-forward neural network for manipulator inverse kinematics. Compared with the results of the fast back propagation learning algorithm (FBP), conventional GA genetic algorithm based elitist reservation (EGA), improved GA (IGA) and immune evolutionary computation (IEC), the simulation results verify the particle swarm optimization neural network (PSONN) is effective for manipulator inverse kinematics control.
Bunnoon, Pituk; Chalermyanont, Kusumal; Limsakul, Chusak
2010-02-01
This paper proposed the discrete transform and neural network algorithms to obtain the monthly peak load demand in mid term load forecasting. The mother wavelet daubechies2 (db2) is employed to decomposed, high pass filter and low pass filter signals from the original signal before using feed forward back propagation neural network to determine the forecasting results. The historical data records in 1997-2007 of Electricity Generating Authority of Thailand (EGAT) is used as reference. In this study, historical information of peak load demand(MW), mean temperature(Tmean), consumer price index (CPI), and industrial index (economic:IDI) are used as feature inputs of the network. The experimental results show that the Mean Absolute Percentage Error (MAPE) is approximately 4.32%. This forecasting results can be used for fuel planning and unit commitment of the power system in the future.
Mona A. Hagras
2013-08-01
Full Text Available In the present study, Artificial Neural Networks (ANNs with different topologies have been evaluated to be used to predict hydrodynamic coefficients of permeable paneled breakwater. Two neural network models are constructed, one to predict wave transmission coefficient (Kt and another for the prediction of wave reflectioncoefficient (Kr. Back propagation algorithm was used to train a multi-layer feed-forward network (Levenberg Marquardt algorithm. The capability of ANN topologies to estimate these coefficients is evaluated using the Mean Squared Error (MSE. Based on training patterns of different ANNs, a 5-7-1 topology has been selected topredict both coefficients. The results of the developed ANN models proved that this technique is reliable in such field. A good match between the measured and predicted values was observed with correlation values varying in the range (0.9508-0.9805 for the training set and (0.9159-0.9877 for the testing set.
Artificial Neural Network based Body Posture Classification from EMG signal analysis
Rajesh Kumar Tripathy
2013-04-01
Full Text Available This paper deals with the body posture Classification from EMG signal analysis using artificial neural network (ANN. The various statistical features extracted from each EMG signal corresponding to different muscles associated with the different body postures are framed using LABVIEW software. Further-more, these features are taken as the input towards the ANN classifier and thus the corresponding output for the respective classifier predicts the postures like Bowing, Handshaking, and Hugging. The performance of the classifier is determined by the classification rate (CR. The outcome of result indicates that the CR of Multilayer Feed Forward Neural Network (MFNN type of ANN is rounded up to a percentage of 71.02%.
An artificial neural network based $b$ jet identification algorithm at the CDF Experiment
Freeman, J; Ketchum, W; Poprocki, S; Pronko, A; Rusu, V; Wittich, P
2011-01-01
We present the development and validation of a new multivariate $b$ jet identification algorithm ("$b$ tagger") used at the CDF experiment at the Fermilab Tevatron. At collider experiments, $b$ taggers allow one to distinguish particle jets containing $B$ hadrons from other jets. Employing feed-forward neural network architectures, this tagger is unique in its emphasis on using information from individual tracks. This tagger not only contains the usual advantages of a multivariate technique such as maximal use of information in a jet and tunable purity/efficiency operating points, but is also capable of evaluating jets with only a single track. To demonstrate the effectiveness of the tagger, we employ a novel method wherein we calculate the false tag rate and tag efficiency as a function of the placement of a lower threshold on a jet's neural network output value in $Z+1$ jet and $t\\bar{t}$ candidate samples, rich in light flavor and $b$ jets, respectively.
THE USE OF NEURAL NETWORK TECHNOLOGY TO MODEL SWIMMING PERFORMANCE
António José Silva
2007-03-01
Full Text Available The aims of the present study were: to identify the factors which are able to explain the performance in the 200 meters individual medley and 400 meters front crawl events in young swimmers, to model the performance in those events using non-linear mathematic methods through artificial neural networks (multi-layer perceptrons and to assess the neural network models precision to predict the performance. A sample of 138 young swimmers (65 males and 73 females of national level was submitted to a test battery comprising four different domains: kinanthropometric evaluation, dry land functional evaluation (strength and flexibility, swimming functional evaluation (hydrodynamics, hydrostatic and bioenergetics characteristics and swimming technique evaluation. To establish a profile of the young swimmer non-linear combinations between preponderant variables for each gender and swim performance in the 200 meters medley and 400 meters font crawl events were developed. For this purpose a feed forward neural network was used (Multilayer Perceptron with three neurons in a single hidden layer. The prognosis precision of the model (error lower than 0.8% between true and estimated performances is supported by recent evidence. Therefore, we consider that the neural network tool can be a good approach in the resolution of complex problems such as performance modeling and the talent identification in swimming and, possibly, in a wide variety of sports
Model of Information Security Risk Assessment based on Improved Wavelet Neural Network
Gang Chen
2013-09-01
Full Text Available This paper concentrates on the information security risk assessment model utilizing the improved wavelet neural network. The structure of wavelet neural network is similar to the multi-layer neural network, which is a feed-forward neural network with one or more inputs. Afterwards, we point out that the training process of wavelet neural networks is made up of four steps until the value of error function can satisfy a pre-defined error criteria. In order to enhance the quality of information security risk assessment, we proposed a modified version of wavelet neural network which can effectively combine all influencing factors in assessing information security risk by linear integrating several weights. Furthermore, the proposed wavelet neural network is trained by the BP algorithm with batch mode, and the weight coefficients of the wavelet are modified with the adopting mode. Finally, a series of experiments are conduct to make performance evaluation. From the experimental results, we can see that the proposed model can assess information security risk accurately and rapidly
Tsang, L.; Kong, J. A.
1974-01-01
With applications to geophysical subsurface probings, electromagnetic fields due to a horizontal electric dipole laid on the surface of a two-layer medium are solved by a combination of analytic and numerical methods. Interference patterns are calculated for various layer thickness. The results are interpreted in terms of normal modes, and the accuracies of the methods are discussed.
Abakarova, D S
2007-01-01
Characteristics of the main components of a new effective long-lasting dosage form--biopolymer two-layer adhesive solcoseryl containing film Diplen-denta C--are presented. It has a potent wound-healing action on oral mucosa, retains therapeutic properties during long time, is self dissolving and can be easily fixed on oral mucous membrane.
Lai, Yen-Shou; Tsai, Hung-Hsu; Yu, Pao-Ta
2011-01-01
This paper proposes a new presentation system integrating a Microsoft PowerPoint presentation in a two-layer method, called the TL system, to promote learning in a physical classroom. With the TL system, teachers can readily control hints or annotations as a way of making them visible or invisible to students so as to reduce information load. In…
Cotter, C.J.; Frank, J.E.; Reich, S.
2004-01-01
We develop a particle-mesh method for two-layer shallow-water equations subject to the rigid-lid approximation. The method is based on the recently proposed Hamiltonian particle-mesh (HPM) method and the interpretation of the rigid-lid approximation as a set of holonomic constraints. The suggested s
Neural Network Based State of Health Diagnostics for an Automated Radioxenon Sampler/Analyzer
Keller, Paul E.; Kangas, Lars J.; Hayes, James C.; Schrom, Brian T.; Suarez, Reynold; Hubbard, Charles W.; Heimbigner, Tom R.; McIntyre, Justin I.
2009-05-13
Artificial neural networks (ANNs) are used to determine the state-of-health (SOH) of the Automated Radioxenon Analyzer/Sampler (ARSA). ARSA is a gas collection and analysis system used for non-proliferation monitoring in detecting radioxenon released during nuclear tests. SOH diagnostics are important for automated, unmanned sensing systems so that remote detection and identification of problems can be made without onsite staff. Both recurrent and feed-forward ANNs are presented. The recurrent ANN is trained to predict sensor values based on current valve states, which control air flow, so that with only valve states the normal SOH sensor values can be predicted. Deviation between modeled value and actual is an indication of a potential problem. The feed-forward ANN acts as a nonlinear version of principal components analysis (PCA) and is trained to replicate the normal SOH sensor values. Because of ARSA’s complexity, this nonlinear PCA is better able to capture the relationships among the sensors than standard linear PCA and is applicable to both sensor validation and recognizing off-normal operating conditions. Both models provide valuable information to detect impending malfunctions before they occur to avoid unscheduled shutdown. Finally, the ability of ANN methods to predict the system state is presented.
邱长青; 黄声华
2015-01-01
四象限级联型变频器功率单元 H 桥的瞬时输出功率以2倍和4倍频率脉动，使得直流母线产生2次和4次纹波电压。单个功率单元输入端PWM整流器采用前馈控制策略能有效抑制母线电压波动，且总的并网电流无低次谐波。从功率单元的数学模型出发，推导出输入输出的瞬时有功功率，提出了基于瞬时 abc 理论的瞬时有功电流前馈控制来抑制直流母线电压波动，同时建立了基于Kalman滤波的负载电流估计模型。最后通过功率单元实验测试，验证了控制策略的可行性。%The instantaneous output power of the power cell H-bridge in four-quadrant cascade converter pulsates at twice and quadruple the output frequency, generating the second and fourth harmonic DC bus voltage. Using feed-forward control scheme in PWM rectifier of single power cell can effectively restrain DC bus voltage ripple and make the total grid-connected current without low-order harmonics. From the mathematical model of power cell, the instantaneous active power is derived. Based on instantaneous abc theory, instantaneous active current feed-forward control have been proposed to restrain the DC bus voltage ripple. Moreover, load current estimation model based on Kalman theory is established. Finally, the experimental results are given to prove the effectiveness of the proposed control scheme.
姚兴佳; 刘玥; 郭庆鼎
2012-01-01
依据风速特性及桨叶的空气动力学分析得到独立变桨距控制的基本控制规律,提出基于前馈补偿的方位角权系数分程独立变桨距控制,此控制方法采用方位角权系数分配分别对3个桨叶的桨距角进行调整,实现独立变桨距控制,然后根据前馈补偿理论对变桨距过程进行分程独立变桨距控制.在Matlab中进行仿真.仿真结果表明,该控制方法不仅可实现风力机的独立变桨,在稳定输出功率的同时减小桨叶的拍打振动,且可避免由于全程独立变桨距桨叶调节频繁所引起的电动变桨执行电机因过热损坏的问题.控制方法简单,更适合用于独立动作的电动变桨距执行机构.%The individual control law was obtained by analyzing of wind characteristics and wind turbine aerodynamics.A control method for split range individual pitch was proposed based on feed-forward compensator azimuth angle weight number assignment.The separate distribution for pitch angle of blades using azimuth angle weight number assignment was adopted to achieve individual pitch control.Then,the split range individual pitch control with feed-forward compensator was used to control wind turbine.The simulation results show that this control strategy can make the output power keep stable and the flapwise fluctuation be reduced at the same time.Moreover,the method can prevent the blades from adjusting frequently and the actuator motor superheating damage.The method is easy to control and more suitable for electric pitch regulated mechanism.
Analysis of surface ozone using a recurrent neural network.
Biancofiore, Fabio; Verdecchia, Marco; Di Carlo, Piero; Tomassetti, Barbara; Aruffo, Eleonora; Busilacchio, Marcella; Bianco, Sebastiano; Di Tommaso, Sinibaldo; Colangeli, Carlo
2015-05-01
Hourly concentrations of ozone (O₃) and nitrogen dioxide (NO₂) have been measured for 16 years, from 1998 to 2013, in a seaside town in central Italy. The seasonal trends of O₃ and NO₂ recorded in this period have been studied. Furthermore, we used the data collected during one year (2005), to define the characteristics of a multiple linear regression model and a neural network model. Both models are used to model the hourly O₃ concentration, using, two scenarios: 1) in the first as inputs, only meteorological parameters and 2) in the second adding photochemical parameters at those of the first scenario. In order to evaluate the performance of the model four statistical criteria are used: correlation coefficient, fractional bias, normalized mean squared error and a factor of two. All the criteria show that the neural network gives better results, compared to the regression model, in all the model scenarios. Predictions of O₃ have been carried out by many authors using a feed forward neural architecture. In this paper we show that a recurrent architecture significantly improves the performances of neural predictors. Using only the meteorological parameters as input, the recurrent architecture shows performance better than the multiple linear regression model that uses meteorological and photochemical data as input, making the neural network model with recurrent architecture a more useful tool in areas where only weather measurements are available. Finally, we used the neural network model to forecast the O₃ hourly concentrations 1, 3, 6, 12, 24 and 48 h ahead. The performances of the model in predicting O₃ levels are discussed. Emphasis is given to the possibility of using the neural network model in operational ways in areas where only meteorological data are available, in order to predict O₃ also in sites where it has not been measured yet. Copyright © 2015 Elsevier B.V. All rights reserved.
敬刘凯; 吴文伟; 翁震平
2014-01-01
文章针对浮筏隔振系统低频线谱噪声，设计了基于x-LMS算法的自适应前馈控制律的主动吸振控制方案，采用导纳综合方法仿真分析了浮筏隔振系统在多通道主动动力吸振装置作用下的振动控制效果。仿真结果表明，带主动动力吸振器的浮筏隔振系统对低频线谱振动有着较好的控制效果。%To improve the isolation performance of the conventional floating raft system, active dynamic vi-bration absorbers (AVAs) were applied, and an evaluation function about reducing the sum of mean square error of vibration response of four observation points which were located on the flexible foundation of float-ing raft system with AVAs was formatted. With this objective function and based on filtered x-LMS algo-rithm, the multi-channel self-adaptive feed forward law for the floating raft system with AVAs was designed and simulated. The simulation result shows that it is effective to use the floating raft system with AVAs for reducing the vibration of mechanical device at low frequency.
Precipitation Nowcast using Deep Recurrent Neural Network
Akbari Asanjan, A.; Yang, T.; Gao, X.; Hsu, K. L.; Sorooshian, S.
2016-12-01
An accurate precipitation nowcast (0-6 hours) with a fine temporal and spatial resolution has always been an important prerequisite for flood warning, streamflow prediction and risk management. Most of the popular approaches used for forecasting precipitation can be categorized into two groups. One type of precipitation forecast relies on numerical modeling of the physical dynamics of atmosphere and another is based on empirical and statistical regression models derived by local hydrologists or meteorologists. Given the recent advances in artificial intelligence, in this study a powerful Deep Recurrent Neural Network, termed as Long Short-Term Memory (LSTM) model, is creatively used to extract the patterns and forecast the spatial and temporal variability of Cloud Top Brightness Temperature (CTBT) observed from GOES satellite. Then, a 0-6 hours precipitation nowcast is produced using a Precipitation Estimation from Remote Sensing Information using Artificial Neural Network (PERSIANN) algorithm, in which the CTBT nowcast is used as the PERSIANN algorithm's raw inputs. Two case studies over the continental U.S. have been conducted that demonstrate the improvement of proposed approach as compared to a classical Feed Forward Neural Network and a couple simple regression models. The advantages and disadvantages of the proposed method are summarized with regard to its capability of pattern recognition through time, handling of vanishing gradient during model learning, and working with sparse data. The studies show that the LSTM model performs better than other methods, and it is able to learn the temporal evolution of the precipitation events through over 1000 time lags. The uniqueness of PERSIANN's algorithm enables an alternative precipitation nowcast approach as demonstrated in this study, in which the CTBT prediction is produced and used as the inputs for generating precipitation nowcast.
Markopoulos, Angelos P.; Georgiopoulos, Sotirios; Manolakos, Dimitrios E.
2016-03-01
Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same problem. More specifically, feed-forward artificial neural networks are trained with three different back propagation algorithms, namely the adaptive back propagation algorithm of the steepest descent with the use of momentum term, the back propagation Levenberg-Marquardt algorithm and the back propagation Bayesian algorithm. Moreover, radial basis function neural networks are examined. All the aforementioned algorithms are used for the prediction of surface roughness in milling, trained with the same input parameters and output data so that they can be compared. The advantages and disadvantages, in terms of the quality of the results, computational cost and time are identified. An algorithm for the selection of the spread constant is applied and tests are performed for the determination of the neural network with the best performance. The finally selected neural networks can satisfactorily predict the quality of the manufacturing process performed, through simulation and input-output surfaces for combinations of the input data, which correspond to milling cutting conditions.
A neural network device for on-line particle identification in cosmic ray experiments
Scrimaglio, R. E-mail: renato.scrimaglio@aquila.infn.it; Finetti, N.; D' Altorio, L.; Rantucci, E.; Raso, M.; Segreto, E.; Tassoni, A.; Cardarilli, G.C
2004-05-21
On-line particle identification is one of the main goals of many experiments in space both for rare event studies and for optimizing measurements along the orbital trajectory. Neural networks can be a useful tool for signal processing and real time data analysis in such experiments. In this document we report on the performances of a programmable neural device which was developed in VLSI analog/digital technology. Neurons and synapses were accomplished by making use of Operational Transconductance Amplifier (OTA) structures. In this paper we report on the results of measurements performed in order to verify the agreement of the characteristic curves of each elementary cell with simulations and on the device performances obtained by implementing simple neural structures on the VLSI chip. A feed-forward neural network (Multi-Layer Perceptron, MLP) was implemented on the VLSI chip and trained to identify particles by processing the signals of two-dimensional position-sensitive Si detectors. The radiation monitoring device consisted of three double-sided silicon strip detectors. From the analysis of a set of simulated data it was found that the MLP implemented on the neural device gave results comparable with those obtained with the standard method of analysis confirming that the implemented neural network could be employed for real time particle identification.
AN INTELLIGENT CONTROL SYSTEM BASED ON RECURRENT NEURAL FUZZY NETWORK AND ITS APPLICATION TO CSTR
JIA Li; YU Jinshou
2005-01-01
In this paper, an intelligent control system based on recurrent neural fuzzy network is presented for complex, uncertain and nonlinear processes, in which a recurrent neural fuzzy network is used as controller (RNFNC) to control a process adaptively and a recurrent neural network based on recursive predictive error algorithm (RNNM) is utilized to estimate the gradient information (ey)/(e)u for optimizing the parameters of controller.Compared with many neural fuzzy control systems, it uses recurrent neural network to realize the fuzzy controller. Moreover, recursive predictive error algorithm (RPE) is implemented to construct RNNM on line. Lastly, in order to evaluate the performance of theproposed control system, the presented control system is applied to continuously stirred tank reactor (CSTR). Simulation comparisons, based on control effect and output error,with general fuzzy controller and feed-forward neural fuzzy network controller (FNFNC),are conducted. In addition, the rates of convergence of RNNM respectively using RPE algorithm and gradient learning algorithm are also compared. The results show that the proposed control system is better for controlling uncertain and nonlinear processes.
Artificial Neural Network Analysis in Preclinical Breast Cancer
Gholamreza Motalleb
2013-01-01
Full Text Available Objective: In this study, artificial neural network (ANN analysis of virotherapy in preclinical breast cancer was investigated.Materials and Methods: In this research article, a multilayer feed-forward neural network trained with an error back-propagation algorithm was incorporated in order to develop a predictive model. The input parameters of the model were virus dose, week and tamoxifen citrate, while tumor weight was included in the output parameter. Two different training algorithms, namely quick propagation (QP and Levenberg-Marquardt (LM, were used to train ANN.Results: The results showed that the LM algorithm, with 3-9-1 arrangement is more efficient compared to QP. Using LM algorithm, the coefficient of determination (R2 between the actual and predicted values was determined as 0.897118 for all data.Conclusion: It can be concluded that this ANN model may provide good ability to predict the biometry information of tumor in preclinical breast cancer virotherapy. The results showed that the LM algorithm employed by Neural Power software gave the better performance compared with the QP and virus dose, and it is more important factor compared to tamoxifen and time (week.
Estimating Type Ia Supernova Metallicities Using Neural Networks
Villar, V. Ashley
2017-01-01
Normal Type Ia supernovae (SNe) can be used as standardizable candles because their progenitors, white dwarfs, are a fairly homogenous class of objects. However, intrinsic variability in these events arise from a number of factors, including metallicity. Recent studies have investigated the effects of metallicity on Type Ia SNe observables from both a theoretical approach, by tuning model metallicity to analyze spectral features, and an observational approach, by studying the effect of host metallicity on light curves. In this work, we take a new, data-driven approach to the problem. Inspired by the success of neural networks in the field of image processing, we aim to estimate the metallicities of Type Ia SNe progenitors from their near-maximum spectra using feed-forward neural networks. We first collect a sample of near-maximum Type Ia SNe spectra from the literature to be smoothed and down-sampled. We then estimate the metallicities of the SNe hosts using the B-band magnitudes. We build a multilayer perceptron to generate a model that takes as input the down-sampled spectra and returns a scalar metallicity. Finally, we discuss basic considerations to be taken when working with spectral (as opposed to image) data using neural networks.
Software Aging Analysis of Web Server Using Neural Networks
G.Sumathi
2012-05-01
Full Text Available Software aging is a phenomenon that refers to progressive performance degradation or transient failures or even crashes in long running software systems such as web servers. It mainly occurs due to the deterioration of operating system resource, fragmentation and numerical error accumulation. A primitive method to fight against software aging is software rejuvenation. Software rejuvenation is a proactive fault management technique aimed at cleaning up the system internal state to prevent the occurrence of more severe crash failures in the future. It involves occasionally stopping the running software, cleaning its internal state and restarting it. An optimized schedule for performing the software rejuvenation has to be derived in advance because a long running application could not be put down now and then as it may lead to waste of cost. This paper proposes a method to derive an accurate and optimized schedule for rejuvenation of a web server (Apache by using Radial Basis Function (RBF based Feed Forward Neural Network, a variant of Artificial Neural Networks (ANN. Aging indicators are obtained through experimental setup involving Apache web server and clients, which acts as input to the neural network model. This method is better than existing ones because usage of RBF leads to better accuracy and speed in convergence.
Bergmann, B.; Caicedo, I.; Leroy, C.; Pospisil, S.; Vykydal, Z.
2016-10-01
A two-layer pixel detector setup (ATLAS-TPX), designed for thermal and fast neutron detection and radiation field characterization is presented. It consists of two segmented silicon detectors (256 × 256 pixels, pixel pitch 55 μm, thicknesses 300 μm and 500 μm) facing each other. To enhance the neutron detection efficiency a set of converter layers is inserted in between these detectors. The pixelation and the two-layer design allow a discrimination of neutrons against γs by pattern recognition and against charged particles by using the coincidence and anticoincidence information. The neutron conversion and detection efficiencies are measured in a thermal neutron field and fast neutron fields with energies up to 600 MeV. A Geant4 simulation model is presented, which is validated against the measured detector responses. The reliability of the coincidence and anticoincidence technique is demonstrated and possible applications of the detector setup are briefly outlined.
Lucie Zarybnicka
2016-01-01
Full Text Available The present work deals with the surface modification of a commercial microfiltration poly(ethersulfone membrane by graft polymerization technique. Poly(styrene-co-divinylbenzene-co-4-vinylbenzylchloride surface layer was covalently attached onto the poly(ethersulfone support layer to improve the membrane electrochemical properties. Followed by amination, a two-layer anion-exchange membrane was prepared. The effect of surface layer treatment using the extraction in various solvents on membrane morphological and electrochemical characteristics was studied. The membranes were tested from the point of view of water content, ion-exchange capacity, specific resistance, permselectivity, FT-IR spectroscopy, and SEM analysis. It was found that the two-layer anion-exchange membranes after the extraction using tetrahydrofuran or toluene exhibited smooth and porous surface layer, which resulted in improved ion-exchange capacity, electrical resistance, and permselectivity of the membranes.
ZHANG Yunqing; GUO Zhiying; DONG Xianghuai; LI Dequn
2008-01-01
Tensile properties of automotive needlepunched carpets made up of two layers of different materials (a fabric layer and a foam layer) in their thermoforming temperatures ranges with or without heat dispersion were discussed. Effects of forming temperature, extensile speed and fiber orientation on the tensile properties were studied based on an orthogonal experiment design. The experimental results show that automotive carpets are rate-dependent anisotropic materials and more strongly depend on forming temperature than the extensile speed and fiber orientation. Furthermore,contributions of the fabric layer and the foam layer to the overall tensile performance were investigated by comparing the tensile results of single fabric layer with those of the overall carpet. Both the fabric layer and the foam layer show positive effects on the overall tensile strength which is the combination of the two layers' tensile strength and independent of temperature, extensile speed and fiber orientation.On the other hand, their influences on the overall deformation are relatively complicated.
Yong Deng; Qiang Lu; Qingming Luo
2006-01-01
We report a new method for measuring particle size distribution (PSD) and refractive index of the top layer in a two-layer tissue phantom simulated epithelium tissue by varying the azimuth angle of incident linearly polarized light. The polarization gating technique is used to decouple the single and multiple scattering components in the returned signal. The theoretical model based on Mie theory is presented and a nonlinear inversion method - floating genetic algorithm - is applied to inverting the azimuth dependence of component of polarization light backscattered. The experiment results demonstrate that the size distribution and refractive index of the scatters of the top layer can be determined by measuring and analyzing the differential signal of the parallel and perpendicular components from a two-layer tissue phantom. The method implies to detect precancerous changes in human epithelial tissue.
Unsupervised neural networks for solving Troesch's problem
Muhammad, Asif Zahoor Raja
2014-01-01
In this study, stochastic computational intelligence techniques are presented for the solution of Troesch's boundary value problem. The proposed stochastic solvers use the competency of a feed-forward artificial neural network for mathematical modeling of the problem in an unsupervised manner, whereas the learning of unknown parameters is made with local and global optimization methods as well as their combinations. Genetic algorithm (GA) and pattern search (PS) techniques are used as the global search methods and the interior point method (IPM) is used for an efficient local search. The combination of techniques like GA hybridized with IPM (GA-IPM) and PS hybridized with IPM (PS-IPM) are also applied to solve different forms of the equation. A comparison of the proposed results obtained from GA, PS, IPM, PS-IPM and GA-IPM has been made with the standard solutions including well known analytic techniques of the Adomian decomposition method, the variational iterational method and the homotopy perturbation method. The reliability and effectiveness of the proposed schemes, in term of accuracy and convergence, are evaluated from the results of statistical analysis based on sufficiently large independent runs.
Sturtevant, John L.; Liubich, Vlad; Gupta, Rachit
2016-04-01
Edge placement error (EPE) was a term initially introduced to describe the difference between predicted pattern contour edge and the design target for a single design layer. Strictly speaking, this quantity is not directly measurable in the fab. What is of vital importance is the relative edge placement errors between different design layers, and in the era of multipatterning, the different constituent mask sublayers for a single design layer. The critical dimensions (CD) and overlay between two layers can be measured in the fab, and there has always been a strong emphasis on control of overlay between design layers. The progress in this realm has been remarkable, accelerated in part at least by the proliferation of multipatterning, which reduces the available overlay budget by introducing a coupling of overlay and CD errors for the target layer. Computational lithography makes possible the full-chip assessment of two-layer edge to edge distances and two-layer contact overlap area. We will investigate examples of via-metal model-based analysis of CD and overlay errors. We will investigate both single patterning and double patterning. For single patterning, we show the advantage of contour-to-contour simulation over contour to target simulation, and how the addition of aberrations in the optical models can provide a more realistic CD-overlay process window (PW) for edge placement errors. For double patterning, the interaction of 4-layer CD and overlay errors is very complex, but we illustrate that not only can full-chip verification identify potential two-layer hotspots, the optical proximity correction engine can act to mitigate such hotspots and enlarge the joint CD-overlay PW.
Dynamics of the outflow and its effect on the hydraulics of two-layer exchange flows in a channel
无
2011-01-01
This paper reports that an experimental study is conducted to examine the dynamics of the outflow in two-layer exchange flows in a channel connecting between two water bodies with a small density difference. The experiments reveal the generation of Kelvin-Helmholtz (KH) instabilities within the hydraulically sub-critical flow region of the channel. During maximal exchange, those KH instabilities develops into large-amplitude KH waves as they escape the channel exit into the reservoir. The propagation speed ...
Two-Layer Microstructures Fabricated by One-Step Anisotropic Wet Etching of Si in KOH Solution
Han Lu
2016-01-01
Full Text Available Anisotropic etching of silicon in potassium hydroxide (KOH is an important technology in micromachining. The residue deposition from KOH etching of Si is typically regarded as a disadvantage of this technology. In this report, we make use of this residue as a second masking layer to fabricate two-layer complex structures. Square patterns with size in the range of 15–150 μm and gap distance of 5 μm have been designed and tested. The residue masking layer appears when the substrate is over-etched in hydrofluoric acid (HF solution over a threshold. The two-layer structures of micropyramids surrounded by wall-like structures are obtained according to the two different masking layers of SiO2 and residue. The residue masking layer is stable and can survive over KOH etching for long time to achieve deep Si etching. The process parameters of etchant concentration, temperature, etching time and pattern size have been investigated. With well-controlled two-layer structures, useful structures could be designed for applications in plasmonic and microfluidic devices in the future.
Laboratory Research of the Two-Layer Liquid Dynamics at the Wind Surge in a Strait Canal
S.F. Dotsenko
2017-06-01
Full Text Available The results of laboratory experiments in a straight aerohydrocanal of the rectangular cross-section filled with the two-layer (fresh-salty liquid are represented. The disturbance generator is the air flow directed to the area above the canal. The cases of the two-layer liquid dynamics in the canal with the horizontal flat bottom and in the presence of the bottom obstacle of finite width are considered. It is shown that during the surge in the straight canal, one of the possible exchange mechanisms on the boundary of fresh and salty layers may consist in the salt water emissions (resulted from the Kelvin-Helmholtz instability to the upper freshwater layer. The subsequent eviction can possibly be accompanied by occurrence of undulations at the interface. Besides, the evictions can be followed by formation of the oscillating layer, i.e. the layer with maximum density gradient the oscillations of which propagate to the overlying layers. Presence of the bottom obstacle complicates the structure of the two-layer liquid motions. In particular, it results in emergence of the mixed layers and transformation of the flow behind the obstacle into a turbulent one, formation of the wave-like disturbances over the obstacle, sharp change of the interface position and occurrence of large-scale vortices with the horizontal axes. It is revealed that the maximum peak of the flow velocity horizontal component is shifted upstream from the obstacle.