A Constrained Multi-Objective Learning Algorithm for Feed-Forward Neural Network Classifiers

Directory of Open Access Journals (Sweden)

M. Njah

2017-06-01

Full Text Available This paper proposes a new approach to address the optimal design of a Feed-forward Neural Network (FNN based classifier. The originality of the proposed methodology, called CMOA, lie in the use of a new constraint handling technique based on a self-adaptive penalty procedure in order to direct the entire search effort towards finding only Pareto optimal solutions that are acceptable. Neurons and connections of the FNN Classifier are dynamically built during the learning process. The approach includes differential evolution to create new individuals and then keeps only the non-dominated ones as the basis for the next generation. The designed FNN Classifier is applied to six binary classification benchmark problems, obtained from the UCI repository, and results indicated the advantages of the proposed approach over other existing multi-objective evolutionary neural networks classifiers reported recently in the literature.

Feed-Forward Propagation of Temporal and Rate Information between Cortical Populations during Coherent Activation in Engineered In Vitro Networks.

Science.gov (United States)

DeMarse, Thomas B; Pan, Liangbin; Alagapan, Sankaraleengam; Brewer, Gregory J; Wheeler, Bruce C

2016-01-01

Transient propagation of information across neuronal assembles is thought to underlie many cognitive processes. However, the nature of the neural code that is embedded within these transmissions remains uncertain. Much of our understanding of how information is transmitted among these assemblies has been derived from computational models. While these models have been instrumental in understanding these processes they often make simplifying assumptions about the biophysical properties of neurons that may influence the nature and properties expressed. To address this issue we created an in vitro analog of a feed-forward network composed of two small populations (also referred to as assemblies or layers) of living dissociated rat cortical neurons. The populations were separated by, and communicated through, a microelectromechanical systems (MEMS) device containing a strip of microscale tunnels. Delayed culturing of one population in the first layer followed by the second a few days later induced the unidirectional growth of axons through the microtunnels resulting in a primarily feed-forward communication between these two small neural populations. In this study we systematically manipulated the number of tunnels that connected each layer and hence, the number of axons providing communication between those populations. We then assess the effect of reducing the number of tunnels has upon the properties of between-layer communication capacity and fidelity of neural transmission among spike trains transmitted across and within layers. We show evidence based on Victor-Purpura's and van Rossum's spike train similarity metrics supporting the presence of both rate and temporal information embedded within these transmissions whose fidelity increased during communication both between and within layers when the number of tunnels are increased. We also provide evidence reinforcing the role of synchronized activity upon transmission fidelity during the spontaneous synchronized

Neural Network Based Model of an Industrial Oil-Fired Boiler System ...

African Journals Online (AJOL)

A two-layer feed-forward neural network with Hyperbolic tangent sigmoid ... The neural network model when subjected to test, using the validation input data; ... Proportional Integral Derivative (PID) Controller is used to control the neural ...

Implementation of multi-layer feed forward neural network on PIC16F877 microcontroller

International Nuclear Information System (INIS)

Nur Aira Abd Rahman

2005-01-01

Artificial Neural Network (ANN) is an electronic model based on the neural structure of the brain. Similar to human brain, ANN consists of interconnected simple processing units or neurons that process input to generate output signals. ANN operation is divided into 2 categories; training mode and service mode. This project aims to implement ANN on PIC micro-controller that enable on-chip or stand alone training and service mode. The input can varies from sensors or switches, while the output can be used to control valves, motors, light source and a lot more. As partial development of the project, this paper reports the current status and results of the implemented ANN. The hardware fraction of this project incorporates Microchip PIC16F877A microcontrollers along with uM-FPU math co-processor. uM-FPU is a 32-bit floating point co-processor utilized to execute complex calculation requires by the sigmoid activation function for neuron. ANN algorithm is converted to software program written in assembly language. The implemented ANN structure is three layer with one hidden layer, and five neurons with two hidden neurons. To prove the operability and functionality, the network is trained to solve three common logic gate operations; AND, OR, and XOR. This paper concludes that the ANN had been successfully implemented on PIC16F877a and uM-FPU math co-processor hardware that works accordingly on both training and service mode. (Author)

Interpretation of correlated neural variability from models of feed-forward and recurrent circuits

Science.gov (United States)

2018-01-01

Neural populations respond to the repeated presentations of a sensory stimulus with correlated variability. These correlations have been studied in detail, with respect to their mechanistic origin, as well as their influence on stimulus discrimination and on the performance of population codes. A number of theoretical studies have endeavored to link network architecture to the nature of the correlations in neural activity. Here, we contribute to this effort: in models of circuits of stochastic neurons, we elucidate the implications of various network architectures—recurrent connections, shared feed-forward projections, and shared gain fluctuations—on the stimulus dependence in correlations. Specifically, we derive mathematical relations that specify the dependence of population-averaged covariances on firing rates, for different network architectures. In turn, these relations can be used to analyze data on population activity. We examine recordings from neural populations in mouse auditory cortex. We find that a recurrent network model with random effective connections captures the observed statistics. Furthermore, using our circuit model, we investigate the relation between network parameters, correlations, and how well different stimuli can be discriminated from one another based on the population activity. As such, our approach allows us to relate properties of the neural circuit to information processing. PMID:29408930

Interpretation of correlated neural variability from models of feed-forward and recurrent circuits.

Directory of Open Access Journals (Sweden)

Volker Pernice

2018-02-01

Full Text Available Neural populations respond to the repeated presentations of a sensory stimulus with correlated variability. These correlations have been studied in detail, with respect to their mechanistic origin, as well as their influence on stimulus discrimination and on the performance of population codes. A number of theoretical studies have endeavored to link network architecture to the nature of the correlations in neural activity. Here, we contribute to this effort: in models of circuits of stochastic neurons, we elucidate the implications of various network architectures-recurrent connections, shared feed-forward projections, and shared gain fluctuations-on the stimulus dependence in correlations. Specifically, we derive mathematical relations that specify the dependence of population-averaged covariances on firing rates, for different network architectures. In turn, these relations can be used to analyze data on population activity. We examine recordings from neural populations in mouse auditory cortex. We find that a recurrent network model with random effective connections captures the observed statistics. Furthermore, using our circuit model, we investigate the relation between network parameters, correlations, and how well different stimuli can be discriminated from one another based on the population activity. As such, our approach allows us to relate properties of the neural circuit to information processing.

neural network based model o work based model of an industrial oil

African Journals Online (AJOL)

eobe

technique. g, Neural Network Model, Regression, Mean Square Error, PID controller. ... during the training processes. An additio ... used to carry out simulation studies of the mode .... A two-layer feed-forward neural network with Matlab.

Natural Language Processing with Small Feed-Forward Networks

OpenAIRE

Botha, Jan A.; Pitler, Emily; Ma, Ji; Bakalov, Anton; Salcianu, Alex; Weiss, David; McDonald, Ryan; Petrov, Slav

2017-01-01

We show that small and shallow feed-forward neural networks can achieve near state-of-the-art results on a range of unstructured and structured language processing tasks while being considerably cheaper in memory and computational requirements than deep recurrent models. Motivated by resource-constrained environments like mobile phones, we showcase simple techniques for obtaining such small neural network models, and investigate different tradeoffs when deciding how to allocate a small memory...

Feed-Forward Neural Networks and Minimal Search Space Learning

Czech Academy of Sciences Publication Activity Database

Neruda, Roman

2005-01-01

Roč. 4, č. 12 (2005), s. 1867-1872 ISSN 1109-2750 R&D Projects: GA ČR GA201/05/0557 Institutional research plan: CEZ:AV0Z10300504 Keywords : search space * feed-forward networks * genetic algorithm s Subject RIV: BA - General Mathematics

Experimental calibration of forward and inverse neural networks for rotary type magnetorheological damper

DEFF Research Database (Denmark)

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...

Precision requirements for single-layer feed-forward neural networks

NARCIS (Netherlands)

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

Feed-forward segmentation of figure-ground and assignment of border-ownership.

Directory of Open Access Journals (Sweden)

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.

Feed-forward segmentation of figure-ground and assignment of border-ownership.

Science.gov (United States)

Supèr, Hans; Romeo, August; Keil, Matthias

2010-05-19

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.

A two-layered forward model of tissue for electrical impedance tomography

International Nuclear Information System (INIS)

Kulkarni, Rujuta; Saulnier, Gary J; Kao, Tzu-Jen; Newell, Jonathan C; Boverman, Gregory; Isaacson, David

2009-01-01

Electrical impedance tomography is being explored as a technique to detect breast cancer, exploiting the differences in admittivity between normal tissue and tumors. In this paper, the geometry is modeled as an infinite half space under a hand-held probe. A forward solution and a reconstruction algorithm for this geometry were developed previously by Mueller et al (1999 IEEE Trans. Biomed. Eng. 46 1379). In this paper, we present a different approach which uses the decomposition of the forward solution into its Fourier components to obtain the forward solution and the reconstructions. The two approaches are compared in terms of the forward solutions and the reconstructions of experimental tank data. We also introduce a two-layered model to incorporate the presence of the skin that surrounds the body area being imaged. We demonstrate an improvement in the reconstruction of a target in a layered medium using this layered model with finite difference simulated data. We then extend the application of our layered model to human subject data and estimate the skin and the tissue admittivities for data collected on the human abdomen using an ultrasound-like hand-held EIT probe. Lastly, we show that for this set of human subject data, the layered model yields an improvement in predicting the measured voltages of around 81% for the lowest temporal frequency (3 kHz) and around 61% for the highest temporal frequency (1 MHz) applied when compared to the homogeneous model

Genetic algorithm for neural networks optimization

Science.gov (United States)

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«.

Layer-by-Layer Assembly for Preparation of High-Performance Forward Osmosis Membrane

Science.gov (United States)

Yang, Libin; Zhang, Jinglong; Song, Peng; Wang, Zhan

2018-01-01

Forward osmosis (FO) membrane with high separation performance is needed to promote its practical applications. Herein, layer-by-layer (LbL) approach was used to prepare a thin and highly cross-linked polyamide layer on a polyacrylonitrile substrate surface to prepare a thin-film composite forward osmosis (TFC-FO) membrane with enhanced FO performance. The effects of monomer concentrations and assembly cycles on the performance of the TFC-FO membranes were systematically investigated. Under the optimal preparation condition, TFC-FO membrane achieved the best performance, exhibiting the water flux of 14.4/6.9 LMH and reverse salt flux of 7.7/3.8 gMH under the pressure retarded osmosis/forward osmosis (PRO/FO) mode using 1M NaCl as the draw against a DI-water feed, and a rejection of 96.1% for 2000 mg/L NaCl aqueous solution. The result indicated that layer-by-layer method was a potential method to regulate the structure and performance of the TFC-FO membrane.

Separation prediction in two dimensional boundary layer flows using artificial neural networks

International Nuclear Information System (INIS)

Sabetghadam, F.; Ghomi, H.A.

2003-01-01

In this article, the ability of artificial neural networks in prediction of separation in steady two dimensional boundary layer flows is studied. Data for network training is extracted from numerical solution of an ODE obtained from Von Karman integral equation with approximate one parameter Pohlhousen velocity profile. As an appropriate neural network, a two layer radial basis generalized regression artificial neural network is used. The results shows good agreements between the overall behavior of the flow fields predicted by the artificial neural network and the actual flow fields for some cases. The method easily can be extended to unsteady separation and turbulent as well as compressible boundary layer flows. (author)

Learning and Generalisation in Neural Networks with Local Preprocessing

OpenAIRE

Kutsia, Merab

2007-01-01

We study learning and generalisation ability of a specific two-layer feed-forward neural network and compare its properties to that of a simple perceptron. The input patterns are mapped nonlinearly onto a hidden layer, much larger than the input layer, and this mapping is either fixed or may result from an unsupervised learning process. Such preprocessing of initially uncorrelated random patterns results in the correlated patterns in the hidden layer. The hidden-to-output mapping of the net...

Noise-enhanced categorization in a recurrently reconnected neural network

International Nuclear Information System (INIS)

Monterola, Christopher; Zapotocky, Martin

2005-01-01

We investigate the interplay of recurrence and noise in neural networks trained to categorize spatial patterns of neural activity. We develop the following procedure to demonstrate how, in the presence of noise, the introduction of recurrence permits to significantly extend and homogenize the operating range of a feed-forward neural network. We first train a two-level perceptron in the absence of noise. Following training, we identify the input and output units of the feed-forward network, and thus convert it into a two-layer recurrent network. We show that the performance of the reconnected network has features reminiscent of nondynamic stochastic resonance: the addition of noise enables the network to correctly categorize stimuli of subthreshold strength, with optimal noise magnitude significantly exceeding the stimulus strength. We characterize the dynamics leading to this effect and contrast it to the behavior of a more simple associative memory network in which noise-mediated categorization fails

Noise-enhanced categorization in a recurrently reconnected neural network

Science.gov (United States)

Monterola, Christopher; Zapotocky, Martin

2005-03-01

We investigate the interplay of recurrence and noise in neural networks trained to categorize spatial patterns of neural activity. We develop the following procedure to demonstrate how, in the presence of noise, the introduction of recurrence permits to significantly extend and homogenize the operating range of a feed-forward neural network. We first train a two-level perceptron in the absence of noise. Following training, we identify the input and output units of the feed-forward network, and thus convert it into a two-layer recurrent network. We show that the performance of the reconnected network has features reminiscent of nondynamic stochastic resonance: the addition of noise enables the network to correctly categorize stimuli of subthreshold strength, with optimal noise magnitude significantly exceeding the stimulus strength. We characterize the dynamics leading to this effect and contrast it to the behavior of a more simple associative memory network in which noise-mediated categorization fails.

Thalamocortical control of feed-forward inhibition in awake somatosensory 'barrel' cortex.

OpenAIRE

Swadlow, Harvey A

2002-01-01

Intracortical inhibition plays a role in shaping sensory cortical receptive fields and is mediated by both feed-forward and feedback mechanisms. Feed-forward inhibition is the faster of the two processes, being generated by inhibitory interneurons driven by monosynaptic thalamocortical (TC) input. In principle, feed-forward inhibition can prevent targeted cortical neurons from ever reaching threshold when TC input is weak. To do so, however, inhibitory interneurons must respond to TC input at...

Neural network tagging in a toy model

International Nuclear Information System (INIS)

Milek, Marko; Patel, Popat

1999-01-01

The purpose of this study is a comparison of Artificial Neural Network approach to HEP analysis against the traditional methods. A toy model used in this analysis consists of two types of particles defined by four generic properties. A number of 'events' was created according to the model using standard Monte Carlo techniques. Several fully connected, feed forward multi layered Artificial Neural Networks were trained to tag the model events. The performance of each network was compared to the standard analysis mechanisms and significant improvement was observed

Character Recognition Using Genetically Trained Neural Networks

Energy Technology Data Exchange (ETDEWEB)

Diniz, C.; Stantz, K.M.; Trahan, M.W.; Wagner, J.S.

1998-10-01

Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfid recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the

Development of Artificial Neural Network Model for Diesel Fuel Properties Prediction using Vibrational Spectroscopy.

Science.gov (United States)

Bolanča, Tomislav; Marinović, Slavica; Ukić, Sime; Jukić, Ante; Rukavina, Vinko

2012-06-01

This paper describes development of artificial neural network models which can be used to correlate and predict diesel fuel properties from several FTIR-ATR absorbances and Raman intensities as input variables. Multilayer feed forward and radial basis function neural networks have been used to rapid and simultaneous prediction of cetane number, cetane index, density, viscosity, distillation temperatures at 10% (T10), 50% (T50) and 90% (T90) recovery, contents of total aromatics and polycyclic aromatic hydrocarbons of commercial diesel fuels. In this study two-phase training procedures for multilayer feed forward networks were applied. While first phase training algorithm was constantly the back propagation one, two second phase training algorithms were varied and compared, namely: conjugate gradient and quasi Newton. In case of radial basis function network, radial layer was trained using K-means radial assignment algorithm and three different radial spread algorithms: explicit, isotropic and K-nearest neighbour. The number of hidden layer neurons and experimental data points used for the training set have been optimized for both neural networks in order to insure good predictive ability by reducing unnecessary experimental work. This work shows that developed artificial neural network models can determine main properties of diesel fuels simultaneously based on a single and fast IR or Raman measurement.

Introduction to Artificial Neural Networks

DEFF Research Database (Denmark)

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....

Selection of W-pair-production in DELPHI with feed-forward neural networks

International Nuclear Information System (INIS)

Becks, K.-H.; Buschmann, P.; Drees, J.; Mueller, U.; Wahlen, H.

2001-01-01

Since 1998 feed-forward networks have been applied for the separation of hadronic WW-decays from background processes measured by the DELPHI collaboration at different center-of-mass energies of the Large Electron Positron collider at CERN. Prior to the publication of the 189 GeV results intensive studies of systematic effects and uncertainties were performed. The methods and results will be discussed and compared to standard selection procedures

Feed Forward Artificial Neural Network Model to Estimate the TPH Removal Efficiency in Soil Washing Process

Directory of Open Access Journals (Sweden)

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.

Learning behavior and temporary minima of two-layer neural networks

NARCIS (Netherlands)

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

Feed-Forward Control in Resonant DC Link Inverter

OpenAIRE

Apinan Aurasopon; Worawat Sa-ngiavibool

2008-01-01

This paper proposes a feed-forward control in resonant dc link inverter. The feed-forward control configuration is based on synchronous sigma-delta modulation. The simulation results showing the proposed technique can reject non-ideal dc bus improving the total harmonic distortion.

A robust neural network-based approach for microseismic event detection

KAUST Repository

Akram, Jubran; Ovcharenko, Oleg; Peter, Daniel

2017-01-01

We present an artificial neural network based approach for robust event detection from low S/N waveforms. We use a feed-forward network with a single hidden layer that is tuned on a training dataset and later applied on the entire example dataset

Forward Osmosis Process

KAUST Repository

Duan, Jintang

2013-12-05

A process that can alleviate the internal concentration polarization and can enhance membrane performance of a forward osmosis system includes the steps of passing a fluid in a forward osmosis system from a feed solution with a first osmotic pressure, through a membrane into a draw solution comprising a draw solute with a second osmotic pressure, where the first osmotic pressure is lower than the second osmotic pressure, the membrane includes an active layer and a support layer, and the membrane is oriented such that the active layer of the membrane faces a draw side, and the support layer faces a feed side; and applying an external force to the fluid on the feed side of the membrane.

Forward Osmosis Process

KAUST Repository

Duan, Jintang; Pinnau, Ingo; Litwiller, Eric

2013-01-01

A process that can alleviate the internal concentration polarization and can enhance membrane performance of a forward osmosis system includes the steps of passing a fluid in a forward osmosis system from a feed solution with a first osmotic pressure, through a membrane into a draw solution comprising a draw solute with a second osmotic pressure, where the first osmotic pressure is lower than the second osmotic pressure, the membrane includes an active layer and a support layer, and the membrane is oriented such that the active layer of the membrane faces a draw side, and the support layer faces a feed side; and applying an external force to the fluid on the feed side of the membrane.

Two-Layer Feedback Neural Networks with Associative Memories

International Nuclear Information System (INIS)

Gui-Kun, Wu; Hong, Zhao

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. (general)

High-speed linear optics quantum computing using active feed-forward.

Science.gov (United States)

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.

Feed-Forward Neural Network Soft-Sensor Modeling of Flotation Process Based on Particle Swarm Optimization and Gravitational Search Algorithm

Directory of Open Access Journals (Sweden)

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.

A two-layer recurrent neural network for nonsmooth convex optimization problems.

Science.gov (United States)

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.

Forward and reverse mapping for milling process using artificial neural networks

Directory of Open Access Journals (Sweden)

Rashmi L. Malghan

2018-02-01

Full Text Available The data set presented is related to the milling process of AA6061-4.5%Cu-5%SiCp composite. The data primarily concentrates on predicting values of some machining responses, such as cutting force, surface finish and power utilization utilizing using forward back propagation neural network based approach, i.e. ANN based on three process parameters, such as spindle speed, feed rate and depth of cut.The comparing reverse model is likewise created to prescribe the ideal settings of processing parameters for accomplishing the desired responses as indicated by the necessities of the end clients. These modelling approaches are very proficient to foresee the benefits of machining responses and also process parameter settings in light of the experimental technique. Keywords: ANN, Forward mapping, Reverse mapping, Milling process

Feed-Forward versus Feedback Inhibition in a Basic Olfactory Circuit.

Directory of Open Access Journals (Sweden)

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.

Bringing Interpretability and Visualization with Artificial Neural Networks

Science.gov (United States)

Gritsenko, Andrey

2017-01-01

Extreme Learning Machine (ELM) is a training algorithm for Single-Layer Feed-forward Neural Network (SLFN). The difference in theory of ELM from other training algorithms is in the existence of explicitly-given solution due to the immutability of initialed weights. In practice, ELMs achieve performance similar to that of other state-of-the-art…

Adaptive feed forward in the LANL RF control system

International Nuclear Information System (INIS)

Ziomek, C.D.

1992-01-01

This paper describes an adaptive feed forward system that corrects repetitive errors in the amplitude and phase of the RF field of a pulsed accelerator. High-frequency disturbances that are beyond the effective bandwidth of the RF-field feedback control system can be eliminated with a feed forward system. Many RF-field disturbances for a pulsed accelerator are repetitive, occurring at the same relative time in every pulse. This design employs digital signal processing hardware to adaptively determine and track the control signals required to eliminate the repetitive errors in the feedback control system. In order to provide the necessary high-frequency response, the adaptive feed forward hardware provides the calculated control signal prior to the repetitive disturbance that it corrects. This system has been demonstrated to reduce the transient disturbances caused by beam pulses. Furthermore, it has been shown to negate high-frequency phase and amplitude oscillations in a high-power klystron amplifier caused by PFN ripple on the high-voltage. The design and results of the adaptive feed forward system are presented. (Author) 3 figs., 2 refs

Theoretical properties of the global optimizer of two layer neural network

OpenAIRE

Boob, Digvijay; Lan, Guanghui

2017-01-01

In this paper, we study the problem of optimizing a two-layer artificial neural network that best fits a training dataset. We look at this problem in the setting where the number of parameters is greater than the number of sampled points. We show that for a wide class of differentiable activation functions (this class involves "almost" all functions which are not piecewise linear), we have that first-order optimal solutions satisfy global optimality provided the hidden layer is non-singular. ...

On Optimal Input Design for Feed-forward Control

OpenAIRE

Hägg, Per; Wahlberg, Bo

2013-01-01

This paper considers optimal input design when the intended use of the identified model is to construct a feed-forward controller based on measurable disturbances. The objective is to find a minimum power excitation signal to be used in a system identification experiment, such that the corresponding model-based feed-forward controller guarantees, with a given probability, that the variance of the output signal is within given specifications. To start with, some low order model problems are an...

Fastest learning in small-world neural networks

International Nuclear Information System (INIS)

Simard, D.; Nadeau, L.; Kroeger, H.

2005-01-01

We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition

A low-complexity feed-forward I/Q imbalance compensation algorithm

NARCIS (Netherlands)

Moseley, N.A.; Slump, Cornelis H.

2006-01-01

This paper presents a low-complexity adaptive feed- forward I/Q imbalance compensation algorithm. The feed-forward so- lution has guaranteed stability. Due to its blind nature the algorithm is easily incorporated into an existing receiver design. The algorithm uses three estimators to obtain the

Reverse-feeding effect of epidemic by propagators in two-layered networks

International Nuclear Information System (INIS)

Wu Dayu; Zhao Yanping; Zheng Muhua; Zhou Jie; Liu Zonghua

2016-01-01

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. (paper)

An automatic system for Turkish word recognition using Discrete Wavelet Neural Network based on adaptive entropy

International Nuclear Information System (INIS)

Avci, E.

2007-01-01

In this paper, an automatic system is presented for word recognition using real Turkish word signals. This paper especially deals with combination of the feature extraction and classification from real Turkish word signals. A Discrete Wavelet Neural Network (DWNN) model is used, which consists of two layers: discrete wavelet layer and multi-layer perceptron. The discrete wavelet layer is used for adaptive feature extraction in the time-frequency domain and is composed of Discrete Wavelet Transform (DWT) and wavelet entropy. The multi-layer perceptron used for classification is a feed-forward neural network. The performance of the used system is evaluated by using noisy Turkish word signals. Test results showing the effectiveness of the proposed automatic system are presented in this paper. The rate of correct recognition is about 92.5% for the sample speech signals. (author)

Estimation of effective connectivity using multi-layer perceptron artificial neural network.

Science.gov (United States)

Talebi, Nasibeh; Nasrabadi, Ali Motie; Mohammad-Rezazadeh, Iman

2018-02-01

Studies on interactions between brain regions estimate effective connectivity, (usually) based on the causality inferences made on the basis of temporal precedence. In this study, the causal relationship is modeled by a multi-layer perceptron feed-forward artificial neural network, because of the ANN's ability to generate appropriate input-output mapping and to learn from training examples without the need of detailed knowledge of the underlying system. At any time instant, the past samples of data are placed in the network input, and the subsequent values are predicted at its output. To estimate the strength of interactions, the measure of " Causality coefficient " is defined based on the network structure, the connecting weights and the parameters of hidden layer activation function. Simulation analysis demonstrates that the method, called "CREANN" (Causal Relationship Estimation by Artificial Neural Network), can estimate time-invariant and time-varying effective connectivity in terms of MVAR coefficients. The method shows robustness with respect to noise level of data. Furthermore, the estimations are not significantly influenced by the model order (considered time-lag), and the different initial conditions (initial random weights and parameters of the network). CREANN is also applied to EEG data collected during a memory recognition task. The results implicate that it can show changes in the information flow between brain regions, involving in the episodic memory retrieval process. These convincing results emphasize that CREANN can be used as an appropriate method to estimate the causal relationship among brain signals.

The mechanism of synchronization in feed-forward neuronal networks

International Nuclear Information System (INIS)

Goedeke, S; Diesmann, M

2008-01-01

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

Reverse-feeding effect of epidemic by propagators in two-layered networks

Science.gov (United States)

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).

Potential usefulness of an artificial neural network for assessing ventricular size

International Nuclear Information System (INIS)

Fukuda, Haruyuki; Nakajima, Hideyuki; Usuki, Noriaki; Saiwai, Shigeo; Miyamoto, Takeshi; Inoue, Yuichi; Onoyama, Yasuto.

1995-01-01

An artificial neural network approach was applied to assess ventricular size from computed tomograms. Three layer, feed-forward neural networks with a back propagation algorithm were designed to distinguish between three degree of enlargement of the ventricles on the basis of patient's age and six items of computed tomographic information. Data for training and testing the neural network were created with computed tomograms of the brains selected at random from daily examinations. Four radiologists decided by mutual consent subjectively based on their experience whether the ventricles were within normal limits, slightly enlarged, or enlarged for the patient's age. The data for training was obtained from 38 patients. The data for testing was obtained from 47 other patients. The performance of the neural network trained using the data for training was evaluated by the rate of correct answers to the data for testing. The valid solution ratio to response of the test data obtained from the trained neural networks was more than 90% for all conditions in this study. The solutions were completely valid in the neural networks with two or three units at the hidden layer with 2,200 learning iterations, and with two units at the hidden layer with 11,000 learning iterations. The squared error decreased remarkably in the range from 0 to 500 learning iterations, and was close to a contrast over two thousand learning iterations. The neural network with a hidden layer having two or three units showed high decision performance. The preliminary results strongly suggest that the neural network approach has potential utility in computer-aided estimation of enlargement of the ventricles. (author)

Crop Classification by Forward Neural Network with Adaptive Chaotic Particle Swarm Optimization

Directory of Open Access Journals (Sweden)

Yudong Zhang

2011-05-01

Full Text Available This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR images. The feature sets consisted of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM based texture features. Then, the features were reduced by principle component analysis (PCA. Finally, a two-hidden-layer forward neural network (NN was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO. K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP, adaptive BP (ABP, momentum BP (MBP, Particle Swarm Optimization (PSO, and Resilient back-propagation (RPROP methods. Moreover, the computation time for each pixel is only 1.08 × 10−7 s.

A new backpropagation learning algorithm for layered neural networks with nondifferentiable units.

Science.gov (United States)

Oohori, Takahumi; Naganuma, Hidenori; Watanabe, Kazuhisa

2007-05-01

We propose a digital version of the backpropagation algorithm (DBP) for three-layered neural networks with nondifferentiable binary units. This approach feeds teacher signals to both the middle and output layers, whereas with a simple perceptron, they are given only to the output layer. The additional teacher signals enable the DBP to update the coupling weights not only between the middle and output layers but also between the input and middle layers. A neural network based on DBP learning is fast and easy to implement in hardware. Simulation results for several linearly nonseparable problems such as XOR demonstrate that the DBP performs favorably when compared to the conventional approaches. Furthermore, in large-scale networks, simulation results indicate that the DBP provides high performance.

Modification of Hidden Layer Weight in Extreme Learning Machine Using Gain Ratio

Directory of Open Access Journals (Sweden)

Anggraeny Fetty Tri

2016-01-01

Full Text Available Extreme Learning Machine (ELM is a method of learning feed forward neural network quickly and has a fairly good accuracy. This method is devoted to a feed forward neural network with one hidden layer where the parameters (i.e. weight and bias are adjusted one time randomly at the beginning of the learning process. In neural network, the input layer is connected to all characteristics/features, and the output layer is connected to all classes of species. This research used three datasets from UCI database, which were Iris, Breast Wisconsin, and Dermatology, with each dataset having several features. Each characteristic/feature of the data has a role in the process of classification levels, starting from the most influencing role to non-influencing at all. Gain ratio was used to extract each feature role on each datasets. Gain ratio is a method to extract feature role in order to develop a decision tree structure. In this study, ELM structure has been modified, where the random weights of the hidden layer were adjusted to the level of each feature role in determining the species class, so as to improve the level of training and testing accuracy. The proposed method has higher classification accuracy rate than basic ELM on all three datasets, which were 99%, 96%, and 82%, respectively.

Classification of Urinary Calculi using Feed-Forward Neural Networks

African Journals Online (AJOL)

NJD

Genetic algorithms were used for optimization of neural networks and for selection of the ... Urinary calculi, infrared spectroscopy, classification, neural networks, variable ..... note that the best accuracy is obtained for whewellite, weddellite.

DeepNet: An Ultrafast Neural Learning Code for Seismic Imaging

International Nuclear Information System (INIS)

Barhen, J.; Protopopescu, V.; Reister, D.

1999-01-01

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

Artificial neural network modeling and optimization of ultrahigh pressure extraction of green tea polyphenols.

Science.gov (United States)

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.

Relating performance of thin-film composite forward osmosis membranes to support layer formation and structure

KAUST Repository

Tiraferri, Alberto

2011-02-01

Osmotically driven membrane processes have the potential to treat impaired water sources, desalinate sea/brackish waters, and sustainably produce energy. The development of a membrane tailored for these processes is essential to advance the technology to the point that it is commercially viable. Here, a systematic investigation of the influence of thin-film composite membrane support layer structure on forward osmosis performance is conducted. The membranes consist of a selective polyamide active layer formed by interfacial polymerization on top of a polysulfone support layer fabricated by phase separation. By systematically varying the conditions used during the casting of the polysulfone layer, an array of support layers with differing structures was produced. The role that solvent quality, dope polymer concentration, fabric layer wetting, and casting blade gate height play in the support layer structure formation was investigated. Using a 1M NaCl draw solution and a deionized water feed, water fluxes ranging from 4 to 25Lm-2h-1 with consistently high salt rejection (>95.5%) were produced. The relationship between membrane structure and performance was analyzed. This study confirms the hypothesis that the optimal forward osmosis membrane consists of a mixed-structure support layer, where a thin sponge-like layer sits on top of highly porous macrovoids. Both the active layer transport properties and the support layer structural characteristics need to be optimized in order to fabricate a high performance forward osmosis membrane. © 2010 Elsevier B.V.

Neural Networks in Control Applications

DEFF Research Database (Denmark)

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...

Prediction of the binary density of the ILs+ water using back-propagated feed forward artificial neural network

Directory of Open Access Journals (Sweden)

Shojaee Safar Ali

2014-01-01

Full Text Available In this study, feasibility of a back-propagated artificial neural network to correlate the binary density of ionic liquids (ILs mixtures containing water as the common solvent has been investigated. To verify the optimized parameters of the neural network, total of 1668 data were collected and divided into two different subsets. The first subsets consisted of more than two-third (1251 data points of data bank was used to find the optimum parameters including weights and biases, number of neurons (7 neurons, transfer functions in hidden and output layer which were tansig and purelin, respectively. In addition, the correlative capability of network was examined using testing subset (417 data points not considered during the training stage. The overall obtained results revealed that the proposed network is accurate enough to correlate the binary density of the ionic liquids mixtures with average absolute relative deviation (AARD % and average relative deviation (ARD % of 1.56% and -0.04 %, respectively. Finally, the correlative capability of the proposed ANN model was compared with one of the available correlations proposed by Rodríguez and Brennecke.

A novel controller for bipedal locomotion integrating feed-forward and feedback mechanisms

NARCIS (Netherlands)

Xiong, Xiaofeng; Sartori, Massimo; Dosen, Strahinja; González-Vargas, José; Wörgötter, Florentin; Farina, Dario; Ibanez, J.; González-Vargas, J.; Azorin, J.M.; Akay, M.; Pons, J.L.

2017-01-01

It has been recognized that bipedal locomotion is controlled using feed-forward (e.g., patterned) and feedback (e.g., reflex) control schemes. However, most current controllers fail to integrate the two schemes to simplify speed control of bipedal locomotion. To solve this problem, we here propose a

Diagnosis of Alzheimer’s Disease Using Dual-Tree Complex Wavelet Transform, PCA, and Feed-Forward Neural Network

Directory of Open Access Journals (Sweden)

Debesh Jha

2017-01-01

Full Text Available Background. Error-free diagnosis of Alzheimer’s disease (AD from healthy control (HC patients at an early stage of the disease is a major concern, because information about the condition’s severity and developmental risks present allows AD sufferer to take precautionary measures before irreversible brain damage occurs. Recently, there has been great interest in computer-aided diagnosis in magnetic resonance image (MRI classification. However, distinguishing between Alzheimer’s brain data and healthy brain data in older adults (age > 60 is challenging because of their highly similar brain patterns and image intensities. Recently, cutting-edge feature extraction technologies have found extensive application in numerous fields, including medical image analysis. Here, we propose a dual-tree complex wavelet transform (DTCWT for extracting features from an image. The dimensionality of feature vector is reduced by using principal component analysis (PCA. The reduced feature vector is sent to feed-forward neural network (FNN to distinguish AD and HC from the input MR images. These proposed and implemented pipelines, which demonstrate improvements in classification output when compared to that of recent studies, resulted in high and reproducible accuracy rates of 90.06 ± 0.01% with a sensitivity of 92.00 ± 0.04%, a specificity of 87.78 ± 0.04%, and a precision of 89.6 ± 0.03% with 10-fold cross-validation.

Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm

International Nuclear Information System (INIS)

Yu, Lean; Wang, Shouyang; Lai, Kin Keung

2008-01-01

In this study, an empirical mode decomposition (EMD) based neural network ensemble learning paradigm is proposed for world crude oil spot price forecasting. For this purpose, the original crude oil spot price series were first decomposed into a finite, and often small, number of intrinsic mode functions (IMFs). Then a three-layer feed-forward neural network (FNN) model was used to model each of the extracted IMFs, so that the tendencies of these IMFs could be accurately predicted. Finally, the prediction results of all IMFs are combined with an adaptive linear neural network (ALNN), to formulate an ensemble output for the original crude oil price series. For verification and testing, two main crude oil price series, West Texas Intermediate (WTI) crude oil spot price and Brent crude oil spot price, are used to test the effectiveness of the proposed EMD-based neural network ensemble learning methodology. Empirical results obtained demonstrate attractiveness of the proposed EMD-based neural network ensemble learning paradigm. (author)

Aversive Learning and Appetitive Motivation Toggle Feed-Forward Inhibition in the Drosophila Mushroom Body.

Science.gov (United States)

Perisse, Emmanuel; Owald, David; Barnstedt, Oliver; Talbot, Clifford B; Huetteroth, Wolf; Waddell, Scott

2016-06-01

In Drosophila, negatively reinforcing dopaminergic neurons also provide the inhibitory control of satiety over appetitive memory expression. Here we show that aversive learning causes a persistent depression of the conditioned odor drive to two downstream feed-forward inhibitory GABAergic interneurons of the mushroom body, called MVP2, or mushroom body output neuron (MBON)-γ1pedc>α/β. However, MVP2 neuron output is only essential for expression of short-term aversive memory. Stimulating MVP2 neurons preferentially inhibits the odor-evoked activity of avoidance-directing MBONs and odor-driven avoidance behavior, whereas their inhibition enhances odor avoidance. In contrast, odor-evoked activity of MVP2 neurons is elevated in hungry flies, and their feed-forward inhibition is required for expression of appetitive memory at all times. Moreover, imposing MVP2 activity promotes inappropriate appetitive memory expression in food-satiated flies. Aversive learning and appetitive motivation therefore toggle alternate modes of a common feed-forward inhibitory MVP2 pathway to promote conditioned odor avoidance or approach. Copyright © 2016 The Author(s). Published by Elsevier Inc. All rights reserved.

MIMO feed-forward design in wafer scanners using a gradient approximation-based algorithm

NARCIS (Netherlands)

Heertjes, M.F.; Hennekens, D.W.T.; Steinbuch, M.

2010-01-01

An experimental demonstration is given of a data-based multi-input multi-output (MIMO) feed-forward control design applied to the motion systems of a wafer scanner. Atop a nominal single-input single-output (SISO) feed-forward controller, a MIMO controller is designed having a finite impulse

Training feed-forward neural networks with gain constraints

Science.gov (United States)

Hartman

2000-04-01

Inaccurate input-output gains (partial derivatives of outputs with respect to inputs) are common in neural network models when input variables are correlated or when data are incomplete or inaccurate. Accurate gains are essential for optimization, control, and other purposes. We develop and explore a method for training feedforward neural networks subject to inequality or equality-bound constraints on the gains of the learned mapping. Gain constraints are implemented as penalty terms added to the objective function, and training is done using gradient descent. Adaptive and robust procedures are devised for balancing the relative strengths of the various terms in the objective function, which is essential when the constraints are inconsistent with the data. The approach has the virtue that the model domain of validity can be extended via extrapolation training, which can dramatically improve generalization. The algorithm is demonstrated here on artificial and real-world problems with very good results and has been advantageously applied to dozens of models currently in commercial use.

Position Control of Servo Systems Using Feed-Forward Friction Compensation

International Nuclear Information System (INIS)

Park, Min Gyu; Kim, Han Me; Shin, Jong Min; Kim, Jong Shik

2009-01-01

Friction is an important factor for precise position tracking control of servo systems. Servo systems with highly nonlinear friction are sensitive to the variation of operating condition. To overcome this problem, we use the LuGre friction model which can consider dynamic characteristics of friction. The LuGre friction model is used as a feed-forward compensator to improve tracking performance of servo systems. The parameters of the LuGre friction model are identified through experiments. The experimental result shows that the tracking performance of servo systems with higherly nonlinear friction can be improved by using feed-forward friction compensation

A Feed-forward Geometrical Compensation and Adaptive Feedback Control Algorithm for Hydraulic Robot Manipulators

DEFF Research Database (Denmark)

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....

Comparison between extreme learning machine and wavelet neural networks in data classification

Science.gov (United States)

Yahia, Siwar; Said, Salwa; Jemai, Olfa; Zaied, Mourad; Ben Amar, Chokri

2017-03-01

Extreme learning Machine is a well known learning algorithm in the field of machine learning. It's about a feed forward neural network with a single-hidden layer. It is an extremely fast learning algorithm with good generalization performance. In this paper, we aim to compare the Extreme learning Machine with wavelet neural networks, which is a very used algorithm. We have used six benchmark data sets to evaluate each technique. These datasets Including Wisconsin Breast Cancer, Glass Identification, Ionosphere, Pima Indians Diabetes, Wine Recognition and Iris Plant. Experimental results have shown that both extreme learning machine and wavelet neural networks have reached good results.

Milling tool wear diagnosis by feed motor current signal using an artificial neural network

Energy Technology Data Exchange (ETDEWEB)

Khajavi, Mehrdad Nouri; Nasernia, Ebrahim; Rostaghi, Mostafa [Dept. of Mechanical Engineering, Shahid Rajaee Teacher Training University, Tehran (Iran, Islamic Republic of)

2016-11-15

In this paper, a Multi-layer perceptron (MLP) neural network was used to predict tool wear in face milling. For this purpose, a series of experiments was conducted using a milling machine on a CK45 work piece. Tool wear was measured by an optical microscope. To improve the accuracy and reliability of the monitoring system, tool wear state was classified into five groups, namely, no wear, slight wear, normal wear, severe wear and broken tool. Experiments were conducted with the aforementioned tool wear states, and different machining conditions and data were extracted. An increase in current amplitude was observed as the tool wear increased. Furthermore, effects of parameters such as tool wear, feed, and cut depth on motor current consumption were analyzed. Considering the complexity of the wear state classification, a multi-layer neural network was used. The root mean square of motor current, feed, cut depth, and tool rpm were chosen as the input and amount of flank wear as the output of MLP. Results showed good performance of the designed tool wear monitoring system.

Novel Adaptive Forward Neural MIMO NARX Model for the Identification of Industrial 3-DOF Robot Arm Kinematics

Directory of Open Access Journals (Sweden)

Ho Pham Huy Anh

2012-10-01

Full Text Available In this paper, a novel forward adaptive neural MIMO NARX model is used for modelling and identifying the forward kinematics of an industrial 3-DOF robot arm system. The nonlinear features of the forward kinematics of the industrial robot arm drive are thoroughly modelled based on the forward adaptive neural NARX model-based identification process using experimental input-output training data. This paper proposes a novel use of a back propagation (BP algorithm to generate the forward neural MIMO NARX (FNMN model for the forward kinematics of the industrial 3-DOF robot arm. The results show that the proposed adaptive neural NARX model trained by a Back Propagation learning algorithm yields outstanding performance and perfect accuracy.

Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control.

Science.gov (United States)

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.

Modular representation of layered neural networks.

Science.gov (United States)

Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio

2018-01-01

Layered neural networks have greatly improved the performance of various applications including image processing, speech recognition, natural language processing, and bioinformatics. However, it is still difficult to discover or interpret knowledge from the inference provided by a layered neural network, since its internal representation has many nonlinear and complex parameters embedded in hierarchical layers. Therefore, it becomes important to establish a new methodology by which layered neural networks can be understood. In this paper, we propose a new method for extracting a global and simplified structure from a layered neural network. Based on network analysis, the proposed method detects communities or clusters of units with similar connection patterns. We show its effectiveness by applying it to three use cases. (1) Network decomposition: it can decompose a trained neural network into multiple small independent networks thus dividing the problem and reducing the computation time. (2) Training assessment: the appropriateness of a trained result with a given hyperparameter or randomly chosen initial parameters can be evaluated by using a modularity index. And (3) data analysis: in practical data it reveals the community structure in the input, hidden, and output layers, which serves as a clue for discovering knowledge from a trained neural network. Copyright © 2017 Elsevier Ltd. All rights reserved.

Anti-fouling and high water permeable forward osmosis membrane fabricated via layer by layer assembly of chitosan/graphene oxide

Science.gov (United States)

Salehi, Hasan; Rastgar, Masoud; Shakeri, Alireza

2017-08-01

To date, forward osmosis (FO) has received considerable attention due to its potential application in seawater desalination. FO does not require external hydraulic pressure and consequently is believed to have a low fouling propensity. Despite the numerous privileges of FO process, a major challenge ahead for its development is the lack of high performance membranes. In this study, we fabricated a novel highly-efficient FO membrane using layer-by-layer (LbL) assembly of positive chitosan (CS) and negative graphene oxide (GO) nanosheets via electrostatic interaction on a porous support layer. The support layer was prepared by blending hydrophilic sulfonated polyethersulfone (SPES) into polyethersulfone (PES) matrix using wet phase inversion process. Various characterization techniques were used to confirm successful fabrication of LbL membrane. The number of layers formed on the SPES-PES support layer was easily adjusted by repeating the CS and GO deposition cycles. Thin film composite (TFC) membrane was also prepared by the same SPES-PES support layer and polyamide (PA) active layer to compare membranes performances. The water permeability and salt rejection of the fabricated membranes were obtained by two kinds of draw solutions (including Na2SO4 and sucrose) under two different membrane orientations. The results showed that membrane coated by a CS/GO bilayers had water flux of 2-4 orders of magnitude higher than the TFC one. By increasing the number of CS/GO bilayers, the selectivity of the LbL membrane was improved. The novel fabricated LbL membrane showed better fouling resistance than the TFC one in the feed solution containing 200 ppm of sodium alginate as a foulant model.

Novel Adaptive Forward Neural MIMO NARX Model for the Identification of Industrial 3-DOF Robot Arm Kinematics

OpenAIRE

Ho Pham Huy Anh; Nguyen Thanh Nam

2012-01-01

In this paper, a novel forward adaptive neural MIMO NARX model is used for modelling and identifying the forward kinematics of an industrial 3‐DOF robot arm system. The nonlinear features of the forward kinematics of the industrial robot arm drive are thoroughly modelled based on the forward adaptive neural NARX model‐based identification process using experimental input‐output training data. This paper proposes a novel use of a back propagation (BP) algorithm to generate the forward neural M...

Neural network approximation of nonlinearity in laser nano-metrology system based on TLMI

Energy Technology Data Exchange (ETDEWEB)

Olyaee, Saeed; Hamedi, Samaneh, E-mail: s_olyaee@srttu.edu [Nano-photonics and Optoelectronics Research Laboratory (NORLab), Faculty of Electrical and Computer Engineering, Shahid Rajaee Teacher Training University (SRTTU), Lavizan, 16788, Tehran (Iran, Islamic Republic of)

2011-02-01

In this paper, an approach based on neural network (NN) for nonlinearity modeling in a nano-metrology system using three-longitudinal-mode laser heterodyne interferometer (TLMI) for length and displacement measurements is presented. We model nonlinearity errors that arise from elliptically and non-orthogonally polarized laser beams, rotational error in the alignment of laser head with respect to the polarizing beam splitter, rotational error in the alignment of the mixing polarizer, and unequal transmission coefficients in the polarizing beam splitter. Here we use a neural network algorithm based on the multi-layer perceptron (MLP) network. The simulation results show that multi-layer feed forward perceptron network is successfully applicable to real noisy interferometer signals.

Neural network approximation of nonlinearity in laser nano-metrology system based on TLMI

International Nuclear Information System (INIS)

Olyaee, Saeed; Hamedi, Samaneh

2011-01-01

In this paper, an approach based on neural network (NN) for nonlinearity modeling in a nano-metrology system using three-longitudinal-mode laser heterodyne interferometer (TLMI) for length and displacement measurements is presented. We model nonlinearity errors that arise from elliptically and non-orthogonally polarized laser beams, rotational error in the alignment of laser head with respect to the polarizing beam splitter, rotational error in the alignment of the mixing polarizer, and unequal transmission coefficients in the polarizing beam splitter. Here we use a neural network algorithm based on the multi-layer perceptron (MLP) network. The simulation results show that multi-layer feed forward perceptron network is successfully applicable to real noisy interferometer signals.

Neural networks within multi-core optic fibers.

Science.gov (United States)

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.

Feed-Forward Corrections for Tune and Chromaticity Injection Decay During 2015 LHC Operation

CERN Document Server

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.

Artificial neural network for modeling the extraction of aromatic hydrocarbons from lube oil cuts

Energy Technology Data Exchange (ETDEWEB)

Mehrkesh, A.H.; Hajimirzaee, S. [Islamic Azad University, Majlesi Branch, Isfahan (Iran, Islamic Republic of); Hatamipour, M.S.; Tavakoli, T. [Department of Chemical Engineering, University of Isfahan, Isfahan (Iran, Islamic Republic of)

2011-03-15

An artificial neural network (ANN) approach was used to obtain a simulation model to predict the rotating disc contactor (RDC) performance during the extraction of aromatic hydrocarbons from lube oil cuts, to produce a lubricating base oil using furfural as solvent. The field data used for training the ANN model was obtained from a lubricating oil production company. The input parameters of the ANN model were the volumetric flow rates of feed and solvent, the temperatures of feed and solvent, and the disc rotation rate. The output parameters were the volumetric flow rate of the raffinate phase and the extraction yield. In this study, a feed-forward multi-layer perceptron neural network was successfully used to demonstrate the complex relationship between the mentioned input and output parameters. (Copyright copyright 2011 WILEY-VCH Verlag GmbH and Co. KGaA, Weinheim)

Two distinct neural mechanisms underlying indirect reciprocity.

Science.gov (United States)

Watanabe, Takamitsu; Takezawa, Masanori; Nakawake, Yo; Kunimatsu, Akira; Yamasue, Hidenori; Nakamura, Mitsuhiro; Miyashita, Yasushi; Masuda, Naoki

2014-03-18

Cooperation is a hallmark of human society. Humans often cooperate with strangers even if they will not meet each other again. This so-called indirect reciprocity enables large-scale cooperation among nonkin and can occur based on a reputation mechanism or as a succession of pay-it-forward behavior. Here, we provide the functional and anatomical neural evidence for two distinct mechanisms governing the two types of indirect reciprocity. Cooperation occurring as reputation-based reciprocity specifically recruited the precuneus, a region associated with self-centered cognition. During such cooperative behavior, the precuneus was functionally connected with the caudate, a region linking rewards to behavior. Furthermore, the precuneus of a cooperative subject had a strong resting-state functional connectivity (rsFC) with the caudate and a large gray matter volume. In contrast, pay-it-forward reciprocity recruited the anterior insula (AI), a brain region associated with affective empathy. The AI was functionally connected with the caudate during cooperation occurring as pay-it-forward reciprocity, and its gray matter volume and rsFC with the caudate predicted the tendency of such cooperation. The revealed difference is consistent with the existing results of evolutionary game theory: although reputation-based indirect reciprocity robustly evolves as a self-interested behavior in theory, pay-it-forward indirect reciprocity does not on its own. The present study provides neural mechanisms underlying indirect reciprocity and suggests that pay-it-forward reciprocity may not occur as myopic profit maximization but elicit emotional rewards.

System Identification, Prediction, Simulation and Control with Neural Networks

DEFF Research Database (Denmark)

Sørensen, O.

1997-01-01

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......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...

Feed-forward general-purpose computer

Energy Technology Data Exchange (ETDEWEB)

Yamada, H; Yoshioka, Y; Nakamura, T; Shigei, Y

1983-08-01

The feed forward machine (FFM) proposed by the authors has a CPU composed of many fixed arithmetic units and registers. Many features of the FFM which are compatible with concurrent operating and reduce the instruction requirement for store are reported. In order to evaluate the FFM, the minimum execution time of instructions is discussed by using the Petri Net model. From this it is predicted that the execution time will be 0.46-0.6 times the real execution time. Furthermore, it is concluded that the program for the FFM will be reduced in size with respect to the program for the Von Neumann computers. 12 references.

Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control †

Directory of Open Access Journals (Sweden)

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 †

Science.gov (United States)

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

Pattern Recognition and Classification of Fatal Traffic Accidents in Israel A Neural Network Approach

DEFF Research Database (Denmark)

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...

In vivo temporal property of GABAergic neural transmission in collateral feed-forward inhibition system of hippocampal-prefrontal pathway.

Science.gov (United States)

Takita, Masatoshi; Kuramochi, Masahito; Izaki, Yoshinori; Ohtomi, Michiko

2007-05-30

Anatomical evidence suggests that rat CA1 hippocampal afferents collaterally innervate excitatory projecting pyramidal neurons and inhibitory interneurons, creating a disynaptic, feed-forward inhibition microcircuit in the medial prefrontal cortex (mPFC). We investigated the temporal relationship between the frequency of paired synaptic transmission and gamma-aminobutyric acid (GABA)ergic receptor-mediated modulation of the microcircuit in vivo under urethane anesthesia. Local perfusions of a GABAa antagonist (-)-bicuculline into the mPFC via microdialysis resulted in a statistically significant disinhibitory effect on intrinsic GABA action, increasing the first and second mPFC responses following hippocampal paired stimulation at interstimulus intervals of 100-200 ms, but not those at 25-50 ms. This (-)-bicuculline-induced disinhibition was compensated by the GABAa agonist muscimol, which itself did not attenuate the intrinsic oscillation of the local field potentials. The perfusion of a sub-minimal concentration of GABAb agonist (R)-baclofen slightly enhanced the synaptic transmission, regardless of the interstimulus interval. In addition to the tonic control by spontaneous fast-spiking GABAergic neurons, it is clear the sequential transmission of the hippocampal-mPFC pathway can phasically drive the collateral feed-forward inhibition system through activation of a GABAa receptor, bringing an active signal filter to the various types of impulse trains that enter the mPFC from the hippocampus in vivo.

Predicting Student Academic Performance: A Comparison of Two Meta-Heuristic Algorithms Inspired by Cuckoo Birds for Training Neural Networks

Directory of Open Access Journals (Sweden)

Jeng-Fung Chen

2014-10-01

Full Text Available Predicting student academic performance with a high accuracy facilitates admission decisions and enhances educational services at educational institutions. This raises the need to propose a model that predicts student performance, based on the results of standardized exams, including university entrance exams, high school graduation exams, and other influential factors. In this study, an approach to the problem based on the artificial neural network (ANN with the two meta-heuristic algorithms inspired by cuckoo birds and their lifestyle, namely, Cuckoo Search (CS and Cuckoo Optimization Algorithm (COA is proposed. In particular, we used previous exam results and other factors, such as the location of the student’s high school and the student’s gender as input variables, and predicted the student academic performance. The standard CS and standard COA were separately utilized to train the feed-forward network for prediction. The algorithms optimized the weights between layers and biases of the neuron network. The simulation results were then discussed and analyzed to investigate the prediction ability of the neural network trained by these two algorithms. The findings demonstrated that both CS and COA have potential in training ANN and ANN-COA obtained slightly better results for predicting student academic performance in this case. It is expected that this work may be used to support student admission procedures and strengthen the service system in educational institutions.

Cell-type specific short-term plasticity at auditory nerve synapses controls feed-forward inhibition in the dorsal cochlear nucleus

Directory of Open Access Journals (Sweden)

Miloslav eSedlacek

2014-07-01

Full Text Available Feedforward inhibition represents a powerful mechanism by which control of the timing and fidelity of action potentials in local synaptic circuits of various brain regions is achieved. In the cochlear nucleus, the auditory nerve provides excitation to both principal neurons and inhibitory interneurons. Here, we investigated the synaptic circuit associated with fusiform cells (FCs, principal neurons of the dorsal cochlear nucleus (DCN that receive excitation from auditory nerve fibers and inhibition from tuberculoventral cells (TVCs on their basal dendrites in the deep layer of DCN. Despite the importance of these inputs in regulating fusiform cell firing behavior, the mechanisms determining the balance of excitation and feed-forward inhibition in this circuit are not well understood. Therefore, we examined the timing and plasticity of auditory nerve driven feed-forward inhibition (FFI onto FCs. We find that in some FCs, excitatory and inhibitory components of feed-forward inhibition had the same stimulation thresholds indicating they could be triggered by activation of the same fibers. In other FCs, excitation and inhibition exhibit different stimulus thresholds, suggesting FCs and TVCs might be activated by different sets of fibers. In addition we find that during repetitive activation, synapses formed by the auditory nerve onto TVCs and FCs exhibit distinct modes of short-term plasticity. Feed-forward inhibitory post-synaptic currents (IPSCs in FCs exhibit short-term depression because of prominent synaptic depression at the auditory nerve-TVC synapse. Depression of this feedforward inhibitory input causes a shift in the balance of fusiform cell synaptic input towards greater excitation and suggests that fusiform cell spike output will be enhanced by physiological patterns of auditory nerve activity.

Regularization and Complexity Control in Feed-forward Networks

OpenAIRE

Bishop, C. M.

1995-01-01

In this paper we consider four alternative approaches to complexity control in feed-forward networks based respectively on architecture selection, regularization, early stopping, and training with noise. We show that there are close similarities between these approaches and we argue that, for most practical applications, the technique of regularization should be the method of choice.

A novel nature inspired firefly algorithm with higher order neural network: Performance analysis

Directory of Open Access Journals (Sweden)

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 network-based survey analysis of risk management practices in new product development

DEFF Research Database (Denmark)

Kampianakis, Andreas N.; Oehmen, Josef

2017-01-01

The current study investigates the applicability of Artificial Neural Networks (ANNs) to analyse survey data on the effectiveness of risk management practices in product development (PD) projects, and its ability to forecast project outcomes. Moreover, this study presents the relations between risk...... Neural Networks. Dataset used is a filtered survey of 291 product development programs. Answers of this survey are used as training input and target output, in pattern recognition two-layer feed forward networks, using various transfer functions. Using this method, relations among 6 project practices...... and 13 outcome metrics were revealed. Results of this analysis are compared with existent results made through statistical analysis in prior work of one of the authors. Future investigation is needed in order to tackle the lack of data and create an easy to use platform for industrial use....

Artificial neural network modeling of jatropha oil fueled diesel engine for emission predictions

Directory of Open Access Journals (Sweden)

Ganapathy Thirunavukkarasu

2009-01-01

Full Text Available This paper deals with artificial neural network modeling of diesel engine fueled with jatropha oil to predict the unburned hydrocarbons, smoke, and NOx emissions. The experimental data from the literature have been used as the data base for the proposed neural network model development. For training the networks, the injection timing, injector opening pressure, plunger diameter, and engine load are used as the input layer. The outputs are hydrocarbons, smoke, and NOx emissions. The feed forward back propagation learning algorithms with two hidden layers are used in the networks. For each output a different network is developed with required topology. The artificial neural network models for hydrocarbons, smoke, and NOx emissions gave R2 values of 0.9976, 0.9976, and 0.9984 and mean percent errors of smaller than 2.7603, 4.9524, and 3.1136, respectively, for training data sets, while the R2 values of 0.9904, 0.9904, and 0.9942, and mean percent errors of smaller than 6.5557, 6.1072, and 4.4682, respectively, for testing data sets. The best linear fit of regression to the artificial neural network models of hydrocarbons, smoke, and NOx emissions gave the correlation coefficient values of 0.98, 0.995, and 0.997, respectively.

Spike-timing computation properties of a feed-forward neural network model

Directory of Open Access Journals (Sweden)

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.

Recognition of decays of charged tracks with neural network techniques

International Nuclear Information System (INIS)

Stimpfl-Abele, G.

1991-01-01

We developed neural-network learning techniques for the recognition of decays of charged tracks using a feed-forward network with error back-propagation. Two completely different methods are described in detail and their efficiencies for several NN architectures are compared with conventional methods. Excellent results are obtained. (orig.)

Artificial neural network based approach to transmission lines protection

International Nuclear Information System (INIS)

Joorabian, M.

1999-05-01

The aim of this paper is to present and accurate fault detection technique for high speed distance protection using artificial neural networks. The feed-forward multi-layer neural network with the use of supervised learning and the common training rule of error back-propagation is chosen for this study. Information available locally at the relay point is passed to a neural network in order for an assessment of the fault location to be made. However in practice there is a large amount of information available, and a feature extraction process is required to reduce the dimensionality of the pattern vectors, whilst retaining important information that distinguishes the fault point. The choice of features is critical to the performance of the neural networks learning and operation. A significant feature in this paper is that an artificial neural network has been designed and tested to enhance the precision of the adaptive capabilities for distance protection

New approach to ECG's features recognition involving neural network

International Nuclear Information System (INIS)

Babloyantz, A.; Ivanov, V.V.; Zrelov, P.V.

2001-01-01

A new approach for the detection of slight changes in the form of the ECG signal is proposed. It is based on the approximation of raw ECG data inside each RR-interval by the expansion in polynomials of special type and on the classification of samples represented by sets of expansion coefficients using a layered feed-forward neural network. The transformation applied provides significantly simpler data structure, stability to noise and to other accidental factors. A by-product of the method is the compression of ECG data with factor 5

A Neural Network Approach for GMA Butt Joint Welding

DEFF Research Database (Denmark)

Christensen, Kim Hardam; Sørensen, Torben

2003-01-01

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...

A Neural Network Approach for GMA Butt Joint Welding

DEFF Research Database (Denmark)

Christensen, Kim Hardam; Sørensen, Torben

2003-01-01

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......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...

Synchronization and Inter-Layer Interactions of Noise-Driven Neural Networks.

Science.gov (United States)

Yuniati, Anis; Mai, Te-Lun; Chen, Chi-Ming

2017-01-01

In this study, we used the Hodgkin-Huxley (HH) model of neurons to investigate the phase diagram of a developing single-layer neural network and that of a network consisting of two weakly coupled neural layers. These networks are noise driven and learn through the spike-timing-dependent plasticity (STDP) or the inverse STDP rules. We described how these networks transited from a non-synchronous background activity state (BAS) to a synchronous firing state (SFS) by varying the network connectivity and the learning efficacy. In particular, we studied the interaction between a SFS layer and a BAS layer, and investigated how synchronous firing dynamics was induced in the BAS layer. We further investigated the effect of the inter-layer interaction on a BAS to SFS repair mechanism by considering three types of neuron positioning (random, grid, and lognormal distributions) and two types of inter-layer connections (random and preferential connections). Among these scenarios, we concluded that the repair mechanism has the largest effect for a network with the lognormal neuron positioning and the preferential inter-layer connections.

Global forward-predicting dynamic routing for traffic concurrency space stereo multi-layer scale-free network

International Nuclear Information System (INIS)

Xie Wei-Hao; Zhou Bin; Liu En-Xiao; Lu Wei-Dang; Zhou Ting

2015-01-01

Many real communication networks, such as oceanic monitoring network and land environment observation network, can be described as space stereo multi-layer structure, and the traffic in these networks is concurrent. Understanding how traffic dynamics depend on these real communication networks and finding an effective routing strategy that can fit the circumstance of traffic concurrency and enhance the network performance are necessary. In this light, we propose a traffic model for space stereo multi-layer complex network and introduce two kinds of global forward-predicting dynamic routing strategies, global forward-predicting hybrid minimum queue (HMQ) routing strategy and global forward-predicting hybrid minimum degree and queue (HMDQ) routing strategy, for traffic concurrency space stereo multi-layer scale-free networks. By applying forward-predicting strategy, the proposed routing strategies achieve better performances in traffic concurrency space stereo multi-layer scale-free networks. Compared with the efficient routing strategy and global dynamic routing strategy, HMDQ and HMQ routing strategies can optimize the traffic distribution, alleviate the number of congested packets effectively and reach much higher network capacity. (paper)

Molecular annotation of integrative feeding neural circuits.

Science.gov (United States)

Pérez, Cristian A; Stanley, Sarah A; Wysocki, Robert W; Havranova, Jana; Ahrens-Nicklas, Rebecca; Onyimba, Frances; Friedman, Jeffrey M

2011-02-02

The identity of higher-order neurons and circuits playing an associative role to control feeding is unknown. We injected pseudorabies virus, a retrograde tracer, into masseter muscle, salivary gland, and tongue of BAC-transgenic mice expressing GFP in specific neural populations and identified several CNS regions that project multisynaptically to the periphery. MCH and orexin neurons were identified in the lateral hypothalamus, and Nurr1 and Cnr1 in the amygdala and insular/rhinal cortices. Cholera toxin β tracing showed that insular Nurr1(+) and Cnr1(+) neurons project to the amygdala or lateral hypothalamus, respectively. Finally, we show that cortical Cnr1(+) neurons show increased Cnr1 mRNA and c-Fos expression after fasting, consistent with a possible role for Cnr1(+) neurons in feeding. Overall, these studies define a general approach for identifying specific molecular markers for neurons in complex neural circuits. These markers now provide a means for functional studies of specific neuronal populations in feeding or other complex behaviors. Copyright © 2011 Elsevier Inc. All rights reserved.

A NEURAL NETWORK BASED TRAFFIC-AWARE FORWARDING STRATEGY IN NAMED DATA NETWORKING

OpenAIRE

Parisa Bazmi; Manijeh Keshtgary

2016-01-01

Named Data Networking (NDN) is a new Internet architecture which has been proposed to eliminate TCP/IP Internet architecture restrictions. This architecture is abstracting away the notion of host and working based on naming datagrams. However, one of the major challenges of NDN is supporting QoS-aware forwarding strategy so as to forward Interest packets intelligently over multiple paths based on the current network condition. In this paper, Neural Network (NN) Based Traffic-aware Forwarding ...

The modelling of lead removal from water by deep eutectic solvents functionalized CNTs: artificial neural network (ANN) approach.

Science.gov (United States)

Fiyadh, Seef Saadi; AlSaadi, Mohammed Abdulhakim; AlOmar, Mohamed Khalid; Fayaed, Sabah Saadi; Hama, Ako R; Bee, Sharifah; El-Shafie, Ahmed

2017-11-01

The main challenge in the lead removal simulation is the behaviour of non-linearity relationships between the process parameters. The conventional modelling technique usually deals with this problem by a linear method. The substitute modelling technique is an artificial neural network (ANN) system, and it is selected to reflect the non-linearity in the interaction among the variables in the function. Herein, synthesized deep eutectic solvents were used as a functionalized agent with carbon nanotubes as adsorbents of Pb 2+ . Different parameters were used in the adsorption study including pH (2.7 to 7), adsorbent dosage (5 to 20 mg), contact time (3 to 900 min) and Pb 2+ initial concentration (3 to 60 mg/l). The number of experimental trials to feed and train the system was 158 runs conveyed in laboratory scale. Two ANN types were designed in this work, the feed-forward back-propagation and layer recurrent; both methods are compared based on their predictive proficiency in terms of the mean square error (MSE), root mean square error, relative root mean square error, mean absolute percentage error and determination coefficient (R 2 ) based on the testing dataset. The ANN model of lead removal was subjected to accuracy determination and the results showed R 2 of 0.9956 with MSE of 1.66 × 10 -4 . The maximum relative error is 14.93% for the feed-forward back-propagation neural network model.

Türkiye’de Enflasyonun İleri ve Geri Beslemeli Yapay Sinir Ağlarının Melez Yaklaşımı ile Öngörüsü = Forecasting of Turkey Inflation with Hybrid of Feed Forward and Recurrent Artifical Neural Networks

Directory of Open Access Journals (Sweden)

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.

Forward and Reverse Process Models for the Squeeze Casting Process Using Neural Network Based Approaches

Directory of Open Access Journals (Sweden)

Manjunath Patel Gowdru Chandrashekarappa

2014-01-01

Full Text Available The present research work is focussed to develop an intelligent system to establish the input-output relationship utilizing forward and reverse mappings of artificial neural networks. Forward mapping aims at predicting the density and secondary dendrite arm spacing (SDAS from the known set of squeeze cast process parameters such as time delay, pressure duration, squeezes pressure, pouring temperature, and die temperature. An attempt is also made to meet the industrial requirements of developing the reverse model to predict the recommended squeeze cast parameters for the desired density and SDAS. Two different neural network based approaches have been proposed to carry out the said task, namely, back propagation neural network (BPNN and genetic algorithm neural network (GA-NN. The batch mode of training is employed for both supervised learning networks and requires huge training data. The requirement of huge training data is generated artificially at random using regression equation derived through real experiments carried out earlier by the same authors. The performances of BPNN and GA-NN models are compared among themselves with those of regression for ten test cases. The results show that both models are capable of making better predictions and the models can be effectively used in shop floor in selection of most influential parameters for the desired outputs.

Wind Resource Assessment and Forecast Planning with Neural Networks

Directory of Open Access Journals (Sweden)

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.

Sequential neural models with stochastic layers

DEFF Research Database (Denmark)

Fraccaro, Marco; Sønderby, Søren Kaae; Paquet, Ulrich

2016-01-01

How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural...... generative model. The clear separation of deterministic and stochastic layers allows a structured variational inference network to track the factorization of the model's posterior distribution. By retaining both the nonlinear recursive structure of a recurrent neural network and averaging over...

Investigating transfer gate potential barrier by feed-forward effect measurement

NARCIS (Netherlands)

Xu, Y.; Ge, X.; Theuwissen, A.J.P.

2015-01-01

In a 4T pixel, the transfer gate (TG) “OFF” surface potential is one of the important parameters, which determines the pinned photodiode (PPD) full well capacity. The feed-forward effect measurement is a powerful tool to characterize the relationship of the PPD injection potential and the

Forcast of TEXT plasma disruptions using soft X-rays as input signal in a neural network

International Nuclear Information System (INIS)

Vannucci, A.; Oliveira, K.A.; Tajima, T.

1998-02-01

A feed-forward neural network with two hidden layers is used in this work to forecast major and minor disruptive instabilities in TEXT discharges. Using soft X-ray signals as input data, the neural net is trained with one disruptive plasma pulse, and a different disruptive discharge is used for validation. After being properly trained the networks, with the same set of weights. is then used to forecast disruptions in two others different plasma pulses. It is observed that the neural net is able to predict the incoming of a disruption more than 3 ms in advance. This time interval is almost three times longer than the one already obtained previously when magnetic signal from a Mirnov coil was used to feed the neural networks with. To our own eye we fail to see any indication of an upcoming disruption from the experimental data this far back from the time of disruption. Finally, from what we observe in the predictive behavior of our network, speculations are made whether the disruption triggering mechanism would be associated to an increase of the m = 2 magnetic island, that disturbs the central part of the plasma column afterwards or, in face of the results from this work, the initial perturbation would have occurred first in the central part of the plasma column, within the q = 1 magnetic surface, and then the m = 2 MHD mode would be destabilized afterwards

A neural network device for on-line particle identification in cosmic ray experiments

International Nuclear Information System (INIS)

Scrimaglio, R.; Finetti, N.; D'Altorio, L.; Rantucci, E.; Raso, M.; Segreto, E.; Tassoni, A.; Cardarilli, G.C.

2004-01-01

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

A neural network-based optimal spatial filter design method for motor imagery classification.

Directory of Open Access Journals (Sweden)

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.

A high-speed tunable beam splitter for feed-forward photonic quantum information processing.

Science.gov (United States)

Ma, Xiao-Song; Zotter, Stefan; Tetik, Nuray; Qarry, Angie; Jennewein, Thomas; Zeilinger, Anton

2011-11-07

We realize quantum gates for path qubits with a high-speed, polarization-independent and tunable beam splitter. Two electro-optical modulators act in a Mach-Zehnder interferometer as high-speed phase shifters and rapidly tune its splitting ratio. We test its performance with heralded single photons, observing a polarization-independent interference contrast above 95%. The switching time is about 5.6 ns, and a maximal repetition rate is 2.5 MHz. We demonstrate tunable feed-forward operations of a single-qubit gate of path-encoded qubits and a two-qubit gate via measurement-induced interaction between two photons.

Reliability analysis of C-130 turboprop engine components using artificial neural network

Science.gov (United States)

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

Hippocampus-driven feed-forward inhibition of the prefrontal cortex mediates relapse of extinguished fear.

Science.gov (United States)

Marek, Roger; Jin, Jingji; Goode, Travis D; Giustino, Thomas F; Wang, Qian; Acca, Gillian M; Holehonnur, Roopashri; Ploski, Jonathan E; Fitzgerald, Paul J; Lynagh, Timothy; Lynch, Joseph W; Maren, Stephen; Sah, Pankaj

2018-03-01

The medial prefrontal cortex (mPFC) has been implicated in the extinction of emotional memories, including conditioned fear. We found that ventral hippocampal (vHPC) projections to the infralimbic (IL) cortex recruited parvalbumin-expressing interneurons to counter the expression of extinguished fear and promote fear relapse. Whole-cell recordings ex vivo revealed that optogenetic activation of vHPC input to amygdala-projecting pyramidal neurons in the IL was dominated by feed-forward inhibition. Selectively silencing parvalbumin-expressing, but not somatostatin-expressing, interneurons in the IL eliminated vHPC-mediated inhibition. In behaving rats, pharmacogenetic activation of vHPC→IL projections impaired extinction recall, whereas silencing IL projectors diminished fear renewal. Intra-IL infusion of GABA receptor agonists or antagonists, respectively, reproduced these effects. Together, our findings describe a previously unknown circuit mechanism for the contextual control of fear, and indicate that vHPC-mediated inhibition of IL is an essential neural substrate for fear relapse.

Tutorial on neural network applications in high energy physics: A 1992 perspective

International Nuclear Information System (INIS)

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

Consistently Trained Artificial Neural Network for Automatic Ship Berthing Control

Directory of Open Access Journals (Sweden)

Y.A. Ahmed

2015-09-01

Full Text Available In this paper, consistently trained Artificial Neural Network controller for automatic ship berthing is discussed. Minimum time course changing manoeuvre is utilised to ensure such consistency and a new concept named ‘virtual window’ is introduced. Such consistent teaching data are then used to train two separate multi-layered feed forward neural networks for command rudder and propeller revolution output. After proper training, several known and unknown conditions are tested to judge the effectiveness of the proposed controller using Monte Carlo simulations. After getting acceptable percentages of success, the trained networks are implemented for the free running experiment system to judge the network’s real time response for Esso Osaka 3-m model ship. The network’s behaviour during such experiments is also investigated for possible effect of initial conditions as well as wind disturbances. Moreover, since the final goal point of the proposed controller is set at some distance from the actual pier to ensure safety, therefore a study on automatic tug assistance is also discussed for the final alignment of the ship with actual pier.

Neural Control and Adaptive Neural Forward Models for Insect-like, Energy-Efficient, and Adaptable Locomotion of Walking Machines

DEFF Research Database (Denmark)

Manoonpong, Poramate; Parlitz, Ulrich; Wörgötter, Florentin

2013-01-01

such natural properties with artificial legged locomotion systems by using different approaches including machine learning algorithms, classical engineering control techniques, and biologically-inspired control mechanisms. However, their levels of performance are still far from the natural ones. By contrast...... on sensory feedback and adaptive neural forward models with efference copies. This neural closed-loop controller enables a walking machine to perform a multitude of different walking patterns including insect-like leg movements and gaits as well as energy-efficient locomotion. In addition, the forward models...... allow the machine to autonomously adapt its locomotion to deal with a change of terrain, losing of ground contact during stance phase, stepping on or hitting an obstacle during swing phase, leg damage, and even to promote cockroach-like climbing behavior. Thus, the results presented here show...

Application of structured support vector machine backpropagation to a convolutional neural network for human pose estimation.

Science.gov (United States)

Witoonchart, Peerajak; Chongstitvatana, Prabhas

2017-08-01

In this study, for the first time, we show how to formulate a structured support vector machine (SSVM) as two layers in a convolutional neural network, where the top layer is a loss augmented inference layer and the bottom layer is the normal convolutional layer. We show that a deformable part model can be learned with the proposed structured SVM neural network by backpropagating the error of the deformable part model to the convolutional neural network. The forward propagation calculates the loss augmented inference and the backpropagation calculates the gradient from the loss augmented inference layer to the convolutional layer. Thus, we obtain a new type of convolutional neural network called an Structured SVM convolutional neural network, which we applied to the human pose estimation problem. This new neural network can be used as the final layers in deep learning. Our method jointly learns the structural model parameters and the appearance model parameters. We implemented our method as a new layer in the existing Caffe library. Copyright © 2017 Elsevier Ltd. All rights reserved.

A mixed incoherent feed-forward loop contributes to the regulation of bacterial photosynthesis genes.

Science.gov (United States)

Mank, Nils N; Berghoff, Bork A; Klug, Gabriele

2013-03-01

Living cells use a variety of regulatory network motifs for accurate gene expression in response to changes in their environment or during differentiation processes. In Rhodobacter sphaeroides, a complex regulatory network controls expression of photosynthesis genes to guarantee optimal energy supply on one hand and to avoid photooxidative stress on the other hand. Recently, we identified a mixed incoherent feed-forward loop comprising the transcription factor PrrA, the sRNA PcrZ and photosynthesis target genes as part of this regulatory network. This point-of-view provides a comparison to other described feed-forward loops and discusses the physiological relevance of PcrZ in more detail.

A novel and generalized approach in the inversion of geoelectrical resistivity data using Artificial Neural Networks (ANN)

Science.gov (United States)

Raj, A. Stanley; Srinivas, Y.; Oliver, D. Hudson; Muthuraj, D.

2014-03-01

The non-linear apparent resistivity problem in the subsurface study of the earth takes into account the model parameters in terms of resistivity and thickness of individual subsurface layers using the trained synthetic data by means of Artificial Neural Networks (ANN). Here we used a single layer feed-forward neural network with fast back propagation learning algorithm. So on proper training of back propagation networks it tends to give the resistivity and thickness of the subsurface layer model of the field resistivity data with reference to the synthetic data trained in the appropriate network. During training, the weights and biases of the network are iteratively adjusted to make network performance function level more efficient. On adequate training, errors are minimized and the best result is obtained using the artificial neural networks. The network is trained with more number of VES data and this trained network is demonstrated by the field data. The accuracy of inversion depends upon the number of data trained. In this novel and specially designed algorithm, the interpretation of the vertical electrical sounding has been done successfully with the more accurate layer model.

Using Elman recurrent neural networks with conjugate gradient algorithm in determining the anesthetic the amount of anesthetic medicine to be applied.

Science.gov (United States)

Güntürkün, Rüştü

2010-08-01

In this study, Elman recurrent neural networks have been defined by using conjugate gradient algorithm in order to determine the depth of anesthesia in the continuation stage of the anesthesia and to estimate the amount of medicine to be applied at that moment. The feed forward neural networks are also used for comparison. The conjugate gradient algorithm is compared with back propagation (BP) for training of the neural Networks. The applied artificial neural network is composed of three layers, namely the input layer, the hidden layer and the output layer. The nonlinear activation function sigmoid (sigmoid function) has been used in the hidden layer and the output layer. EEG data has been recorded with Nihon Kohden 9200 brand 22-channel EEG device. The international 8-channel bipolar 10-20 montage system (8 TB-b system) has been used in assembling the recording electrodes. EEG data have been recorded by being sampled once in every 2 milliseconds. The artificial neural network has been designed so as to have 60 neurons in the input layer, 30 neurons in the hidden layer and 1 neuron in the output layer. The values of the power spectral density (PSD) of 10-second EEG segments which correspond to the 1-50 Hz frequency range; the ratio of the total power of PSD values of the EEG segment at that moment in the same range to the total of PSD values of EEG segment taken prior to the anesthesia.

LIDAR Wind Speed Measurement Analysis and Feed-Forward Blade Pitch Control for Load Mitigation in Wind Turbines: January 2010--January 2011

Energy Technology Data Exchange (ETDEWEB)

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

Neural Control and Adaptive Neural Forward Models for Insect-like, Energy-Efficient, and Adaptable Locomotion of Walking Machines

Directory of Open Access Journals (Sweden)

Poramate eManoonpong

2013-02-01

Full Text Available Living creatures, like walking animals, have found fascinating solutions for the problem of locomotion control. Their movements show the impression of elegance including versatile, energy-efficient, and adaptable locomotion. During the last few decades, roboticists have tried to imitate such natural properties with artificial legged locomotion systems by using different approaches including machine learning algorithms, classical engineering control techniques, and biologically-inspired control mechanisms. However, their levels of performance are still far from the natural ones. By contrast, animal locomotion mechanisms seem to largely depend not only on central mechanisms (central pattern generators, CPGs and sensory feedback (afferent-based control but also on internal forward models (efference copies. They are used to a different degree in different animals. Generally, CPGs organize basic rhythmic motions which are shaped by sensory feedback while internal models are used for sensory prediction and state estimations. According to this concept, we present here adaptive neural locomotion control consisting of a CPG mechanism with neuromodulation and local leg control mechanisms based on sensory feedback and adaptive neural forward models with efference copies. This neural closed-loop controller enables a walking machine to perform a multitude of different walking patterns including insect-like leg movements and gaits as well as energy-efficient locomotion. In addition, the forward models allow the machine to autonomously adapt its locomotion to deal with a change of terrain, losing of ground contact during stance phase, stepping on or hitting an obstacle during swing phase, leg damage, and even to promote cockroach-like climbing behavior. Thus, the results presented here show that the employed embodied neural closed-loop system can be a powerful way for developing robust and adaptable machines.

Fault detection and classification in electrical power transmission system using artificial neural network.

Science.gov (United States)

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.

Gas metal arc welding of butt joint with varying gap width based on neural networks

DEFF Research Database (Denmark)

Christensen, Kim Hardam; Sørensen, Torben

2005-01-01

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......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...

Feed forward control: An implementation at CIRFEL

International Nuclear Information System (INIS)

Krishnaswamy, J.; Lehrman, I.S.; Hartley, R.

1995-01-01

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 3μsec pulse

Expanding the occupational health methodology: A concatenated artificial neural network approach to model the burnout process in Chinese nurses.

Science.gov (United States)

Ladstätter, Felix; Garrosa, Eva; Moreno-Jiménez, Bernardo; Ponsoda, Vicente; Reales Aviles, José Manuel; Dai, Junming

2016-01-01

Artificial neural networks are sophisticated modelling and prediction tools capable of extracting complex, non-linear relationships between predictor (input) and predicted (output) variables. This study explores this capacity by modelling non-linearities in the hardiness-modulated burnout process with a neural network. Specifically, two multi-layer feed-forward artificial neural networks are concatenated in an attempt to model the composite non-linear burnout process. Sensitivity analysis, a Monte Carlo-based global simulation technique, is then utilised to examine the first-order effects of the predictor variables on the burnout sub-dimensions and consequences. Results show that (1) this concatenated artificial neural network approach is feasible to model the burnout process, (2) sensitivity analysis is a prolific method to study the relative importance of predictor variables and (3) the relationships among variables involved in the development of burnout and its consequences are to different degrees non-linear. Many relationships among variables (e.g., stressors and strains) are not linear, yet researchers use linear methods such as Pearson correlation or linear regression to analyse these relationships. Artificial neural network analysis is an innovative method to analyse non-linear relationships and in combination with sensitivity analysis superior to linear methods.

Cocoa Husk/Cassava Leaf Inclusions in Layers Mash Produced Quality Cheap Feeds

Directory of Open Access Journals (Sweden)

Olubamiwa

2001-01-01

Full Text Available A 10-week trial was conducted to investigate the effects of cocoa husk meal (CHM/cassava leaf meal (CLM mixtures in layers mash on laying hen production performance and egg quality. Results were compared with those obtained using two locally popular standard commercial feeds (CFDs. CHM/CLM mixtures were included in the two test diets in the following order : Diet 1 (7.3 CHM/2.7 % CLM and Diet 2 (14.6 CHM/5.4 CLM. Forty 6-month-in-lay individually caged Black Nera hens were randomly allocated to the four diets. Feeding was ad libitum Feed intake, egg weight and percentage egg production were reduced (P <0.05 on Diet 2 relative to the CFDs. The reduction in egg weight was however marginal while the values were in line with the 56-58 g in the literature. Similarly, the value of 65 % percent egg production was considered not poor. Feed efficiency, yolk colour index, shell thickness and yolk percentage were not influenced by diet. On average, feed cost of the CHM/CLM diets were 60 % of those of the CFDs while the feed cost/kg egg was roughly doubled on the latter. It was concluded that the inclusion of CHM/CLM in layers mash promises to be a very economically rewarding venture where the two farm by-products are available.

Automatic target recognition using a feature-based optical neural network

Science.gov (United States)

Chao, Tien-Hsin

1992-01-01

An optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.

Germ layers, the neural crest and emergent organization in development and evolution.

Science.gov (United States)

Hall, Brian K

2018-04-10

Discovered in chick embryos by Wilhelm His in 1868 and named the neural crest by Arthur Milnes Marshall in 1879, the neural crest cells that arise from the neural folds have since been shown to differentiate into almost two dozen vertebrate cell types and to have played major roles in the evolution of such vertebrate features as bone, jaws, teeth, visceral (pharyngeal) arches, and sense organs. I discuss the discovery that ectodermal neural crest gave rise to mesenchyme and the controversy generated by that finding; the germ layer theory maintained that only mesoderm could give rise to mesenchyme. A second topic of discussion is germ layers (including the neural crest) as emergent levels of organization in animal development and evolution that facilitated major developmental and evolutionary change. The third topic is gene networks, gene co-option, and the evolution of gene-signaling pathways as key to developmental and evolutionary transitions associated with the origin and evolution of the neural crest and neural crest cells. © 2018 Wiley Periodicals, Inc.

Feed-Forward Control of Kite Power Systems

International Nuclear Information System (INIS)

Fechner, Uwe; Schmehl, Roland

2014-01-01

Kite power technology is a novel solution to harvest wind energy from altitudes that can not be reached by conventional wind turbines. The use of a lightweight but strong tether in place of an expensive tower provides an additional cost advantage, next to the higher capacity factor. This paper describes a method to estimate the wind velocity at the kite using measurement data at the kite and at the ground. Focussing on a kite power system, which is converting the traction power of a kite in a pumping mode of operation, a reel-out speed predictor is presented for use in feed-forward control of the tether reel-out speed of the winch. The results show, that the developed feedforward controller improves the force control accuracy by a factor of two compared to the previously used feedback controller. This allows to use a higher set force during the reel-out phase which in turn increases the average power output by more than 4%. Due to its straightforward implementation and low computational requirements feedforward control is considered a promising technique for the reliable and efficient operation of traction-based kite power systems

Diagonal recurrent neural network based adaptive control of nonlinear dynamical systems using lyapunov stability criterion.

Science.gov (United States)

Kumar, Rajesh; Srivastava, Smriti; Gupta, J R P

2017-03-01

In this paper adaptive control of nonlinear dynamical systems using diagonal recurrent neural network (DRNN) is proposed. The structure of DRNN is a modification of fully connected recurrent neural network (FCRNN). Presence of self-recurrent neurons in the hidden layer of DRNN gives it an ability to capture the dynamic behaviour of the nonlinear plant under consideration (to be controlled). To ensure stability, update rules are developed using lyapunov stability criterion. These rules are then used for adjusting the various parameters of DRNN. The responses of plants obtained with DRNN are compared with those obtained when multi-layer feed forward neural network (MLFFNN) is used as a controller. Also, in example 4, FCRNN is also investigated and compared with DRNN and MLFFNN. Robustness of the proposed control scheme is also tested against parameter variations and disturbance signals. Four simulation examples including one-link robotic manipulator and inverted pendulum are considered on which the proposed controller is applied. The results so obtained show the superiority of DRNN over MLFFNN as a controller. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Artificial neural network based modelling approach for municipal solid waste gasification in a fluidized bed reactor.

Science.gov (United States)

Pandey, Daya Shankar; Das, Saptarshi; Pan, Indranil; Leahy, James J; Kwapinski, Witold

2016-12-01

In this paper, multi-layer feed forward neural networks are used to predict the lower heating value of gas (LHV), lower heating value of gasification products including tars and entrained char (LHV p ) and syngas yield during gasification of municipal solid waste (MSW) during gasification in a fluidized bed reactor. These artificial neural networks (ANNs) with different architectures are trained using the Levenberg-Marquardt (LM) back-propagation algorithm and a cross validation is also performed to ensure that the results generalise to other unseen datasets. A rigorous study is carried out on optimally choosing the number of hidden layers, number of neurons in the hidden layer and activation function in a network using multiple Monte Carlo runs. Nine input and three output parameters are used to train and test various neural network architectures in both multiple output and single output prediction paradigms using the available experimental datasets. The model selection procedure is carried out to ascertain the best network architecture in terms of predictive accuracy. The simulation results show that the ANN based methodology is a viable alternative which can be used to predict the performance of a fluidized bed gasifier. Copyright © 2016 Elsevier Ltd. All rights reserved.

A Feed-Forward Control Realizing Fast Response for Three-Branch Interleaved DC-DC Converter in DC Microgrid

Directory of Open Access Journals (Sweden)

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.

A Feed-Forward Control Realizing Fast Response for Three-Branch Interleaved DC-DC Converter in DC Microgrid

DEFF Research Database (Denmark)

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 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....

SpineCreator: a Graphical User Interface for the Creation of Layered Neural Models.

Science.gov (United States)

Cope, A J; Richmond, P; James, S S; Gurney, K; Allerton, D J

2017-01-01

There is a growing requirement in computational neuroscience for tools that permit collaborative model building, model sharing, combining existing models into a larger system (multi-scale model integration), and are able to simulate models using a variety of simulation engines and hardware platforms. Layered XML model specification formats solve many of these problems, however they are difficult to write and visualise without tools. Here we describe a new graphical software tool, SpineCreator, which facilitates the creation and visualisation of layered models of point spiking neurons or rate coded neurons without requiring the need for programming. We demonstrate the tool through the reproduction and visualisation of published models and show simulation results using code generation interfaced directly into SpineCreator. As a unique application for the graphical creation of neural networks, SpineCreator represents an important step forward for neuronal modelling.

Flank wears Simulation by using back propagation neural network when cutting hardened H-13 steel in CNC End Milling

Science.gov (United States)

Hazza, Muataz Hazza F. Al; Adesta, Erry Y. T.; Riza, Muhammad

2013-12-01

High speed milling has many advantages such as higher removal rate and high productivity. However, higher cutting speed increase the flank wear rate and thus reducing the cutting tool life. Therefore estimating and predicting the flank wear length in early stages reduces the risk of unaccepted tooling cost. This research presents a neural network model for predicting and simulating the flank wear in the CNC end milling process. A set of sparse experimental data for finish end milling on AISI H13 at hardness of 48 HRC have been conducted to measure the flank wear length. Then the measured data have been used to train the developed neural network model. Artificial neural network (ANN) was applied to predict the flank wear length. The neural network contains twenty hidden layer with feed forward back propagation hierarchical. The neural network has been designed with MATLAB Neural Network Toolbox. The results show a high correlation between the predicted and the observed flank wear which indicates the validity of the models.

Flank wears Simulation by using back propagation neural network when cutting hardened H-13 steel in CNC End Milling

International Nuclear Information System (INIS)

Al Hazza, Muataz Hazza F; Adesta, Erry Y T; Riza, Muhammad

2013-01-01

High speed milling has many advantages such as higher removal rate and high productivity. However, higher cutting speed increase the flank wear rate and thus reducing the cutting tool life. Therefore estimating and predicting the flank wear length in early stages reduces the risk of unaccepted tooling cost. This research presents a neural network model for predicting and simulating the flank wear in the CNC end milling process. A set of sparse experimental data for finish end milling on AISI H13 at hardness of 48 HRC have been conducted to measure the flank wear length. Then the measured data have been used to train the developed neural network model. Artificial neural network (ANN) was applied to predict the flank wear length. The neural network contains twenty hidden layer with feed forward back propagation hierarchical. The neural network has been designed with MATLAB Neural Network Toolbox. The results show a high correlation between the predicted and the observed flank wear which indicates the validity of the models

Peak load demand forecasting using two-level discrete wavelet decomposition and neural network algorithm

Science.gov (United States)

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.

Predicting wettability behavior of fluorosilica coated metal surface using optimum neural network

Science.gov (United States)

Taghipour-Gorjikolaie, Mehran; Valipour Motlagh, Naser

2018-02-01

The interaction between variables, which are effective on the surface wettability, is very complex to predict the contact angles and sliding angles of liquid drops. In this paper, in order to solve this complexity, artificial neural network was used to develop reliable models for predicting the angles of liquid drops. Experimental data are divided into training data and testing data. By using training data and feed forward structure for the neural network and using particle swarm optimization for training the neural network based models, the optimum models were developed. The obtained results showed that regression index for the proposed models for the contact angles and sliding angles are 0.9874 and 0.9920, respectively. As it can be seen, these values are close to unit and it means the reliable performance of the models. Also, it can be inferred from the results that the proposed model have more reliable performance than multi-layer perceptron and radial basis function based models.

Real time monitoring of powder blend bulk density for coupled feed-forward/feed-back control of a continuous direct compaction tablet manufacturing process.

Science.gov (United States)

Singh, Ravendra; Román-Ospino, Andrés D; Romañach, Rodolfo J; Ierapetritou, Marianthi; Ramachandran, Rohit

2015-11-10

The pharmaceutical industry is strictly regulated, where precise and accurate control of the end product quality is necessary to ensure the effectiveness of the drug products. For such control, the process and raw materials variability ideally need to be fed-forward in real time into an automatic control system so that a proactive action can be taken before it can affect the end product quality. Variations in raw material properties (e.g., particle size), feeder hopper level, amount of lubrication, milling and blending action, applied shear in different processing stages can affect the blend density significantly and thereby tablet weight, hardness and dissolution. Therefore, real time monitoring of powder bulk density variability and its incorporation into the automatic control system so that its effect can be mitigated proactively and efficiently is highly desired. However, real time monitoring of powder bulk density is still a challenging task because of different level of complexities. In this work, powder bulk density which has a significant effect on the critical quality attributes (CQA's) has been monitored in real time in a pilot-plant facility, using a NIR sensor. The sensitivity of the powder bulk density on critical process parameters (CPP's) and CQA's has been analyzed and thereby feed-forward controller has been designed. The measured signal can be used for feed-forward control so that the corrective actions on the density variations can be taken before they can influence the product quality. The coupled feed-forward/feed-back control system demonstrates improved control performance and improvements in the final product quality in the presence of process and raw material variations. Copyright © 2015 Elsevier B.V. All rights reserved.

Flood forecasting for the upper reach of the Red River Basin, North ...

African Journals Online (AJOL)

This is a multilayer feed forward neural network with a back- ... 2 with the input layer, one hidden layer, andthe output layer with only one node . Theactivation ..... Thepaper is aresult of theresearch project entitled FLOod Control. Decision ...

THE USE OF NEURAL NETWORK TECHNOLOGY TO MODEL SWIMMING PERFORMANCE

Directory of Open Access Journals (Sweden)

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

Prediction of paddy drying kinetics: A comparative study between mathematical and artificial neural network modelling

Directory of Open Access Journals (Sweden)

Beigi Mohsen

2017-01-01

Full Text Available The present study aimed at investigation of deep bed drying of rough rice kernels at various thin layers at different drying air temperatures and flow rates. A comparative study was performed between mathematical thin layer models and artificial neural networks to estimate the drying curves of rough rice. The suitability of nine mathematical models in simulating the drying kinetics was examined and the Midilli model was determined as the best approach for describing drying curves. Different feed forward-back propagation artificial neural networks were examined to predict the moisture content variations of the grains. The ANN with 4-18-18-1 topology, transfer function of hyperbolic tangent sigmoid and a Levenberg-Marquardt back propagation training algorithm provided the best results with the maximum correlation coefficient and the minimum mean square error values. Furthermore, it was revealed that ANN modeling had better performance in prediction of drying curves with lower root mean square error values.

Prediction of littoral drift with artificial neural networks

Digital Repository Service at National Institute of Oceanography (India)

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...

Visual language recognition with a feed-forward network of spiking neurons

Energy Technology Data Exchange (ETDEWEB)

Rasmussen, Craig E [Los Alamos National Laboratory; Garrett, Kenyan [Los Alamos National Laboratory; Sottile, Matthew [GALOIS; Shreyas, Ns [INDIANA UNIV.

2010-01-01

An analogy is made and exploited between the recognition of visual objects and language parsing. A subset of regular languages is used to define a one-dimensional 'visual' language, in which the words are translational and scale invariant. This allows an exploration of the viewpoint invariant languages that can be solved by a network of concurrent, hierarchically connected processors. A language family is defined that is hierarchically tiling system recognizable (HREC). As inspired by nature, an algorithm is presented that constructs a cellular automaton that recognizes strings from a language in the HREC family. It is demonstrated how a language recognizer can be implemented from the cellular automaton using a feed-forward network of spiking neurons. This parser recognizes fixed-length strings from the language in parallel and as the computation is pipelined, a new string can be parsed in each new interval of time. The analogy with formal language theory allows inferences to be drawn regarding what class of objects can be recognized by visual cortex operating in purely feed-forward fashion and what class of objects requires a more complicated network architecture.

Optical implementation of a feature-based neural network with application to automatic target recognition

Science.gov (United States)

Chao, Tien-Hsin; Stoner, William W.

1993-01-01

An optical neural network based on the neocognitron paradigm is introduced. A novel aspect of the architecture design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the ouput of the feature correlator interatively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.

A NEURAL NETWORK BASED TRAFFIC-AWARE FORWARDING STRATEGY IN NAMED DATA NETWORKING

Directory of Open Access Journals (Sweden)

Parisa Bazmi

2016-11-01

Full Text Available Named Data Networking (NDN is a new Internet architecture which has been proposed to eliminate TCP/IP Internet architecture restrictions. This architecture is abstracting away the notion of host and working based on naming datagrams. However, one of the major challenges of NDN is supporting QoS-aware forwarding strategy so as to forward Interest packets intelligently over multiple paths based on the current network condition. In this paper, Neural Network (NN Based Traffic-aware Forwarding strategy (NNTF is introduced in order to determine an optimal path for Interest forwarding. NN is embedded in NDN routers to select next hop dynamically based on the path overload probability achieved from the NN. This solution is characterized by load balancing and QoS-awareness via monitoring the available path and forwarding data on the traffic-aware shortest path. The performance of NNTF is evaluated using ndnSIM which shows the efficiency of this scheme in terms of network QoS improvementof17.5% and 72% reduction in network delay and packet drop respectively.

Feed-forward and feedback projections of midbrain reticular formation neurons in the cat

Directory of Open Access Journals (Sweden)

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.

Real-Time Analysis of Online Product Reviews by Means of Multi-Layer Feed-Forward Neural Networks

Directory of Open Access Journals (Sweden)

Reinhold Decker

2014-11-01

Full Text Available In the recent past, the quantitative analysis of online product reviews (OPRs has become a popular manifestation of marketing intelligence activities focusing on products that are frequently subject to electronic word-of-mouth (eWOM. Typical elements of OPRs are overall star ratings, product at- tribute scores, recommendations, pros and cons, and free texts. The first three elements are of pa r- ticular interest because they provide an aggregate view of reviewers’ opinions about the products of interest. However, the significance of individual product attributes in the overall evaluation pro c- ess  can  vary  in  the  course  of  time.  Accordingly,  ad  hoc  analyses  of  OPRs  that  have  been downloaded at a certain point in time are of limited value for dynamic eWOM monitoring because of their snapshot character. On the other hand, opinion platforms can increase the meaningfulness of the OPRs posted there and, therewith, the usefulness of the platform as a whole, by directing eWOM activities to those product attributes that really matter at present. This paper therefore in- troduces a neural network-based approach that allows the dynamic tracking of the influence the posted scores of product attributes have on the overall star ratings of the concerning products. By using an elasticity measure, this approach supports the identification of those attributes that tend to lose or gain significance in the product evaluation process over time. The usability of this ap- proach is demonstrated using real OPR data on digital cameras and hotels.

Feed-forward and generalized regression neural networks in modeling feeding behavior of pigs in the grow-finishing phase

Science.gov (United States)

Feeding patterns in group-housed grow-finishing pigs have been investigated for use in management decisions, identifying sick animals, and determining genetic differences within a herd. Development of models to predict swine feeding behaviour has been limited due the large number of potential enviro...

Multi-Layer Approach for the Detection of Selective Forwarding Attacks.

Science.gov (United States)

Alajmi, Naser; Elleithy, Khaled

2015-11-19

Security breaches are a major threat in wireless sensor networks (WSNs). WSNs are increasingly used due to their broad range of important applications in both military and civilian domains. WSNs are prone to several types of security attacks. Sensor nodes have limited capacities and are often deployed in dangerous locations; therefore, they are vulnerable to different types of attacks, including wormhole, sinkhole, and selective forwarding attacks. Security attacks are classified as data traffic and routing attacks. These security attacks could affect the most significant applications of WSNs, namely, military surveillance, traffic monitoring, and healthcare. Therefore, there are different approaches to detecting security attacks on the network layer in WSNs. Reliability, energy efficiency, and scalability are strong constraints on sensor nodes that affect the security of WSNs. Because sensor nodes have limited capabilities in most of these areas, selective forwarding attacks cannot be easily detected in networks. In this paper, we propose an approach to selective forwarding detection (SFD). The approach has three layers: MAC pool IDs, rule-based processing, and anomaly detection. It maintains the safety of data transmission between a source node and base station while detecting selective forwarding attacks. Furthermore, the approach is reliable, energy efficient, and scalable.

Multi-Layer Approach for the Detection of Selective Forwarding Attacks

Directory of Open Access Journals (Sweden)

Naser Alajmi

2015-11-01

Full Text Available Security breaches are a major threat in wireless sensor networks (WSNs. WSNs are increasingly used due to their broad range of important applications in both military and civilian domains. WSNs are prone to several types of security attacks. Sensor nodes have limited capacities and are often deployed in dangerous locations; therefore, they are vulnerable to different types of attacks, including wormhole, sinkhole, and selective forwarding attacks. Security attacks are classified as data traffic and routing attacks. These security attacks could affect the most significant applications of WSNs, namely, military surveillance, traffic monitoring, and healthcare. Therefore, there are different approaches to detecting security attacks on the network layer in WSNs. Reliability, energy efficiency, and scalability are strong constraints on sensor nodes that affect the security of WSNs. Because sensor nodes have limited capabilities in most of these areas, selective forwarding attacks cannot be easily detected in networks. In this paper, we propose an approach to selective forwarding detection (SFD. The approach has three layers: MAC pool IDs, rule-based processing, and anomaly detection. It maintains the safety of data transmission between a source node and base station while detecting selective forwarding attacks. Furthermore, the approach is reliable, energy efficient, and scalable.

A Fusion Face Recognition Approach Based on 7-Layer Deep Learning Neural Network

Directory of Open Access Journals (Sweden)

Jianzheng Liu

2016-01-01

Full Text Available This paper presents a method for recognizing human faces with facial expression. In the proposed approach, a motion history image (MHI is employed to get the features in an expressive face. The face can be seen as a kind of physiological characteristic of a human and the expressions are behavioral characteristics. We fused the 2D images of a face and MHIs which were generated from the same face’s image sequences with expression. Then the fusion features were used to feed a 7-layer deep learning neural network. The previous 6 layers of the whole network can be seen as an autoencoder network which can reduce the dimension of the fusion features. The last layer of the network can be seen as a softmax regression; we used it to get the identification decision. Experimental results demonstrated that our proposed method performs favorably against several state-of-the-art methods.

Prediction of geomagnetic storm using neural networks: Comparison of the efficiency of the Satellite and ground-based input parameters

International Nuclear Information System (INIS)

Stepanova, Marina; Antonova, Elizavieta; Munos-Uribe, F A; Gordo, S L Gomez; Torres-Sanchez, M V

2008-01-01

Different kinds of neural networks have established themselves as an effective tool in the prediction of different geomagnetic indices, including the Dst being the most important constituent for determination of the impact of Space Weather on the human life. Feed-forward networks with one hidden layer are used to forecast the Dst variation, using separately the solar wind paramenters, polar cap index, and auroral electrojet index as input parameters. It was found that in all three cases the storm-time intervals were predicted much more precisely as quite time intervals. The majority of cross-correlation coefficients between predicted and observed Dst of strong geomagnetic storms are situated between 0.8 and 0.9. Changes in the neural network architecture, including the number of nodes in the input and hidden layers and the transfer functions between them lead to an improvement of a network performance up to 10%.

Application of neural network technique to determine a corrector surface for global geopotential model using GPS/levelling measurements in Egypt

Science.gov (United States)

Elshambaky, Hossam Talaat

2018-01-01

Owing to the appearance of many global geopotential models, it is necessary to determine the most appropriate model for use in Egyptian territory. In this study, we aim to investigate three global models, namely EGM2008, EIGEN-6c4, and GECO. We use five mathematical transformation techniques, i.e., polynomial expression, exponential regression, least-squares collocation, multilayer feed forward neural network, and radial basis neural networks to make the conversion from regional geometrical geoid to global geoid models and vice versa. From a statistical comparison study based on quality indexes between previous transformation techniques, we confirm that the multilayer feed forward neural network with two neurons is the most accurate of the examined transformation technique, and based on the mean tide condition, EGM2008 represents the most suitable global geopotential model for use in Egyptian territory to date. The final product gained from this study was the corrector surface that was used to facilitate the transformation process between regional geometrical geoid model and the global geoid model.

Designing an artificial neural network for prediction of pregnancy outcomes in women with systemic lupus erythematosus in Iran

Directory of Open Access Journals (Sweden)

Mahmoud Akbarian

2015-07-01

Results: Twelve features with P<0.05 and four features with P<0.1 were identified by using binary logistic regression as effective features. These sixteen features were used as input variables in artificial neural networks. The accuracy, sensitivity and specificity of the test data for the MLP network were 90.9%, 80.0%, and 94.1% respectively and for the total data were 97.3%, 93.5%, and 99.0% respectively. Conclusion: According to the results, we concluded that feed-forward Multi-Layer Perceptron (MLP neural network with scaled conjugate gradient (trainscg back propagation learning algorithm can help physicians to predict the pregnancy outcomes (spontaneous abortion and live birth among pregnant women with lupus by using identified effective variables.

IMPLEMENTATION OF ARTIFICIAL NEURAL NETWORK FOR FACE RECOGNITION USING GABOR FEATURE EXTRACTION

Directory of Open Access Journals (Sweden)

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.

Local excitation-inhibition ratio for synfire chain propagation in feed-forward neuronal networks

Science.gov (United States)

Guo, Xinmeng; Yu, Haitao; Wang, Jiang; Liu, Jing; Cao, Yibin; Deng, Bin

2017-09-01

A leading hypothesis holds that spiking activity propagates along neuronal sub-populations which are connected in a feed-forward manner, and the propagation efficiency would be affected by the dynamics of sub-populations. In this paper, how the interaction between local excitation and inhibition effects on synfire chain propagation in feed-forward network (FFN) is investigated. The simulation results show that there is an appropriate excitation-inhibition (EI) ratio maximizing the performance of synfire chain propagation. The optimal EI ratio can significantly enhance the selectivity of FFN to synchronous signals, which thereby increases the stability to background noise. Moreover, the effect of network topology on synfire chain propagation is also investigated. It is found that synfire chain propagation can be maximized by an optimal interlayer linking probability. We also find that external noise is detrimental to synchrony propagation by inducing spiking jitter. The results presented in this paper may provide insights into the effects of network dynamics on neuronal computations.

Phonematic translation of Polish texts by the neural network

International Nuclear Information System (INIS)

Bielecki, A.; Podolak, I.T.; Wosiek, J.; Majkut, E.

1996-01-01

Using the back propagation algorithm, we have trained the feed forward neural network to pronounce Polish language, more precisely to translate Polish text into its phonematic counterpart. Depending on the input coding and network architecture, 88%-95% translation efficiency was achieved. (author)

Prediction of the rejection of organic compounds (neutral and ionic) by nanofiltration and reverse osmosis membranes using neural networks

Energy Technology Data Exchange (ETDEWEB)

Ammi, Yamina; Khaouane, Latifa; Hanini, Salah [University of Medea, Medea (Algeria)

2015-11-15

This work investigates the use of neural networks in modeling the rejection processes of organic compounds (neutral and ionic) by nanofiltration and reverse osmosis membranes. Three feed-forward neural network (NN) models, characterized by a similar structure (eleven neurons for NN1 and NN2 and twelve neurons for NN3 in the input layer, one hidden layer and one neuron in the output layer), are constructed with the aim of predicting the rejection of organic compounds (neutral and ionic). A set of 956 data points for NN1 and 701 data points for NN2 and NN3 were used to test the neural networks. 80%, 10%, and 10% of the total data were used, respectively, for the training, the validation, and the test of the three models. For the most promising neural network models, the predicted rejection values of the test dataset were compared to measured rejections values; good correlations were found (R= 0.9128 for NN1, R=0.9419 for NN2, and R=0.9527 for NN3). The root mean squared errors for the total dataset were 11.2430% for NN1, 9.0742% for NN2, and 8.2047% for NN3. Furthermore, the comparison between the predicted results and QSAR models shows that the neural network models gave far better.

Prediction of the rejection of organic compounds (neutral and ionic) by nanofiltration and reverse osmosis membranes using neural networks

International Nuclear Information System (INIS)

Ammi, Yamina; Khaouane, Latifa; Hanini, Salah

2015-01-01

This work investigates the use of neural networks in modeling the rejection processes of organic compounds (neutral and ionic) by nanofiltration and reverse osmosis membranes. Three feed-forward neural network (NN) models, characterized by a similar structure (eleven neurons for NN1 and NN2 and twelve neurons for NN3 in the input layer, one hidden layer and one neuron in the output layer), are constructed with the aim of predicting the rejection of organic compounds (neutral and ionic). A set of 956 data points for NN1 and 701 data points for NN2 and NN3 were used to test the neural networks. 80%, 10%, and 10% of the total data were used, respectively, for the training, the validation, and the test of the three models. For the most promising neural network models, the predicted rejection values of the test dataset were compared to measured rejections values; good correlations were found (R= 0.9128 for NN1, R=0.9419 for NN2, and R=0.9527 for NN3). The root mean squared errors for the total dataset were 11.2430% for NN1, 9.0742% for NN2, and 8.2047% for NN3. Furthermore, the comparison between the predicted results and QSAR models shows that the neural network models gave far better.

Modeling Broadband Microwave Structures by Artificial Neural Networks

Directory of Open Access Journals (Sweden)

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.

Optimized Neural Network for Fault Diagnosis and Classification

International Nuclear Information System (INIS)

Elaraby, S.M.

2005-01-01

This paper presents a developed and implemented toolbox for optimizing neural network structure of fault diagnosis and classification. Evolutionary algorithm based on hierarchical genetic algorithm structure is used for optimization. The simplest feed-forward neural network architecture is selected. Developed toolbox has friendly user interface. Multiple solutions are generated. The performance and applicability of the proposed toolbox is verified with benchmark data patterns and accident diagnosis of Egyptian Second research reactor (ETRR-2)

Implementation of a feed-forward artificial neural network in VHDL on FPGA

NARCIS (Netherlands)

Dondon, P.; Carvalho, J.; Gardere, R.; Lahalle, P.; Tsenov, G.; Mladenov, V.M.; Reljin, B.; Stankovic, S.

2014-01-01

Describing an Artificial Neural Network (ANN) using VHDL allows a further implementation of such a system on FPGA. Indeed, the principal point of using FPGA for ANNs is flexibility that gives it an advantage toward other systems like ASICS which are entirely dedicated to one unique architecture and

The application of artificial neural networks to TLD dose algorithm

International Nuclear Information System (INIS)

Moscovitch, M.

1997-01-01

We review the application of feed forward neural networks to multi element thermoluminescence dosimetry (TLD) dose algorithm development. A Neural Network is an information processing method inspired by the biological nervous system. A dose algorithm based on a neural network is a fundamentally different approach from conventional algorithms, as it has the capability to learn from its own experience. The neural network algorithm is shown the expected dose values (output) associated with a given response of a multi-element dosimeter (input) many times.The algorithm, being trained that way, eventually is able to produce its own unique solution to similar (but not exactly the same) dose calculation problems. For personnel dosimetry, the output consists of the desired dose components: deep dose, shallow dose, and eye dose. The input consists of the TL data obtained from the readout of a multi-element dosimeter. For this application, a neural network architecture was developed based on the concept of functional links network (FLN). The FLN concept allowed an increase in the dimensionality of the input space and construction of a neural network without any hidden layers. This simplifies the problem and results in a relatively simple and reliable dose calculation algorithm. Overall, the neural network dose algorithm approach has been shown to significantly improve the precision and accuracy of dose calculations. (authors)

Modelling the Flow Stress of Alloy 316L using a Multi-Layered Feed Forward Neural Network with Bayesian Regularization

Science.gov (United States)

Abiriand Bhekisipho Twala, Olufunminiyi

2017-08-01

In this paper, a multilayer feedforward neural network with Bayesian regularization constitutive model is developed for alloy 316L during high strain rate and high temperature plastic deformation. The input variables are strain rate, temperature and strain while the output value is the flow stress of the material. The results show that the use of Bayesian regularized technique reduces the potential of overfitting and overtraining. The prediction quality of the model is thereby improved. The model predictions are in good agreement with experimental measurements. The measurement data used for the network training and model comparison were taken from relevant literature. The developed model is robust as it can be generalized to deformation conditions slightly below or above the training dataset.

Associative account of self-cognition: extended forward model and multi-layer structure

Directory of Open Access Journals (Sweden)

Motoaki eSugiura

2013-08-01

Full Text Available The neural correlates of self identified by neuroimaging studies differ depending on which aspects of self are addressed. Here, three categories of self are proposed based on neuroimaging findings and an evaluation of the likely underlying cognitive processes. The physical self, representing self-agency of action, body ownership, and bodily self-recognition, is supported by the sensory and motor association cortices located primarily in the right hemisphere. The interpersonal self, representing the attention or intentions of others directed at the self, is supported by several amodal association cortices in the dorsomedial frontal and lateral posterior cortices. The social self, representing the self as a collection of context-dependent social values, is supported by the ventral aspect of the medial prefrontal cortex and the posterior cingulate cortex. Despite differences in the underlying cognitive processes and neural substrates, all three categories of self are likely to share the computational characteristics of the forward model, which is underpinned by internal schema or learned associations between one’s behavioral output and the consequential input. Additionally, these three categories exist within a hierarchical layer structure based on developmental processes that updates the schema through the attribution of prediction error. In this account, most of the association cortices critically contribute to some aspect of the self through associative learning while the primary regions involved shift from the lateral to the medial cortices in a sequence from the physical to the interpersonal to the social self.

Artificial neural networks for modeling time series of beach litter in the southern North Sea.

Science.gov (United States)

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.

A one-layer recurrent neural network for constrained nonsmooth invex optimization.

Science.gov (United States)

Li, Guocheng; Yan, Zheng; Wang, Jun

2014-02-01

Invexity is an important notion in nonconvex optimization. In this paper, a one-layer recurrent neural network is proposed for solving constrained nonsmooth invex optimization problems, designed based on an exact penalty function method. It is proved herein that any state of the proposed neural network is globally convergent to the optimal solution set of constrained invex optimization problems, with a sufficiently large penalty parameter. In addition, any neural state is globally convergent to the unique optimal solution, provided that the objective function and constraint functions are pseudoconvex. Moreover, any neural state is globally convergent to the feasible region in finite time and stays there thereafter. The lower bounds of the penalty parameter and convergence time are also estimated. Two numerical examples are provided to illustrate the performances of the proposed neural network. Copyright © 2013 Elsevier Ltd. All rights reserved.

Estimation of operational parameters for a direct injection turbocharged spark ignition engine by using regression analysis and artificial neural network

Directory of Open Access Journals (Sweden)

Tosun Erdi

2017-01-01

Full Text Available This study was aimed at estimating the variation of several engine control parameters within the rotational speed-load map, using regression analysis and artificial neural network techniques. Duration of injection, specific fuel consumption, exhaust gas at turbine inlet, and within the catalytic converter brick were chosen as the output parameters for the models, while engine speed and brake mean effective pressure were selected as independent variables for prediction. Measurements were performed on a turbocharged direct injection spark ignition engine fueled with gasoline. A three-layer feed-forward structure and back-propagation algorithm was used for training the artificial neural network. It was concluded that this technique is capable of predicting engine parameters with better accuracy than linear and non-linear regression techniques.

Prediction of friction factor of pure water flowing inside vertical smooth and microfin tubes by using artificial neural networks

Science.gov (United States)

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.

Investigation of turbulent boundary layer over forward-facing step via direct numerical simulation

International Nuclear Information System (INIS)

Hattori, Hirofumi; Nagano, Yasutaka

2010-01-01

This paper presents observations and investigations of the detailed turbulent structure of a boundary layer over a forward-facing step. The present DNSs are conducted under conditions with three Reynolds numbers based on step height, or three Reynolds numbers based on momentum thickness so as to investigate the effects of step height and inlet boundary layer thickness. DNS results show the quantitative turbulent statistics and structures of boundary layers over a forward-facing step, where pronounced counter-gradient diffusion phenomena (CDP) are especially observed on the step near the wall. Also, a quadrant analysis is conducted in which the results indicate in detail the turbulence motion around the step.

An Artificial Neural Networks Approach to Estimate Occupational Accident: A National Perspective for Turkey

Directory of Open Access Journals (Sweden)

Hüseyin Ceylan

2014-01-01

Full Text Available Occupational accident estimation models were developed by using artificial neural networks (ANNs for Turkey. Using these models the number of occupational accidents and death and permanent incapacity numbers resulting from occupational accidents were estimated for Turkey until the year of 2025 by the three different scenarios. In the development of the models, insured workers, workplace, occupational accident, death, and permanent incapacity values were used as model parameters with data between 1970 and 2012. 2-5-1 neural network architecture was selected as the best network architecture. Sigmoid was used in hidden layers and linear function was used at output layer. The feed forward back propagation algorithm was used to train the network. In order to obtain a useful model, the network was trained between 1970 and 1999 to estimate the values of 2000 to 2012. The result was compared with the real values and it was seen that it is applicable for this aim. The performances of all developed models were evaluated using mean absolute percent errors (MAPE, mean absolute errors (MAE, and root mean square errors (RMSE.

Input data preprocessing method for exchange rate forecasting via neural network

Directory of Open Access Journals (Sweden)

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

Efficacy of Feed Forward and Feedback Signaling for Inflations and Chest Compression Pressure During Cardiopulmonary Resuscitation in a Newborn Mannequin

Science.gov (United States)

Andriessen, Peter; Oetomo, Sidarto Bambang; Chen, Wei; Feijs, Loe MG

2012-01-01

Background The objective of the study was to evaluate a device that supports professionals during neonatal cardiopulmonary resuscitation (CPR). The device features a box that generates an audio-prompted rate guidance (feed forward) for inflations and compressions, and a transparent foil that is placed over the chest with marks for inter nipple line and sternum with LED’s incorporated in the foil indicating the exerted force (feedback). Methods Ten pairs (nurse/doctor) performed CPR on a newborn resuscitation mannequin. All pairs initially performed two sessions. Thereafter two sessions were performed in similar way, after randomization in 5 pairs that used the device and 5 pairs that performed CPR without the device (controls). A rhythm score was calculated based on the number of CPR cycles that were performed correctly. Results The rhythm score with the device improved from 85 ± 14 to 99 ± 2% (P CPR device compared to the controls. Conclusion Feed forward and feedback signaling leads to a more constant rhythm and chest compression pressure during CPR. PMID:22870175

Mass reconstruction with a neural network

International Nuclear Information System (INIS)

Loennblad, L.; Peterson, C.; Roegnvaldsson, T.

1992-01-01

A feed-forward neural network method is developed for reconstructing the invariant mass of hadronic jets appearing in a calorimeter. The approach is illustrated in W→qanti q, where W-bosons are produced in panti p reactions at SPS collider energies. The neural network method yields results that are superior to conventional methods. This neural network application differs from the classification ones in the sense that an analog number (the mass) is computed by the network, rather than a binary decision being made. As a by-product our application clearly demonstrates the need for using 'intelligent' variables in instances when the amount of training instances is limited. (orig.)

Demonstration of feed-forward control for linear optics quantum computation

International Nuclear Information System (INIS)

Pittman, T.B.; Jacobs, B.C.; Franson, J.D.

2002-01-01

One of the main requirements in linear optics quantum computing is the ability to perform single-qubit operations that are controlled by classical information fed forward from the output of single-photon detectors. These operations correspond to predetermined combinations of phase corrections and bit flips that are applied to the postselected output modes of nondeterministic quantum logic devices. Corrections of this kind are required in order to obtain the correct logical output for certain detection events, and their use can increase the overall success probability of the devices. In this paper, we report on the experimental demonstration of the use of this type of feed-forward system to increase the probability of success of a simple nondeterministic quantum logic operation from approximately (1/4) to (1/2). This logic operation involves the use of one target qubit and one ancilla qubit which, in this experiment, are derived from a parametric down-conversion photon pair. Classical information describing the detection of the ancilla photon is fed forward in real time and used to alter the quantum state of the output photon. A fiber-optic delay line is used to store the output photon until a polarization-dependent phase shift can be applied using a high-speed Pockels cell

Tracking and vertex finding with drift chambers and neural networks

International Nuclear Information System (INIS)

Lindsey, C.

1991-09-01

Finding tracks, track vertices and event vertices with neural networks from drift chamber signals is discussed. Simulated feed-forward neural networks have been trained with back-propagation to give track parameters using Monte Carlo simulated tracks in one case and actual experimental data in another. Effects on network performance of limited weight resolution, noise and drift chamber resolution are given. Possible implementations in hardware are discussed. 7 refs., 10 figs

Spatial interpolation and radiological mapping of ambient gamma dose rate by using artificial neural networks and fuzzy logic methods.

Science.gov (United States)

Yeşilkanat, Cafer Mert; Kobya, Yaşar; Taşkın, Halim; Çevik, Uğur

2017-09-01

The aim of this study was to determine spatial risk dispersion of ambient gamma dose rate (AGDR) by using both artificial neural network (ANN) and fuzzy logic (FL) methods, compare the performances of methods, make dose estimations for intermediate stations with no previous measurements and create dose rate risk maps of the study area. In order to determine the dose distribution by using artificial neural networks, two main networks and five different network structures were used; feed forward ANN; Multi-layer perceptron (MLP), Radial basis functional neural network (RBFNN), Quantile regression neural network (QRNN) and recurrent ANN; Jordan networks (JN), Elman networks (EN). In the evaluation of estimation performance obtained for the test data, all models appear to give similar results. According to the cross-validation results obtained for explaining AGDR distribution, Pearson's r coefficients were calculated as 0.94, 0.91, 0.89, 0.91, 0.91 and 0.92 and RMSE values were calculated as 34.78, 43.28, 63.92, 44.86, 46.77 and 37.92 for MLP, RBFNN, QRNN, JN, EN and FL, respectively. In addition, spatial risk maps showing distributions of AGDR of the study area were created by all models and results were compared with geological, topological and soil structure. Copyright © 2017 Elsevier Ltd. All rights reserved.

An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks

International Nuclear Information System (INIS)

Wu, Ji; Zhang, Chenbin; Chen, Zonghai

2016-01-01

Highlights: • An online RUL estimation method for lithium-ion battery is proposed. • RUL is described by the difference among battery terminal voltage curves. • A feed forward neural network is employed for RUL estimation. • Importance sampling is utilized to select feed forward neural network inputs. - Abstract: An accurate battery remaining useful life (RUL) estimation can facilitate the design of a reliable battery system as well as the safety and reliability of actual operation. A reasonable definition and an effective prediction algorithm are indispensable for the achievement of an accurate RUL estimation result. In this paper, the analysis of battery terminal voltage curves under different cycle numbers during charge process is utilized for RUL definition. Moreover, the relationship between RUL and charge curve is simulated by feed forward neural network (FFNN) for its simplicity and effectiveness. Considering the nonlinearity of lithium-ion charge curve, importance sampling (IS) is employed for FFNN input selection. Based on these results, an online approach using FFNN and IS is presented to estimate lithium-ion battery RUL in this paper. Experiments and numerical comparisons are conducted to validate the proposed method. The results show that the FFNN with IS is an accurate estimation method for actual operation.

PEAK TRACKING WITH A NEURAL NETWORK FOR SPECTRAL RECOGNITION

NARCIS (Netherlands)

COENEGRACHT, PMJ; METTING, HJ; VANLOO, EM; SNOEIJER, GJ; DOORNBOS, DA

1993-01-01

A peak tracking method based on a simulated feed-forward neural network with back-propagation is presented. The network uses the normalized UV spectra and peak areas measured in one chromatogram for peak recognition. It suffices to train the network with only one set of spectra recorded in one

Early tube leak detection system for steam boiler at KEV power plant

Directory of Open Access Journals (Sweden)

Ismail Firas B.

2016-01-01

Full Text Available Tube leakage in boilers has been a major contribution to trips which eventually leads to power plant shut downs. Training of network and developing artificial neural network (ANN models are essential in fault detection in critically large systems. This research focusses on the ANN modelling through training and validation of real data acquired from a sub-critical boiler unit. The artificial neural network (ANN was used to develop a compatible model and to evaluate the working properties and behaviour of boiler. The training and validation of real data has been applied using the feed-forward with back-propagation (BP. The right combination of number of neurons, number of hidden layers, training algorithms and training functions was run to achieve the best ANN model with lowest error. The ANN was trained and validated using real site data acquired from a coal fired power plant in Malaysia. The results showed that the Neural Network (NN with one hidden layers performed better than two hidden layer using feed-forward back-propagation network. The outcome from this study give us the best ANN model which eventually allows for early detection of boiler tube leakages, and forecast of a trip before the real shutdown. This will eventually reduce shutdowns in power plants.

Control of beam halo-chaos using neural network self-adaptation method

International Nuclear Information System (INIS)

Fang Jinqing; Huang Guoxian; Luo Xiaoshu

2004-11-01

Taking the advantages of neural network control method for nonlinear complex systems, control of beam halo-chaos in the periodic focusing channels (network) of high intensity accelerators is studied by feed-forward back-propagating neural network self-adaptation method. The envelope radius of high-intensity proton beam is reached to the matching beam radius by suitably selecting the control structure of neural network and the linear feedback coefficient, adjusted the right-coefficient of neural network. The beam halo-chaos is obviously suppressed and shaking size is much largely reduced after the neural network self-adaptation control is applied. (authors)

Using neural networks with jet shapes to identify b jets in e+e- interactions

International Nuclear Information System (INIS)

Bellantoni, L.; Conway, J.S.; Jacobsen, J.E.; Pan, Y.B.; Wu Saulan

1991-01-01

A feed-forward neural network trained using backpropagation was used to discriminate between b and light quark jets in e + e - → Z 0 → qanti q events. The information presented to the network consisted of 25 jet shape variables. The network successfully identified b jets in two- and three-jet events modeled using a detector simulation. The jet identification efficiency for two-jet events was 61% and the probability to call a light quark jet a b jet equal to 20%. (orig.)

Neural network based expert system for fault diagnosis of particle accelerators

International Nuclear Information System (INIS)

Dewidar, M.M.

1997-01-01

Particle accelerators are generators that produce beams of charged particles, acquiring different energies, depending on the accelerator type. The MGC-20 cyclotron is a cyclic particle accelerator used for accelerating protons, deuterons, alpha particles, and helium-3 to different energies. Its applications include isotope production, nuclear reaction, and mass spectroscopy studies. It is a complicated machine, it consists of five main parts, the ion source, the deflector, the beam transport system, the concentric and harmonic coils, and the radio frequency system. The diagnosis of this device is a very complex task. it depends on the conditions of 27 indicators of the control panel of the device. The accurate diagnosis can lead to a high system reliability and save maintenance costs. so an expert system for the cyclotron fault diagnosis is necessary to be built. In this thesis , a hybrid expert system was developed for the fault diagnosis of the MGC-20 cyclotron. Two intelligent techniques, multilayer feed forward back propagation neural network and the rule based expert system, are integrated as a pre-processor loosely coupled model to build the proposed hybrid expert system. The architecture of the developed hybrid expert system consists of two levels. The first level is two feed forward back propagation neural networks, used for isolating the faulty part of the cyclotron. The second level is the rule based expert system, used for troubleshooting the faults inside the isolated faulty part. 4-6 tabs., 4-5 figs., 36 refs

Neural network stochastic simulation applied for quantifying uncertainties

Directory of Open Access Journals (Sweden)

N Foudil-Bey

2016-09-01

Full Text Available Generally the geostatistical simulation methods are used to generate several realizations of physical properties in the sub-surface, these methods are based on the variogram analysis and limited to measures correlation between variables at two locations only. In this paper, we propose a simulation of properties based on supervised Neural network training at the existing drilling data set. The major advantage is that this method does not require a preliminary geostatistical study and takes into account several points. As a result, the geological information and the diverse geophysical data can be combined easily. To do this, we used a neural network with multi-layer perceptron architecture like feed-forward, then we used the back-propagation algorithm with conjugate gradient technique to minimize the error of the network output. The learning process can create links between different variables, this relationship can be used for interpolation of the properties on the one hand, or to generate several possible distribution of physical properties on the other hand, changing at each time and a random value of the input neurons, which was kept constant until the period of learning. This method was tested on real data to simulate multiple realizations of the density and the magnetic susceptibility in three-dimensions at the mining camp of Val d'Or, Québec (Canada.

Meta-modeling of the pesticide fate model MACRO for groundwater exposure assessments using artificial neural networks

Science.gov (United States)

Stenemo, Fredrik; Lindahl, Anna M. L.; Gärdenäs, Annemieke; Jarvis, Nicholas

2007-08-01

Several simple index methods that use easily accessible data have been developed and included in decision-support systems to estimate pesticide leaching across larger areas. However, these methods often lack important process descriptions (e.g. macropore flow), which brings into question their reliability. Descriptions of macropore flow have been included in simulation models, but these are too complex and demanding for spatial applications. To resolve this dilemma, a neural network simulation meta-model of the dual-permeability macropore flow model MACRO was created for pesticide groundwater exposure assessment. The model was parameterized using pedotransfer functions that require as input the clay and sand content of the topsoil and subsoil, and the topsoil organic carbon content. The meta-model also requires the topsoil pesticide half-life and the soil organic carbon sorption coefficient as input. A fully connected feed-forward multilayer perceptron classification network with two hidden layers, linked to fully connected feed-forward multilayer perceptron neural networks with one hidden layer, trained on sub-sets of the target variable, was shown to be a suitable meta-model for the intended purpose. A Fourier amplitude sensitivity test showed that the model output (the 80th percentile average yearly pesticide concentration at 1 m depth for a 20 year simulation period) was sensitive to all input parameters. The two input parameters related to pesticide characteristics (i.e. soil organic carbon sorption coefficient and topsoil pesticide half-life) were the most influential, but texture in the topsoil was also quite important since it was assumed to control the mass exchange coefficient that regulates the strength of macropore flow. This is in contrast to models based on the advection-dispersion equation where soil texture is relatively unimportant. The use of the meta-model is exemplified with a case-study where the spatial variability of pesticide leaching is

A GIS-based multi-criteria seismic vulnerability assessment using the integration of granular computing rule extraction and artificial neural networks

NARCIS (Netherlands)

Sheikhian, Hossein; Delavar, Mahmoud Reza; Stein, Alfred

2017-01-01

This study proposes multi‐criteria group decision‐making to address seismic physical vulnerability assessment. Granular computing rule extraction is combined with a feed forward artificial neural network to form a classifier capable of training a neural network on the basis of the rules provided by

Moving image compression and generalization capability of constructive neural networks

Science.gov (United States)

Ma, Liying; Khorasani, Khashayar

2001-03-01

To date numerous techniques have been proposed to compress digital images to ease their storage and transmission over communication channels. Recently, a number of image compression algorithms using Neural Networks NNs have been developed. Particularly, several constructive feed-forward neural networks FNNs have been proposed by researchers for image compression, and promising results have been reported. At the previous SPIE AeroSense conference 2000, we proposed to use a constructive One-Hidden-Layer Feedforward Neural Network OHL-FNN for compressing digital images. In this paper, we first investigate the generalization capability of the proposed OHL-FNN in the presence of additive noise for network training and/ or generalization. Extensive experimental results for different scenarios are presented. It is revealed that the constructive OHL-FNN is not as robust to additive noise in input image as expected. Next, the constructive OHL-FNN is applied to moving images, video sequences. The first, or other specified frame in a moving image sequence is used to train the network. The remaining moving images that follow are then generalized/compressed by this trained network. Three types of correlation-like criteria measuring the similarity of any two images are introduced. The relationship between the generalization capability of the constructed net and the similarity of images is investigated in some detail. It is shown that the constructive OHL-FNN is promising even for changing images such as those extracted from a football game.

Permutation parity machines for neural cryptography.

Science.gov (United States)

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.

Permutation parity machines for neural cryptography

International Nuclear Information System (INIS)

Reyes, Oscar Mauricio; Zimmermann, Karl-Heinz

2010-01-01

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.

Neural Model for Left-Handed CPW Bandpass Filter Loaded Split Ring Resonator

Science.gov (United States)

Liu, Haiwen; Wang, Shuxin; Tan, Mingtao; Zhang, Qijun

2010-02-01

Compact left-handed coplanar waveguide (CPW) bandpass filter loaded split ring resonator (SRR) is presented in this paper. The proposed filter exhibits a quasi-elliptic function response and its circuit size occupies only 12 × 11.8 mm2 (≈0.21 λg × 0.20 λg). Also, a simple circuit model is given and the parametric study of this filter is discussed. Then, with the aid of NeuroModeler software, a five-layer feed-forward perceptron neural networks model is built up to optimize the proposed filter design fast and accurately. Finally, this newly left-handed CPW bandpass filter was fabricated and measured. A good agreement between simulations and measurement verifies the proposed left-handed filter and the validity of design methodology.

Feed-forward control of a solid oxide fuel cell system with anode offgas recycle

Science.gov (United States)

Carré, Maxime; Brandenburger, Ralf; Friede, Wolfgang; Lapicque, François; Limbeck, Uwe; da Silva, Pedro

2015-05-01

In this work a combined heat and power unit (CHP unit) based on the solid oxide fuel cell (SOFC) technology is analysed. This unit has a special feature: the anode offgas is partially recycled to the anode inlet. Thus it is possible to increase the electrical efficiency and the system can be operated without external water feeding. A feed-forward control concept which allows secure operating conditions of the CHP unit as well as a maximization of its electrical efficiency is introduced and validated experimentally. The control algorithm requires a limited number of measurement values and few deterministic relations for its description.

Control of 12-Cylinder Camless Engine with Neural Networks

OpenAIRE

Ashhab Moh’d Sami

2017-01-01

The 12-cyliner camless engine breathing process is modeled with artificial neural networks (ANN’s). The inputs to the net are the intake valve lift (IVL) and intake valve closing timing (IVC) whereas the output of the net is the cylinder air charge (CAC). The ANN is trained with data collected from an engine simulation model which is based on thermodynamics principles and calibrated against real engine data. A method for adapting single-output feed-forward neural networks is proposed and appl...

Gas ultracentrifuge separative parameters modeling using hybrid neural networks

International Nuclear Information System (INIS)

Crus, Maria Ursulina de Lima

2005-01-01

A hybrid neural network is developed for the calculation of the separative performance of an ultracentrifuge. A feed forward neural network is trained to estimate the internal flow parameters of a gas ultracentrifuge, and then these parameters are applied in the diffusion equation. For this study, a 573 experimental data set is used to establish the relation between the separative performance and the controlled variables. The process control variables considered are: the feed flow rate F, the cut θ and the product pressure Pp. The mechanical arrangements consider the radial waste scoop dimension, the rotating baffle size D s and the axial feed location Z E . The methodology was validated through the comparison of the calculated separative performance with experimental values. This methodology may be applied to other processes, just by adapting the phenomenological procedures. (author)

Artificial neural networks for plasma spectroscopy analysis

International Nuclear Information System (INIS)

Morgan, W.L.; Larsen, J.T.; Goldstein, W.H.

1992-01-01

Artificial neural networks have been applied to a variety of signal processing and image recognition problems. Of the several common neural models the feed-forward, back-propagation network is well suited for the analysis of scientific laboratory data, which can be viewed as a pattern recognition problem. The authors present a discussion of the basic neural network concepts and illustrate its potential for analysis of experiments by applying it to the spectra of laser produced plasmas in order to obtain estimates of electron temperatures and densities. Although these are high temperature and density plasmas, the neural network technique may be of interest in the analysis of the low temperature and density plasmas characteristic of experiments and devices in gaseous electronics

Hardware implementation of stochastic spiking neural networks.

Science.gov (United States)

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.

Beneficial role of noise in artificial neural networks

International Nuclear Information System (INIS)

Monterola, Christopher; Saloma, Caesar; Zapotocky, Martin

2008-01-01

We demonstrate enhancement of neural networks efficacy to recognize frequency encoded signals and/or to categorize spatial patterns of neural activity as a result of noise addition. For temporal information recovery, noise directly added to the receiving neurons allow instantaneous improvement of signal-to-noise ratio [Monterola and Saloma, Phys. Rev. Lett. 2002]. For spatial patterns however, recurrence is necessary to extend and homogenize the operating range of a feed-forward neural network [Monterola and Zapotocky, Phys. Rev. E 2005]. Finally, using the size of the basin of attraction of the networks learned patterns (dynamical fixed points), a procedure for estimating the optimal noise is demonstrated

Fuel economy and torque tracking in camless engines through optimization of neural networks

International Nuclear Information System (INIS)

Ashhab, Moh'd Sami S.

2008-01-01

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 gurantees 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

Artificial Neural Network Model for Monitoring Oil Film Regime in Spur Gear Based on Acoustic Emission Data

Directory of Open Access Journals (Sweden)

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.

Tests of track segment and vertex finding with neural networks

International Nuclear Information System (INIS)

Denby, B.; Lessner, E.; Lindsey, C.S.

1990-04-01

Feed forward neural networks have been trained, using back-propagation, to find the slopes of simulated track segments in a straw chamber and to find the vertex of tracks from both simulated and real events in a more conventional drift chamber geometry. Network architectures, training, and performance are presented. 12 refs., 7 figs

Use of artificial neural networks for transport energy demand modeling

International Nuclear Information System (INIS)

Murat, Yetis Sazi; Ceylan, Halim

2006-01-01

The paper illustrates an artificial neural network (ANN) approach based on supervised neural networks for the transport energy demand forecasting using socio-economic and transport related indicators. The ANN transport energy demand model is developed. The actual forecast is obtained using a feed forward neural network, trained with back propagation algorithm. In order to investigate the influence of socio-economic indicators on the transport energy demand, the ANN is analyzed based on gross national product (GNP), population and the total annual average veh-km along with historical energy data available from 1970 to 2001. Comparing model predictions with energy data in testing period performs the model validation. The projections are made with two scenarios. It is obtained that the ANN reflects the fluctuation in historical data for both dependent and independent variables. The results obtained bear out the suitability of the adopted methodology for the transport energy-forecasting problem

Table making system for feed forward control to improve transient emissions; Katoji haiki gas joka table no sakusei system

Energy Technology Data Exchange (ETDEWEB)

Sakamaki, T; Morita, S; Takada, Y [Osaka City University, Osaka (Japan)

1997-10-01

Intake manifold fuel injection type engines have a weak point that the emissions are not so good in transient operation, because the balance of fuel adhesion and evaporation goes out, so that three way catalyst does not work in good efficiency. For this countermeasure, it is effective to add feed forward control to conventional O2 feedback one. In order to achieve this feed forward control, the fuel table is necessary, and to make it needs enormous time and effort even for one target type engine. To overcome this difficulty, table making system was constructed, and expected result was obtained. 4 refs., 8 figs.

Spatial frequency domain spectroscopy of two layer media

Science.gov (United States)

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.

Artificial neural networks for dynamic monitoring of simulated-operating parameters of high temperature gas cooled engineering test reactor (HTTR)

International Nuclear Information System (INIS)

Seker, Serhat; Tuerkcan, Erdinc; Ayaz, Emine; Barutcu, Burak

2003-01-01

This paper addresses to the problem of utilisation of the artificial neural networks (ANNs) for detecting anomalies as well as physical parameters of a nuclear power plant during power operation in real time. Three different types of neural network algorithms were used namely, feed-forward neural network (back-propagation, BP) and two types of recurrent neural networks (RNN). The data used in this paper were gathered from the simulation of the power operation of the Japan's High Temperature Engineering Testing Reactor (HTTR). For the wide range of power operation, 56 signals were generated by the reactor dynamic simulation code for several hours of normal power operation at different power ramps between 30 and 100% nominal power. Paper will compare the outcomes of different neural networks and presents the neural network system and the determination of physical parameters from the simulated operating data

Journal of Earth System Science | Indian Academy of Sciences

Indian Academy of Sciences (India)

... in the subsurface study of the earth takes into account the model parameters in ... and thickness of individual subsurface layers using the trained synthetic data by ... feed-forward neural network with fast back propagation learning algorithm.

Detection of directional eye movements based on the electrooculogram signals through an artificial neural network

International Nuclear Information System (INIS)

Erkaymaz, Hande; Ozer, Mahmut; Orak, İlhami Muharrem

2015-01-01

The electrooculogram signals are very important at extracting information about detection of directional eye movements. Therefore, in this study, we propose a new intelligent detection model involving an artificial neural network for the eye movements based on the electrooculogram signals. In addition to conventional eye movements, our model also involves the detection of tic and blinking of an eye. We extract only two features from the electrooculogram signals, and use them as inputs for a feed-forwarded artificial neural network. We develop a new approach to compute these two features, which we call it as a movement range. The results suggest that the proposed model have a potential to become a new tool to determine the directional eye movements accurately

Detection of Pistachio Aflatoxin Using Raman Spectroscopy and Artificial Neural Networks

Directory of Open Access Journals (Sweden)

R Mohammadigol

2015-03-01

Full Text Available Pistachio contamination to aflatoxin has been known as a serious problem for pistachio exportation. With regards to the increasing demand for Raman spectroscopy to detect and classify different materials and also the current experimental and technical problems for measuring toxin (such as being expensive and time-consuming, the main objective of this study was to detect aflatoxin contamination in pistachio by using Raman spectroscopy technique and artificial neural networks. Three sets of samples were prepared: non-contaminated (healthy and contaminated samples with 20 and 100 ppb of the total aflatoxins (B1+B2+G1+G2. After spectral acquisition, considering to the results, spectral data were normalized and then principal components (PCs were extracted to reduce the data dimensions. For classification of the samples spectra, an artificial neural network was used with a feed forward back propagation algorithm for 4 inputs and 3 neurons in hidden layer. Mean overall accuracy was achieved to be 98 percent; therefore, non-liner Raman spectra data modeling by ANN for samples classification was successful.

Comparison Of Power Quality Disturbances Classification Based On Neural Network

Directory of Open Access Journals (Sweden)

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.

Reservoir-based Online Adaptive Forward Models with Neural Control for Complex Locomotion in a Hexapod Robot

DEFF Research Database (Denmark)

Manoonpong, Poramate; Dasgupta, Sakyasingha; Goldschmidt, Dennis

2014-01-01

Walking animals show fascinating locomotor abilities and complex behaviors. Biological study has revealed that such complex behaviors is a result of a combination of biomechanics and neural mechanisms. While biomechanics allows for flexibility and a variety of movements, neural mechanisms generate...... locomotion, make predictions, and provide adaptation. Inspired by this finding, we present here an artificial bio-inspired walking system which combines biomechanics (in terms of its body and leg structures) and neural mechanisms. The neural mechanisms consist of 1) central pattern generator-based control...... for generating basic rhythmic patterns and coordinated movements, 2) reservoir-based adaptive forward models with efference copies for sensory prediction as well as state estimation, and 3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental...

3-D inversion of borehole-to-surface electrical data using a back-propagation neural network

Science.gov (United States)

Ho, Trong Long

2009-08-01

The "fluid-flow tomography", an advanced technique for geoelectrical survey based on the conventional mise-à-la-masse measurement, has been developed by Exploration Geophysics Laboratory at the Kyushu University. This technique is proposed to monitor fluid-flow behavior during water injection and production in a geothermal field. However data processing of this technique is very costly. In this light, this paper will discuss the solution to cost reduction by applying a neural network in the data processing. A case study in the Takigami geothermal field in Japan will be used to illustrate this. The achieved neural network in this case study is three-layered and feed-forward. The most successful learning algorithm in this network is the Resilient Propagation (RPROP). Consequently, the study advances the pragmatism of the "fluid-flow tomography" technique which can be widely used for geothermal fields. Accuracy of the solution is then verified by using root mean square (RMS) misfit error as an indicator.

Neural node network and model, and method of teaching same

Science.gov (United States)

Parlos, Alexander G. (Inventor); Atiya, Amir F. (Inventor); Fernandez, Benito (Inventor); Tsai, Wei K. (Inventor); Chong, Kil T. (Inventor)

1995-01-01

The present invention is a fully connected feed forward network that includes at least one hidden layer 16. The hidden layer 16 includes nodes 20 in which the output of the node is fed back to that node as an input with a unit delay produced by a delay device 24 occurring in the feedback path 22 (local feedback). Each node within each layer also receives a delayed output (crosstalk) produced by a delay unit 36 from all the other nodes within the same layer 16. The node performs a transfer function operation based on the inputs from the previous layer and the delayed outputs. The network can be implemented as analog or digital or within a general purpose processor. Two teaching methods can be used: (1) back propagation of weight calculation that includes the local feedback and the crosstalk or (2) more preferably a feed forward gradient decent which immediately follows the output computations and which also includes the local feedback and the crosstalk. Subsequent to the gradient propagation, the weights can be normalized, thereby preventing convergence to a local optimum. Education of the network can be incremental both on and off-line. An educated network is suitable for modeling and controlling dynamic nonlinear systems and time series systems and predicting the outputs as well as hidden states and parameters. The educated network can also be further educated during on-line processing.

Analysis of the Growth Process of Neural Cells in Culture Environment Using Image Processing Techniques

Science.gov (United States)

Mirsafianf, Atefeh S.; Isfahani, Shirin N.; Kasaei, Shohreh; Mobasheri, Hamid

Here we present an approach for processing neural cells images to analyze their growth process in culture environment. We have applied several image processing techniques for: 1- Environmental noise reduction, 2- Neural cells segmentation, 3- Neural cells classification based on their dendrites' growth conditions, and 4- neurons' features Extraction and measurement (e.g., like cell body area, number of dendrites, axon's length, and so on). Due to the large amount of noise in the images, we have used feed forward artificial neural networks to detect edges more precisely.

Artificial neural networks for processing fluorescence spectroscopy data in skin cancer diagnostics

International Nuclear Information System (INIS)

Lenhardt, L; Zeković, I; Dramićanin, T; Dramićanin, M D

2013-01-01

Over the years various optical spectroscopic techniques have been widely used as diagnostic tools in the discrimination of many types of malignant diseases. Recently, synchronous fluorescent spectroscopy (SFS) coupled with chemometrics has been applied in cancer diagnostics. The SFS method involves simultaneous scanning of both emission and excitation wavelengths while keeping the interval of wavelengths (constant-wavelength mode) or frequencies (constant-energy mode) between them constant. This method is fast, relatively inexpensive, sensitive and non-invasive. Total synchronous fluorescence spectra of normal skin, nevus and melanoma samples were used as input for training of artificial neural networks. Two different types of artificial neural networks were trained, the self-organizing map and the feed-forward neural network. Histopathology results of investigated skin samples were used as the gold standard for network output. Based on the obtained classification success rate of neural networks, we concluded that both networks provided high sensitivity with classification errors between 2 and 4%. (paper)

A robust neural network-based approach for microseismic event detection

KAUST Repository

Akram, Jubran

2017-08-17

We present an artificial neural network based approach for robust event detection from low S/N waveforms. We use a feed-forward network with a single hidden layer that is tuned on a training dataset and later applied on the entire example dataset for event detection. The input features used include the average of absolute amplitudes, variance, energy-ratio and polarization rectilinearity. These features are calculated in a moving-window of same length for the entire waveform. The output is set as a user-specified relative probability curve, which provides a robust way of distinguishing between weak and strong events. An optimal network is selected by studying the weight-based saliency and effect of number of neurons on the predicted results. Using synthetic data examples, we demonstrate that this approach is effective in detecting weaker events and reduces the number of false positives.

Backpropagation Neural Ensemble for Localizing and Recognizing Non-Standardized Malaysia’s Car Plates

OpenAIRE

Chin Kim On; Teo Kein Yau; Rayner Alfred; Jason Teo; Patricia Anthony; Wang Cheng

2016-01-01

In this paper, we describe a research project that autonomously localizes and recognizes non-standardized Malaysian’s car plates using conventional Backpropagation algorithm (BPP) in combination with Ensemble Neural Network (ENN). We compared the results with the results obtained using simple Feed-Forward Neural Network (FFNN). This research aims to solve four main issues; (1) localization of car plates that has the same colour with the vehicle colour, (2) detection and recognition of car pla...

Analysis and optimization of gas-centrifugal separation of uranium isotopes by neural networks

Directory of Open Access Journals (Sweden)

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.

A feed-forward circuit linking wingless, fat-dachsous signaling, and the warts-hippo pathway to Drosophila wing growth.

Directory of Open Access Journals (Sweden)

Myriam Zecca

2010-06-01

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.

ECO INVESTMENT PROJECT MANAGEMENT THROUGH TIME APPLYING ARTIFICIAL NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

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.

An artificial neural network to predict resting energy expenditure in obesity.

Science.gov (United States)

Disse, Emmanuel; Ledoux, Séverine; Bétry, Cécile; Caussy, Cyrielle; Maitrepierre, Christine; Coupaye, Muriel; Laville, Martine; Simon, Chantal

2017-09-01

The resting energy expenditure (REE) determination is important in nutrition for adequate dietary prescription. The gold standard i.e. indirect calorimetry is not available in clinical settings. Thus, several predictive equations have been developed, but they lack of accuracy in subjects with extreme weight including obese populations. Artificial neural networks (ANN) are useful predictive tools in the area of artificial intelligence, used in numerous clinical fields. The aim of this study was to determine the relevance of ANN in predicting REE in obesity. A Multi-Layer Perceptron (MLP) feed-forward neural network with a back propagation algorithm was created and cross-validated in a cohort of 565 obese subjects (BMI within 30-50 kg m -2 ) with weight, height, sex and age as clinical inputs and REE measured by indirect calorimetry as output. The predictive performances of ANN were compared to those of 23 predictive REE equations in the training set and in two independent sets of 100 and 237 obese subjects for external validation. Among the 23 established prediction equations for REE evaluated, the Harris & Benedict equations recalculated by Roza were the most accurate for the obese population, followed by the USA DRI, Müller and the original Harris & Benedict equations. The final 5-fold cross-validated three-layer 4-3-1 feed-forward back propagation ANN model developed in that study improved precision and accuracy of REE prediction over linear equations (precision = 68.1%, MAPE = 8.6% and RMSPE = 210 kcal/d), independently from BMI subgroups within 30-50 kg m -2 . External validation confirmed the better predictive performances of ANN model (precision = 73% and 65%, MAPE = 7.7% and 8.6%, RMSPE = 187 kcal/d and 200 kcal/d in the 2 independent datasets) for the prediction of REE in obese subjects. We developed and validated an ANN model for the prediction of REE in obese subjects that is more precise and accurate than established REE predictive

Cell-type specific short-term plasticity at auditory nerve synapses controls feed-forward inhibition in the dorsal cochlear nucleus.

Science.gov (United States)

Sedlacek, Miloslav; Brenowitz, Stephan D

2014-01-01

Feed-forward inhibition (FFI) represents a powerful mechanism by which control of the timing and fidelity of action potentials in local synaptic circuits of various brain regions is achieved. In the cochlear nucleus, the auditory nerve provides excitation to both principal neurons and inhibitory interneurons. Here, we investigated the synaptic circuit associated with fusiform cells (FCs), principal neurons of the dorsal cochlear nucleus (DCN) that receive excitation from auditory nerve fibers and inhibition from tuberculoventral cells (TVCs) on their basal dendrites in the deep layer of DCN. Despite the importance of these inputs in regulating fusiform cell firing behavior, the mechanisms determining the balance of excitation and FFI in this circuit are not well understood. Therefore, we examined the timing and plasticity of auditory nerve driven FFI onto FCs. We find that in some FCs, excitatory and inhibitory components of FFI had the same stimulation thresholds indicating they could be triggered by activation of the same fibers. In other FCs, excitation and inhibition exhibit different stimulus thresholds, suggesting FCs and TVCs might be activated by different sets of fibers. In addition, we find that during repetitive activation, synapses formed by the auditory nerve onto TVCs and FCs exhibit distinct modes of short-term plasticity. Feed-forward inhibitory post-synaptic currents (IPSCs) in FCs exhibit short-term depression because of prominent synaptic depression at the auditory nerve-TVC synapse. Depression of this feedforward inhibitory input causes a shift in the balance of fusiform cell synaptic input towards greater excitation and suggests that fusiform cell spike output will be enhanced by physiological patterns of auditory nerve activity.

Application of artificial neural networks in particle physics

International Nuclear Information System (INIS)

Kolanoski, H.

1995-04-01

The application of Artificial Neural Networks in Particle Physics is reviewed. Most common is the use of feed-forward nets for event classification and function approximation. This network type is best suited for a hardware implementation and special VLSI chips are available which are used in fast trigger processors. Also discussed are fully connected networks of the Hopfield type for pattern recognition in tracking detectors. (orig.)

Two neural network based strategies for the detection of a total instantaneous blockage of a sodium-cooled fast reactor

International Nuclear Information System (INIS)

Martinez-Martinez, Sinuhe; Messai, Nadhir; Jeannot, Jean-Philippe; Nuzillard, Danielle

2015-01-01

The total instantaneous blockage (TIB) of an assembly in the core of a sodium-cooled fast reactor (SFR) is investigated. Such incident could appear as an abnormal rise in temperature on the assemblies neighbouring the blockage. Its detection relies on a dataset of temperature measurements of the assemblies making up the core of the French Phenix Nuclear Reactor. The data are provided by the French Commission of Atomic and Alternatives Energies (CEA). Here, two strategies are proposed depending on whether the sensor measurement of the suspected assembly is reliable or not. The proposed methodology implements a time-lagged feed-forward neural (TLFFN) Network in order to predict the one-step-ahead temperature of a given assembly. The incident is declared if the difference between the predicted process and the actual one exceeds a threshold. In these simulated conditions, the method is efficient to detect small gradients as expected in reality. - Highlights: • We study the total instantaneous blockage (TIB) of a sodium-cooled fast reactor. • The TIB symptom is simulated as an abrupt rise on temperature (0.1–1 °C/s). • The goal is to improve the early detection of the incident. • Two strategies laying on neural networks are proposed. • TIB is detected in 3 s for 1 °C/s and 18–21 s for 0.1 °C/s

Learning text representation using recurrent convolutional neural network with highway layers

OpenAIRE

Wen, Ying; Zhang, Weinan; Luo, Rui; Wang, Jun

2016-01-01

Recently, the rapid development of word embedding and neural networks has brought new inspiration to various NLP and IR tasks. In this paper, we describe a staged hybrid model combining Recurrent Convolutional Neural Networks (RCNN) with highway layers. The highway network module is incorporated in the middle takes the output of the bi-directional Recurrent Neural Network (Bi-RNN) module in the first stage and provides the Convolutional Neural Network (CNN) module in the last stage with the i...

Cell cycle regulation by feed-forward loops coupling transcription and phosphorylation

DEFF Research Database (Denmark)

Csikász-Nagy, Attila; Kapuy, Orsolya; Tóth, Attila

2009-01-01

of these EPs. From genome-scale data sets of budding yeast, we identify 126 EPs that are regulated by Cdk1 both through direct phosphorylation of the EP and through phosphorylation of the transcription factors that control expression of the EP, so that each of these EPs is regulated by a feed-forward loop (FFL......) from Cdk1. By mathematical modelling, we show that such FFLs can activate EPs at different phases of the cell cycle depending of the effective signs (+ or -) of the regulatory steps of the FFL. We provide several case studies of EPs that are controlled by FFLs exactly as our models predict. The signal...

Dynamic Pricing in Electronic Commerce Using Neural Network

Science.gov (United States)

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.

Pervaporation dehydration of ethanol by hyaluronic acid/sodium alginate two-active-layer composite membranes.

Science.gov (United States)

Gao, Chengyun; Zhang, Minhua; Ding, Jianwu; Pan, Fusheng; Jiang, Zhongyi; Li, Yifan; Zhao, Jing

2014-01-01

The composite membranes with two-active-layer (a capping layer and an inner layer) were prepared by sequential spin-coatings of hyaluronic acid (HA) and sodium alginate (NaAlg) on the polyacrylonitrile (PAN) support layer. The SEM showed a mutilayer structure and a distinct interface between the HA layer and the NaAlg layer. The coating sequence of two-active-layer had an obvious influence on the pervaporation dehydration performance of membranes. When the operation temperature was 80 °C and water concentration in feed was 10 wt.%, the permeate fluxes of HA/Alg/PAN membrane and Alg/HA/PAN membrane were similar, whereas the separation factor were 1130 and 527, respectively. It was found that the capping layer with higher hydrophilicity and water retention capacity, and the inner layer with higher permselectivity could increase the separation performance of the composite membranes. Meanwhile, effects of operation temperature and water concentration in feed on pervaporation performance as well as membrane properties were studied. Copyright © 2013 Elsevier Ltd. All rights reserved.

Kernel Function Tuning for Single-Layer Neural Networks

Czech Academy of Sciences Publication Activity Database

Vidnerová, Petra; Neruda, Roman

-, accepted 28.11. 2017 (2018) ISSN 2278-0149 R&D Projects: GA ČR GA15-18108S Institutional support: RVO:67985807 Keywords : single-layer neural networks * kernel methods * kernel function * optimisation Subject RIV: IN - Informatics, Computer Science http://www.ijmerr.com/

Antibacterial, anti-inflammatory and neuroprotective layer-by-layer coatings for neural implants

Science.gov (United States)

Zhang, Zhiling; Nong, Jia; Zhong, Yinghui

2015-08-01

Objective. Infection, inflammation, and neuronal loss are common issues that seriously affect the functionality and longevity of chronically implanted neural prostheses. Minocycline hydrochloride (MH) is a broad-spectrum antibiotic and effective anti-inflammatory drug that also exhibits potent neuroprotective activities. In this study, we investigated the development of biocompatible thin film coatings capable of sustained release of MH for improving the long term performance of implanted neural electrodes. Approach. We developed a novel magnesium binding-mediated drug delivery mechanism for controlled and sustained release of MH from an ultrathin hydrophilic layer-by-layer (LbL) coating and characterized the parameters that control MH loading and release. The anti-biofilm, anti-inflammatory and neuroprotective potencies of the LbL coating and released MH were also examined. Main results. Sustained release of physiologically relevant amount of MH for 46 days was achieved from the Mg2+-based LbL coating at a thickness of 1.25 μm. In addition, MH release from the LbL coating is pH-sensitive. The coating and released MH demonstrated strong anti-biofilm, anti-inflammatory, and neuroprotective potencies. Significance. This study reports, for the first time, the development of a bioactive coating that can target infection, inflammation, and neuroprotection simultaneously, which may facilitate the translation of neural interfaces to clinical applications.

Mitigation of ground motion effects in linear accelerators via feed-forward control

Directory of Open Access Journals (Sweden)

J. Pfingstner

2014-12-01

Full Text Available Ground motion is a severe problem for many particle accelerators, since it excites beam oscillations, which decrease the beam quality and create beam-beam offset (at colliders. Orbit feedback systems can only compensate ground motion effects at frequencies significantly smaller than the beam repetition rate. In linear colliders, where the repetition rate is low, additional counter measures have to be put in place. For this reason, a ground motion mitigation method based on feed-forward control is presented in this paper. It has several advantages compared to other techniques (stabilization systems and intratrain feedback systems such as cost reduction and potential performance improvement. An analytical model is presented that allows the derivation of hardware specification and performance estimates for a specific accelerator and ground motion model. At the Accelerator Test Facility (ATF2, ground motion sensors have been installed to verify the feasibility of important parts of the mitigation strategy. In experimental studies, it has been shown that beam excitations due to ground motion can be predicted from ground motion measurements on a pulse-to-pulse basis. Correlations of up to 80% between the estimated and measured orbit jitter have been observed. Additionally, an orbit jitter source was identified and has been removed, which halved the orbit jitter power at ATF2 and shows that the feed-forward scheme is also very useful for the detection of installation issues. We believe that the presented mitigation method has the potential to reduce costs and improve the performance of linear colliders and potentially other linear accelerators.

A new method to estimate parameters of linear compartmental models using artificial neural networks

International Nuclear Information System (INIS)

Gambhir, Sanjiv S.; Keppenne, Christian L.; Phelps, Michael E.; Banerjee, Pranab K.

1998-01-01

At present, the preferred tool for parameter estimation in compartmental analysis is an iterative procedure; weighted nonlinear regression. For a large number of applications, observed data can be fitted to sums of exponentials whose parameters are directly related to the rate constants/coefficients of the compartmental models. Since weighted nonlinear regression often has to be repeated for many different data sets, the process of fitting data from compartmental systems can be very time consuming. Furthermore the minimization routine often converges to a local (as opposed to global) minimum. In this paper, we examine the possibility of using artificial neural networks instead of weighted nonlinear regression in order to estimate model parameters. We train simple feed-forward neural networks to produce as outputs the parameter values of a given model when kinetic data are fed to the networks' input layer. The artificial neural networks produce unbiased estimates and are orders of magnitude faster than regression algorithms. At noise levels typical of many real applications, the neural networks are found to produce lower variance estimates than weighted nonlinear regression in the estimation of parameters from mono- and biexponential models. These results are primarily due to the inability of weighted nonlinear regression to converge. These results establish that artificial neural networks are powerful tools for estimating parameters for simple compartmental models. (author)

Flux patterns and membrane fouling propensity during desalination of seawater by forward osmosis

KAUST Repository

Li, Zhenyu; Yangali-Quintanilla, Victor; Valladares Linares, Rodrigo; Li, Qingyu; Zhan, Tong; Amy, Gary L.

2012-01-01

The membrane fouling propensity of natural seawater during forward osmosis was studied. Seawater from the Red Sea was used as the feed in a forward osmosis process while a 2. M sodium chloride solution was used as the draw solution. The process was conducted in a semi-batch mode under two crossflow velocities, 16.7. cm/s and 4.2. cm/s. For the first time reported, silica scaling was found to be the dominant inorganic fouling (scaling) on the surface of membrane active layer during seawater forward osmosis. Polymerization of dissolved silica was the major mechanism for the formation of silica scaling. After ten batches of seawater forward osmosis, the membrane surface was covered by a fouling layer of assorted polymerized silica clusters and natural organic matter, especially biopolymers. Moreover, the absorbed biopolymers also provided bacterial attachment sites. The accumulated organic fouling could be partially removed by water flushing while the polymerized silica was difficult to remove. The rate of flux decline was about 53% with a crossflow velocity of 16.7. cm/s while reaching more than 70% with a crossflow velocity of 4.2. cm/s. Both concentration polarization and fouling played roles in the decrease of flux. The salt rejection was stable at about 98% during seawater forward osmosis. In addition, an almost complete rejection of natural organic matter was attained. The results from this study are valuable for the design and development of a successful protocol for a pretreatment process before seawater forward osmosis and a cleaning method for fouled membranes. © 2011 Elsevier Ltd.

A one-layer recurrent neural network for constrained nonsmooth optimization.

Science.gov (United States)

Liu, Qingshan; Wang, Jun

2011-10-01

This paper presents a novel one-layer recurrent neural network modeled by means of a differential inclusion for solving nonsmooth optimization problems, in which the number of neurons in the proposed neural network is the same as the number of decision variables of optimization problems. Compared with existing neural networks for nonsmooth optimization problems, the global convexity condition on the objective functions and constraints is relaxed, which allows the objective functions and constraints to be nonconvex. It is proven that the state variables of the proposed neural network are convergent to optimal solutions if a single design parameter in the model is larger than a derived lower bound. Numerical examples with simulation results substantiate the effectiveness and illustrate the characteristics of the proposed neural network.

Noise processing by microRNA-mediated circuits: The Incoherent Feed-Forward Loop, revisited

Directory of Open Access Journals (Sweden)

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.

Neural correlates of food anticipatory activity in mice subjected to once- or twice-daily feeding periods.

Science.gov (United States)

Rastogi, Ashutosh; Mintz, Eric M

2017-10-01

In rodents, restricted food access to a limited period each day at a predictable time results in the appearance of food anticipatory activity (FAA). Two shorter periods of food access each day can result in two FAA bouts. In this study, we examine FAA under 12:12 and 18:6 photoperiods in mice (Mus musculus) with one or two food access periods per day and measure the activation of the suprachiasmatic, dorsomedial and arcuate nuclei by assaying Fos protein expression, while making use of tissue-type plasminogen activator knockout mice to assess the role of neural plasticity in adaptation to restricted feeding cycles. Long days were utilised to allow for temporal separation of two restricted feeding periods during the light phase. Mice fed twice per day generally divided FAA into two distinct bouts, with mice lacking tissue-type plasminogen activator showing reduced FAA. Increases in Fos expression in response to one restricted feeding period per day were seen in the dorsomedial and arcuate nuclei in both 12:12 and 18:6 conditions, with an increase seen in the SCN in only the 12:12 condition. These increases were eliminated or reduced in the two feeding time conditions (done in 18:6 only). Both activity patterns and Fos expression differed for single restricted feeding times between 18:6 and 12:12 photoperiods. Fos activation was lower during RF in 18:6 than 12:12 across all three brain regions, a pattern not reflective of changes in FAA. These data suggest that involvement of these regions in FAA may be influenced by photoperiodic context. © 2017 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.

Growth kinetics of borided layers: Artificial neural network and least square approaches

Science.gov (United States)

Campos, I.; Islas, M.; Ramírez, G.; VillaVelázquez, C.; Mota, C.

2007-05-01

The present study evaluates the growth kinetics of the boride layer Fe 2B in AISI 1045 steel, by means of neural networks and the least square techniques. The Fe 2B phase was formed at the material surface using the paste boriding process. The surface boron potential was modified considering different boron paste thicknesses, with exposure times of 2, 4 and 6 h, and treatment temperatures of 1193, 1223 and 1273 K. The neural network and the least square models were set by the layer thickness of Fe 2B phase, and assuming that the growth of the boride layer follows a parabolic law. The reliability of the techniques used is compared with a set of experiments at a temperature of 1223 K with 5 h of treatment time and boron potentials of 2, 3, 4 and 5 mm. The results of the Fe 2B layer thicknesses show a mean error of 5.31% for the neural network and 3.42% for the least square method.

High performance thin-film composite forward osmosis membrane.

Science.gov (United States)

Yip, Ngai Yin; Tiraferri, Alberto; Phillip, William A; Schiffman, Jessica D; Elimelech, Menachem

2010-05-15

Recent studies show that osmotically driven membrane processes may be a viable technology for desalination, water and wastewater treatment, and power generation. However, the absence of a membrane designed for such processes is a significant obstacle hindering further advancements of this technology. This work presents the development of a high performance thin-film composite membrane for forward osmosis applications. The membrane consists of a selective polyamide active layer formed by interfacial polymerization on top of a polysulfone support layer fabricated by phase separation onto a thin (40 mum) polyester nonwoven fabric. By careful selection of the polysulfone casting solution (i.e., polymer concentration and solvent composition) and tailoring the casting process, we produced a support layer with a mix of finger-like and sponge-like morphologies that give significantly enhanced membrane performance. The structure and performance of the new thin-film composite forward osmosis membrane are compared with those of commercial membranes. Using a 1.5 M NaCl draw solution and a pure water feed, the fabricated membranes produced water fluxes exceeding 18 L m(2-)h(-1), while consistently maintaining observed salt rejection greater than 97%. The high water flux of the fabricated thin-film composite forward osmosis membranes was directly related to the thickness, porosity, tortuosity, and pore structure of the polysulfone support layer. Furthermore, membrane performance did not degrade after prolonged exposure to an ammonium bicarbonate draw solution.

High Performance Thin-Film Composite Forward Osmosis Membrane

KAUST Repository

Yip, Ngai Yin

2010-05-15

Recent studies show that osmotically driven membrane processes may be a viable technology for desalination, water and wastewater treatment, and power generation. However, the absence of a membrane designed for such processes is a significant obstacle hindering further advancements of this technology. This work presents the development of a high performance thin-film composite membrane for forward osmosis applications. The membrane consists of a selective polyamide active layer formed by interfacial polymerization on top of a polysulfone support layer fabricated by phase separation onto a thin (40 μm) polyester nonwoven fabric. By careful selection of the polysulfone casting solution (i.e., polymer concentration and solvent composition) and tailoring the casting process, we produced a support layer with a mix of finger-like and sponge-like morphologies that give significantly enhanced membrane performance. The structure and performance of the new thin-film composite forward osmosis membrane are compared with those of commercial membranes. Using a 1.5 M NaCl draw solution and a pure water feed, the fabricated membranes produced water fluxes exceeding 18 L m2-h-1, while consistently maintaining observed salt rejection greater than 97%. The high water flux of the fabricated thin-film composite forward osmosis membranes was directly related to the thickness, porosity, tortuosity, and pore structure of the polysulfone support layer. Furthermore, membrane performance did not degrade after prolonged exposure to an ammonium bicarbonate draw solution. © 2010 American Chemical Society.

Seismic activity prediction using computational intelligence techniques in northern Pakistan

Science.gov (United States)

Asim, Khawaja M.; Awais, Muhammad; Martínez-Álvarez, F.; Iqbal, Talat

2017-10-01

Earthquake prediction study is carried out for the region of northern Pakistan. The prediction methodology includes interdisciplinary interaction of seismology and computational intelligence. Eight seismic parameters are computed based upon the past earthquakes. Predictive ability of these eight seismic parameters is evaluated in terms of information gain, which leads to the selection of six parameters to be used in prediction. Multiple computationally intelligent models have been developed for earthquake prediction using selected seismic parameters. These models include feed-forward neural network, recurrent neural network, random forest, multi layer perceptron, radial basis neural network, and support vector machine. The performance of every prediction model is evaluated and McNemar's statistical test is applied to observe the statistical significance of computational methodologies. Feed-forward neural network shows statistically significant predictions along with accuracy of 75% and positive predictive value of 78% in context of northern Pakistan.

Neural Network Training by Integration of Adjoint Systems of Equations Forward in Time

Science.gov (United States)

Toomarian, Nikzad (Inventor); Barhen, Jacob (Inventor)

1999-01-01

A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically. it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved. but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. Tbc trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

In vivo spatial frequency domain spectroscopy of two layer media

Science.gov (United States)

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.

Particle identification with neural networks using a rotational invariant moment representation

International Nuclear Information System (INIS)

Sinkus, R.

1997-01-01

A feed-forward neural network is used to identify electromagnetic particles based upon their showering properties within a segmented calorimeter. The novel feature is the expansion of the energy distribution in terms of moments of the so-called Zernike functions which are invariant under rotation. The multidimensional input distribution for the neural network is transformed via a principle component analysis and rescaled by its respective variances to ensure input values of the order of one. This results is a better performance in identifying and separating electromagnetic from hadronic particles, especially at low energies. (orig.)

Unlearning in feed-forward multi-nets

NARCIS (Netherlands)

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

Adaptive Feed-Forward Control of Low Frequency Interior Noise

CERN Document Server

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.

Protecting nonlocality of multipartite states by feed-forward control

Science.gov (United States)

Li, Xiao-Gang; Zou, Jian; Shao, Bin

2018-06-01

Nonlocality is a useful resource in quantum communication and quantum information processing. In practical quantum communication, multipartite entangled states must be distributed between different users in different places through a channel. However, the channel is usually inevitably disturbed by the environment in quantum state distribution processing and then the nonlocality of states will be weakened and even lost. In this paper, we use a feed-forward control scheme to protect the nonlocality of the Bell and GHZ states against dissipation. We find that this protection scheme is very effective, specifically, for the Bell state, we can increase the noise threshold from 0.5 to 0.98, and for GHZ state from 0.29 to 0.96. And we also find that entanglement is relatively easier to be protected than nonlocality. For our scheme, protecting entanglement is equivalent to protecting the state in the case of Bell state, while protecting nonlocality is not.

Control of 12-Cylinder Camless Engine with Neural Networks

Directory of Open Access Journals (Sweden)

Ashhab Moh’d Sami

2017-01-01

Full Text Available The 12-cyliner camless engine breathing process is modeled with artificial neural networks (ANN’s. The inputs to the net are the intake valve lift (IVL and intake valve closing timing (IVC whereas the output of the net is the cylinder air charge (CAC. The ANN is trained with data collected from an engine simulation model which is based on thermodynamics principles and calibrated against real engine data. A method for adapting single-output feed-forward neural networks is proposed and applied to the camless engine ANN model. As a consequence the overall 12-cyliner camless engine feedback controller is upgraded and the necessary changes are implemented in order to contain the adaptive neural network with the objective of tracking the cylinder air charge (driver’s torque demand while minimizing the pumping losses (increasing engine efficiency. All the needed measurements are extracted only from the two conventional and inexpensive sensors, namely, the mass air flow through the throttle body (MAF and the intake manifold absolute pressure (MAP sensors. The feedback controller’s capability is demonstrated through computer simulation.

Generalized Predictive Control and Neural Generalized Predictive Control

Directory of Open Access Journals (Sweden)

Sadhana CHIDRAWAR

2008-12-01

Full Text Available As Model Predictive Control (MPC relies on the predictive Control using a multilayer feed forward network as the plants linear model is presented. In using Newton-Raphson as the optimization algorithm, the number of iterations needed for convergence is significantly reduced from other techniques. This paper presents a detailed derivation of the Generalized Predictive Control and Neural Generalized Predictive Control with Newton-Raphson as minimization algorithm. Taking three separate systems, performances of the system has been tested. Simulation results show the effect of neural network on Generalized Predictive Control. The performance comparison of this three system configurations has been given in terms of ISE and IAE.

Gradual DropIn of Layers to Train Very Deep Neural Networks

OpenAIRE

Smith, Leslie N.; Hand, Emily M.; Doster, Timothy

2015-01-01

We introduce the concept of dynamically growing a neural network during training. In particular, an untrainable deep network starts as a trainable shallow network and newly added layers are slowly, organically added during training, thereby increasing the network's depth. This is accomplished by a new layer, which we call DropIn. The DropIn layer starts by passing the output from a previous layer (effectively skipping over the newly added layers), then increasingly including units from the ne...

Psychological Processing in Chronic Pain: A Neural Systems Approach

OpenAIRE

Simons, Laura; Elman, Igor; Borsook, David

2013-01-01

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 implementati...

An Artificial Neural Network for Data Forecasting Purposes

Directory of Open Access Journals (Sweden)

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.

Enhancing the top-quark signal at Fermilab Tevatron using neural nets

International Nuclear Information System (INIS)

Ametller, L.; Garrido, L.; Talavera, P.

1994-01-01

We show, in agreement with previous studies, that neural nets can be useful for top-quark analysis at the Fermilab Tevatron. The main features of t bar t and background events in a mixed sample are projected on a single output, which controls the efficiency, purity, and statistical significance of the t bar t signal. We consider a feed-forward multilayer neural net for the CDF reported top-quark mass, using six kinematical variables as inputs. Our main results are based on the exhaustive comparison of the neural net performances with those obtainable from the standard experimental analysis, by imposing different sets of linear cuts over the same variables, showing how the neural net approach improves the standard analysis results

Modeling by artificial neural networks. Application to the management of fuel in a nuclear power plant

International Nuclear Information System (INIS)

Gaudier, F.

1999-01-01

The determination of the family of optimum core loading patterns for Pressurized Water Reactors (PWRs) involves the assessment of the core attributes, such as the power peaking factor for thousands of candidate loading patterns. Despite the rapid advances in computer architecture, the direct calculation of these attributes by a neutronic code needs a lot of of time and memory. With the goal of reducing the calculation time and optimizing the loading pattern, we propose in this thesis a method based on ideas of neural and statistical learning to provide a feed forward neural network capable of calculating the power peaking corresponding to an eighth core PWR. We use statistical methods to deduct judicious inputs (reduction of the input space dimension) and neural methods to train the model (learning capabilities). Indeed, on one hand, a principal component analysis allows us to characterize more efficiently the fuel assemblies (neural model inputs) and the other hand, the introduction of the a priori knowledge allows us to reducing the number of freedom parameters in the neural network. The model was built using a multi layered perceptron trained with the standard back propagation algorithm. We introduced our neural network in the automatic optimization code FORMOSA, and on EDF real problems we showed an important saving in time. Finally, we propose an hybrid method which combining the best characteristics of the linear local approximator GPT (Generalized Perturbation Theory) and the artificial neural network. (author)

On the approximation by single hidden layer feedforward neural networks with fixed weights

OpenAIRE

Guliyev, Namig J.; Ismailov, Vugar E.

2017-01-01

International audience; Feedforward neural networks have wide applicability in various disciplines of science due to their universal approximation property. Some authors have shown that single hidden layer feedforward neural networks (SLFNs) with fixed weights still possess the universal approximation property provided that approximated functions are univariate. But this phenomenon does not lay any restrictions on the number of neurons in the hidden layer. The more this number, the more the p...

A one-layer recurrent neural network for constrained nonconvex optimization.

Science.gov (United States)

Li, Guocheng; Yan, Zheng; Wang, Jun

2015-01-01

In this paper, a one-layer recurrent neural network is proposed for solving nonconvex optimization problems subject to general inequality constraints, designed based on an exact penalty function method. It is proved herein that any neuron state of the proposed neural network is convergent to the feasible region in finite time and stays there thereafter, provided that the penalty parameter is sufficiently large. The lower bounds of the penalty parameter and convergence time are also estimated. In addition, any neural state of the proposed neural network is convergent to its equilibrium point set which satisfies the Karush-Kuhn-Tucker conditions of the optimization problem. Moreover, the equilibrium point set is equivalent to the optimal solution to the nonconvex optimization problem if the objective function and constraints satisfy given conditions. Four numerical examples are provided to illustrate the performances of the proposed neural network.

The application of artificial neural network in radon disaster model of uranium mining

International Nuclear Information System (INIS)

Zhu Yufeng; Zhu Guogen; Zhou Shijian

2012-01-01

The structural features, data analysis and learning process of feed-forward neural network (BP ANN) were analyzed at first. Rodon sample from Fuzhou Jinan Uranium Industry Limited Company were used to training the network and make the forecast then, and a forecasting model was established for the radon disaster in uranium mines. The method and effectiveness of BP neural network in predicting radon disaster was discussed. The test of training samples showed that the BP network had gotten fairly satisfied result in predicting mine radon disaster. (authors)

A One-Layer Recurrent Neural Network for Constrained Complex-Variable Convex Optimization.

Science.gov (United States)

Qin, Sitian; Feng, Jiqiang; Song, Jiahui; Wen, Xingnan; Xu, Chen

2018-03-01

In this paper, based on calculus and penalty method, a one-layer recurrent neural network is proposed for solving constrained complex-variable convex optimization. It is proved that for any initial point from a given domain, the state of the proposed neural network reaches the feasible region in finite time and converges to an optimal solution of the constrained complex-variable convex optimization finally. In contrast to existing neural networks for complex-variable convex optimization, the proposed neural network has a lower model complexity and better convergence. Some numerical examples and application are presented to substantiate the effectiveness of the proposed neural network.

Relationship between Parental Feeding Practices and Neural Responses to Food Cues in Adolescents.

Directory of Open Access Journals (Sweden)

Harriet A Allen

response to parental teaching and modelling of behaviour. Parental restrictive feeding and parental teaching and modelling affected neural responses to food cues in different ways, depending on motivations and diagnoses, illustrating a social influence on neural responses to food cues.

Relationship between Parental Feeding Practices and Neural Responses to Food Cues in Adolescents

Science.gov (United States)

Chambers, Alison; Blissett, Jacqueline; Chechlacz, Magdalena; Barrett, Timothy; Higgs, Suzanne; Nouwen, Arie

2016-01-01

parental teaching and modelling of behaviour. Parental restrictive feeding and parental teaching and modelling affected neural responses to food cues in different ways, depending on motivations and diagnoses, illustrating a social influence on neural responses to food cues. PMID:27479051

Cardiac Arrhythmia Classification by Multi-Layer Perceptron and Convolution Neural Networks

Directory of Open Access Journals (Sweden)

Shalin Savalia

2018-05-01

Full Text Available The electrocardiogram (ECG plays an imperative role in the medical field, as it records heart signal over time and is used to discover numerous cardiovascular diseases. If a documented ECG signal has a certain irregularity in its predefined features, this is called arrhythmia, the types of which include tachycardia, bradycardia, supraventricular arrhythmias, and ventricular, etc. This has encouraged us to do research that consists of distinguishing between several arrhythmias by using deep neural network algorithms such as multi-layer perceptron (MLP and convolution neural network (CNN. The TensorFlow library that was established by Google for deep learning and machine learning is used in python to acquire the algorithms proposed here. The ECG databases accessible at PhysioBank.com and kaggle.com were used for training, testing, and validation of the MLP and CNN algorithms. The proposed algorithm consists of four hidden layers with weights, biases in MLP, and four-layer convolution neural networks which map ECG samples to the different classes of arrhythmia. The accuracy of the algorithm surpasses the performance of the current algorithms that have been developed by other cardiologists in both sensitivity and precision.

Cardiac Arrhythmia Classification by Multi-Layer Perceptron and Convolution Neural Networks.

Science.gov (United States)

Savalia, Shalin; Emamian, Vahid

2018-05-04

The electrocardiogram (ECG) plays an imperative role in the medical field, as it records heart signal over time and is used to discover numerous cardiovascular diseases. If a documented ECG signal has a certain irregularity in its predefined features, this is called arrhythmia, the types of which include tachycardia, bradycardia, supraventricular arrhythmias, and ventricular, etc. This has encouraged us to do research that consists of distinguishing between several arrhythmias by using deep neural network algorithms such as multi-layer perceptron (MLP) and convolution neural network (CNN). The TensorFlow library that was established by Google for deep learning and machine learning is used in python to acquire the algorithms proposed here. The ECG databases accessible at PhysioBank.com and kaggle.com were used for training, testing, and validation of the MLP and CNN algorithms. The proposed algorithm consists of four hidden layers with weights, biases in MLP, and four-layer convolution neural networks which map ECG samples to the different classes of arrhythmia. The accuracy of the algorithm surpasses the performance of the current algorithms that have been developed by other cardiologists in both sensitivity and precision.

Selection of Hidden Layer Neurons and Best Training Method for FFNN in Application of Long Term Load Forecasting

Science.gov (United States)

Singh, Navneet K.; Singh, Asheesh K.; Tripathy, Manoj

2012-05-01

For power industries electricity load forecast plays an important role for real-time control, security, optimal unit commitment, economic scheduling, maintenance, energy management, and plant structure planning etc. A new technique for long term load forecasting (LTLF) using optimized feed forward artificial neural network (FFNN) architecture is presented in this paper, which selects optimal number of neurons in the hidden layer as well as the best training method for the case study. The prediction performance of proposed technique is evaluated using mean absolute percentage error (MAPE) of Thailand private electricity consumption and forecasted data. The results obtained are compared with the results of classical auto-regressive (AR) and moving average (MA) methods. It is, in general, observed that the proposed method is prediction wise more accurate.

Estimating surface longwave radiative fluxes from satellites utilizing artificial neural networks

Science.gov (United States)

Nussbaumer, Eric A.; Pinker, Rachel T.

2012-04-01

A novel approach for calculating downwelling surface longwave (DSLW) radiation under all sky conditions is presented. The DSLW model (hereafter, DSLW/UMD v2) similarly to its predecessor, DSLW/UMD v1, is driven with a combination of Moderate Resolution Imaging Spectroradiometer (MODIS) level-3 cloud parameters and information from the European Centre for Medium-Range Weather Forecasts (ECMWF) ERA-Interim model. To compute the clear sky component of DSLW a two layer feed-forward artificial neural network with sigmoid hidden neurons and linear output neurons is implemented; it is trained with simulations derived from runs of the Rapid Radiative Transfer Model (RRTM). When computing the cloud contribution to DSLW, the cloud base temperature is estimated by using an independent artificial neural network approach of similar architecture as previously mentioned, and parameterizations. The cloud base temperature neural network is trained using spatially and temporally co-located MODIS and CloudSat Cloud Profiling Radar (CPR) and the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) observations. Daily average estimates of DSLW from 2003 to 2009 are compared against ground measurements from the Baseline Surface Radiation Network (BSRN) giving an overall correlation coefficient of 0.98, root mean square error (rmse) of 15.84 W m-2, and a bias of -0.39 W m-2. This is an improvement over an earlier version of the model (DSLW/UMD v1) which for the same time period has an overall correlation coefficient 0.97 rmse of 17.27 W m-2, and bias of 0.73 W m-2.

Turbulent boundary layer under the control of different schemes.

Science.gov (United States)

Qiao, Z X; Zhou, Y; Wu, Z

2017-06-01

This work explores experimentally the control of a turbulent boundary layer over a flat plate based on wall perturbation generated by piezo-ceramic actuators. Different schemes are investigated, including the feed-forward, the feedback, and the combined feed-forward and feedback strategies, with a view to suppressing the near-wall high-speed events and hence reducing skin friction drag. While the strategies may achieve a local maximum drag reduction slightly less than their counterpart of the open-loop control, the corresponding duty cycles are substantially reduced when compared with that of the open-loop control. The results suggest a good potential to cut down the input energy under these control strategies. The fluctuating velocity, spectra, Taylor microscale and mean energy dissipation are measured across the boundary layer with and without control and, based on the measurements, the flow mechanism behind the control is proposed.

Parametric optimization design for supercritical CO2 power cycle using genetic algorithm and artificial neural network

International Nuclear Information System (INIS)

Wang Jiangfeng; Sun Zhixin; Dai Yiping; Ma Shaolin

2010-01-01

Supercritical CO 2 power cycle shows a high potential to recover low-grade waste heat due to its better temperature glide matching between heat source and working fluid in the heat recovery vapor generator (HRVG). Parametric analysis and exergy analysis are conducted to examine the effects of thermodynamic parameters on the cycle performance and exergy destruction in each component. The thermodynamic parameters of the supercritical CO 2 power cycle is optimized with exergy efficiency as an objective function by means of genetic algorithm (GA) under the given waste heat condition. An artificial neural network (ANN) with the multi-layer feed-forward network type and back-propagation training is used to achieve parametric optimization design rapidly. It is shown that the key thermodynamic parameters, such as turbine inlet pressure, turbine inlet temperature and environment temperature have significant effects on the performance of the supercritical CO 2 power cycle and exergy destruction in each component. It is also shown that the optimum thermodynamic parameters of supercritical CO 2 power cycle can be predicted with good accuracy using artificial neural network under variable waste heat conditions.

Structural Study and Modification of Support Layer for Forward Osmosis Membranes

KAUST Repository

Shi, Meixia

2016-06-01

Water scarcity is a serious global issue, due to the increasing population and developing economy, and membrane technology is an essential way to address this problem. Forward osmosis (FO) is an emerging membrane process, due to its low energy consumption (not considering the draw solute regeneration). A bottleneck to advance this technology is the design of the support layer for FO membranes to minimize the internal concentration polarization. In this dissertation, we focus on the structural study and modification of the support layer for FO membranes. Firstly, we digitally reconstruct different membrane morphologies in 3D and propose a method for predicting performance in ultrafiltration operations. Membranes with analogous morphologies are later used as substrate for FO membranes. Secondly, we experimentally apply substrates with different potentially suitable morphologies as an FO support layer. We investigate their FO performance after generating a selective polyamide layer on the top, by interfacial polymerization. Among the different substrates we include standard asymmetric porous membranes prepared from homopolymers, such as polysulfone. Additionally block copolymer membrane and Anodisc alumina membrane are chosen based on their exceptional structures, with cylindrical pores at least in part. 3D digitally reconstructed porous substrates, analogous to those investigated for ultrafiltration, are then used to model the performance in FO operation. Finally, we analyze the effect of intermediate layers between the porous substrate and the interfacial polymerized layer. We investigate two materials including chitosan and hydrogel. The main results are the following. Pore-scale modeling for digital membrane generation effectively predicts the velocity profile in different layers of the membrane and the performance in UF experiments. Flow simulations confirm the advantage of finger-like substrates over sponge-like ones, when high water permeance is sought

Approximate solutions of dual fuzzy polynomials by feed-back neural networks

Directory of Open Access Journals (Sweden)

Ahmad Jafarian

2012-11-01

Full Text Available Recently, artificial neural networks (ANNs have been extensively studied and used in different areas such as pattern recognition, associative memory, combinatorial optimization, etc. In this paper, we investigate the ability of fuzzy neural networks to approximate solution of a dual fuzzy polynomial of the form $a_{1}x+ ...+a_{n}x^n =b_{1}x+ ...+b_{n}x^n+d,$ where $a_{j},b_{j},d epsilon E^1 (for j=1,...,n.$ Since the operation of fuzzy neural networks is based on Zadeh's extension principle. For this scope we train a fuzzified neural network by back-propagation-type learning algorithm which has five layer where connection weights are crisp numbers. This neural network can get a crisp input signal and then calculates its corresponding fuzzy output. Presented method can give a real approximate solution for given polynomial by using a cost function which is defined for the level sets of fuzzy output and target output. The simulation results are presented to demonstrate the efficiency and effectiveness of the proposed approach.

Biofouling in forward osmosis systems: An experimental and numerical study.

Science.gov (United States)

Bucs, Szilárd S; Valladares Linares, Rodrigo; Vrouwenvelder, Johannes S; Picioreanu, Cristian

2016-12-01

This study evaluates with numerical simulations supported by experimental data the impact of biofouling on membrane performance in a cross-flow forward osmosis (FO) system. The two-dimensional numerical model couples liquid flow with solute transport in the FO feed and draw channels, in the FO membrane support layer and in the biofilm developed on one or both sides of the membrane. The developed model was tested against experimental measurements at various osmotic pressure differences and in batch operation without and with the presence of biofilm on the membrane active layer. Numerical studies explored the effect of biofilm properties (thickness, hydraulic permeability and porosity), biofilm membrane surface coverage, and biofilm location on salt external concentration polarization and on the permeation flux. The numerical simulations revealed that (i) when biofouling occurs, external concentration polarization became important, (ii) the biofilm hydraulic permeability and membrane surface coverage have the highest impact on water flux, and (iii) the biofilm formed in the draw channel impacts the process performance more than when formed in the feed channel. The proposed mathematical model helps to understand the impact of biofouling in FO membrane systems and to develop possible strategies to reduce and control biofouling. Copyright © 2016 Elsevier Ltd. All rights reserved.

Biofouling in forward osmosis systems: An experimental and numerical study

KAUST Repository

Bucs, Szilard

2016-09-20

This study evaluates with numerical simulations supported by experimental data the impact of biofouling on membrane performance in a cross-flow forward osmosis (FO) system. The two-dimensional numerical model couples liquid flow with solute transport in the FO feed and draw channels, in the FO membrane support layer and in the biofilm developed on one or both sides of the membrane. The developed model was tested against experimental measurements at various osmotic pressure differences and in batch operation without and with the presence of biofilm on the membrane active layer. Numerical studies explored the effect of biofilm properties (thickness, hydraulic permeability and porosity), biofilm membrane surface coverage, and biofilm location on salt external concentration polarization and on the permeation flux. The numerical simulations revealed that (i) when biofouling occurs, external concentration polarization became important, (ii) the biofilm hydraulic permeability and membrane surface coverage have the highest impact on water flux, and (iii) the biofilm formed in the draw channel impacts the process performance more than when formed in the feed channel. The proposed mathematical model helps to understand the impact of biofouling in FO membrane systems and to develop possible strategies to reduce and control biofouling. © 2016 Elsevier Ltd

Artificial neural networks in the nuclear engineering (Part 2)

International Nuclear Information System (INIS)

Baptista Filho, Benedito Dias

2002-01-01

The field of Artificial Neural Networks (ANN), one of the branches of Artificial Intelligence has been waking up a lot of interest in the Nuclear Engineering (NE). ANN can be used to solve problems of difficult modeling, when the data are fail or incomplete and in high complexity problems of control. The first part of this work began a discussion with feed-forward neural networks in back-propagation. In this part of the work, the Multi-synaptic neural networks is applied to control problems. Also, the self-organized maps is presented in a typical pattern classification problem: transients classification. The main purpose of the work is to show that ANN can be successfully used in NE if a carefully choice of its type is done: the application sets this choice. (author)

Neural networks for predicting breeding values and genetic gains

Directory of Open Access Journals (Sweden)

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.

Optimisation of the addition of carrot dietary fibre to a dry fermented sausage (sobrassada) using artificial neural networks.

Science.gov (United States)

Eim, Valeria S; Simal, Susana; Rosselló, Carmen; Femenia, Antoni; Bon, José

2013-07-01

An optimisation problem was formulated to maximise the amount of carrot dietary fibre (CDF) in a dry fermented sausage, while maintaining product quality, by using 0-12% CDF as the decision variable, and limiting values of several physico-chemical and textural parameters (moisture content, water activity, pH, colour, non-protein nitrogen, free fatty acid, compression work and hardness) as constraints. The evolution of each quality parameter during the ripening process was estimated by developing a multi-layer feed forward artificial neural network (ANN), taking into consideration the CDF concentration and the ripening time as independent variables. Results indicate an optimum CDF concentration of 4.9% with a good correlation between experimental and estimated values (mean relative error≤3.35%). Copyright © 2013 Elsevier Ltd. All rights reserved.

Neuro-Based Artificial Intelligence Model for Loan Decisions

OpenAIRE

Shorouq F. Eletter; Saad G. Yaseen; Ghaleb A. Elrefae

2010-01-01

Problem statement: Despite the increase in consumer loans defaults and competition in the banking market, most of the Jordanian commercial banks are reluctant to use artificial intelligence software systems for supporting loan decisions. Approach: This study developed a proposed model that identifies artificial neural network as an enabling tool for evaluating credit applications to support loan decisions in the Jordanian Commercial banks. A multi-layer feed-forward neural network with backpr...

Design of alluvial Egyptian irrigation canals using artificial neural networks method

Directory of Open Access Journals (Sweden)

Hassan Ibrahim Mohamed

2013-06-01

Full Text Available In the present study, artificial neural networks method (ANNs is used to estimate the main parameters which used in design of stable alluvial channels. The capability of ANN models to predict the stable alluvial channels dimensions is investigated, where the flow rate and sediment mean grain size were considered as input variables and wetted perimeter, hydraulic radius, and water surface slope were considered as output variables. The used ANN models are based on a back propagation algorithm to train a multi-layer feed-forward network (Levenberg Marquardt algorithm. The proposed models were verified using 311 data sets of field data collected from 61 manmade canals and drains. Several statistical measures and graphical representation are used to check the accuracy of the models in comparison with previous empirical equations. The results of the developed ANN model proved that this technique is reliable in such field compared with previously developed methods.

Distributed Recurrent Neural Forward Models with Synaptic Adaptation and CPG-based control for Complex Behaviors of Walking Robots

Directory of Open Access Journals (Sweden)

Sakyasingha eDasgupta

2015-09-01

Full Text Available Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain a variety of movements, the neural mechanisms generate movements while making appropriate predictions crucial for achieving adaptation. Such predictions or planning ahead can be achieved by way of internal models that are grounded in the overall behavior of the animal. Inspired by these findings, we present here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures with the underlying neural mechanisms. The neural mechanisms consist of 1 central pattern generator based control for generating basic rhythmic patterns and coordinated movements, 2 distributed (at each leg recurrent neural network based adaptive forward models with efference copies as internal models for sensory predictions and instantaneous state estimations, and 3 searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Using simulations we show that this bio-inspired approach with adaptive internal models allows the walking robot to perform complex locomotive behaviors as observed in insects, including walking on undulated terrains, crossing large gaps as well as climbing over high obstacles. Furthermore we demonstrate that the newly developed recurrent network based approach to sensorimotor prediction outperforms the previous state of the art adaptive neuron

Assessment of aflatoxin B1 in livestock feed and feed ingredients by high-performance thin layer chromatography

Directory of Open Access Journals (Sweden)

Korrapati Kotinagu

2015-12-01

Full Text Available Aim: Detection of aflatoxin B1 in Livestock compound Feed and feed ingredients by high-performance thin layer chromatography (HPTLC. Materials and Methods: Chromatography was performed on HPTLC silica gel 60 F 254, aluminum sheets by CAMAG automatic TLC sampler 4, with mobile phase condition chloroform:acetone:water (28:4:0.06. Extraction of aflatoxin B1 from samples was done as per AOAC method and screening and quantification done by HPTLC Scanner 4 under wavelength 366 nm. Results: A total of 97 livestock feed (48 and feed ingredients (49 samples received from different livestock farms and farmers were analyzed for aflatoxin B1of which 29 samples were contaminated, constituting 30%. Out of 48 livestock compound feed samples, aflatoxin B1 could be detected in 16 samples representing 33%, whereas in livestock feed ingredients out of 49 samples, 13 found positive for aflatoxin B1 representing 24.5%. Conclusion: HPTLC assures good recovery, precision, and linearity in the quantitative determination of aflatoxin B1 extracted from Livestock compound feed and feed ingredients. As more number of feed and feed ingredients are contaminated with aflatoxin B1 which causes deleterious effects in both animal and human beings, so there is a need for identifying the source of contamination, executing control measures, enabling better risk assessment techniques, and providing economic benefits.

NNETS - NEURAL NETWORK ENVIRONMENT ON A TRANSPUTER SYSTEM

Science.gov (United States)

Villarreal, J.

1994-01-01

The primary purpose of NNETS (Neural Network Environment on a Transputer System) is to provide users a high degree of flexibility in creating and manipulating a wide variety of neural network topologies at processing speeds not found in conventional computing environments. To accomplish this purpose, NNETS supports back propagation and back propagation related algorithms. The back propagation algorithm used is an implementation of Rumelhart's Generalized Delta Rule. NNETS was developed on the INMOS Transputer. NNETS predefines a Back Propagation Network, a Jordan Network, and a Reinforcement Network to assist users in learning and defining their own networks. The program also allows users to configure other neural network paradigms from the NNETS basic architecture. The Jordan network is basically a feed forward network that has the outputs connected to a pseudo input layer. The state of the network is dependent on the inputs from the environment plus the state of the network. The Reinforcement network learns via a scalar feedback signal called reinforcement. The network propagates forward randomly. The environment looks at the outputs of the network to produce a reinforcement signal that is fed back to the network. NNETS was written for the INMOS C compiler D711B version 1.3 or later (MS-DOS version). A small portion of the software was written in the OCCAM language to perform the communications routing between processors. NNETS is configured to operate on a 4 X 10 array of Transputers in sequence with a Transputer based graphics processor controlled by a master IBM PC 286 (or better) Transputer. A RGB monitor is required which must be capable of 512 X 512 resolution. It must be able to receive red, green, and blue signals via BNC connectors. NNETS is meant for experienced Transputer users only. The program is distributed on 5.25 inch 1.2Mb MS-DOS format diskettes. NNETS was developed in 1991. Transputer and OCCAM are registered trademarks of Inmos Corporation. MS

Real-time solution of the forward kinematics for a parallel haptic device using a numerical approach based on neural networks

International Nuclear Information System (INIS)

Liu, Guan Yang; Zhang, Yuru; Wang, Yan; Xie, Zheng

2015-01-01

This paper proposes a neural network (NN)-based approach to solve the forward kinematics of a 3-RRR spherical parallel mechanism designed for a haptic device. The proposed algorithm aims to remarkably speed up computation to meet the requirement of high frequency rendering for haptic display. To achieve high accuracy, the workspace of the haptic device is divided into smaller subspaces. The proposed algorithm contains NNs of two different precision levels: a rough estimation NN to identify the index of the subspace and several precise estimation networks with expected accuracy to calculate the forward kinematics. For continuous motion, the algorithm structure is further simplified to save internal memory and increase computing speed, which are critical for a haptic device control system running on an embedded platform. Compared with the mostly used Newton-Raphson method, the proposed algorithm and its simplified version greatly increase the calculation speed by about four times and 10 times, respectively, while achieving the same accuracy level. The proposed approach is of great significance for solving the forward kinematics of parallel mechanism used as haptic devices when high update frequency is needed but hardware resources are limited.

Shadowgraphy investigation of laser-induced forward transfer: Front side and back side ablation of the triazene polymer sacrificial layer

International Nuclear Information System (INIS)

Fardel, Romain; Nagel, Matthias; Nueesch, Frank; Lippert, Thomas; Wokaun, Alexander

2009-01-01

Thin films of a photodecomposible triazene polymer are used as sacrificial layer for the micro-deposition of sensitive materials by laser-induced forward transfer. To understand the ablation process of this sacrificial layer, the ultraviolet laser ablation of triazene films was investigated by time-resolved shadowgraphy. Irradiation from the film side shows a complete decomposition into gaseous fragments, while ablation through the substrate causes ejection of a solid flyer of polymer. The occurence of the flyer depends on the film thickness as well as on the applied fluence, and a compact flyer is obtaind when these two parameters are optimized

Empirical modeling of a dewaxing system of lubricant oil using Artificial Neural Network (ANN); Modelagem empirica de um sistema de desparafinacao de oleo lubrificante usando redes neurais artificiais

Energy Technology Data Exchange (ETDEWEB)

Fontes, Cristiano Hora de Oliveira; Medeiros, Ana Claudia Gondim de; Silva, Marcone Lopes; Neves, Sergio Bello; Carvalho, Luciene Santos de; Guimaraes, Paulo Roberto Britto; Pereira, Magnus; Vianna, Regina Ferreira [Universidade Salvador (UNIFACS), Salvador, BA (Brazil). Dept. de Engenharia e Arquitetura]. E-mail: paulorbg@unifacs.br; Santos, Nilza Maria Querino dos [PETROBRAS S.A., Rio de Janeiro, RJ (Brazil)]. E-mail: nilzaq@petrobras.com.br

2003-07-01

The MIBK (m-i-b-ketone) dewaxing unit, located at the Landulpho Alves refinery, allows two different operating modes: dewaxing ND oil removal. The former is comprised of an oil-wax separation process, which generates a wax stream with 2 - 5% oil. The latter involves the reprocessing of the wax stream to reduce its oil content. Both involve a two-stage filtration process (primary and secondary) with rotative filters. The general aim of this research is to develop empirical models to predict variables, for both unit-operating modes, to be used in control algorithms, since many data are not available during normal plant operation and therefore need to be estimated. Studies have suggested that the oil content is an essential variable to develop reliable empirical models and this work is concerned with the development of an empirical model for the prediction of the oil content in the wax stream leaving the primary filters. The model is based on a feed forward Artificial Neural Network (ANN) and tests with one and two hidden layers indicate very good agreement between experimental and predicted values. (author)

Understanding the risk of scaling and fouling in hollow fiber forward osmosis membrane application

KAUST Repository

Majeed, Tahir; Phuntsho, Sherub; Jeong, Sanghyun; Zhao, Yanxia; Gao, Baoyu; Shon, Ho Kyong

2016-01-01

Fouling studies of forward osmosis (FO) were mostly conducted based on fouling evaluation principals applied to pressure membrane processes such as reverse osmosis (RO)/nanofiltration (NF)/microfiltration (MF)/ultrafiltration (UF). For RO/NF/MF/UF processes, the single flux driving force (hydraulic pressure) remains constant, thus the fouling effect is easily evaluated by comparing flux data with the baseline. Whilst, the scenario of fouling effects for FO process is entirely different from RO/NF/MF/UF processes. Continuously changing driving force (osmotic pressure difference), the changes in concentration polarization associated with the varying draw solution/feed solution concentration and the fouling layer effects collectively influence the FO flux. Thus, usual comparison of the FO flux outcome with the baseline results can not exactly indicate the real affect of membrane fouling, rather presents a misleading cumulative effect. This study compares the existing FO fouling technique with an alternate fouling evaluation approach using two FO set-ups. Scaling and fouling risk for hollow fiber FO was separately investigated using synthetic water samples and model organic foulants as alginate, humic acid and bovine serum albumin. Results indicated that FO flux declines up to 5% and 49% in active layer-feed solution and active layer-draw solution orientations respectively.

Understanding the risk of scaling and fouling in hollow fiber forward osmosis membrane application

KAUST Repository

Majeed, Tahir

2016-06-23

Fouling studies of forward osmosis (FO) were mostly conducted based on fouling evaluation principals applied to pressure membrane processes such as reverse osmosis (RO)/nanofiltration (NF)/microfiltration (MF)/ultrafiltration (UF). For RO/NF/MF/UF processes, the single flux driving force (hydraulic pressure) remains constant, thus the fouling effect is easily evaluated by comparing flux data with the baseline. Whilst, the scenario of fouling effects for FO process is entirely different from RO/NF/MF/UF processes. Continuously changing driving force (osmotic pressure difference), the changes in concentration polarization associated with the varying draw solution/feed solution concentration and the fouling layer effects collectively influence the FO flux. Thus, usual comparison of the FO flux outcome with the baseline results can not exactly indicate the real affect of membrane fouling, rather presents a misleading cumulative effect. This study compares the existing FO fouling technique with an alternate fouling evaluation approach using two FO set-ups. Scaling and fouling risk for hollow fiber FO was separately investigated using synthetic water samples and model organic foulants as alginate, humic acid and bovine serum albumin. Results indicated that FO flux declines up to 5% and 49% in active layer-feed solution and active layer-draw solution orientations respectively.

AIR POLLUITON INDEX PREDICTION USING MULTIPLE NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

Zainal Ahmad

2017-05-01

Full Text Available Air quality monitoring and forecasting tools are necessary for the purpose of taking precautionary measures against air pollution, such as reducing the effect of a predicted air pollution peak on the surrounding population and ecosystem. In this study a single Feed-forward Artificial Neural Network (FANN is shown to be able to predict the Air Pollution Index (API with a Mean Squared Error (MSE and coefficient determination, R2, of 0.1856 and 0.7950 respectively. However, due to the non-robust nature of single FANN, a selective combination of Multiple Neural Networks (MNN is introduced using backward elimination and a forward selection method. The results show that both selective combination methods can improve the robustness and performance of the API prediction with the MSE and R2 of 0.1614 and 0.8210 respectively. This clearly shows that it is possible to reduce the number of networks combined in MNN for API prediction, without losses of any information in terms of the performance of the final API prediction model.

Development of an Accurate Feed-Forward Temperature Control Tankless Water Heater

Energy Technology Data Exchange (ETDEWEB)

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

Relating performance of thin-film composite forward osmosis membranes to support layer formation and structure

KAUST Repository

Tiraferri, Alberto; Yip, Ngai Yin; Phillip, William A.; Schiffman, Jessica D.; Elimelech, Menachem

2011-01-01

the technology to the point that it is commercially viable. Here, a systematic investigation of the influence of thin-film composite membrane support layer structure on forward osmosis performance is conducted. The membranes consist of a selective polyamide

Forecast of TEXT plasma disruptions using soft X-rays as input signal in a neural network

International Nuclear Information System (INIS)

Vannucci, A.; Oliveira, K.A.; Tajima, T.; Tajima, Y.J.

2001-01-01

A feed-forward neural network is used to forecast major and minor disruptions in TEXT tokamak discharges. Using the experimental data of soft X-ray signals as input data, the neural net is trained with one disruptive plasma discharge, while a different disruptive discharge is used for validation. After proper training, the net works with the same set of weights, it is then used to forecast disruptions in two other different plasma discharges. It is observed that the neural net is capable of predicting the onset of a disruption up to 3.12 ms in advance. From what we observe in the predictive behavior of our network, speculations are made whether the disruption triggering mechanism is associated with an increase in the m=2 magnetic island, that disturbs the central part of the plasma column afterwards, or the initial perturbation has first occurred in the central part of the plasma column and then the m=2 MHD mode is destabilized. (author)

Stellar Image Interpretation System using Artificial Neural Networks: Unipolar Function Case

Directory of Open Access Journals (Sweden)

F. I. Younis

2001-01-01

Full Text Available An artificial neural network based system for interpreting astronomical images has been developed. The system is based on feed-forward Artificial Neural Networks (ANNs with error back-propagation learning. Knowledge about images of stars, cosmic ray events and noise found in images is used to prepare two sets of input patterns to train and test our approach. The system has been developed and implemented to scan astronomical digital images in order to segregate stellar images from other entities. It has been coded in C language for users of personal computers. An astronomical image of a star cluster from other objects is undertaken as a test case. The obtained results are found to be in very good agreement with those derived from the DAOPHOTII package, which is widely used in the astronomical community. It is proved that our system is simpler, much faster and more reliable. Moreover, no prior knowledge, or initial data from the frame to be analysed is required.

SpikeTemp: An Enhanced Rank-Order-Based Learning Approach for Spiking Neural Networks With Adaptive Structure.

Science.gov (United States)

Wang, Jinling; Belatreche, Ammar; Maguire, Liam P; McGinnity, Thomas Martin

2017-01-01

This paper presents an enhanced rank-order-based learning algorithm, called SpikeTemp, for spiking neural networks (SNNs) with a dynamically adaptive structure. The trained feed-forward SNN consists of two layers of spiking neurons: 1) an encoding layer which temporally encodes real-valued features into spatio-temporal spike patterns and 2) an output layer of dynamically grown neurons which perform spatio-temporal classification. Both Gaussian receptive fields and square cosine population encoding schemes are employed to encode real-valued features into spatio-temporal spike patterns. Unlike the rank-order-based learning approach, SpikeTemp uses the precise times of the incoming spikes for adjusting the synaptic weights such that early spikes result in a large weight change and late spikes lead to a smaller weight change. This removes the need to rank all the incoming spikes and, thus, reduces the computational cost of SpikeTemp. The proposed SpikeTemp algorithm is demonstrated on several benchmark data sets and on an image recognition task. The results show that SpikeTemp can achieve better classification performance and is much faster than the existing rank-order-based learning approach. In addition, the number of output neurons is much smaller when the square cosine encoding scheme is employed. Furthermore, SpikeTemp is benchmarked against a selection of existing machine learning algorithms, and the results demonstrate the ability of SpikeTemp to classify different data sets after just one presentation of the training samples with comparable classification performance.

Designing an Adaptive Web-Based Learning System Based on Students' Cognitive Styles Identified Online

Science.gov (United States)

Lo, Jia-Jiunn; Chan, Ya-Chen; Yeh, Shiou-Wen

2012-01-01

This study developed an adaptive web-based learning system focusing on students' cognitive styles. The system is composed of a student model and an adaptation model. It collected students' browsing behaviors to update the student model for unobtrusively identifying student cognitive styles through a multi-layer feed-forward neural network (MLFF).…

Modeling the Effects of Cu Content and Deformation Variables on the High-Temperature Flow Behavior of Dilute Al-Fe-Si Alloys Using an Artificial Neural Network.

Science.gov (United States)

Shakiba, Mohammad; Parson, Nick; Chen, X-Grant

2016-06-30

The hot deformation behavior of Al-0.12Fe-0.1Si alloys with varied amounts of Cu (0.002-0.31 wt %) was investigated by uniaxial compression tests conducted at different temperatures (400 °C-550 °C) and strain rates (0.01-10 s -1 ). The results demonstrated that flow stress decreased with increasing deformation temperature and decreasing strain rate, while flow stress increased with increasing Cu content for all deformation conditions studied due to the solute drag effect. Based on the experimental data, an artificial neural network (ANN) model was developed to study the relationship between chemical composition, deformation variables and high-temperature flow behavior. A three-layer feed-forward back-propagation artificial neural network with 20 neurons in a hidden layer was established in this study. The input parameters were Cu content, temperature, strain rate and strain, while the flow stress was the output. The performance of the proposed model was evaluated using the K-fold cross-validation method. The results showed excellent generalization capability of the developed model. Sensitivity analysis indicated that the strain rate is the most important parameter, while the Cu content exhibited a modest but significant influence on the flow stress.

The Multi-Layered Perceptrons Neural Networks for the Prediction of Daily Solar Radiation

OpenAIRE

Radouane Iqdour; Abdelouhab Zeroual

2007-01-01

The Multi-Layered Perceptron (MLP) Neural networks have been very successful in a number of signal processing applications. In this work we have studied the possibilities and the met difficulties in the application of the MLP neural networks for the prediction of daily solar radiation data. We have used the Polack-Ribière algorithm for training the neural networks. A comparison, in term of the statistical indicators, with a linear model most used in literature, is also perfo...

Curriculum Assessment Using Artificial Neural Network and Support Vector Machine Modeling Approaches: A Case Study. IR Applications. Volume 29

Science.gov (United States)

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…

Adaptive Learning Rule for Hardware-based Deep Neural Networks Using Electronic Synapse Devices

OpenAIRE

Lim, Suhwan; Bae, Jong-Ho; Eum, Jai-Ho; Lee, Sungtae; Kim, Chul-Heung; Kwon, Dongseok; Park, Byung-Gook; Lee, Jong-Ho

2017-01-01

In this paper, we propose a learning rule based on a back-propagation (BP) algorithm that can be applied to a hardware-based deep neural network (HW-DNN) using electronic devices that exhibit discrete and limited conductance characteristics. This adaptive learning rule, which enables forward, backward propagation, as well as weight updates in hardware, is helpful during the implementation of power-efficient and high-speed deep neural networks. In simulations using a three-layer perceptron net...

Typology of nonlinear activity waves in a layered neural continuum.

Science.gov (United States)

Koch, Paul; Leisman, Gerry

2006-04-01

Neural tissue, a medium containing electro-chemical energy, can amplify small increments in cellular activity. The growing disturbance, measured as the fraction of active cells, manifests as propagating waves. In a layered geometry with a time delay in synaptic signals between the layers, the delay is instrumental in determining the amplified wavelengths. The growth of the waves is limited by the finite number of neural cells in a given region of the continuum. As wave growth saturates, the resulting activity patterns in space and time show a variety of forms, ranging from regular monochromatic waves to highly irregular mixtures of different spatial frequencies. The type of wave configuration is determined by a number of parameters, including alertness and synaptic conditioning as well as delay. For all cases studied, using numerical solution of the nonlinear Wilson-Cowan (1973) equations, there is an interval in delay in which the wave mixing occurs. As delay increases through this interval, during a series of consecutive waves propagating through a continuum region, the activity within that region changes from a single-frequency to a multiple-frequency pattern and back again. The diverse spatio-temporal patterns give a more concrete form to several metaphors advanced over the years to attempt an explanation of cognitive phenomena: Activity waves embody the "holographic memory" (Pribram, 1991); wave mixing provides a plausible cause of the competition called "neural Darwinism" (Edelman, 1988); finally the consecutive generation of growing neural waves can explain the discontinuousness of "psychological time" (Stroud, 1955).

Modeling and simulation of xylitol production in bioreactor by Debaryomyces nepalensis NCYC 3413 using unstructured and artificial neural network models.

Science.gov (United States)

Pappu, J Sharon Mano; Gummadi, Sathyanarayana N

2016-11-01

This study examines the use of unstructured kinetic model and artificial neural networks as predictive tools for xylitol production by Debaryomyces nepalensis NCYC 3413 in bioreactor. An unstructured kinetic model was proposed in order to assess the influence of pH (4, 5 and 6), temperature (25°C, 30°C and 35°C) and volumetric oxygen transfer coefficient kLa (0.14h(-1), 0.28h(-1) and 0.56h(-1)) on growth and xylitol production. A feed-forward back-propagation artificial neural network (ANN) has been developed to investigate the effect of process condition on xylitol production. ANN configuration of 6-10-3 layers was selected and trained with 339 experimental data points from bioreactor studies. Results showed that simulation and prediction accuracy of ANN was apparently higher when compared to unstructured mechanistic model under varying operational conditions. ANN was found to be an efficient data-driven tool to predict the optimal harvest time in xylitol production. Copyright © 2016 Elsevier Ltd. All rights reserved.

Using a neural network in the search for the Higgs boson

International Nuclear Information System (INIS)

Hultqvist, K.; Jacobsson, R.; Johansson, K.E.

1995-01-01

The search for the Standard Model Higgs boson in high energy e + e - collisions requires analysis techniques which efficiently discriminate against the very large background. A classifier based on a feed-forward neural network has been extensively used in a search in the channel where the Higgs boson is produced in association with neutrinos. The method has significantly improved the sensitivity of the search. With a simple preselection based on event topology followed by a neural network we have obtained a combined background rejection factor of more than 29 000 and a selection efficiency for Higgs particle events of 54%, assuming a mass of 55 GeV/c 2 for the Higgs boson. We describe here the details of the analysis with emphasis on the neural network. (orig.)

An application of artificial intelligence for rainfall–runoff modeling

Indian Academy of Sciences (India)

This study proposes an application of two techniques of artificial intelligence (AI) for rainfall–runoff modeling: the artificial neural networks (ANN) and the evolutionary computation (EC). Two diff- erent ANN techniques, the feed forward back propagation (FFBP) and generalized regression neural network (GRNN) methods ...

Journal of Earth System Science | Indian Academy of Sciences

Indian Academy of Sciences (India)

This study proposes an application of two techniques of artificial intelligence (AI) for rainfall–runoff modeling: the artificial neural networks (ANN) and the evolutionary computation (EC). Two different ANN techniques, the feed forward back propagation (FFBP) and generalized regression neural network (GRNN) methods are ...

Artificial neural network-aided image analysis system for cell counting.

Science.gov (United States)

Sjöström, P J; Frydel, B R; Wahlberg, L U

1999-05-01

In histological preparations containing debris and synthetic materials, it is difficult to automate cell counting using standard image analysis tools, i.e., systems that rely on boundary contours, histogram thresholding, etc. In an attempt to mimic manual cell recognition, an automated cell counter was constructed using a combination of artificial intelligence and standard image analysis methods. Artificial neural network (ANN) methods were applied on digitized microscopy fields without pre-ANN feature extraction. A three-layer feed-forward network with extensive weight sharing in the first hidden layer was employed and trained on 1,830 examples using the error back-propagation algorithm on a Power Macintosh 7300/180 desktop computer. The optimal number of hidden neurons was determined and the trained system was validated by comparison with blinded human counts. System performance at 50x and lO0x magnification was evaluated. The correlation index at 100x magnification neared person-to-person variability, while 50x magnification was not useful. The system was approximately six times faster than an experienced human. ANN-based automated cell counting in noisy histological preparations is feasible. Consistent histology and computer power are crucial for system performance. The system provides several benefits, such as speed of analysis and consistency, and frees up personnel for other tasks.

A neural network based methodology to predict site-specific spectral acceleration values

Science.gov (United States)

Kamatchi, P.; Rajasankar, J.; Ramana, G. V.; Nagpal, A. K.

2010-12-01

A general neural network based methodology that has the potential to replace the computationally-intensive site-specific seismic analysis of structures is proposed in this paper. The basic framework of the methodology consists of a feed forward back propagation neural network algorithm with one hidden layer to represent the seismic potential of a region and soil amplification effects. The methodology is implemented and verified with parameters corresponding to Delhi city in India. For this purpose, strong ground motions are generated at bedrock level for a chosen site in Delhi due to earthquakes considered to originate from the central seismic gap of the Himalayan belt using necessary geological as well as geotechnical data. Surface level ground motions and corresponding site-specific response spectra are obtained by using a one-dimensional equivalent linear wave propagation model. Spectral acceleration values are considered as a target parameter to verify the performance of the methodology. Numerical studies carried out to validate the proposed methodology show that the errors in predicted spectral acceleration values are within acceptable limits for design purposes. The methodology is general in the sense that it can be applied to other seismically vulnerable regions and also can be updated by including more parameters depending on the state-of-the-art in the subject.

Analysis of surface ozone using a recurrent neural network.

Science.gov (United States)

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.

A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks.

Science.gov (United States)

Alauthaman, Mohammad; Aslam, Nauman; Zhang, Li; Alasem, Rafe; Hossain, M A

2018-01-01

In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

Comparing Two Methods of Neural Networks to Evaluate Dead Oil Viscosity

Directory of Open Access Journals (Sweden)

Meysam Dabiri-Atashbeyk

2018-01-01

Full Text Available Reservoir characterization and asset management require comprehensive information about formation fluids. In fact, it is not possible to find accurate solutions to many petroleum engineering problems without having accurate pressure-volume-temperature (PVT data. Traditionally, fluid information has been obtained by capturing samples and then by measuring the PVT properties in a laboratory. In recent years, neural network has been applied to a large number of petroleum engineering problems. In this paper, a multi-layer perception neural network and radial basis function network (both optimized by a genetic algorithm were used to evaluate the dead oil viscosity of crude oil, and it was found out that the estimated dead oil viscosity by the multi-layer perception neural network was more accurate than the one obtained by radial basis function network.

Neural computing thermal comfort index for HVAC systems

International Nuclear Information System (INIS)

Atthajariyakul, S.; Leephakpreeda, T.

2005-01-01

The primary purpose of a heating, ventilating and air conditioning (HVAC) system within a building is to make occupants comfortable. Without real time determination of human thermal comfort, it is not feasible for the HVAC system to yield controlled conditions of the air for human comfort all the time. This paper presents a practical approach to determine human thermal comfort quantitatively via neural computing. The neural network model allows real time determination of the thermal comfort index, where it is not practical to compute the conventional predicted mean vote (PMV) index itself in real time. The feed forward neural network model is proposed as an explicit function of the relation of the PMV index to accessible variables, i.e. the air temperature, wet bulb temperature, globe temperature, air velocity, clothing insulation and human activity. An experiment in an air conditioned office room was done to demonstrate the effectiveness of the proposed methodology. The results show good agreement between the thermal comfort index calculated from the neural network model in real time and those calculated from the conventional PMV model

Simple, low-noise piezo driver with feed-forward for broad tuning of external cavity diode lasers.

Science.gov (United States)

Doret, S Charles

2018-02-01

We present an inexpensive, low-noise (piezo driver suitable for frequency tuning of external-cavity diode lasers. This simple driver improves upon many commercially available drivers by incorporating circuitry to produce a "feed-forward" signal appropriate for making simultaneous adjustments to the piezo voltage and laser current, enabling dramatic improvements in a mode-hop-free laser frequency tuning range. We present the theory behind our driver's operation, characterize its output noise, and demonstrate its use in absorption spectroscopy on the rubidium D 1 line.

PERFORMANCE COMPARISON FOR INTRUSION DETECTION SYSTEM USING NEURAL NETWORK WITH KDD DATASET

Directory of Open Access Journals (Sweden)

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.

Assessing the removal of organic micro-pollutants from anaerobic membrane bioreactor effluent by fertilizer-drawn forward osmosis

KAUST Repository

Kim, Youngjin

2017-03-23

In this study, the behavior of organic micro-pollutants (OMPs) transport including membrane fouling was assessed in fertilizer-drawn forward osmosis (FDFO) during treatment of the anaerobic membrane bioreactor (AnMBR) effluent. The flux decline was negligible when the FO membrane was oriented with active layer facing feed solution (AL-FS) while severe flux decline was observed with active layer facing draw solution (AL-DS) with di-ammonium phosphate (DAP) fertilizer as DS due to struvite scaling inside the membrane support layer. DAP DS however exhibited the lowest OMPs forward flux or higher OMPs rejection rate compared to other two fertilizers (i.e., mono-ammonium phosphate (MAP) and KCl). MAP and KCl fertilizer DS had higher water fluxes that induced higher external concentration polarization (ECP) and enhanced OMPs flux through the FO membrane. Under the AL-DS mode of membrane orientation, OMPs transport was further increased with MAP and KCl as DS due to enhanced concentrative internal concentration polarization while with DAP the internal scaling enhanced mass transfer resistance thereby lowering OMPs flux. Physical or hydraulic cleaning could successfully recover water flux for FO membranes operated under the AL-FS mode but only partial flux recovery was observed for membranes operated under AL-DS mode because of internal scaling and fouling in the support layer. Osmotic backwashing could however significantly improve the cleaning efficiency.

Stability analysis of a three-phase grid-connected DC power supply with small DC-link capacitor and voltage feed-forward compensation

DEFF Research Database (Denmark)

Török, Lajos; Mathe, L.

2017-01-01

The purpose of this work was to investigate effect of the DC-link voltage feed-forward compensation on the stability of the three-phase-grid connected DC power supply, used for electrolysis application, equipped with small DC link capacitor. In case of weak grid condition, the system...

Petri neural network model for the effect of controlled thermomechanical process parameters on the mechanical properties of HSLA steels

Energy Technology Data Exchange (ETDEWEB)

Datta, S.

1999-10-01

The effect of composition and controlled thermomechanical process parameters on the mechanical properties of HSLA steels is modelled using the Widrow-Hoff's concept of training a neural net with feed-forward topology by applying Rumelhart's back propagation type algorithm for supervised learning, using a Petri like net structure. The data used are from laboratory experiments as well as from the published literature. The results from the neural network are found to be consistent and in good agreement with the experimented results. (author)

Strategic Management Accounting and Feed-forward Management: with Reference to the Unified Management of Profit Opportunity and Risk

OpenAIRE

西村, 明

2015-01-01

This paper aims toreexamine strategic management accouning in relation to profit opportunity and risk from the viewpoint of feed-forward management , as few studies to date have discuued the relations between management accounting and the unified management of profit opportunity and risk.Many studies have been conducted that emphasize non-fine information and feedback organizational management in an attept to make traditional management accounting relevant to practical strategic needs. As lon...

Using function approximation to determine neural network accuracy

International Nuclear Information System (INIS)

Wichman, R.F.; Alexander, J.

2013-01-01

Many, if not most, control processes demonstrate nonlinear behavior in some portion of their operating range and the ability of neural networks to model non-linear dynamics makes them very appealing for control. Control of high reliability safety systems, and autonomous control in process or robotic applications, however, require accurate and consistent control and neural networks are only approximators of various functions so their degree of approximation becomes important. In this paper, the factors affecting the ability of a feed-forward back-propagation neural network to accurately approximate a non-linear function are explored. Compared to pattern recognition using a neural network for function approximation provides an easy and accurate method for determining the network's accuracy. In contrast to other techniques, we show that errors arising in function approximation or curve fitting are caused by the neural network itself rather than scatter in the data. A method is proposed that provides improvements in the accuracy achieved during training and resulting ability of the network to generalize after training. Binary input vectors provided a more accurate model than with scalar inputs and retraining using a small number of the outlier x,y pairs improved generalization. (author)

Hacia la predicción del Número R de Wolf de manchas solares utilizando Redes Neuronales con retardos temporales

Science.gov (United States)

Francile, C.; Luoni, M. L.

We present a prediction of the time series of the Wolf number R of sunspots using "time lagged feed forward neural networks". We use two types of networks: the focused and distributed ones which were trained with the back propagation of errors algorithm and the temporal back propagation algorithm respectively. As inputs to neural networks we use the time series of the number R averaged annually and monthly with the method IR5. As data sets for training and test we choose certain intervals of the time series similar to other works, in order to compare the results. Finally we discuss the topology of the networks used, the number of delays used, the number of neurons per layer, the number of hidden layers and the results in the prediction of the series between one and six steps ahead. FULL TEXT IN SPANISH

Transform a Simple Sketch to a Chinese Painting by a Multiscale Deep Neural Network

Directory of Open Access Journals (Sweden)

Daoyu Lin

2018-01-01

Full Text Available Recently, inspired by the power of deep learning, convolution neural networks can produce fantastic images at the pixel level. However, a significant limiting factor for previous approaches is that they focus on some simple datasets such as faces and bedrooms. In this paper, we propose a multiscale deep neural network to transform sketches into Chinese paintings. To synthesize more realistic imagery, we train the generative network by using both L1 loss and adversarial loss. Additionally, users can control the process of the synthesis since the generative network is feed-forward. This network can also be treated as neural style transfer by adding an edge detector. Furthermore, additional experiments on image colorization and image super-resolution demonstrate the universality of our proposed approach.

Generalization and capacity of extensively large two-layered perceptrons

International Nuclear Information System (INIS)

Rosen-Zvi, Michal; Kanter, Ido; Engel, Andreas

2002-01-01

The generalization ability and storage capacity of a treelike two-layered neural network with a number of hidden units scaling as the input dimension is examined. The mapping from the input to the hidden layer is via Boolean functions; the mapping from the hidden layer to the output is done by a perceptron. The analysis is within the replica framework where an order parameter characterizing the overlap between two networks in the combined space of Boolean functions and hidden-to-output couplings is introduced. The maximal capacity of such networks is found to scale linearly with the logarithm of the number of Boolean functions per hidden unit. The generalization process exhibits a first-order phase transition from poor to perfect learning for the case of discrete hidden-to-output couplings. The critical number of examples per input dimension, α c , at which the transition occurs, again scales linearly with the logarithm of the number of Boolean functions. In the case of continuous hidden-to-output couplings, the generalization error decreases according to the same power law as for the perceptron, with the prefactor being different

Two-loop feed water control system in BWR plants

International Nuclear Information System (INIS)

Omori, Takashi; Watanabe, Takao; Hirose, Masao.

1982-01-01

In the process of the start-up and shutdown of BWR plants, the operation of changing over feed pumps corresponding to plant output is performed. Therefore, it is necessary to develop the automatic changeover system for feed pumps, which minimizes the variation of water level in reactors and is easy to operate. The three-element control system with the water level in reactors, the flow rate of main steam and the flow rate of feed water as the input is mainly applied, but long time is required for the changeover of feed pumps. The two-loop feed control system can control simultaneously two pumps being changed over, therefore it is suitable to the automatic changeover control system for feed pumps. Also it is excellent for the control of the recirculating valves of feed pumps. The control characteristics of the two-loop feed water control system against the external disturbance which causes the variation of water level in reactors were examined. The results of analysis by simulation are reported. The features of the two-loop feed water control system, the method of simulation and the evaluation of the two-loop feed water control system are described. Its connection with a digital feed water recirculation control system is expected. (Kako, I.)

Prediction of geomagnetic storms from solar wind data with the use of a neural network

Directory of Open Access Journals (Sweden)

H. Lundstedt

Full Text Available An artificial feed-forward neural network with one hidden layer and error back-propagation learning is used to predict the geomagnetic activity index (D_st one hour in advance. The B_z-component and Σ_Bz, the density, and the velocity of the solar wind are used as input to the network. The network is trained on data covering a total of 8700 h, extracted from the 25-year period from 1963 to 1987, taken from the NSSDC data base. The performance of the network is examined with test data, not included in the training set, which covers 386 h and includes four different storms. Whilst the network predicts the initial and main phase well, the recovery phase is not modelled correctly, implying that a single hidden layer error back-propagation network is not enough, if the measured D_st is not available instantaneously. The performance of the network is independent of whether the raw parameters are used, or the electric field and square root of the dynamical pressure.

Prediction of Air Pollutants Concentration Based on an Extreme Learning Machine: The Case of Hong Kong.

Science.gov (United States)

Zhang, Jiangshe; Ding, Weifu

2017-01-24

With the development of the economy and society all over the world, most metropolitan cities are experiencing elevated concentrations of ground-level air pollutants. It is urgent to predict and evaluate the concentration of air pollutants for some local environmental or health agencies. Feed-forward artificial neural networks have been widely used in the prediction of air pollutants concentration. However, there are some drawbacks, such as the low convergence rate and the local minimum. The extreme learning machine for single hidden layer feed-forward neural networks tends to provide good generalization performance at an extremely fast learning speed. The major sources of air pollutants in Hong Kong are mobile, stationary, and from trans-boundary sources. We propose predicting the concentration of air pollutants by the use of trained extreme learning machines based on the data obtained from eight air quality parameters in two monitoring stations, including Sham Shui Po and Tap Mun in Hong Kong for six years. The experimental results show that our proposed algorithm performs better on the Hong Kong data both quantitatively and qualitatively. Particularly, our algorithm shows better predictive ability, with R 2 increased and root mean square error values decreased respectively.

Prediction of Air Pollutants Concentration Based on an Extreme Learning Machine: The Case of Hong Kong

Directory of Open Access Journals (Sweden)

Jiangshe Zhang

2017-01-01

Full Text Available With the development of the economy and society all over the world, most metropolitan cities are experiencing elevated concentrations of ground-level air pollutants. It is urgent to predict and evaluate the concentration of air pollutants for some local environmental or health agencies. Feed-forward artificial neural networks have been widely used in the prediction of air pollutants concentration. However, there are some drawbacks, such as the low convergence rate and the local minimum. The extreme learning machine for single hidden layer feed-forward neural networks tends to provide good generalization performance at an extremely fast learning speed. The major sources of air pollutants in Hong Kong are mobile, stationary, and from trans-boundary sources. We propose predicting the concentration of air pollutants by the use of trained extreme learning machines based on the data obtained from eight air quality parameters in two monitoring stations, including Sham Shui Po and Tap Mun in Hong Kong for six years. The experimental results show that our proposed algorithm performs better on the Hong Kong data both quantitatively and qualitatively. Particularly, our algorithm shows better predictive ability, with R 2 increased and root mean square error values decreased respectively.

The cost of hovering and forward flight in a nectar-feeding bat, Glossophaga soricina, estimated from aerodynamic theory

DEFF Research Database (Denmark)

Norberg, U M; Kunz, T H; Steffensen, J F

1993-01-01

Energy expenditure during flight in animals can best be understood and quantified when both theoretical and empirical approaches are used concurrently. This paper examines one of four methods that we have used to estimate the cost of flight in a neotropical nectar-feeding bat Glossophaga soricina...... on metabolic power requirements estimated from nectar intake gives a mechanical efficiency of 0.15 for hovering flight and 0.11 for forward flight near the minimum power speed....

Stability analysis of rubblemound breakwater using ANN

Digital Repository Service at National Institute of Oceanography (India)

Mandal, S.; Rao, S.; Manjunath, Y.R.; Kim, D.H.

relation is not clear. In more practical terms networks are non-linear modeling tools and they can be used to model complex relationship between input and output system. Earlier applications of neural networks for stability analysis of rubble mound.... WORKING PRINCIPLE OF NEURAL NETWORK The feed forward neural networks have ability to approximate any continuous function or complex phenomena into a simple one. The working of neural network as described below. A feed forward neural network as shown...

What the success of brain imaging implies about the neural code.

Science.gov (United States)

Guest, Olivia; Love, Bradley C

2017-01-19

The success of fMRI places constraints on the nature of the neural code. The fact that researchers can infer similarities between neural representations, despite fMRI's limitations, implies that certain neural coding schemes are more likely than others. For fMRI to succeed given its low temporal and spatial resolution, the neural code must be smooth at the voxel and functional level such that similar stimuli engender similar internal representations. Through proof and simulation, we determine which coding schemes are plausible given both fMRI's successes and its limitations in measuring neural activity. Deep neural network approaches, which have been forwarded as computational accounts of the ventral stream, are consistent with the success of fMRI, though functional smoothness breaks down in the later network layers. These results have implications for the nature of the neural code and ventral stream, as well as what can be successfully investigated with fMRI.

Methods for discriminating gas-liquid two phase flow patterns based on gray neural networks and SVM

International Nuclear Information System (INIS)

Li Jingjing; Zhou Tao; Duan Jun; Zhang Lei

2013-01-01

Background: The flow patterns of two phase flow will directly influence the heat transfer and mass transfer of the flow. Purpose: By wavelet analysis of the pressure drop experimental data, the wavelet coefficients of different frequency can be obtained. Methods: Get the wavelet energy and then train them in the model of BP neural network to distinguish the flow patterns. Introduced the implant gray neural networks model and use it for the two phase flow for the first time. At the same time, set up the method of training the pressure data and wavelet energy data in the support vector machine. Results: Through treatment of the gray layer, the result of the neural network is more accuracy. It can obviously reduce the effect of data marginalization. The accuracy of the pressure drop Lib-SVM method is 95.2%. Conclusions: The results show that these three methods can make a distinction among the different flow patterns and the Lib-SVM method gets the best result, then the gray neural networks, and at last the BP neural networks. (authors)

Microstructural characterization of materials by neural network technique

Energy Technology Data Exchange (ETDEWEB)

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.

Identification of Non-Linear Structures using Recurrent Neural Networks

DEFF Research Database (Denmark)

Kirkegaard, Poul Henning; Nielsen, Søren R. K.; Hansen, H. I.

Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure.......Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure....

Identification of Non-Linear Structures using Recurrent Neural Networks

DEFF Research Database (Denmark)

Kirkegaard, Poul Henning; Nielsen, Søren R. K.; Hansen, H. I.

1995-01-01

Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure.......Two different partially recurrent neural networks structured as Multi Layer Perceptrons (MLP) are investigated for time domain identification of a non-linear structure....

Feed-forward motor control of ultrafast, ballistic movements.

Science.gov (United States)

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.

Laser induced forward transfer of graphene

NARCIS (Netherlands)

Smits, E.C.P.; Walter, A.; Leeuw, D.M. de; Asadi, K.

2017-01-01

Transfer of graphene and other two-dimensional materials is still a technical challenge. The 2D-materials are typically patterned after transfer, which leads to a major loss of material. Here, we present laser induced forward transfer of chemical vapor deposition grown graphene layers with

Hippocampus-driven feed-forward inhibition of the prefrontal cortex mediates relapse of extinguished fear

DEFF Research Database (Denmark)

Marek, Roger; Jin, Jingji; Goode, Travis D.

2018-01-01

The medial prefrontal cortex (mPFC) has been implicated in the extinction of emotional memories, including conditioned fear. We found that ventral hippocampal (vHPC) projections to the infralimbic (IL) cortex recruited parvalbumin-expressing interneurons to counter the expression of extinguished...... fear and promote fear relapse. Whole-cell recordings ex vivo revealed that optogenetic activation of vHPC input to amygdala-projecting pyramidal neurons in the IL was dominated by feed-forward inhibition. Selectively silencing parvalbumin-expressing, but not somatostatin-expressing, interneurons...... in the IL eliminated vHPC-mediated inhibition. In behaving rats, pharmacogenetic activation of vHPC→IL projections impaired extinction recall, whereas silencing IL projectors diminished fear renewal. Intra-IL infusion of GABA receptor agonists or antagonists, respectively, reproduced these effects. Together...

Modeling of yield and environmental impact categories in tea processing units based on artificial neural networks.

Science.gov (United States)

Khanali, Majid; Mobli, Hossein; Hosseinzadeh-Bandbafha, Homa

2017-12-01

In this study, an artificial neural network (ANN) model was developed for predicting the yield and life cycle environmental impacts based on energy inputs required in processing of black tea, green tea, and oolong tea in Guilan province of Iran. A life cycle assessment (LCA) approach was used to investigate the environmental impact categories of processed tea based on the cradle to gate approach, i.e., from production of input materials using raw materials to the gate of tea processing units, i.e., packaged tea. Thus, all the tea processing operations such as withering, rolling, fermentation, drying, and packaging were considered in the analysis. The initial data were obtained from tea processing units while the required data about the background system was extracted from the EcoInvent 2.2 database. LCA results indicated that diesel fuel and corrugated paper box used in drying and packaging operations, respectively, were the main hotspots. Black tea processing unit caused the highest pollution among the three processing units. Three feed-forward back-propagation ANN models based on Levenberg-Marquardt training algorithm with two hidden layers accompanied by sigmoid activation functions and a linear transfer function in output layer, were applied for three types of processed tea. The neural networks were developed based on energy equivalents of eight different input parameters (energy equivalents of fresh tea leaves, human labor, diesel fuel, electricity, adhesive, carton, corrugated paper box, and transportation) and 11 output parameters (yield, global warming, abiotic depletion, acidification, eutrophication, ozone layer depletion, human toxicity, freshwater aquatic ecotoxicity, marine aquatic ecotoxicity, terrestrial ecotoxicity, and photochemical oxidation). The results showed that the developed ANN models with R 2 values in the range of 0.878 to 0.990 had excellent performance in predicting all the output variables based on inputs. Energy consumption for

Estimating wheat and maize daily evapotranspiration using artificial neural network

Science.gov (United States)

Abrishami, Nazanin; Sepaskhah, Ali Reza; Shahrokhnia, Mohammad Hossein

2018-02-01

In this research, artificial neural network (ANN) is used for estimating wheat and maize daily standard evapotranspiration. Ten ANN models with different structures were designed for each crop. Daily climatic data [maximum temperature (T max), minimum temperature (T min), average temperature (T ave), maximum relative humidity (RHmax), minimum relative humidity (RHmin), average relative humidity (RHave), wind speed (U 2), sunshine hours (n), net radiation (Rn)], leaf area index (LAI), and plant height (h) were used as inputs. For five structures of ten, the evapotranspiration (ETC) values calculated by ETC = ET0 × K C equation (ET0 from Penman-Monteith equation and K C from FAO-56, ANNC) were used as outputs, and for the other five structures, the ETC values measured by weighing lysimeter (ANNM) were used as outputs. In all structures, a feed forward multiple-layer network with one or two hidden layers and sigmoid transfer function and BR or LM training algorithm was used. Favorite network was selected based on various statistical criteria. The results showed the suitable capability and acceptable accuracy of ANNs, particularly those having two hidden layers in their structure in estimating the daily evapotranspiration. Best model for estimation of maize daily evapotranspiration is «M»ANN1 C (8-4-2-1), with T max, T min, RHmax, RHmin, U 2, n, LAI, and h as input data and LM training rule and its statistical parameters (NRMSE, d, and R2) are 0.178, 0.980, and 0.982, respectively. Best model for estimation of wheat daily evapotranspiration is «W»ANN5 C (5-2-3-1), with T max, T min, Rn, LAI, and h as input data and LM training rule, its statistical parameters (NRMSE, d, and R 2) are 0.108, 0.987, and 0.981 respectively. In addition, if the calculated ETC used as the output of the network for both wheat and maize, higher accurate estimation was obtained. Therefore, ANN is suitable method for estimating evapotranspiration of wheat and maize.

Back-propagation neural network-based approximate analysis of true stress-strain behaviors of high-strength metallic material

International Nuclear Information System (INIS)

Doh, Jaeh Yeok; Lee, Jong Soo; Lee, Seung Uk

2016-01-01

In this study, a Back-propagation neural network (BPN) is employed to conduct an approximation of a true stress-strain curve using the load-displacement experimental data of DP590, a high-strength material used in automobile bodies and chassis. The optimized interconnection weights are obtained with hidden layers and output layers of the BPN through intelligent learning and training of the experimental data; by using these weights, a mathematical model of the material's behavior is suggested through this feed-forward neural network. Generally, the material properties from the tensile test cannot be acquired until the fracture regions, since it is difficult to measure the cross-section area of a specimen after diffusion necking. For this reason, the plastic properties of the true stress-strain are extrapolated using the weighted-average method after diffusion necking. The accuracies of BPN-based meta-models for predicting material properties are validated in terms of the Root mean square error (RMSE). By applying the approximate material properties, the reliable finite element solution can be obtained to realize the different shapes of the finite element models. Furthermore, the sensitivity analysis of the approximate meta-model is performed using the first-order approximate derivatives of the BPN and is compared with the results of the finite difference method. In addition, we predict the tension velocity's effect on the material property through a first-order sensitivity analysis.

Kinetic model-based feed-forward controlled fed-batch fermentation of Lactobacillus rhamnosus for the production of lactic acid from Arabic date juice.

Science.gov (United States)

Choi, Minsung; Al-Zahrani, Saeed M; Lee, Sang Yup

2014-06-01

Arabic date is overproduced in Arabic countries such as Saudi Arabia and Iraq and is mostly composed of sugars (70-80 wt%). Here we developed a fed-batch fermentation process by using a kinetic model for the efficient production of lactic acid to a high concentration from Arabic date juice. First, a kinetic model of Lactobacillus rhamnosus grown on date juice in batch fermentation was constructed in EXCEL so that the estimation of parameters and simulation of the model can be easily performed. Then, several fed-batch fermentations were conducted by employing different feeding strategies including pulsed feeding, exponential feeding, and modified exponential feeding. Based on the results of fed-batch fermentations, the kinetic model for fed-batch fermentation was also developed. This new model was used to perform feed-forward controlled fed-batch fermentation, which resulted in the production of 171.79 g l(-1) of lactic acid with the productivity and yield of 1.58 and 0.87 g l(-1) h(-1), respectively.

Prediction of Weld Penetration in FCAW of HSLA steel using Artificial Neural Networks

International Nuclear Information System (INIS)

Asl, Y. Dadgar; Mostafa, N. B.; Panahizadeh, V. R.; Seyedkashi, S. M. H.

2011-01-01

Flux-cored arc welding (FCAW) is a semiautomatic or automatic arc welding process that requires a continuously-fed consumable tubular electrode containing a flux. The main FCAW process parameters affecting the depth of penetration are welding current, arc voltage, nozzle-to-work distance, torch angle and welding speed. Shallow depth of penetration may contribute to failure of a welded structure since penetration determines the stress-carrying capacity of a welded joint. To avoid such occurrences; the welding process parameters influencing the weld penetration must be properly selected to obtain an acceptable weld penetration and hence a high quality joint. Artificial neural networks (ANN), also called neural networks (NN), are computational models used to express complex non-linear relationships between input and output data. In this paper, artificial neural network (ANN) method is used to predict the effects of welding current, arc voltage, nozzle-to-work distance, torch angle and welding speed on weld penetration depth in gas shielded FCAW of a grade of high strength low alloy steel. 32 experimental runs were carried out using the bead-on-plate welding technique. Weld penetrations were measured and on the basis of these 32 sets of experimental data, a feed-forward back-propagation neural network was created. 28 sets of the experiments were used as the training data and the remaining 4 sets were used for the testing phase of the network. The ANN has one hidden layer with eight neurons and is trained after 840 iterations. The comparison between the experimental results and ANN results showed that the trained network could predict the effects of the FCAW process parameters on weld penetration adequately.

Failure detection studies by layered neural network

International Nuclear Information System (INIS)

Ciftcioglu, O.; Seker, S.; Turkcan, E.

1991-06-01

Failure detection studies by layered neural network (NN) are described. The particular application area is an operating nuclear power plant and the failure detection is of concern as result of system surveillance in real-time. The NN system is considered to be consisting of 3 layers, one of which being hidden, and the NN parameters are determined adaptively by the backpropagation (BP) method, the process being the training phase. Studies are performed using the power spectra of the pressure signal of the primary system of an operating nuclear power plant of PWR type. The studies revealed that, by means of NN approach, failure detection can effectively be carried out using the redundant information as well as this is the case in this work; namely, from measurement of the primary pressure signals one can estimate the primary system coolant temperature and hence the deviation from the operational temperature state, the operational status identified in the training phase being referred to as normal. (author). 13 refs.; 4 figs.; 2 tabs

A two-dimensional, two-phase mass transport model for liquid-feed DMFCs

International Nuclear Information System (INIS)

Yang, W.W.; Zhao, T.S.

2007-01-01

A two-dimensional, isothermal two-phase mass transport model for a liquid-feed direct methanol fuel cell (DMFC) is presented in this paper. The two-phase mass transport in the anode and cathode porous regions is formulated based on the classical multiphase flow in porous media without invoking the assumption of constant gas pressure in the unsaturated porous medium flow theory. The two-phase flow behavior in the anode flow channel is modeled by utilizing the drift-flux model, while in the cathode flow channel the homogeneous mist-flow model is used. In addition, a micro-agglomerate model is developed for the cathode catalyst layer. The model also accounts for the effects of both methanol and water crossover through the membrane. The comprehensive model formed by integrating those in the different regions is solved numerically using a home-written computer code and validated against the experimental data in the literature. The model is then used to investigate the effects of various operating and structural parameters, such as methanol concentration, anode flow rate, porosities of both anode and cathode electrodes, the rate of methanol crossover, and the agglomerate size, on cell performance

Estimation of airway smooth muscle stiffness changes due to length oscillation using artificial neural network.

Science.gov (United States)

Al-Jumaily, Ahmed; Chen, Leizhi

2012-10-07

This paper presents a novel approach to estimate stiffness changes in airway smooth muscles due to external oscillation. Artificial neural networks are used to model the stiffness changes due to cyclic stretches of the smooth muscles. The nonlinear relationship between stiffness ratios and oscillation frequencies is modeled by a feed-forward neural network (FNN) model. The structure of the FNN is selected through the training and validation using literature data from 11 experiments with different muscle lengths, muscle masses, oscillation frequencies and amplitudes. Data pre-processing methods are used to improve the robustness of the neural network model to match the non-linearity. The validation results show that the FNN model can predict the stiffness ratio changes with a mean square error of 0.0042. Copyright © 2012 Elsevier Ltd. All rights reserved.

Quasi-static analysis of flexible pavements based on predicted frequencies using Fast Fourier Transform and Artificial Neural Network

Directory of Open Access Journals (Sweden)

Ali Reza Ghanizadeh

2018-01-01

Full Text Available New trend in design of flexible pavements is mechanistic-empirical approach. The first step for applying this method is analyzing the pavement structure for several times and computation of critical stresses and strains, which needs a fast analysis method with good accuracy. This paper aims to introduce a new rapid pavement analysis approach, which can consider the history of loading and rate effect. To this end, 1200 flexible pavement sections were analyzed, and equivalent frequencies (EF were calculated using Fast Fourier Transform (FFT method at various depths of asphalt layer. A nonlinear regression equation has been presented for determining EF at different depths of asphalt layer. For more accurate predicting of EF at low frequencies, a feed-forward Artificial Neural Network (ANN was employed, which allows accurate prediction of EF. The frequencies obtained by the proposed regression equation and ANN were compared with frequencies observed in Virginia Smart Road project, and it was found that there is a good agreement between observed and predicted frequencies. Comparison of quasi-static analysis of flexible pavements by frequencies obtained using FFT method and full dynamic analysis by 3D-Move program approves that the critical responses of pavement computed by proposed quasi-static analysis approach are comparable to critical responses computed using full dynamic analysis. Keywords: Equivalent frequency, Fast Fourier Transform (FFT, Pavement quasi-static analysis, Dynamic modulus, Artificial Neural Network (ANN

Bifunctional polymer hydrogel layers as forward osmosis draw agents for continuous production of fresh water using solar energy.

Science.gov (United States)

Razmjou, Amir; Liu, Qi; Simon, George P; Wang, Huanting

2013-11-19

The feasibility of bilayer polymer hydrogels as draw agent in forward osmosis process has been investigated. The dual-functionality hydrogels consist of a water-absorptive layer (particles of a copolymer of sodium acrylate and N-isopropylacrylamide) to provide osmotic pressure, and a dewatering layer (particles of N-isopropylacrylamide) to allow the ready release of the water absorbed during the FO drawing process at lower critical solution temperature (32 °C). The use of solar concentrated energy as the source of heat resulted in a significant increase in the dewatering rate as the temperature of dewatering layer increased to its LSCT more rapidly. Dewatering flux rose from 10 to 25 LMH when the solar concentrator increased the input energy from 0.5 to 2 kW/m(2). Thermodynamic analysis was also performed to find out the minimum energy requirement of such a bilayer hydrogel-driven FO process. This study represents a significant step forward toward the commercial implementation of hydrogel-driven FO system for continuous production of fresh water from saline water or wastewaters.

An approach to unfold the response of a multi-element system using an artificial neural network

International Nuclear Information System (INIS)

Cordes, E.; Fehrenbacher, G.; Schuetz, R.; Sprunck, M.; Hahn, K.; Hofmann, R.; Wahl, W.

1998-01-01

An unfolding procedure is proposed which aims at obtaining spectral information of a neutron radiation field by the analysis of the response of a multi-element system consisting of converter type semiconductors. For the unfolding procedure an artificial neural network (feed forward network), trained by the back-propagation method, was used. The response functions of the single elements to neutron radiation were calculated by application of a computational model for an energy range from 10 -2 eV to 10 MeV. The training of the artificial neural network was based on the computation of responses of a six-element system for a set of 300 neutron spectra and the application of the back-propagation method. The validation was performed by the unfolding of 100 computed responses. Two unfolding examples were pointed out for the determination of the neutron spectra. The spectra resulting from the unfolding procedure agree well with the original spectra used for the response computation

Modeling by artificial neural networks. Application to the management of fuel in a nuclear power plant; Modelisation par reseaux de neurones. Application a la gestion du combustible dans un reacteur

Energy Technology Data Exchange (ETDEWEB)

Gaudier, F

1999-07-01

The determination of the family of optimum core loading patterns for Pressurized Water Reactors (PWRs) involves the assessment of the core attributes, such as the power peaking factor for thousands of candidate loading patterns. Despite the rapid advances in computer architecture, the direct calculation of these attributes by a neutronic code needs a lot of of time and memory. With the goal of reducing the calculation time and optimizing the loading pattern, we propose in this thesis a method based on ideas of neural and statistical learning to provide a feed forward neural network capable of calculating the power peaking corresponding to an eighth core PWR. We use statistical methods to deduct judicious inputs (reduction of the input space dimension) and neural methods to train the model (learning capabilities). Indeed, on one hand, a principal component analysis allows us to characterize more efficiently the fuel assemblies (neural model inputs) and the other hand, the introduction of the a priori knowledge allows us to reducing the number of freedom parameters in the neural network. The model was built using a multi layered perceptron trained with the standard back propagation algorithm. We introduced our neural network in the automatic optimization code FORMOSA, and on EDF real problems we showed an important saving in time. Finally, we propose an hybrid method which combining the best characteristics of the linear local approximator GPT (Generalized Perturbation Theory) and the artificial neural network. (author)

A One-Layer Recurrent Neural Network for Real-Time Portfolio Optimization With Probability Criterion.

Science.gov (United States)

Liu, Qingshan; Dang, Chuangyin; Huang, Tingwen

2013-02-01

This paper presents a decision-making model described by a recurrent neural network for dynamic portfolio optimization. The portfolio-optimization problem is first converted into a constrained fractional programming problem. Since the objective function in the programming problem is not convex, the traditional optimization techniques are no longer applicable for solving this problem. Fortunately, the objective function in the fractional programming is pseudoconvex on the feasible region. It leads to a one-layer recurrent neural network modeled by means of a discontinuous dynamic system. To ensure the optimal solutions for portfolio optimization, the convergence of the proposed neural network is analyzed and proved. In fact, the neural network guarantees to get the optimal solutions for portfolio-investment advice if some mild conditions are satisfied. A numerical example with simulation results substantiates the effectiveness and illustrates the characteristics of the proposed neural network.

Two layer powder pressing

International Nuclear Information System (INIS)

Schreiner, H.

1979-01-01

First, significance and advantages of sintered materials consisting of two layers are pointed out. By means of the two layer powder pressing technique metal powders are formed resulting in compacts with high accuracy of shape and mass. Attributes of basic powders, different filling methods and pressing techniques are discussed. The described technique is supposed to find further applications in the field of two layer compacts in the near future

Estimation of monthly global solar radiation in the eastern Mediterranean region in Turkey by using artificial neural networks

International Nuclear Information System (INIS)

Sahan, Muhittin; Yakut, Emre

2016-01-01

In this study, an artificial neural network (ANN) model was used to estimate monthly average global solar radiation on a horizontal surface for selected 5 locations in Mediterranean region for period of 18 years (1993-2010). Meteorological and geographical data were taken from Turkish State Meteorological Service. The ANN architecture designed is a feed-forward back-propagation model with one-hidden layer containing 21 neurons with hyperbolic tangent sigmoid as the transfer function and one output layer utilized a linear transfer function (purelin). The training algorithm used in ANN model was the Levenberg Marquand back propagation algorith (trainlm). Results obtained from ANN model were compared with measured meteorological values by using statistical methods. A correlation coefficient of 97.97 (~98%) was obtained with root mean square error (RMSE) of 0.852 MJ/m 2 , mean square error (MSE) of 0.725 MJ/m 2 , mean absolute bias error (MABE) 10.659MJ/m 2 , and mean absolute percentage error (MAPE) of 4.8%. Results show good agreement between the estimated and measured values of global solar radiation. We suggest that the developed ANN model can be used to predict solar radiation another location and conditions

Multistability in bidirectional associative memory neural networks

International Nuclear Information System (INIS)

Huang Gan; Cao Jinde

2008-01-01

In this Letter, the multistability issue is studied for Bidirectional Associative Memory (BAM) neural networks. Based on the existence and stability analysis of the neural networks with or without delay, it is found that the 2n-dimensional networks can have 3 n equilibria and 2 n equilibria of them are locally exponentially stable, where each layer of the BAM network has n neurons. Furthermore, the results has been extended to (n+m)-dimensional BAM neural networks, where there are n and m neurons on the two layers respectively. Finally, two numerical examples are presented to illustrate the validity of our results

Multistability in bidirectional associative memory neural networks

Science.gov (United States)

Huang, Gan; Cao, Jinde

2008-04-01

In this Letter, the multistability issue is studied for Bidirectional Associative Memory (BAM) neural networks. Based on the existence and stability analysis of the neural networks with or without delay, it is found that the 2 n-dimensional networks can have 3 equilibria and 2 equilibria of them are locally exponentially stable, where each layer of the BAM network has n neurons. Furthermore, the results has been extended to (n+m)-dimensional BAM neural networks, where there are n and m neurons on the two layers respectively. Finally, two numerical examples are presented to illustrate the validity of our results.

A feed-forward regulation of endothelin receptors by c-Jun in human non-pigmented ciliary epithelial cells and retinal ganglion cells.

Directory of Open Access Journals (Sweden)

Junming Wang

, thereby generating a positive feed-forward loop of endothelin receptor activation and expression. This feed-forward regulation may contribute to RGC death and astrocyte proliferation following ET-1 treatment.

Double-Skinned Forward Osmosis Membranes for Reducing Internal Concentration Polarization within the Porous Sublayer

KAUST Repository

Wang, Kai Yu

2010-05-19

A scheme to fabricate forward osmosis membranes comprising a highly porous sublayer sandwiched between two selective skin layers via phase inversion was proposed. One severe deficiency of existing composite and asymmetric membranes used in forward osmosis is the presence of unfavorable internal concentration polarization within the porous support layer that hinders both (i) separation (salt flux) and (ii) the performance (water flux). The double skin layers of the tailored membrane may mitigate the internal concentration polarization by preventing the salt and other solutes in the draw solution from penetrating into the membrane porous support. The prototype double-skinned cellulose acetate membrane displayed a water flux of 48.2 L·m-2·h -1 and lower reverse salt transport of 6.5 g·m -2·h-1 using 5.0 M MgCl2 as the draw solution in a forward osmosis process performed at 22 °C. This can be attributed to the effective salt rejection by the double skin layers and the low water transport resistance within the porous support layer. The prospects of utilizing the double-selective layer membranes may have potential application in forward osmosis for desalination. This study may help pave the way to improve the membrane design for the forward osmosis process. © 2010 American Chemical Society.

Double-Skinned Forward Osmosis Membranes for Reducing Internal Concentration Polarization within the Porous Sublayer

KAUST Repository

Wang, Kai Yu; Ong, Rui Chin; Chung, Tai-Shung

2010-01-01

A scheme to fabricate forward osmosis membranes comprising a highly porous sublayer sandwiched between two selective skin layers via phase inversion was proposed. One severe deficiency of existing composite and asymmetric membranes used in forward osmosis is the presence of unfavorable internal concentration polarization within the porous support layer that hinders both (i) separation (salt flux) and (ii) the performance (water flux). The double skin layers of the tailored membrane may mitigate the internal concentration polarization by preventing the salt and other solutes in the draw solution from penetrating into the membrane porous support. The prototype double-skinned cellulose acetate membrane displayed a water flux of 48.2 L·m-2·h -1 and lower reverse salt transport of 6.5 g·m -2·h-1 using 5.0 M MgCl2 as the draw solution in a forward osmosis process performed at 22 °C. This can be attributed to the effective salt rejection by the double skin layers and the low water transport resistance within the porous support layer. The prospects of utilizing the double-selective layer membranes may have potential application in forward osmosis for desalination. This study may help pave the way to improve the membrane design for the forward osmosis process. © 2010 American Chemical Society.

Particle identification with neural networks using a rotational invariant moment representation

Science.gov (United States)

Sinkus, Ralph; Voss, Thomas

1997-02-01

A feed-forward neural network is used to identify electromagnetic particles based upon their showering properties within a segmented calorimeter. A preprocessing procedure is applied to the spatial energy distribution of the particle shower in order to account for the varying geometry of the calorimeter. The novel feature is the expansion of the energy distribution in terms of moments of the so-called Zernike functions which are invariant under rotation. The distributions of moments exhibit very different scales, thus the multidimensional input distribution for the neural network is transformed via a principal component analysis and rescaled by its respective variances to ensure input values of the order of one. This increases the sensitivity of the network and thus results in better performance in identifying and separating electromagnetic from hadronic particles, especially at low energies.

Particle identification with neural networks using a rotational invariant moment representation

International Nuclear Information System (INIS)

Sinkus, R.

1997-01-01

A feed-forward neural network is used to identify electromagnetic particles based upon their showering properties within a segmented calorimeter. A preprocessing procedure is applied to the spatial energy distribution of the particle shower in order to account for the varying geometry of the calorimeter. The novel feature is the expansion of the energy distribution in terms of moments of the so-called Zernike functions which are invariant under rotation. The distributions of moments exhibit very different scales, thus the multidimensional input distribution for the neural network is transformed via a principal component analysis and rescaled by its respective variances to ensure input values of the order of one. This increases the sensitivity of the network and thus results in better performance in identifying and separating electromagnetic from hadronic particles, especially at low energies. (orig.)

Application of Artificial Neural Network and Response Surface Methodology in Modeling of Surface Roughness in WS2 Solid Lubricant Assisted MQL Turning of Inconel 718

Science.gov (United States)

Maheshwera Reddy Paturi, Uma; Devarasetti, Harish; Abimbola Fadare, David; Reddy Narala, Suresh Kumar

2018-04-01

In the present paper, the artificial neural network (ANN) and response surface methodology (RSM) are used in modeling of surface roughness in WS2 (tungsten disulphide) solid lubricant assisted minimal quantity lubrication (MQL) machining. The real time MQL turning of Inconel 718 experimental data considered in this paper was available in the literature [1]. In ANN modeling, performance parameters such as mean square error (MSE), mean absolute percentage error (MAPE) and average error in prediction (AEP) for the experimental data were determined based on Levenberg–Marquardt (LM) feed forward back propagation training algorithm with tansig as transfer function. The MATLAB tool box has been utilized in training and testing of neural network model. Neural network model with three input neurons, one hidden layer with five neurons and one output neuron (3-5-1 architecture) is found to be most confidence and optimal. The coefficient of determination (R2) for both the ANN and RSM model were seen to be 0.998 and 0.982 respectively. The surface roughness predictions from ANN and RSM model were related with experimentally measured values and found to be in good agreement with each other. However, the prediction efficacy of ANN model is relatively high when compared with RSM model predictions.

Gap Filling of Daily Sea Levels by Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Lyubka Pashova

2013-06-01

Full Text Available In the recent years, intelligent methods as artificial neural networks are successfully applied for data analysis from different fields of the geosciences. One of the encountered practical problems is the availability of gaps in the time series that prevent their comprehensive usage for the scientific and practical purposes. The article briefly describes two types of the artificial neural network (ANN architectures - Feed-Forward Backpropagation (FFBP and recurrent Echo state network (ESN. In some cases, the ANN can be used as an alternative on the traditional methods, to fill in missing values in the time series. We have been conducted several experiments to fill the missing values of daily sea levels spanning a 5-years period using both ANN architectures. A multiple linear regression for the same purpose has been also applied. The sea level data are derived from the records of the tide gauge Burgas, which is located on the western Black Sea coast. The achieved results have shown that the performance of ANN models is better than that of the classical one and they are very promising for the real-time interpolation of missing data in the time series.

Investigation of tt-bar in the full hadronic final state at CDF with a neural network approach

International Nuclear Information System (INIS)

Sidoti, A.; Azzi, P.; Busetto, G.; Castro, A.; Dusini, S.; Lazzizzera, I.; Wyss, J.L.

2001-01-01

In this work we present the results of a neural network (NN) approach to the measurement of the tt-bar production cross-section and top mass in the all-hadronic channel, analyzing data collected at the Collider Detector at Fermilab (CDF) experiment. We have used a hardware implementation of a feed forward neural network, TOTEM, the product of a collaboration of INFN (Istituto Nazionale Fisica Nucleare) - IRST (Istituto per la Ricerca Scientifica e Tecnologica) - University of Trento, Italy. Particular attention has been paid to the evaluation of the systematics specifically related to the NN approach. The results are consistent with those obtained at CDF by conventional data selection techniques

Feeding Value of Low and High Protein Dried Distillers Grains and Corn Gluten Meal for Layer

Directory of Open Access Journals (Sweden)

B. Tangendjaja

2011-08-01

Full Text Available A feeding trial has been conducted to compare feeding value of low and high protein dried distillers grains with solubles (DDGS, and corn gluten meal (CGM to brown layer in the tropics. Both types of DDGS was included at level 0%, 4%, 8%, 12%, and 16% in the diet while CGM was included at 0%, 2%, 4%, 6%, and 8% in similar content of metabolizable energy (ME value (2650 kcal/kg and protein (17%. Each dietary treatment was fed to 4 birds in individual wire cage and replicated 5 times. The trial was performed for 10 weeks and egg production, egg weight, feed intake was measured. At the end of feeding period, manure was collected and analyzed for moisture content while samples of eggs were measured for yolk color and the yolk was analyzed for xanthophyll level. Result showed that feeding Lopro DDGS, Hipro DDGS, and CGM did not affect egg production (egg mass, egg number, and egg weight, however, feeding DDGS resulted in less feed intake (111 g/day compared to feeding CGM (114 g/day. Feeding DDGS up to 16% did not affect egg production and similar to feeding CGM up to 8%. Feeding high level of DDGS or CGM did not significantly affect the moisture content of excreta which were between 78.1%-81.9%. Increasing levels of DDGS or CGM increased yolk color score related to the higher level of xanthophylls content in egg yolk. The coloring ability of CGM to egg yolk was higher than that of DDGS. In conclusion, DDGS can be fed to layer up to 16% without affecting egg production while CGM can be fed up to 8% in the diet. DDGS can be used as source of yellow pigment for egg yolk as also found in CGM.

A one-layer recurrent neural network for non-smooth convex optimization subject to linear inequality constraints

International Nuclear Information System (INIS)

Liu, Xiaolan; Zhou, Mi

2016-01-01

In this paper, a one-layer recurrent network is proposed for solving a non-smooth convex optimization subject to linear inequality constraints. Compared with the existing neural networks for optimization, the proposed neural network is capable of solving more general convex optimization with linear inequality constraints. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed as long as the designed parameters in the model are larger than the derived lower bounds.

A multifactorial analysis of obesity as CVD risk factor: Use of neural network based methods in a nutrigenetics context

Directory of Open Access Journals (Sweden)

Valavanis Ioannis K

2010-09-01

Full Text Available Abstract Background Obesity is a multifactorial trait, which comprises an independent risk factor for cardiovascular disease (CVD. The aim of the current work is to study the complex etiology beneath obesity and identify genetic variations and/or factors related to nutrition that contribute to its variability. To this end, a set of more than 2300 white subjects who participated in a nutrigenetics study was used. For each subject a total of 63 factors describing genetic variants related to CVD (24 in total, gender, and nutrition (38 in total, e.g. average daily intake in calories and cholesterol, were measured. Each subject was categorized according to body mass index (BMI as normal (BMI ≤ 25 or overweight (BMI > 25. Two artificial neural network (ANN based methods were designed and used towards the analysis of the available data. These corresponded to i a multi-layer feed-forward ANN combined with a parameter decreasing method (PDM-ANN, and ii a multi-layer feed-forward ANN trained by a hybrid method (GA-ANN which combines genetic algorithms and the popular back-propagation training algorithm. Results PDM-ANN and GA-ANN were comparatively assessed in terms of their ability to identify the most important factors among the initial 63 variables describing genetic variations, nutrition and gender, able to classify a subject into one of the BMI related classes: normal and overweight. The methods were designed and evaluated using appropriate training and testing sets provided by 3-fold Cross Validation (3-CV resampling. Classification accuracy, sensitivity, specificity and area under receiver operating characteristics curve were utilized to evaluate the resulted predictive ANN models. The most parsimonious set of factors was obtained by the GA-ANN method and included gender, six genetic variations and 18 nutrition-related variables. The corresponding predictive model was characterized by a mean accuracy equal of 61.46% in the 3-CV testing sets

A multifactorial analysis of obesity as CVD risk factor: use of neural network based methods in a nutrigenetics context.

Science.gov (United States)

Valavanis, Ioannis K; Mougiakakou, Stavroula G; Grimaldi, Keith A; Nikita, Konstantina S

2010-09-08

Obesity is a multifactorial trait, which comprises an independent risk factor for cardiovascular disease (CVD). The aim of the current work is to study the complex etiology beneath obesity and identify genetic variations and/or factors related to nutrition that contribute to its variability. To this end, a set of more than 2300 white subjects who participated in a nutrigenetics study was used. For each subject a total of 63 factors describing genetic variants related to CVD (24 in total), gender, and nutrition (38 in total), e.g. average daily intake in calories and cholesterol, were measured. Each subject was categorized according to body mass index (BMI) as normal (BMI ≤ 25) or overweight (BMI > 25). Two artificial neural network (ANN) based methods were designed and used towards the analysis of the available data. These corresponded to i) a multi-layer feed-forward ANN combined with a parameter decreasing method (PDM-ANN), and ii) a multi-layer feed-forward ANN trained by a hybrid method (GA-ANN) which combines genetic algorithms and the popular back-propagation training algorithm. PDM-ANN and GA-ANN were comparatively assessed in terms of their ability to identify the most important factors among the initial 63 variables describing genetic variations, nutrition and gender, able to classify a subject into one of the BMI related classes: normal and overweight. The methods were designed and evaluated using appropriate training and testing sets provided by 3-fold Cross Validation (3-CV) resampling. Classification accuracy, sensitivity, specificity and area under receiver operating characteristics curve were utilized to evaluate the resulted predictive ANN models. The most parsimonious set of factors was obtained by the GA-ANN method and included gender, six genetic variations and 18 nutrition-related variables. The corresponding predictive model was characterized by a mean accuracy equal of 61.46% in the 3-CV testing sets. The ANN based methods revealed factors

A One-Layer Recurrent Neural Network for Pseudoconvex Optimization Problems With Equality and Inequality Constraints.

Science.gov (United States)

Qin, Sitian; Yang, Xiudong; Xue, Xiaoping; Song, Jiahui

2017-10-01

Pseudoconvex optimization problem, as an important nonconvex optimization problem, plays an important role in scientific and engineering applications. In this paper, a recurrent one-layer neural network is proposed for solving the pseudoconvex optimization problem with equality and inequality constraints. It is proved that from any initial state, the state of the proposed neural network reaches the feasible region in finite time and stays there thereafter. It is also proved that the state of the proposed neural network is convergent to an optimal solution of the related problem. Compared with the related existing recurrent neural networks for the pseudoconvex optimization problems, the proposed neural network in this paper does not need the penalty parameters and has a better convergence. Meanwhile, the proposed neural network is used to solve three nonsmooth optimization problems, and we make some detailed comparisons with the known related conclusions. In the end, some numerical examples are provided to illustrate the effectiveness of the performance of the proposed neural network.

Boron removal in radioactive liquid waste by forward osmosis membrane

Energy Technology Data Exchange (ETDEWEB)

Doo Seong Hwang; Hei Min Choi; Kune Woo Lee; Jei Kwon Moon [KAERI, Daejeon (Korea, Republic of)

2013-07-01

This study investigated the treatment of boric acid contained in liquid radioactive waste using a forward osmosis membrane. The boron permeation through the membrane depends on the type of membrane, membrane orientation, pH of the feed solution, salt and boron concentration in the feed solution, and osmotic pressure of the draw solution. The boron flux begins to decline from pH 7 and increases with an increase of the osmotic driving force. The boron flux decreases slightly with the salt concentration, but is not heavily influenced by a low salt concentration. The boron flux increases linearly with the concentration of boron. No element except for boron was permeated through the FO membrane in the multi-component system. The maximum boron flux is obtained in an active layer facing a draw solution orientation of the CTA-ES membrane under conditions of less than pH 7 and high osmotic pressure. (authors)

Long-term effects of dietary supplementation with an essential oil mixture on the growth and laying performance of two layer strains

Directory of Open Access Journals (Sweden)

Abdullah U. Çatli

2012-01-01

Full Text Available One thousand two hundred 1-day-old Lohmann LSL white and Lohmann Brown layer chickens were fed diets supplemented with either an antibiotic growth promoter (AGP or an herbal essential oil mixture (EOM till 58 wk of age to reveal the long-term effects of those additives on growth, performance and wholesome egg quality parameters. The study was arranged in a 2x3 factorial design with two layer strains and three feed additive regimens. Thus, the layer birds of both strains were randomly assigned to the three dietary treatments, i.e., standard basal diet (control, control with AGP (specifically, avilamycin, 10 mg/kg diet and control with EOM (24 mg/kg diet. The data regarding egg production were recorded between 22 to 58 weeks of age. Neither the dietary treatments nor the bird strain influenced the body weight and mortality of the birds in both the growing and laying period. AGP or EOM supplementation to the laying hen diet significantly increased the egg production rate and egg weight as compared to the control  diet alone, but egg mass output, feed consumption, and feed conversion ratio were not effected  by the dietary treatments. Neither dietary treatment created any statistically significantly differences in egg quality parameters with the exception of Haugh unit. The research findings have confirmed the beneficial effects of supplementation with feed-grade EOM on the laying rate and egg weight of both white and brown layers. Indeed, EOM, being a novel feed additive natural origin, proved to be as efficacious as AGP in promoting egg yield.

Effects of Forward- and Backward-Facing Steps on the Crossflow Receptivity and Stability in Supersonic Boundary Layers

Science.gov (United States)

Balakumar, P.; King, Rudolph A.; Eppink, Jenna L.

2014-01-01

The effects of forward- and backward-facing steps on the receptivity and stability of three-dimensional supersonic boundary layers over a swept wing with a blunt leading edge are numerically investigated for a freestream Mach number of 3 and a sweep angle of 30 degrees. The flow fields are obtained by solving the full Navier-Stokes equations. The evolution of instability waves generated by surface roughness is simulated with and without the forward- and backward-facing steps. The separation bubble lengths are about 5-10 step heights for the forward-facing step and are about 10 for the backward-facing step. The linear stability calculations show very strong instability in the separated region with a large frequency domain. The simulation results show that the presence of backward-facing steps decreases the amplitude of the stationary crossflow vortices with longer spanwise wavelengths by about fifty percent and the presence of forward-facing steps does not modify the amplitudes noticeably across the steps. The waves with the shorter wavelengths grow substantially downstream of the step in agreement with the linear stability prediction.

The effect of an exogenous magnetic field on neural coding in deep spiking neural networks.

Science.gov (United States)

Guo, Lei; Zhang, Wei; Zhang, Jialei

2018-01-01

A ten-layer feed forward network is constructed in the presence of an exogenous alternating magnetic field. Specifically, our results indicate that for rate coding, the firing rate is significantly increased in the presence of an exogenous alternating magnetic field and particularly with increasing enhancement of the alternating magnetic field amplitude. For temporal coding, the interspike intervals of the spiking sequence are decreased and the distribution of the interspike intervals of the spiking sequence tends to be uniform in the presence of alternating magnetic field.

Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets

OpenAIRE

Romanuke Vadim V.

2017-01-01

A technique of DropOut for preventing overfitting of convolutional neural networks for image classification is considered in the paper. The goal is to find a rule of rationally allocating DropOut layers of 0.5 rate to maximise performance. To achieve the goal, two common network architectures are used having either 4 or 5 convolutional layers. Benchmarking is fulfilled with CIFAR-10, EEACL26, and NORB datasets. Initially, series of all admissible versions for allocation of DropOut layers are ...

A neural network detection system for lower-hybrid cavities in electron plasma density measured by the FREJA satellite

International Nuclear Information System (INIS)

Waldemark, J.; Karlsson, Jan

1995-03-01

This paper presents a lower-hybrid cavity detection system, CDS, for measurements of electron plasma density on the FREJA satellite wave experiment. The system can reduce the amount of data to be analysed by as much as 96% and still retain more than 85% of the desired information. The CDS is a combination of a hybrid neural network, HNN and expert rules. The HNN is a Self Organizing Map, SOM, combined with a feed forward back propagation neural net, BP. The CDS can be controlled by the user to operate with various degrees of sensitivity. Maximum detection capability is as high as 95% with data reduction lowered to 85%. 10 refs

Entry, Descent and Landing Systems Analysis: Exploration Feed Forward Internal Peer Review Slide Package

Science.gov (United States)

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.

Forecast of TEXT plasma disruptions using soft X rays as input signal in a neural network

International Nuclear Information System (INIS)

Vannucci, A.; Oliveira, K.A.; Tajima, T.

1999-01-01

A feedforward neural network with two hidden layers is used to forecast major and minor disruptive instabilities in TEXT tokamak discharges. Using the experimental data of soft X ray signals as input data, the neural network is trained with one disruptive plasma discharge, and a different disruptive discharge is used for validation. After being properly trained, the networks, with the same set of weights, are used to forecast disruptions in two other plasma discharges. It is observed that the neural network is able to predict the occurrence of a disruption more than 3 ms in advance. This time interval is almost 3 times longer than the one already obtained previously when a magnetic signal from a Mirnov coil was used to feed the neural networks. Visually no indication of an upcoming disruption is seen from the experimental data this far back from the time of disruption. Finally, by observing the predictive behaviour of the network for the disruptive discharges analysed and comparing the soft X ray data with the corresponding magnetic experimental signal, it is conjectured about where inside the plasma column the disruption first started. (author)

Selection of hidden layer nodes in neural networks by statistical tests

International Nuclear Information System (INIS)

Ciftcioglu, Ozer

1992-05-01

A statistical methodology for selection of the number of hidden layer nodes in feedforward neural networks is described. The method considers the network as an empirical model for the experimental data set subject to pattern classification so that the selection process becomes a model estimation through parameter identification. The solution is performed for an overdetermined estimation problem for identification using nonlinear least squares minimization technique. The number of the hidden layer nodes is determined as result of hypothesis testing. Accordingly the redundant network structure with respect to the number of parameters is avoided and the classification error being kept to a minimum. (author). 11 refs.; 4 figs.; 1 tab

Memory trace in feeding neural circuitry underlying conditioned taste aversion in Lymnaea.

Directory of Open Access Journals (Sweden)

Etsuro Ito

Full Text Available BACKGROUND: The pond snail Lymnaea stagnalis can maintain a conditioned taste aversion (CTA as a long-term memory. Previous studies have shown that the inhibitory postsynaptic potential (IPSP evoked in the neuron 1 medial (N1M cell by activation of the cerebral giant cell (CGC in taste aversion-trained snails was larger and lasted longer than that in control snails. The N1M cell is one of the interneurons in the feeding central pattern generator (CPG, and the CGC is a key regulatory neuron for the feeding CPG. METHODOLOGY/PRINCIPLE FINDINGS: Previous studies have suggested that the neural circuit between the CGC and the N1M cell consists of two synaptic connections: (1 the excitatory connection from the CGC to the neuron 3 tonic (N3t cell and (2 the inhibitory connection from the N3t cell to the N1M cell. However, because the N3t cell is too small to access consistently by electrophysiological methods, in the present study the synaptic inputs from the CGC to the N3t cell and those from the N3t cell to the N1M cell were monitored as the monosynaptic excitatory postsynaptic potential (EPSP recorded in the large B1 and B3 motor neurons, respectively. The evoked monosynaptic EPSPs of the B1 motor neurons in the brains isolated from the taste aversion-trained snails were identical to those in the control snails, whereas the spontaneous monosynaptic EPSPs of the B3 motor neurons were significantly enlarged. CONCLUSION/SIGNIFICANCE: These results suggest that, after taste aversion training, the monosynaptic inputs from the N3t cell to the following neurons including the N1M cell are specifically facilitated. That is, one of the memory traces for taste aversion remains as an increase in neurotransmitter released from the N3t cell. We thus conclude that the N3t cell suppresses the N1M cell in the feeding CPG, in response to the conditioned stimulus in Lymnaea CTA.

Memory trace in feeding neural circuitry underlying conditioned taste aversion in Lymnaea.

Science.gov (United States)

Ito, Etsuro; Otsuka, Emi; Hama, Noriyuki; Aonuma, Hitoshi; Okada, Ryuichi; Hatakeyama, Dai; Fujito, Yutaka; Kobayashi, Suguru

2012-01-01

The pond snail Lymnaea stagnalis can maintain a conditioned taste aversion (CTA) as a long-term memory. Previous studies have shown that the inhibitory postsynaptic potential (IPSP) evoked in the neuron 1 medial (N1M) cell by activation of the cerebral giant cell (CGC) in taste aversion-trained snails was larger and lasted longer than that in control snails. The N1M cell is one of the interneurons in the feeding central pattern generator (CPG), and the CGC is a key regulatory neuron for the feeding CPG. Previous studies have suggested that the neural circuit between the CGC and the N1M cell consists of two synaptic connections: (1) the excitatory connection from the CGC to the neuron 3 tonic (N3t) cell and (2) the inhibitory connection from the N3t cell to the N1M cell. However, because the N3t cell is too small to access consistently by electrophysiological methods, in the present study the synaptic inputs from the CGC to the N3t cell and those from the N3t cell to the N1M cell were monitored as the monosynaptic excitatory postsynaptic potential (EPSP) recorded in the large B1 and B3 motor neurons, respectively. The evoked monosynaptic EPSPs of the B1 motor neurons in the brains isolated from the taste aversion-trained snails were identical to those in the control snails, whereas the spontaneous monosynaptic EPSPs of the B3 motor neurons were significantly enlarged. These results suggest that, after taste aversion training, the monosynaptic inputs from the N3t cell to the following neurons including the N1M cell are specifically facilitated. That is, one of the memory traces for taste aversion remains as an increase in neurotransmitter released from the N3t cell. We thus conclude that the N3t cell suppresses the N1M cell in the feeding CPG, in response to the conditioned stimulus in Lymnaea CTA.

Layers and Multilayers of Self-Assembled Polymers: Tunable Engineered Extracellular Matrix Coatings for Neural Cell Growth.

Science.gov (United States)

Landry, Michael J; Rollet, Frédéric-Guillaume; Kennedy, Timothy E; Barrett, Christopher J

2018-03-12

Growing primary cells and tissue in long-term cultures, such as primary neural cell culture, presents many challenges. A critical component of any environment that supports neural cell growth in vivo is an appropriate 2-D surface or 3-D scaffold, typically in the form of a thin polymer layer that coats an underlying plastic or glass substrate and aims to mimic critical aspects of the extracellular matrix. A fundamental challenge to mimicking a hydrophilic, soft natural cell environment is that materials with these properties are typically fragile and are difficult to adhere to and stabilize on an underlying plastic or glass cell culture substrate. In this review, we highlight the current state of the art and overview recent developments of new artificial extracellular matrix (ECM) surfaces for in vitro neural cell culture. Notably, these materials aim to strike a balance between being hydrophilic and soft while also being thick, stable, robust, and bound well to the underlying surface to provide an effective surface to support long-term cell growth. We focus on improved surface and scaffold coating systems that can mimic the natural physicochemical properties that enhance neuronal survival and growth, applied as soft hydrophilic polymer coatings for both in vitro cell culture and for implantable neural probes and 3-D matrixes that aim to enhance stability and longevity to promote neural biocompatibility in vivo. With respect to future developments, we outline four emerging principles that serve to guide the development of polymer assemblies that function well as artificial ECMs: (a) design inspired by biological systems and (b) the employment of principles of aqueous soft bonding and self-assembly to achieve (c) a high-water-content gel-like coating that is stable over time in a biological environment and possesses (d) a low modulus to more closely mimic soft, compliant real biological tissue. We then highlight two emerging classes of thick material coatings that

Detection of different states of sleep in the rodents by the means of artificial neural networks

Science.gov (United States)

Musatov, Viacheslav; Dykin, Viacheslav; Pitsik, Elena; Pisarchik, Alexander

2018-04-01

This paper considers the possibility of classification of electroencephalogram (EEG) and electromyogram (EMG) signals corresponding to different phases of sleep and wakefulness of mice by the means of artificial neural networks. A feed-forward artificial neural network based on multilayer perceptron was created and trained on the data of one of the rodents. The trained network was used to read and classify the EEG and EMG data corresponding to different phases of sleep and wakefulness of the same mouse and other mouse. The results show a good recognition quality of all phases for the rodent on which the training was conducted (80-99%) and acceptable recognition quality for the data collected from the same mouse after a stroke.

Aflatoxin biosynthesis control produced by Aspergillus flavus in layer hens feed during storage period of six months.

Science.gov (United States)

Hassan, S M; Sultana, B; Iqbal, M

2017-06-01

Aflatoxins (AFTs) are a group of closely related toxins that are produced by different fungus species. Food and feed contamination with AFT is a worldwide health-related problem. As a result of fungal attack, the food and feed resulted in a principal socioeconomic loss and toxins produced in feed and food items harm the humans and animals in different ways. The anti-aflatoxigenic effect Psidium guajava, Ficus benghalensis, Gardenia radicans, Punica granatum and Ziziphus jujuba leaves were evaluated against aflatoxins (AFTs), produced by Aspergillus flavus in layer feed during storage. Among the investigated medicinal plant leaves, P. granatum showed highly promising anti-aflatoxigenic activity and completely inhibited the AFTs (B1 and B2) production over storage period without compromising the nutritive quality of feed (ash, protein, fat, fiber, Fe, Ca, P and K contents). Leaves of F. benghalensis and Z. jujuba were also effective however, higher concentration (15%) inhibited the AFTs production up to 99% and also maintained nutritive quality of feed. G. radicans was found least effective in controlling the AFTs production. Results revealed that all plant leaves were effective in controlling AFTs production in layer feed over the storage period of six months and these plants are potential candidate to replace the fungicides used to protect feed and other agricultural commodities from AFTs production during storage. Copyright © 2017 Elsevier Masson SAS. All rights reserved.

Application of neural networks to seismic active control

International Nuclear Information System (INIS)

Tang, Yu.

1995-01-01

An exploratory study on seismic active control using an artificial neural network (ANN) is presented in which a singledegree-of-freedom (SDF) structural system is controlled by a trained neural network. A feed-forward neural network and the backpropagation training method are used in the study. In backpropagation training, the learning rate is determined by ensuring the decrease of the error function at each training cycle. The training patterns for the neural net are generated randomly. Then, the trained ANN is used to compute the control force according to the control algorithm. The control strategy proposed herein is to apply the control force at every time step to destroy the build-up of the system response. The ground motions considered in the simulations are the N21E and N69W components of the Lake Hughes No. 12 record that occurred in the San Fernando Valley in California on February 9, 1971. Significant reduction of the structural response by one order of magnitude is observed. Also, it is shown that the proposed control strategy has the ability to reduce the peak that occurs during the first few cycles of the time history. These promising results assert the potential of applying ANNs to active structural control under seismic loads

Prediction of small hydropower plant power production in Himreen Lake dam (HLD using artificial neural network

Directory of Open Access Journals (Sweden)

Ali Thaeer Hammid

2018-03-01

Full Text Available In developing countries, the power production is properly less than the request of power or load, and sustaining a system stability of power production is a trouble quietly. Sometimes, there is a necessary development to the correct quantity of load demand to retain a system of power production steadily. Thus, Small Hydropower Plant (SHP includes a Kaplan turbine was verified to explore its applicability. This paper concentrates on applying on Artificial Neural Networks (ANNs by approaching of Feed-Forward, Back-Propagation to make performance predictions of the hydropower plant at the Himreen lake dam-Diyala in terms of net turbine head, flow rate of water and power production that data gathered during a research over a 10 year period. The model studies the uncertainties of inputs and output operation and there's a designing to network structure and then trained by means of the entire of 3570 experimental and observed data. Furthermore, ANN offers an analyzing and diagnosing instrument effectively to model performance of the nonlinear plant. The study suggests that the ANN may predict the performance of the plant with a correlation coefficient (R between the variables of predicted and observed output that would be higher than 0.96. Keywords: Himreen Lake Dam, Small Hydropower plants, Artificial Neural Networks, Feed forward-back propagation model, Generation system's prediction

Artificial neural network approach to modeling of alcoholic fermentation of thick juice from sugar beet processing

Directory of Open Access Journals (Sweden)

Jokić Aleksandar I.

2012-01-01

Full Text Available In this paper the bioethanol production in batch culture by free Saccharomyces cerevisiae cells from thick juice as intermediate product of sugar beet processing was examined. The obtained results suggest that it is possible to decrease fermentation time for the cultivation medium based on thick juice with starting sugar content of 5-15 g kg-1. For the fermentation of cultivation medium based on thick juice with starting sugar content of 20 and 25 g kg-1 significant increase in ethanol content was attained during the whole fermentation process, resulting in 12.51 and 10.95 dm3 m-3 ethanol contents after 48 h, respectively. Other goals of this work were to investigate the possibilities for experimental results prediction using artificial neural networks (ANNs and to find its optimal topology. A feed-forward back-propagation artificial neural network was used to test the hypothesis. As input variables fermentation time and starting sugar content were used. Neural networks had one output value, ethanol content, yeast cell number or sugar content. There was one hidden layer and the optimal number of neurons was found to be nine for all selected network outputs. In this study transfer function was tansig and the selected learning rule was Levenberg-Marquardt. Results suggest that artificial neural networks are good prediction tool for selected network outputs. It was found that experimental results are in very good agreement with computed ones. The coefficient of determination (the R-squared was found to be 0.9997, 0.9997 and 0.9999 for ethanol content, yeast cell number and sugar content, respectively.

Distortion correction for x-ray image intensifiers: Local unwarping polynomials and RBF neural networks

International Nuclear Information System (INIS)

Cerveri, P.; Forlani, C.; Borghese, N.A.; Ferrigno, G.

2002-01-01

In this paper we present two novel techniques, namely a local unwarping polynomial (LUP) and a hierarchical radial basis function (HRBF) network, to correct geometric distortions in XRII images. The two techniques have been implemented and compared, in terms of residual error measured at control and intermediate points, with local and global methods reported in the previous literature. In particular, LUP rests on a locally optimized 3rd degree polynomial applied within each quadrilateral cell on the rectilinear calibration grid of points. HRBF, based on a feed-forward neural network paradigm, is constituted by a set of hierarchical layers at increasing cut-off frequency, each characterized by a set of Gaussian functions. Extensive experiments have been performed both on simulated and real data. In simulation, we tested the effect of pincushion, sigmoidal and local distortions, along with the number of calibration points. Provided that a sufficient number of cells of the calibration grid is available, the obtained accuracy for both LUP and HRBF is comparable to or better than that of global polynomial technique. Tests on real data, carried out by using two different (12 in. and 16 in.) XRIIs, showed that the global polynomial accuracy (0.16±0.08 pixels) is slightly worse than that of LUP (0.07±0.05 pixels) and HRBF (0.08±0.04 pixels). The effects of the discontinuity at the border of the local areas and the decreased accuracy at intermediate points, typical of local techniques, have been proved to be smoothed for both LUP and HRBF

Organization of feed-forward loop motifs reveals architectural principles in natural and engineered networks.

Science.gov (United States)

Gorochowski, Thomas E; Grierson, Claire S; di Bernardo, Mario

2018-03-01

Network motifs are significantly overrepresented subgraphs that have been proposed as building blocks for natural and engineered networks. Detailed functional analysis has been performed for many types of motif in isolation, but less is known about how motifs work together to perform complex tasks. To address this issue, we measure the aggregation of network motifs via methods that extract precisely how these structures are connected. Applying this approach to a broad spectrum of networked systems and focusing on the widespread feed-forward loop motif, we uncover striking differences in motif organization. The types of connection are often highly constrained, differ between domains, and clearly capture architectural principles. We show how this information can be used to effectively predict functionally important nodes in the metabolic network of Escherichia coli . Our findings have implications for understanding how networked systems are constructed from motif parts and elucidate constraints that guide their evolution.

Hypothetical Pattern Recognition Design Using Multi-Layer Perceptorn Neural Network For Supervised Learning

Directory of Open Access Journals (Sweden)

Md. Abdullah-al-mamun

2015-08-01

Full Text Available Abstract Humans are capable to identifying diverse shape in the different pattern in the real world as effortless fashion due to their intelligence is grow since born with facing several learning process. Same way we can prepared an machine using human like brain called Artificial Neural Network that can be recognize different pattern from the real world object. Although the various techniques is exists to implementation the pattern recognition but recently the artificial neural network approaches have been giving the significant attention. Because the approached of artificial neural network is like a human brain that is learn from different observation and give a decision the previously learning rule. Over the 50 years research now a days pattern recognition for machine learning using artificial neural network got a significant achievement. For this reason many real world problem can be solve by modeling the pattern recognition process. The objective of this paper is to present the theoretical concept for pattern recognition design using Multi-Layer Perceptorn neural networkin the algorithm of artificial Intelligence as the best possible way of utilizing available resources to make a decision that can be a human like performance.

Neural networks, cellular automata, and robust approach applications for vertex localization in the opera target tracker detector

International Nuclear Information System (INIS)

Dmitrievskij, S.G.; Gornushkin, Yu.A.; Ososkov, G.A.

2005-01-01

A neural-network (NN) approach for neutrino interaction vertex reconstruction in the OPERA experiment with the help of the Target Tracker (TT) detector is described. A feed-forward NN with the standard back propagation option is used. The energy functional minimization of the network is performed by the method of conjugate gradients. Data preprocessing by means of cellular automaton algorithm is performed. The Hough transform is applied for muon track determination and the robust fitting method is used for shower axis reconstruction. A comparison of the proposed approach with earlier studies, based on the use of the neural network package SNNS, shows their similar performance. The further development of the approach is underway

Neural networks and particle physics

CERN Document Server

Peterson, Carsten

1993-01-01

1. Introduction : Structure of the Central Nervous System Generics2. Feed-forward networks, Perceptions, Function approximators3. Self-organisation, Feature Maps4. Feed-back Networks, The Hopfield model, Optimization problems, Feed-back, Networks, Deformable templates, Graph bisection

PERAMALAN KONSUMSI LISTRIK JANGKA PENDEK DENGAN ARIMA MUSIMAN GANDA DAN ELMAN-RECURRENT NEURAL NETWORK

Directory of Open Access Journals (Sweden)

Suhartono Suhartono

2009-07-01

Full Text Available Neural network (NN is one of many method used to predict the electricity consumption per hour in many countries. NN method which is used in many previous studies is Feed-Forward Neural Network (FFNN or Autoregressive Neural Network(AR-NN. AR-NN model is not able to capture and explain the effect of moving average (MA order on a time series of data. This research was conducted with the purpose of reviewing the application of other types of NN, that is Elman-Recurrent Neural Network (Elman-RNN which could explain MA order effect and compare the result of prediction accuracy with multiple seasonal ARIMA (Autoregressive Integrated Moving Average models. As a case study, we used data electricity consumption per hour in Mengare Gresik. Result of analysis showed that the best of double seasonal Arima models suited to short-term forecasting in the case study data is ARIMA([1,2,3,4,6,7,9,10,14,21,33],1,8(0,1,124 (1,1,0168. This model produces a white noise residuals, but it does not have a normal distribution due to suspected outlier. Outlier detection in iterative produce 14 innovation outliers. There are 4 inputs of Elman-RNN network that were examined and tested for forecasting the data, the input according to lag Arima, input such as lag Arima plus 14 dummy outlier, inputs are the lag-multiples of 24 up to lag 480, and the inputs are lag 1 and lag multiples of 24+1. All of four network uses one hidden layer with tangent sigmoid activation function and one output with a linear function. The result of comparative forecast accuracy through value of MAPE out-sample showed that the fourth networks, namely Elman-RNN (22, 3, 1, is the best model for forecasting electricity consumption per hour in short term in Mengare Gresik.

Radiation technology and feed production

International Nuclear Information System (INIS)

Ershov, B.G.

1986-01-01

The use of radiation technology to prepare feeds and feed additions for cattle of non-feed vegetable blends is considered.Physicochemical foundations of radiation-chemical processes, possibilities of the use of various radiation devices are given. Data on practical realization of the technology are presented and prospects of its introduction to solve the tasks put forward by the USSR program on feed production are analyzed

Precipitation Nowcast using Deep Recurrent Neural Network

Science.gov (United States)

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.

A one-layer recurrent neural network for constrained pseudoconvex optimization and its application for dynamic portfolio optimization.

Science.gov (United States)

Liu, Qingshan; Guo, Zhishan; Wang, Jun

2012-02-01

In this paper, a one-layer recurrent neural network is proposed for solving pseudoconvex optimization problems subject to linear equality and bound constraints. Compared with the existing neural networks for optimization (e.g., the projection neural networks), the proposed neural network is capable of solving more general pseudoconvex optimization problems with equality and bound constraints. Moreover, it is capable of solving constrained fractional programming problems as a special case. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed as long as the designed parameters in the model are larger than the derived lower bounds. Numerical examples with simulation results illustrate the effectiveness and characteristics of the proposed neural network. In addition, an application for dynamic portfolio optimization is discussed. Copyright © 2011 Elsevier Ltd. All rights reserved.

Neural Network Target Identification System for False Alarm Reduction

Science.gov (United States)

Ye, David; Edens, Weston; Lu, Thomas T.; Chao, Tien-Hsin

2009-01-01

A multi-stage automated target recognition (ATR) system has been designed to perform computer vision tasks with adequate proficiency in mimicking human vision. The system is able to detect, identify, and track targets of interest. Potential regions of interest (ROIs) are first identified by the detection stage using an Optimum Trade-off Maximum Average Correlation Height (OT-MACH) filter combined with a wavelet transform. False positives are then eliminated by the verification stage using feature extraction methods in conjunction with neural networks. Feature extraction transforms the ROIs using filtering and binning algorithms to create feature vectors. A feed forward back propagation neural network (NN) is then trained to classify each feature vector and remove false positives. This paper discusses the test of the system performance and parameter optimizations process which adapts the system to various targets and datasets. The test results show that the system was successful in substantially reducing the false positive rate when tested on a sonar image dataset.

The effect of structural design parameters on FPGA-based feed-forward space-time trellis coding-orthogonal frequency division multiplexing channel encoders

Science.gov (United States)

Passas, Georgios; Freear, Steven; Fawcett, Darren

2010-08-01

Orthogonal frequency division multiplexing (OFDM)-based feed-forward space-time trellis code (FFSTTC) encoders can be synthesised as very high speed integrated circuit hardware description language (VHDL) designs. Evaluation of their FPGA implementation can lead to conclusions that help a designer to decide the optimum implementation, given the encoder structural parameters. VLSI architectures based on 1-bit multipliers and look-up tables (LUTs) are compared in terms of FPGA slices and block RAMs (area), as well as in terms of minimum clock period (speed). Area and speed graphs versus encoder memory order are provided for quadrature phase shift keying (QPSK) and 8 phase shift keying (8-PSK) modulation and two transmit antennas, revealing best implementation under these conditions. The effect of number of modulation bits and transmit antennas on the encoder implementation complexity is also investigated.

Knowledge Based 3d Building Model Recognition Using Convolutional Neural Networks from LIDAR and Aerial Imageries

Science.gov (United States)

Alidoost, F.; Arefi, H.

2016-06-01

In recent years, with the development of the high resolution data acquisition technologies, many different approaches and algorithms have been presented to extract the accurate and timely updated 3D models of buildings as a key element of city structures for numerous applications in urban mapping. In this paper, a novel and model-based approach is proposed for automatic recognition of buildings' roof models such as flat, gable, hip, and pyramid hip roof models based on deep structures for hierarchical learning of features that are extracted from both LiDAR and aerial ortho-photos. The main steps of this approach include building segmentation, feature extraction and learning, and finally building roof labeling in a supervised pre-trained Convolutional Neural Network (CNN) framework to have an automatic recognition system for various types of buildings over an urban area. In this framework, the height information provides invariant geometric features for convolutional neural network to localize the boundary of each individual roofs. CNN is a kind of feed-forward neural network with the multilayer perceptron concept which consists of a number of convolutional and subsampling layers in an adaptable structure and it is widely used in pattern recognition and object detection application. Since the training dataset is a small library of labeled models for different shapes of roofs, the computation time of learning can be decreased significantly using the pre-trained models. The experimental results highlight the effectiveness of the deep learning approach to detect and extract the pattern of buildings' roofs automatically considering the complementary nature of height and RGB information.

Forward-bias diode parameters, electronic noise, and photoresponse of graphene/silicon Schottky junctions with an interfacial native oxide layer

Science.gov (United States)

An, Yanbin; Behnam, Ashkan; Pop, Eric; Bosman, Gijs; Ural, Ant

2015-09-01

Metal-semiconductor Schottky junction devices composed of chemical vapor deposition grown monolayer graphene on p-type silicon substrates are fabricated and characterized. Important diode parameters, such as the Schottky barrier height, ideality factor, and series resistance, are extracted from forward bias current-voltage characteristics using a previously established method modified to take into account the interfacial native oxide layer present at the graphene/silicon junction. It is found that the ideality factor can be substantially increased by the presence of the interfacial oxide layer. Furthermore, low frequency noise of graphene/silicon Schottky junctions under both forward and reverse bias is characterized. The noise is found to be 1/f dominated and the shot noise contribution is found to be negligible. The dependence of the 1/f noise on the forward and reverse current is also investigated. Finally, the photoresponse of graphene/silicon Schottky junctions is studied. The devices exhibit a peak responsivity of around 0.13 A/W and an external quantum efficiency higher than 25%. From the photoresponse and noise measurements, the bandwidth is extracted to be ˜1 kHz and the normalized detectivity is calculated to be 1.2 ×109 cm Hz1/2 W-1. These results provide important insights for the future integration of graphene with silicon device technology.

Physical Layer Security Using Two-Path Successive Relaying

Directory of Open Access Journals (Sweden)

Qian Yu Liau

2016-06-01

Full Text Available Relaying is one of the useful techniques to enhance wireless physical-layer security. Existing literature shows that employing full-duplex relay instead of conventional half-duplex relay improves secrecy capacity and secrecy outage probability, but this is at the price of sophisticated implementation. As an alternative, two-path successive relaying has been proposed to emulate operation of full-duplex relay by scheduling a pair of half-duplex relays to assist the source transmission alternately. However, the performance of two-path successive relaying in secrecy communication remains unexplored. This paper proposes a secrecy two-path successive relaying protocol for a scenario with one source, one destination and two half-duplex relays. The relays operate alternately in a time division mode to forward messages continuously from source to destination in the presence of an eavesdropper. Analytical results reveal that the use of two half-duplex relays in the proposed scheme contributes towards a quadratically lower probability of interception compared to full-duplex relaying. Numerical simulations show that the proposed protocol achieves the ergodic achievable secrecy rate of full-duplex relaying while delivering the lowest probability of interception and secrecy outage probability compared to the existing half duplex relaying, full duplex relaying and full duplex jamming schemes.

Prediction of hot deformation behavior of high phosphorus steel using artificial neural network

Science.gov (United States)

Singh, Kanchan; Rajput, S. K.; Soota, T.; Verma, Vijay; Singh, Dharmendra

2018-03-01

To predict the hot deformation behavior of high phosphorus steel, the hot compression experiments were performed with the help of thermo-mechanical simulator Gleeble® 3800 in the temperatures ranging from 750 °C to 1050 °C and strain rates of 0.001 s-1, 0.01 s-1, 0.1 s-1, 0.5 s-1, 1.0 s-1 and 10 s-1. The experimental stress-strain data are employed to develop artificial neural network (ANN) model and their predictability. Using different combination of temperature, strain and strain rate as a input parameter and obtained experimental stress as a target, a multi-layer ANN model based on feed-forward back-propagation algorithm is trained, to predict the flow stress for a given processing condition. The relative error between predicted and experimental stress are in the range of ±3.5%, whereas the correlation coefficient (R2) of training and testing data are 0.99986 and 0.99999 respectively. This shows that a well-trained ANN model has excellent capability to predict the hot deformation behavior of materials. Comparative study shows quite good agreement of predicted and experimental values.

Entry, Descent and Landing Systems Analysis Study: Phase 2 Report on Exploration Feed-Forward Systems

Science.gov (United States)

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.;

Prediction of activity coefficients at infinite dilution for organic solutes in ionic liquids by artificial neural network

Energy Technology Data Exchange (ETDEWEB)

Nami, Faezeh [Department of Chemistry, Shahid Beheshti University, G.C., Evin-Tehran 1983963113 (Iran, Islamic Republic of); Deyhimi, Farzad, E-mail: f-deyhimi@sbu.ac.i [Department of Chemistry, Shahid Beheshti University, G.C., Evin-Tehran 1983963113 (Iran, Islamic Republic of)

2011-01-15

To our knowledge, this work illustrates for the first time the ability of artificial neural network (ANN) to predict activity coefficients at infinite dilution for organic solutes in ionic liquids (ILs). Activity coefficient at infinite dilution ({gamma}{sup {infinity}}) is a useful parameter which can be used for the selection of effective solvent in the separation processes. Using a multi-layer feed-forward network with Levenberg-Marquardt optimization algorithm, the resulting ANN model generated activity coefficient at infinite dilution data over a temperature range of 298 to 363 K. The unavailable input data concerning softness (S) of organic compounds (solutes) and dipole moment ({mu}) of ionic liquids were calculated using GAMESS suites of quantum chemistry programs. The resulting ANN model and its validation are based on the investigation of up to 24 structurally different organic compounds (alkanes, alkenes, alkynes, cycloalkanes, aromatics, and alcohols) in 16 common imidazolium-based ionic liquids, at different temperatures within the range of 298 to 363 K (i.e. a total number of 914 {gamma}{sub Solute}{sup {infinity}}for each IL data point). The results show a satisfactory agreement between the predicted ANN and experimental data, where, the root mean square error (RMSE) and the determination coefficient (R{sup 2}) of the designed neural network were found to be 0.103, 0.996 for training data and 0.128, 0.994 for testing data, respectively.

Prediction of activity coefficients at infinite dilution for organic solutes in ionic liquids by artificial neural network

International Nuclear Information System (INIS)

Nami, Faezeh; Deyhimi, Farzad

2011-01-01

To our knowledge, this work illustrates for the first time the ability of artificial neural network (ANN) to predict activity coefficients at infinite dilution for organic solutes in ionic liquids (ILs). Activity coefficient at infinite dilution (γ ∞ ) is a useful parameter which can be used for the selection of effective solvent in the separation processes. Using a multi-layer feed-forward network with Levenberg-Marquardt optimization algorithm, the resulting ANN model generated activity coefficient at infinite dilution data over a temperature range of 298 to 363 K. The unavailable input data concerning softness (S) of organic compounds (solutes) and dipole moment (μ) of ionic liquids were calculated using GAMESS suites of quantum chemistry programs. The resulting ANN model and its validation are based on the investigation of up to 24 structurally different organic compounds (alkanes, alkenes, alkynes, cycloalkanes, aromatics, and alcohols) in 16 common imidazolium-based ionic liquids, at different temperatures within the range of 298 to 363 K (i.e. a total number of 914 γ Solute ∞ for each IL data point). The results show a satisfactory agreement between the predicted ANN and experimental data, where, the root mean square error (RMSE) and the determination coefficient (R 2 ) of the designed neural network were found to be 0.103, 0.996 for training data and 0.128, 0.994 for testing data, respectively.

Predictive zero-dimensional combustion model for DI diesel engine feed-forward control

International Nuclear Information System (INIS)

Catania, Andrea Emilio; Finesso, Roberto; Spessa, Ezio

2011-01-01

Highlights: → Zero-dimensional low-throughput combustion model for real-time control in diesel engine applications. → Feed-forward control of MFB50, p max and IMEP in both conventional and PCCI combustion modes. → Capability of resolving the contribution to HRR of each injection pulse in multiple injection schedule. → Ignition delay and model parameters estimated through physically consistent and easy-to-tune correlations. - Abstract: An innovative zero-dimensional predictive combustion model has been developed for the estimation of HRR (heat release rate) and in-cylinder pressure traces. This model has been assessed and applied to conventional and PCCI (premixed charge compression ignition) DI diesel engines for model-based feed-forward control purposes. The injection rate profile is calculated on the basis of the injected fuel quantities and on the injection parameters, such as SOI (start of injection), ET (energizing time), and DT (dwell time), taking the injector NOD (nozzle opening delay) and NCD (nozzle closure delay) into account. The injection rate profile in turn allows the released chemical energy Q ch to be estimated. The approach starts from the assumption that, at each time instant, the HRR is proportional to the energy associated with the accumulated fuel mass in the combustion chamber. The main novelties of the proposed approach consist of the method that is adopted to estimate the fuel ignition delay and of injection rate splitting for HRR estimation. The procedure allows an accurate calculation to be made of the different combustion parameters that are important for engine calibration, such as SOC (start of combustion) and MFB50 (50% of fuel mass fraction burned angle). On the basis of an estimation of the fuel released chemical energy, of the heat globally exchanged from the charge with the walls and of the energy associated with the fuel evaporation, the charge net energy is calculated, for a subsequent evaluation of the in

Deep Super Learner: A Deep Ensemble for Classification Problems

OpenAIRE

Young, Steven; Abdou, Tamer; Bener, Ayse

2018-01-01

Deep learning has become very popular for tasks such as predictive modeling and pattern recognition in handling big data. Deep learning is a powerful machine learning method that extracts lower level features and feeds them forward for the next layer to identify higher level features that improve performance. However, deep neural networks have drawbacks, which include many hyper-parameters and infinite architectures, opaqueness into results, and relatively slower convergence on smaller datase...

Simulation study on control of spill structure of slow extracted beam from a medical synchrotron with feed-forward and feedback using a fast quadruple magnet and RF-knockout system

Energy Technology Data Exchange (ETDEWEB)

Muraoka, Ryo; Nakanishi, Tetsuya, E-mail: nakanishi.tetsuya@nihon-u.ac.jp

2017-02-21

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.

One Year in the Lower St. Lawrence Estuary: Feeding Niche Separation of Two Co-existing Krill Species

Science.gov (United States)

Winkler, G.; Cabrol, J.; Sage, R.; Nozais, C.; Tremblay, R.; Starr, M.

2016-02-01

The lower St. Lawrence estuary (LSLE) is influenced by river discharge and saltwater inflow. Together with arctic water inflow and ice cover in winter a strong stratification occurs resulting in a cold intermediate layer (CIL) from spring to autumn. This stratification provides thermal habitats. Here, we focus on two krill species Thysanoessa raschii and Meganyctiphanes norvegica that aggregate in the CIL and the warmer deep water layer, respectively. Both species are known to migrate into the surface layer to feed and thus transfering energy through the food web by linking lower with higher trophic levels. However, their specific feeding biology and trophic interactions are poorly understood. We tested the following hypotheses: (1) the diets vary throughout the season depending on food availability, (2) similar to thermal habitat separation, trophic niche separation between T. raschii and M. norvegica occurs, characterized by herbivory in T. raschii and carnivory in M. norvegica. Trophic position and feeding behavior of theses krill populations were monitored throughout one year 2014-2015 using a stable isotope approach. The two species showed a seasonal shift in their trophic position being on a higher trophic level in summer than in spring and autumn, which did not correspond to phytoplankton or zooplankton availability. Within the trophic space of carbon and nitrogen stable isotopes M. norvegica showed a relatively stable position, whereas T. raschii covered a much larger space throughout the year. M. norvegica was always positioned at a higher trophic level than T. raschii. Results of a stable isotope mixing model (SIAR) revealed 50% phytoplankton and 50% copepods in the diet of M. norvegica, while T. raschii showed a higher proportion of ca. 70% phytoplankton in its diet. Both species exploited several trophic levels, but in different proportions, thereby minimizing diet overlap, suggesting a further mechanism to enhance stable co-existence of these krill

Forward Osmosis System And Process

KAUST Repository

Duan, Jintang

2013-08-22

A forward osmosis fluid purification system includes a cross-flow membrane module with a membrane, a channel on each side of the membrane which allows a feed solution and a draw solution to flow through separately, a feed side, a draw side including a draw solute, where the draw solute includes an aryl sulfonate salt. The system can be used in a process to extract water from impure water, such as wastewater or seawater. The purified water can be applied to arid land.

Forward Osmosis System And Process

KAUST Repository

Duan, Jintang

2013-01-01

A forward osmosis fluid purification system includes a cross-flow membrane module with a membrane, a channel on each side of the membrane which allows a feed solution and a draw solution to flow through separately, a feed side, a draw side including a draw solute, where the draw solute includes an aryl sulfonate salt. The system can be used in a process to extract water from impure water, such as wastewater or seawater. The purified water can be applied to arid land.

Improve 3D laser scanner measurements accuracy using a FFBP neural network with Widrow-Hoff weight/bias learning function

Science.gov (United States)

Rodríguez-Quiñonez, J. C.; Sergiyenko, O.; Hernandez-Balbuena, D.; Rivas-Lopez, M.; Flores-Fuentes, W.; Basaca-Preciado, L. C.

2014-12-01

Many laser scanners depend on their mechanical construction to guarantee their measurements accuracy, however, the current computational technologies allow us to improve these measurements by mathematical methods implemented in neural networks. In this article we are going to introduce the current laser scanner technologies, give a description of our 3D laser scanner and adjust their measurement error by a previously trained feed forward back propagation (FFBP) neural network with a Widrow-Hoff weight/bias learning function. A comparative analysis with other learning functions such as the Kohonen algorithm and gradient descendent with momentum algorithm is presented. Finally, computational simulations are conducted to verify the performance and method uncertainty in the proposed system.

Palatability of two artificial feeds for reindeer

Directory of Open Access Journals (Sweden)

Arne Rognmo

1990-09-01

Full Text Available Two groups of 15 reindeer were used to test the palatability of two artificial diets. None of the animals had experienced the diets before. Trials were carried out from April to mid May. Each group of animals was kept in a separate corral (600 sq. meters. Both groups were fed lichens for three days befort trials began. Then they were offered a concentrate feed (RF-80 or «Mill Waste Product» (MWP ad libitum. Both groups ate little or nothing for the first three days of the trial and so lichens were mixed with the two experimental feeds. The mean voluntary food intake of the RF-80-group increased from 0.8 Kg/day/animal to 1.8 Kg/day/animal after three weeks. A mixed feed, RF-80/lichen, was only used the first day for animals in the RF-80 group. Reindeer refused to eat MWP for twelve days despite mixing it with lichens. They were then offered RF-80 ad lib. without a mixture of lichens. The mean voluntary intake of these animals increased from 1.3 Kg RF-80/day/animal on day 13 to 2.3 Kg/day/animal by day 26. Two calves in the MWP-group got diarrhoea after refeeding with RF-80.

Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets

Directory of Open Access Journals (Sweden)

Romanuke Vadim V.

2017-12-01

Full Text Available A technique of DropOut for preventing overfitting of convolutional neural networks for image classification is considered in the paper. The goal is to find a rule of rationally allocating DropOut layers of 0.5 rate to maximise performance. To achieve the goal, two common network architectures are used having either 4 or 5 convolutional layers. Benchmarking is fulfilled with CIFAR-10, EEACL26, and NORB datasets. Initially, series of all admissible versions for allocation of DropOut layers are generated. After the performance against the series is evaluated, normalized and averaged, the compromising rule is found. It consists in non-compactly inserting a few DropOut layers before the last convolutional layer. It is likely that the scheme with two or more DropOut layers fits networks of many convolutional layers for image classification problems with a plenty of features. Such a scheme shall also fit simple datasets prone to overfitting. In fact, the rule “prefers” a fewer number of DropOut layers. The exemplary gain of the rule application is roughly between 10 % and 50 %.

Well-constructed cellulose acetate membranes for forward osmosis: Minimized internal concentration polarization with an ultra-thin selective layer

KAUST Repository

Zhang, Sui

2010-09-01

The design and engineering of membrane structure that produces low salt leakage and minimized internal concentration polarization (ICP) in forward osmosis (FO) processes have been explored in this work. The fundamentals of phase inversion of cellulose acetate (CA) regarding the formation of an ultra-thin selective layer at the bottom interface of polymer and casting substrate were investigated by using substrates with different hydrophilicity. An in-depth understanding of membrane structure and pore size distribution has been elucidated with field emission scanning electronic microscopy (FESEM) and positron annihilation spectroscopy (PAS). A double dense-layer structure is formed when glass plate is used as the casting substrate and water as the coagulant. The thickness of the ultra-thin bottom layer resulted from hydrophilic-hydrophilic interaction is identified to be around 95nm, while a fully porous, open-cell structure is formed in the middle support layer due to spinodal decomposition. Consequently, the membrane shows low salt leakage with mitigated ICP in the FO process for seawater desalination. The structural parameter (St) of the membrane is analyzed by modeling water flux using the theory that considers both external concentration polarization (ECP) and ICP, and the St value of the double dense-layer membrane is much smaller than those reported in literatures. Furthermore, the effects of an intermediate immersion into a solvent/water mixed bath prior to complete immersion in water on membrane formation have been studied. The resultant membranes may have a single dense layer with an even lower St value. A comparison of fouling behavior in a simple FO-membrane bioreactor (MBR) system is evaluated for these two types of membranes. The double dense-layer membrane shows a less fouling propensity. This study may help pave the way to improve the membrane design for new-generation FO membranes. © 2010 Elsevier B.V.

Usage of neural network to predict aluminium oxide layer thickness.

Science.gov (United States)

Michal, Peter; Vagaská, Alena; Gombár, Miroslav; Kmec, Ján; Spišák, Emil; Kučerka, Daniel

2015-01-01

This paper shows an influence of chemical composition of used electrolyte, such as amount of sulphuric acid in electrolyte, amount of aluminium cations in electrolyte and amount of oxalic acid in electrolyte, and operating parameters of process of anodic oxidation of aluminium such as the temperature of electrolyte, anodizing time, and voltage applied during anodizing process. The paper shows the influence of those parameters on the resulting thickness of aluminium oxide layer. The impact of these variables is shown by using central composite design of experiment for six factors (amount of sulphuric acid, amount of oxalic acid, amount of aluminium cations, electrolyte temperature, anodizing time, and applied voltage) and by usage of the cubic neural unit with Levenberg-Marquardt algorithm during the results evaluation. The paper also deals with current densities of 1 A · dm(-2) and 3 A · dm(-2) for creating aluminium oxide layer.

Usage of Neural Network to Predict Aluminium Oxide Layer Thickness

Directory of Open Access Journals (Sweden)

Peter Michal

2015-01-01

Full Text Available This paper shows an influence of chemical composition of used electrolyte, such as amount of sulphuric acid in electrolyte, amount of aluminium cations in electrolyte and amount of oxalic acid in electrolyte, and operating parameters of process of anodic oxidation of aluminium such as the temperature of electrolyte, anodizing time, and voltage applied during anodizing process. The paper shows the influence of those parameters on the resulting thickness of aluminium oxide layer. The impact of these variables is shown by using central composite design of experiment for six factors (amount of sulphuric acid, amount of oxalic acid, amount of aluminium cations, electrolyte temperature, anodizing time, and applied voltage and by usage of the cubic neural unit with Levenberg-Marquardt algorithm during the results evaluation. The paper also deals with current densities of 1 A·dm−2 and 3 A·dm−2 for creating aluminium oxide layer.

Reconstruction of sub-surface archaeological remains from magnetic data using neural computing.

Science.gov (United States)

Bescoby, D. J.; Cawley, G. C.; Chroston, P. N.

2003-04-01

The remains of a former Roman colonial settlement, once part of the classical city of Butrint in southern Albania have been the subject of a high resolution magnetic survey using a caesium-vapour magnetometer. The survey revealed the surviving remains of an extensive planned settlement and a number of outlying buildings, today buried beneath over 0.5 m of alluvial deposits. The aim of the current research is to derive a sub-surface model from the magnetic survey measurements, allowing an enhanced archaeological interpretation of the data. Neural computing techniques are used to perform the non-linear mapping between magnetic data and corresponding sub-surface model parameters. The adoption of neural computing paradigms potentially holds several advantages over other modelling techniques, allowing fast solutions for complex data, while having a high tolerance to noise. A multi-layer perceptron network with a feed-forward architecture is trained to estimate the shape and burial depth of wall foundations using a series of representative models as training data. Parameters used to forward model the training data sets are derived from a number of trial trench excavations targeted over features identified by the magnetic survey. The training of the network was optimized by first applying it to synthetic test data of known source parameters. Pre-processing of the network input data, including the use of a rotationally invariant transform, enhanced network performance and the efficiency of the training data. The approach provides good results when applied to real magnetic data, accurately predicting the depths and layout of wall foundations within the former settlement, verified by subsequent excavation. The resulting sub-surface model is derived from the averaged outputs of a ‘committee’ of five networks, trained with individualized training sets. Fuzzy logic inference has also been used to combine individual network outputs through correlation with data from a second

Preliminary results of neural networks and zernike polynomials for classification of videokeratography maps.

Science.gov (United States)

Carvalho, Luis Alberto

2005-02-01

Our main goal in this work was to develop an artificial neural network (NN) that could classify specific types of corneal shapes using Zernike coefficients as input. Other authors have implemented successful NN systems in the past and have demonstrated their efficiency using different parameters. Our claim is that, given the increasing popularity of Zernike polynomials among the eye care community, this may be an interesting choice to add complementing value and precision to existing methods. By using a simple and well-documented corneal surface representation scheme, which relies on corneal elevation information, one can generate simple NN input parameters that are independent of curvature definition and that are also efficient. We have used the Matlab Neural Network Toolbox (MathWorks, Natick, MA) to implement a three-layer feed-forward NN with 15 inputs and 5 outputs. A database from an EyeSys System 2000 (EyeSys Vision, Houston, TX) videokeratograph installed at the Escola Paulista de Medicina-Sao Paulo was used. This database contained an unknown number of corneal types. From this database, two specialists selected 80 corneas that could be clearly classified into five distinct categories: (1) normal, (2) with-the-rule astigmatism, (3) against-the-rule astigmatism, (4) keratoconus, and (5) post-laser-assisted in situ keratomileusis. The corneal height (SAG) information of the 80 data files was fit with the first 15 Vision Science and it Applications (VSIA) standard Zernike coefficients, which were individually used to feed the 15 neurons of the input layer. The five output neurons were associated with the five typical corneal shapes. A group of 40 cases was randomly selected from the larger group of 80 corneas and used as the training set. The NN responses were statistically analyzed in terms of sensitivity [true positive/(true positive + false negative)], specificity [true negative/(true negative + false positive)], and precision [(true positive + true

A Novel Feed-Forward Modeling System Leads to Sustained Improvements in Attention and Academic Performance.

Science.gov (United States)

McDermott, Ashley F; Rose, Maya; Norris, Troy; Gordon, Eric

2016-01-28

This study tested a novel feed-forward modeling (FFM) system as a nonpharmacological intervention for the treatment of ADHD children and the training of cognitive skills that improve academic performance. This study implemented a randomized, controlled, parallel design comparing this FFM with a nonpharmacological community care intervention. Improvements were measured on parent- and clinician-rated scales of ADHD symptomatology and on academic performance tests completed by the participant. Participants were followed for 3 months after training. Participants in the FFM training group showed significant improvements in ADHD symptomatology and academic performance, while the control group did not. Improvements from FFM were sustained 3 months later. The FFM appeared to be an effective intervention for the treatment of ADHD and improving academic performance. This FFM training intervention shows promise as a first-line treatment for ADHD while improving academic performance. © The Author(s) 2016.

Forward Osmosis in Wastewater Treatment Processes

DEFF Research Database (Denmark)

Korenak, Jasmina; Basu, Subhankar; Balakrishnan, Malini

2017-01-01

In recent years, membrane technology has been widely used in wastewater treatment and water purification. Membrane technology is simple to operate and produces very high quality water for human consumption and industrial purposes. One of the promising technologies for water and wastewater treatment...... is the application of forward osmosis. Essentially, forward osmosis is a process in which water is driven through a semipermeable membrane from a feed solution to a draw solution due to the osmotic pressure gradient across the membrane. The immediate advantage over existing pressure driven membrane technologies...... briefly review some of the applications within water purification and new developments in forward osmosis membrane fabrication....

A comparative study of wire feeding and powder feeding in direct diode laser deposition for rapid prototyping

Energy Technology Data Exchange (ETDEWEB)

Syed, Waheed Ul Haq [Laser Processing Research Centre, School of Mechanical Aerospace and Civil Engineering, Sackville Street Building, University of Manchester, P.O. Box 88, Manchester M60 1QD (United Kingdom)]. E-mail: w.syed@postgrad.manchester.ac.uk; Pinkerton, Andrew J. [Laser Processing Research Centre, School of Mechanical Aerospace and Civil Engineering, Sackville Street Building, University of Manchester, P.O. Box 88, Manchester M60 1QD (United Kingdom); Li Lin [Laser Processing Research Centre, School of Mechanical Aerospace and Civil Engineering, Sackville Street Building, University of Manchester, P.O. Box 88, Manchester M60 1QD (United Kingdom)

2005-07-15

Metal powder feeding has been used widely in various rapid prototyping and tooling processes such as direct laser deposition (DLD) and layered engineered net shaping (LENS) to achieve near net shape accuracy. Although powder recycling has been practiced, the material usage efficiency has been very low (normally below 30%). This study compares the process characteristics, advantages and disadvantages of wire- and powder-feed DLD. A 1.5 kW diode laser is used to build multiple layer parts, which are compared and analysed in terms of surface finish, microstructure and deposition efficiency. Scanning electron microscopy (SEM), X-ray diffraction and optical microscopy are used for the material characterisation. The microstructure of samples from both the methods is similar, with some porosity found in powder-feed components, but the surface finish and material usage efficiency is better for wire-feed samples. The deposition angle is found to be critical in the case of wire feeding and the characteristics of different feed angles are explored. Possible reasons for the different characteristics of the two deposition techniques are discussed.

Pattern recognition and data mining software based on artificial neural networks applied to proton transfer in aqueous environments

International Nuclear Information System (INIS)

Tahat Amani; Marti Jordi; Khwaldeh Ali; Tahat Kaher

2014-01-01

In computational physics proton transfer phenomena could be viewed as pattern classification problems based on a set of input features allowing classification of the proton motion into two categories: transfer ‘occurred’ and transfer ‘not occurred’. The goal of this paper is to evaluate the use of artificial neural networks in the classification of proton transfer events, based on the feed-forward back propagation neural network, used as a classifier to distinguish between the two transfer cases. In this paper, we use a new developed data mining and pattern recognition tool for automating, controlling, and drawing charts of the output data of an Empirical Valence Bond existing code. The study analyzes the need for pattern recognition in aqueous proton transfer processes and how the learning approach in error back propagation (multilayer perceptron algorithms) could be satisfactorily employed in the present case. We present a tool for pattern recognition and validate the code including a real physical case study. The results of applying the artificial neural networks methodology to crowd patterns based upon selected physical properties (e.g., temperature, density) show the abilities of the network to learn proton transfer patterns corresponding to properties of the aqueous environments, which is in turn proved to be fully compatible with previous proton transfer studies. (condensed matter: structural, mechanical, and thermal properties)

Distributed Recurrent Neural Forward Models with Neural Control for Complex Locomotion in Walking Robots

DEFF Research Database (Denmark)

Dasgupta, Sakyasingha; Goldschmidt, Dennis; Wörgötter, Florentin

2015-01-01

here, an artificial bio-inspired walking system which effectively combines biomechanics (in terms of the body and leg structures) with the underlying neural mechanisms. The neural mechanisms consist of (1) central pattern generator based control for generating basic rhythmic patterns and coordinated......Walking animals, like stick insects, cockroaches or ants, demonstrate a fascinating range of locomotive abilities and complex behaviors. The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental...... conditions, like uneven terrains, gaps, obstacles etc. Biological study has revealed that such complex behaviors are a result of a combination of biomechanics and neural mechanism thus representing the true nature of embodied interactions. While the biomechanics helps maintain flexibility and sustain...

A comparative study of two neural networks for document retrieval

International Nuclear Information System (INIS)

Hui, S.C.; Goh, A.

1997-01-01

In recent years there has been specific interest in adopting advanced computer techniques in the field of document retrieval. This interest is generated by the fact that classical methods such as the Boolean search, the vector space model or even probabilistic retrieval cannot handle the increasing demands of end-users in satisfying their needs. The most recent attempt is the application of the neural network paradigm as a means of providing end-users with a more powerful retrieval mechanism. Neural networks are not only good pattern matchers but also highly versatile and adaptable. In this paper, we demonstrate how to apply two neural networks, namely Adaptive Resonance Theory and Fuzzy Kohonen Neural Network, for document retrieval. In addition, a comparison of these two neural networks based on performance is also given

Embedding the dynamics of a single delay system into a feed-forward ring.

Science.gov (United States)

Klinshov, Vladimir; Shchapin, Dmitry; Yanchuk, Serhiy; Wolfrum, Matthias; D'Huys, Otti; Nekorkin, Vladimir

2017-10-01

We investigate the relation between the dynamics of a single oscillator with delayed self-feedback and a feed-forward ring of such oscillators, where each unit is coupled to its next neighbor in the same way as in the self-feedback case. We show that periodic solutions of the delayed oscillator give rise to families of rotating waves with different wave numbers in the corresponding ring. In particular, if for the single oscillator the periodic solution is resonant to the delay, it can be embedded into a ring with instantaneous couplings. We discover several cases where the stability of a periodic solution for the single unit can be related to the stability of the corresponding rotating wave in the ring. As a specific example, we demonstrate how the complex bifurcation scenario of simultaneously emerging multijittering solutions can be transferred from a single oscillator with delayed pulse feedback to multijittering rotating waves in a sufficiently large ring of oscillators with instantaneous pulse coupling. Finally, we present an experimental realization of this dynamical phenomenon in a system of coupled electronic circuits of FitzHugh-Nagumo type.

Direct and inverse neural networks modelling applied to study the influence of the gas diffusion layer properties on PBI-based PEM fuel cells

Energy Technology Data Exchange (ETDEWEB)

Lobato, Justo; Canizares, Pablo; Rodrigo, Manuel A.; Linares, Jose J. [Chemical Engineering Department, University of Castilla-La Mancha, Campus Universitario s/n, 13004 Ciudad Real (Spain); Piuleac, Ciprian-George; Curteanu, Silvia [Faculty of Chemical Engineering and Environmental Protection, Department of Chemical Engineering, ' ' Gh. Asachi' ' Technical University Iasi Bd. D. Mangeron, No. 71A, 700050 IASI (Romania)

2010-08-15

This article shows the application of a very useful mathematical tool, artificial neural networks, to predict the fuel cells results (the value of the tortuosity and the cell voltage, at a given current density, and therefore, the power) on the basis of several properties that define a Gas Diffusion Layer: Teflon content, air permeability, porosity, mean pore size, hydrophobia level. Four neural networks types (multilayer perceptron, generalized feedforward network, modular neural network, and Jordan-Elman neural network) have been applied, with a good fitting between the predicted and the experimental values in the polarization curves. A simple feedforward neural network with one hidden layer proved to be an accurate model with good generalization capability (error about 1% in the validation phase). A procedure based on inverse neural network modelling was able to determine, with small errors, the initial conditions leading to imposed values for characteristics of the fuel cell. In addition, the use of this tool has been proved to be very attractive in order to predict the cell performance, and more interestingly, the influence of the properties of the gas diffusion layer on the cell performance, allowing possible enhancements of this material by changing some of its properties. (author)

Feed water pre-heater with two steam spaces

International Nuclear Information System (INIS)

Tratz, H.; Kelp, F.; Netsch, E.

1976-01-01

A feed water pre-heater for the two stage heating of feed water by condensing steam, having a low installed height is described, which can be installed in the steam ducts of turbines of large output, as in LWRs in nuclear power stations. The inner steam space is closed on one side by the water vessel, while the tubes of the inner steam space go straight from the water vessel, and the tubes of the outer steam space are bent into a U shape and open out into the water vessel. The two-stage preheater is thus surrounded by feedwater in two ways. (UWI) [de

Predictive zero-dimensional combustion model for DI diesel engine feed-forward control

Energy Technology Data Exchange (ETDEWEB)

Catania, Andrea Emilio; Finesso, Roberto [IC Engines Advanced Laboratory, Politecnico di Torino, c.so Duca degli Abruzzi 24, 10129 Torino (Italy); Spessa, Ezio, E-mail: ezio.spessa@polito.it [IC Engines Advanced Laboratory, Politecnico di Torino, c.so Duca degli Abruzzi 24, 10129 Torino (Italy)

2011-09-15

Highlights: {yields} Zero-dimensional low-throughput combustion model for real-time control in diesel engine applications. {yields} Feed-forward control of MFB50, p{sub max} and IMEP in both conventional and PCCI combustion modes. {yields} Capability of resolving the contribution to HRR of each injection pulse in multiple injection schedule. {yields} Ignition delay and model parameters estimated through physically consistent and easy-to-tune correlations. - Abstract: An innovative zero-dimensional predictive combustion model has been developed for the estimation of HRR (heat release rate) and in-cylinder pressure traces. This model has been assessed and applied to conventional and PCCI (premixed charge compression ignition) DI diesel engines for model-based feed-forward control purposes. The injection rate profile is calculated on the basis of the injected fuel quantities and on the injection parameters, such as SOI (start of injection), ET (energizing time), and DT (dwell time), taking the injector NOD (nozzle opening delay) and NCD (nozzle closure delay) into account. The injection rate profile in turn allows the released chemical energy Q{sub ch} to be estimated. The approach starts from the assumption that, at each time instant, the HRR is proportional to the energy associated with the accumulated fuel mass in the combustion chamber. The main novelties of the proposed approach consist of the method that is adopted to estimate the fuel ignition delay and of injection rate splitting for HRR estimation. The procedure allows an accurate calculation to be made of the different combustion parameters that are important for engine calibration, such as SOC (start of combustion) and MFB50 (50% of fuel mass fraction burned angle). On the basis of an estimation of the fuel released chemical energy, of the heat globally exchanged from the charge with the walls and of the energy associated with the fuel evaporation, the charge net energy is calculated, for a subsequent

Dispersion compensation of fiber optic communication system with direct detection using artificial neural networks (ANNs)

Science.gov (United States)

Maghrabi, Mahmoud M. T.; Kumar, Shiva; Bakr, Mohamed H.

2018-02-01

This work introduces a powerful digital nonlinear feed-forward equalizer (NFFE), exploiting multilayer artificial neural network (ANN). It mitigates impairments of optical communication systems arising due to the nonlinearity introduced by direct photo-detection. In a direct detection system, the detection process is nonlinear due to the fact that the photo-current is proportional to the absolute square of the electric field intensity. The proposed equalizer provides the most efficient computational cost with high equalization performance. Its performance is comparable to the benchmark compensation performance achieved by maximum-likelihood sequence estimator. The equalizer trains an ANN to act as a nonlinear filter whose impulse response removes the intersymbol interference (ISI) distortions of the optical channel. Owing to the proposed extensive training of the equalizer, it achieves the ultimate performance limit of any feed-forward equalizer (FFE). The performance and efficiency of the equalizer is investigated by applying it to various practical short-reach fiber optic communication system scenarios. These scenarios are extracted from practical metro/media access networks and data center applications. The obtained results show that the ANN-NFFE compensates for the received BER degradation and significantly increases the tolerance to the chromatic dispersion distortion.

Forward Osmosis in Wastewater Treatment Processes.

Science.gov (United States)

Korenak, Jasmina; Basu, Subhankar; Balakrishnan, Malini; Hélix-Nielsen, Claus; Petrinic, Irena

2017-01-01

In recent years, membrane technology has been widely used in wastewater treatment and water purification. Membrane technology is simple to operate and produces very high quality water for human consumption and industrial purposes. One of the promising technologies for water and wastewater treatment is the application of forward osmosis. Essentially, forward osmosis is a process in which water is driven through a semipermeable membrane from a feed solution to a draw solution due to the osmotic pressure gradient across the membrane. The immediate advantage over existing pressure driven membrane technologies is that the forward osmosis process per se eliminates the need for operation with high hydraulic pressure and forward osmosis has low fouling tendency. Hence, it provides an opportunity for saving energy and membrane replacement cost. However, there are many limitations that still need to be addressed. Here we briefly review some of the applications within water purification and new developments in forward osmosis membrane fabrication.

Estudio de dos estructuras neuronales feedforward para la compresión de imágenes digitales

Directory of Open Access Journals (Sweden)

Andrés Eduardo Gaona Barrera

2012-01-01

Full Text Available This paper shows and explains the process implemented for the development of feed- forward neural networks with the aim of compress digital image color. It sets oul sorne traditional techniques and develops tvvo topologies to implement feed forward. During the development of networks, fue items that are considered: number of layers, number of neurons, image type, size and munber of blocks to train, to optimize performance during final training. It also discusses the standard quality of the image obtained, as peak signal noise relation (PSNR and cornpression, which typically obtain values above 35dB in terms of PSNR and 2 bits per pixel in gray or 3 bpp color images, with maximum time of 3 seconds for images less than I mega pixel. Finally out some dravvbacks and presents conclusions of this type of compression.

Learning of N-layers neural network

Directory of Open Access Journals (Sweden)

Vladimír Konečný

2005-01-01

Full Text Available In the last decade we can observe increasing number of applications based on the Artificial Intelligence that are designed to solve problems from different areas of human activity. The reason why there is so much interest in these technologies is that the classical way of solutions does not exist or these technologies are not suitable because of their robustness. They are often used in applications like Business Intelligence that enable to obtain useful information for high-quality decision-making and to increase competitive advantage.One of the most widespread tools for the Artificial Intelligence are the artificial neural networks. Their high advantage is relative simplicity and the possibility of self-learning based on set of pattern situations.For the learning phase is the most commonly used algorithm back-propagation error (BPE. The base of BPE is the method minima of error function representing the sum of squared errors on outputs of neural net, for all patterns of the learning set. However, while performing BPE and in the first usage, we can find out that it is necessary to complete the handling of the learning factor by suitable method. The stability of the learning process and the rate of convergence depend on the selected method. In the article there are derived two functions: one function for the learning process management by the relative great error function value and the second function when the value of error function approximates to global minimum.The aim of the article is to introduce the BPE algorithm in compact matrix form for multilayer neural networks, the derivation of the learning factor handling method and the presentation of the results.

Simultaneously precise frequency transfer and time synchronization using feed-forward compensation technique via 120 km fiber link.

Science.gov (United States)

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.

Modeling Distillation Column Using ARX Model Structure and Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Reza Pirmoradi

2012-04-01

Full Text Available Distillation is a complex and highly nonlinear industrial process. In general it is not always possible to obtain accurate first principles models for high-purity distillation columns. On the other hand the development of first principles models is usually time consuming and expensive. To overcome these problems, empirical models such as neural networks can be used. One major drawback of empirical models is that the prediction is valid only inside the data domain that is sufficiently covered by measurement data. Modeling distillation columns by means of neural networks is reported in literature by using recursive networks. The recursive networks are proper for modeling purpose, but such models have the problems of high complexity and high computational cost. The objective of this paper is to propose a simple and reliable model for distillation column. The proposed model uses feed forward neural networks which results in a simple model with less parameters and faster training time. Simulation results demonstrate that predictions of the proposed model in all regions are close to outputs of the dynamic model and the error in negligible. This implies that the model is reliable in all regions.

Evaluation of fishmeal protein supplementation to commercial feeds ...

African Journals Online (AJOL)

A total of 140 Lohman pullets layers at eighteenth week of lay were randomly selected and used to study effects of graded levels of fishmeal protein supplementation to two commercial feeds (type A & B) on egg production and quality. Layers were divided into two equal groups each of which was divided into five equal sub ...

Prediction of coal response to froth flotation based on coal analysis using regression and artificial neural network

Energy Technology Data Exchange (ETDEWEB)

Jorjani, E.; Poorali, H.A.; Sam, A.; Chelgani, S.C.; Mesroghli, S.; Shayestehfar, M.R. [Islam Azad University, Tehran (Iran). Dept. of Mining Engineering

2009-10-15

In this paper, the combustible value (i.e. 100-Ash) and combustible recovery of coal flotation concentrate were predicted by regression and artificial neural network based on proximate and group macerals analysis. The regression method shows that the relationships between (a) in (ash), volatile matter and moisture (b) in (ash), in (liptinite), fusinite and vitrinite with combustible value can achieve the correlation coefficients (R{sup 2}) of 0.8 and 0.79, respectively. In addition, the input sets of (c) ash, volatile matter and moisture (d) ash, liptinite and fusinite can predict the combustible recovery with the correlation coefficients of 0.84 and 0.63, respectively. Feed-forward artificial neural network with 6-8-12-11-2-1 arrangement for moisture, ash and volatile matter input set was capable to estimate both combustible value and combustible recovery with correlation of 0.95. It was shown that the proposed neural network model could accurately reproduce all the effects of proximate and group macerals analysis on coal flotation system.

Determination of aflatoxins B1 and M1 in animal feeds and liquid milk using thin layer chromatography

International Nuclear Information System (INIS)

Njue, W.; Gitu, L.; Kaberia, F.

1996-01-01

Animal feed samples were collected from feeding troughs and analysed for levels of aflatoxins B 1 , a toxic and carcinogenic mycotoxin. When aflatoxin B 1 is consumed by dairy cattle some of it is hydroxylated to form aflatoxin M 1 , which can appear in milk. Since aflatoxin M 1 , is also toxic and carcinogenic, it was determined in liquid milk. The determinations were carried out using thin-layer chromatography. Some of the feed samples were found to contain concentrations of aflatoxin B 1 that were above maximum tolerated values in foods and feeds in various countries. Brewers grain and used poultry feed contained 133.4 ppb, while the barley husks had a maximum value of 27.4 ppb. The details of the experimental results and analytical methods used are presented.(author)

Ferric and cobaltous hydroacid complexes for forward osmosis (FO) processes

KAUST Repository

Ge, Qingchun; Fu, Fengjiang; Chung, Neal Tai-Shung

2014-01-01

Cupric and ferric hydroacid complexes have proven their advantages as draw solutes in forward osmosis in terms of high water fluxes, negligible reverse solute fluxes and easy recovery (Ge and Chung, 2013. Hydroacid complexes: A new class of draw solutes to promote forward osmosis (FO) processes. Chemical Communications 49, 8471-8473.). In this study, cobaltous hydroacid complexes were explored as draw solutes and compared with the ferric hydroacid complex to study the factors influencing their FO performance. The solutions of the cobaltous complexes produce high osmotic pressures due to the presence of abundant hydrophilic groups. These solutes are able to dissociate and form a multi-charged anion and Na+ cations in water. In addition, these complexes have expanded structures which lead to negligible reverse solute fluxes and provide relatively easy approaches in regeneration. These characteristics make the newly synthesized cobaltous complexes appropriate as draw solutes. The FO performance of the cobaltous and ferric-citric acid (Fe-CA) complexes were evaluated respectively through cellulose acetate membranes, thin-film composite membranes fabricated on polyethersulfone supports (referred as TFC-PES), and polybenzimidazole and PES dual-layer (referred as PBI/PES) hollow fiber membranes. Under the conditions of DI water as the feed and facing the support layer of TFC-PES FO membranes (PRO mode), draw solutions at 2.0M produced relatively high water fluxes of 39-48 LMH (Lm-2hr-1) with negligible reverse solute fluxes. A water flux of 17.4 LMH was achieved when model seawater of 3.5wt.% NaCl replaced DI water as the feed and 2.0M Fe-CA as the draw solution under the same conditions. The performance of these hydroacid complexes surpasses those of the synthetic draw solutes developed in recent years. This observation, along with the relatively easy regeneration, makes these complexes very promising as a novel class of draw solutes. © 2014 Elsevier Ltd.

Ferric and cobaltous hydroacid complexes for forward osmosis (FO) processes

KAUST Repository

Ge, Qingchun

2014-07-01

Cupric and ferric hydroacid complexes have proven their advantages as draw solutes in forward osmosis in terms of high water fluxes, negligible reverse solute fluxes and easy recovery (Ge and Chung, 2013. Hydroacid complexes: A new class of draw solutes to promote forward osmosis (FO) processes. Chemical Communications 49, 8471-8473.). In this study, cobaltous hydroacid complexes were explored as draw solutes and compared with the ferric hydroacid complex to study the factors influencing their FO performance. The solutions of the cobaltous complexes produce high osmotic pressures due to the presence of abundant hydrophilic groups. These solutes are able to dissociate and form a multi-charged anion and Na+ cations in water. In addition, these complexes have expanded structures which lead to negligible reverse solute fluxes and provide relatively easy approaches in regeneration. These characteristics make the newly synthesized cobaltous complexes appropriate as draw solutes. The FO performance of the cobaltous and ferric-citric acid (Fe-CA) complexes were evaluated respectively through cellulose acetate membranes, thin-film composite membranes fabricated on polyethersulfone supports (referred as TFC-PES), and polybenzimidazole and PES dual-layer (referred as PBI/PES) hollow fiber membranes. Under the conditions of DI water as the feed and facing the support layer of TFC-PES FO membranes (PRO mode), draw solutions at 2.0M produced relatively high water fluxes of 39-48 LMH (Lm-2hr-1) with negligible reverse solute fluxes. A water flux of 17.4 LMH was achieved when model seawater of 3.5wt.% NaCl replaced DI water as the feed and 2.0M Fe-CA as the draw solution under the same conditions. The performance of these hydroacid complexes surpasses those of the synthetic draw solutes developed in recent years. This observation, along with the relatively easy regeneration, makes these complexes very promising as a novel class of draw solutes. © 2014 Elsevier Ltd.

Assessing artificial neural network performance in estimating the layer properties of pavements

Directory of Open Access Journals (Sweden)

Gloria Inés Beltran

2014-05-01

Full Text Available A major concern in assessing the structural condition of existing flexible pavements is the estimation of the mechanical properties of constituent layers, which is useful for the design and decision-making process in road management systems. This parameter identification problem is truly complex due to the large number of variables involved in pavement behavior. To this end, non-conventional adaptive or approximate solutions via Artificial Neural Networks – ANNs – are considered to properly map pavement response field measurements. Previous investigations have demonstrated the exceptional ability of ANNs in layer moduli estimation from non-destructive deflection tests, but most of the reported cases were developed using synthetic deflection data or hypothetical pavement systems. This paper presents further attempts to back-calculate layer moduli via ANN modeling, using a database gathered from field tests performed on three- and four-layer pavement systems. Traditional layer structuring and pavements with a stabilized subbase were considered. A three-stage methodology is developed in this study to design and validate an “optimum” ANN-based model, i.e., the best architecture possible along with adequate learning rules. An assessment of the resulting ANN model demonstrates its forecasting capabilities and efficiency in solving a complex parameter identification problem concerning pavements.

Reconstruction of neutron spectra using neural networks starting from the Bonner spheres spectrometric system

International Nuclear Information System (INIS)

Ortiz R, J.M.; Martinez B, M.R.; Arteaga A, T.; Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.

2005-01-01

The artificial neural networks (RN) have been used successfully to solve a wide variety of problems. However to determine an appropriate set of values of the structural parameters and of learning of these, it continues being even a difficult task. Contrary to previous works, here a set of neural networks is designed to reconstruct neutron spectra starting from the counting rates coming from the detectors of the Bonner spheres system, using a systematic and experimental strategy for the robust design of multilayer neural networks of the feed forward type of inverse propagation. The robust design is formulated as a design problem of Taguchi parameters. It was selected a set of 53 neutron spectra, compiled by the International Atomic Energy Agency, the counting rates were calculated that would take place in a Bonner spheres system, the set was arranged according to the wave form of those spectra. With these data and applying the Taguchi methodology to determine the best parameters of the network topology, it was trained and it proved the same one with the spectra. (Author)

Maximum entropy methods for extracting the learned features of deep neural networks.

Science.gov (United States)

Finnegan, Alex; Song, Jun S

2017-10-01

New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

Predicting the Deflections of Micromachined Electrostatic Actuators Using Artificial Neural Network (ANN