A fast multi-output RBF neural network construction method

This paper investigates the center selection of multi-output radial basis function (RBF) networks, and a multi-output fast recursive algorithm (MFRA) is proposed. This method can not only reveal the significance of each candidate center based on the reduction in the trace of the error covariance matrix, but also can estimate the network weights simultaneously using a back substitution approach. The main contribution is that the center selection procedure and the weight estimation are performed within a well-defined regression context, leading to a significantly reduced computational complexity. The efficiency of the algorithm is confirmed by a computational complexity analysis, and simulation results demonstrate its effectiveness. (C) 2010 Elsevier B.V. All rights reserved.

Neural Network Modeling of Rheological Parameters of Grouts Containing Viscosity-Modifying Agent

The development of artificial neural network (ANN) models to predict the rheological behavior of grouts is described is this paper and the sensitivity of such parameters to the variation in mixture ingredients is also evaluated. The input parameters of the neural network were the mixture ingredients influencing the rheological behavior of grouts, namely the cement content, fly ash, ground-granulated blast-furnace slag, limestone powder, silica fume, water-binder ratio (w/b), high-range water-reducing admixture, and viscosity-modifying agent (welan gum). The six outputs of the ANN models were the mini-slump, the apparent viscosity at low shear, and the yield stress and plastic viscosity values of the Bingham and modified Bingham models, respectively. The model is based on a multi-layer feed-forward neural network. The details of the proposed ANN with its architecture, training, and validation are presented in this paper. A database of 186 mixtures from eight different studies was developed to train and test the ANN model. The effectiveness of the trained ANN model is evaluated by comparing its responses with the experimental data that were used in the training process. The results show that the ANN model can accurately predict the mini-slump, the apparent viscosity at low shear, the yield stress, and the plastic viscosity values of the Bingham and modified Bingham models of the pseudo-plastic grouts used in the training process. The results can also predict these properties of new mixtures within the practical range of the input variables used in the training with an absolute error of 2%, 0.5%, 8%, 4%, 2%, and 1.6%, respectively. The sensitivity of the ANN model showed that the trend data obtained by the models were in good agreement with the actual experimental results, demonstrating the effect of mixture ingredients on fluidity and the rheological parameters with both the Bingham and modified Bingham models.

An efficient neural network approach for nanoscale FinFET modelling and circuit simulation

The present paper demonstrates the suitability of artificial neural network (ANN) for modelling of a FinFET in nano-circuit simulation. The FinFET used in this work is designed using careful engineering of source-drain extension, which simultaneously improves maximum frequency of oscillation f(max) because of lower gate to drain capacitance, and intrinsic gain A(V0) = g(m)/g(ds), due to lower output conductance g(ds). The framework for the ANN-based FinFET model is a common source equivalent circuit, where the dependence of intrinsic capacitances, resistances and dc drain current I-d on drain-source V-ds and gate-source V-gs is derived by a simple two-layered neural network architecture. All extrinsic components of the FinFET model are treated as bias independent. The model was implemented in a circuit simulator and verified by its ability to generate accurate response to excitations not used during training. The model was used to design a low-noise amplifier. At low power (J(ds) similar to 10 mu A/mu m) improvement was observed in both third-order-intercept IIP3 (similar to 10 dBm) and intrinsic gain A(V0) (similar to 20 dB), compared to a comparable bulk MOSFET with similar effective channel length. This is attributed to higher ratio of first-order to third-order derivative of I-d with respect to gate voltage and lower g(ds), in FinFET compared to bulk MOSFET. Copyright (C) 2009 John Wiley & Sons, Ltd.

ARE ARTIFICIAL NEURAL NETS AS SMART AS A RAT

The origins of artificial neural networks are related to animal conditioning theory: both are forms of connectionist theory, which in turn derives from the empiricist philosophers' principle of association. The parallel between animal learning and neural nets suggests that interaction between them should benefit both sides.

Predicting forest attributes In southeast Alaska using artificial neural networks

Artificial neural network (ANN) methods are used to predict forest characteristics. The data source is the Southeast Alaska (SEAK) Grid Inventory, a ground survey compiled by the USDA Forest Service at several thousand sites. The main objective of this article is to predict characteristics at unsurveyed locations between grid sites. A secondary objective is to evaluate the relative performance of different ANNs. Data from the grid sites are used to train six ANNs: multilayer perceptron, fuzzy ARTMAP, probabilistic, generalized regression, radial basis function, and learning vector quantization. A classification and regression tree method is used for comparison. Topographic variables are used to construct models: latitude and longitude coordinates, elevation, slope, and aspect. The models classify three forest characteristics: crown closure, species land cover, and tree size/structure. Models are constructed using n-fold cross-validation. Predictive accuracy is calculated using a method that accounts for the influence of misclassification as well as measuring correct classifications. The probabilistic and generalized regression networks are found to be the most accurate. The predictions of the ANN models are compared with a classification of the Tongass national forest in southeast Alaska based on the interpretation of satellite imagery and are found to be of similar accuracy.

Modeling of titanium alloys by using artificial neural networks

Titanium alloy exhibits an excellent combination of bio-compatibility, corrosion resistance, strength and toughness. The microstructure of an alloy influences the properties. The microstructures depend mainly on alloying elements, method of production, mechanical, and thermal treatments. The relationships between these variables and final properties of the alloy are complex, non-linear in nature, which is the biggest hurdle in developing proper correlations between them by conventional methods. So, we developed artificial neural networks (ANN) models for solving these complex phenomena in titanium alloys.

In the present work, ANN models were used for the analysis and prediction of the correlation between the process parameters, the alloying elements, microstructural features, beta transus temperature and mechanical properties in titanium alloys. Sensitivity analysis of trained neural network models were studied which resulted a better understanding of relationships between inputs and outputs. The model predictions and the analysis are well in agreement with the experimental results. The simulation results show that the average output-prediction error by models are less than 5% of the prediction range in more than 95% of the cases, which is quite acceptable for all metallurgical purposes.

Two-Stage Orthogonal Least Squares Methods for Neural Network Construction

A number of neural networks can be formulated as the linear-in-the-parameters models. Training such networks can be transformed to a model selection problem where a compact model is selected from all the candidates using subset selection algorithms. Forward selection methods are popular fast subset selection approaches. However, they may only produce suboptimal models and can be trapped into a local minimum. More recently, a two-stage fast recursive algorithm (TSFRA) combining forward selection and backward model refinement has been proposed to improve the compactness and generalization performance of the model. This paper proposes unified two-stage orthogonal least squares methods instead of the fast recursive-based methods. In contrast to the TSFRA, this paper derives a new simplified relationship between the forward and the backward stages to avoid repetitive computations using the inherent orthogonal properties of the least squares methods. Furthermore, a new term exchanging scheme for backward model refinement is introduced to reduce computational demand. Finally, given the error reduction ratio criterion, effective and efficient forward and backward subset selection procedures are proposed. Extensive examples are presented to demonstrate the improved model compactness constructed by the proposed technique in comparison with some popular methods.

Non-parametric bill of quantities estimation of concrete road bridges' superstructure: an artificial neural networks approach

Bridge construction responds to the need for environmentally friendly design of motorways and facilitates the passage through sensitive natural areas and the bypassing of urban areas. However, according to numerous research studies, bridge construction presents substantial budget overruns. Therefore, it is necessary early in the planning process for the decision makers to have reliable estimates of the final cost based on previously constructed projects. At the same time, the current European financial crisis reduces the available capital for investments and financial institutions are even less willing to finance transportation infrastructure. Consequently, it is even more necessary today to estimate the budget of high-cost construction projects -such as road bridges- with reasonable accuracy, in order for the state funds to be invested with lower risk and the projects to be designed with the highest possible efficiency. In this paper, a Bill-of-Quantities (BoQ) estimation tool for road bridges is developed in order to support the decisions made at the preliminary planning and design stages of highways. Specifically, a Feed-Forward Artificial Neural Network (ANN) with a hidden layer of 10 neurons is trained to predict the superstructure material quantities (concrete, pre-stressed steel and reinforcing steel) using the width of the deck, the adjusted length of span or cantilever and the type of the bridge as input variables. The training dataset includes actual data from 68 recently constructed concrete motorway bridges in Greece. According to the relevant metrics, the developed model captures very well the complex interrelations in the dataset and demonstrates strong generalisation capability. Furthermore, it outperforms the linear regression models developed for the same dataset. Therefore, the proposed cost estimation model stands as a useful and reliable tool for the construction industry as it enables planners to reach informed decisions for technical and economic planning of concrete bridge projects from their early implementation stages.

Optimization and Prediction of Mechanical and Thermal Properties of Graphene/LLDPE Nanocomposites by Using Artificial Neural Networks

The focus of this work is to develop the knowledge of prediction of the physical and chemical properties of processed linear low density polyethylene (LLDPE)/graphene nanoplatelets composites. Composites made from LLDPE reinforced with 1, 2, 4, 6, 8, and 10 wt% grade C graphene nanoplatelets (C-GNP) were processed in a twin screw extruder with three different screw speeds and feeder speeds (50, 100, and 150 rpm). These applied conditions are used to optimize the following properties: thermal conductivity, crystallization temperature, degradation temperature, and tensile strength while prediction of these properties was done through artificial neural network (ANN). The three first properties increased with increase in both screw speed and C-GNP content. The tensile strength reached a maximum value at 4 wt% C-GNP and a speed of 150 rpm as this represented the optimum condition for the stress transfer through the amorphous chains of the matrix to the C-GNP. ANN can be confidently used as a tool to predict the above material properties before investing in development programs and actual manufacturing, thus significantly saving money, time, and effort.

Use of a Neural Network to Predict Strength and Optimum Compositions of Natural Alumina-Silica-Based Geopolymers

In order to predict compressive strength of geopolymers prepared from alumina-silica natural products, based on the effect of Al 2 O 3 /SiO 2, Na 2 O/Al 2 O 3, Na 2 O/H 2 O, and Na/[Na+K], more than 50 pieces of data were gathered from the literature. The data was utilized to train and test a multilayer artificial neural network (ANN). Therefore a multilayer feedforward network was designed with chemical compositions of alumina silicate and alkali activators as inputs and compressive strength as output. In this study, a feedforward network with various numbers of hidden layers and neurons were tested to select the optimum network architecture. The developed three-layer neural network simulator model used the feedforward back propagation architecture, demonstrated its ability in training the given input/output patterns. The cross-validation data was used to show the validity and high prediction accuracy of the network. This leads to the optimum chemical composition and the best paste can be made from activated alumina-silica natural products using alkaline hydroxide, and alkaline silicate. The research results are in agreement with mechanism of geopolymerization.


Read More: http://ascelibrary.org/doi/abs/10.1061/(ASCE)MT.1943-5533.0000829

A neural network based tool for semi-automatic code transformation

A neural network based tool has been developed to assist in the process of code transformation. The tool offers advice on appropriate transformations within a knowledge-driven, semi-automatic parallelisation environment. We have identified the essential characteristics of codes relevant to loop transformations. A Kohonen network is used to discover structure in the characterised codes thus revealing new knowledge that may be brought to bear on the mapping between codes and transformations or transformation sequences. A transform selector based on this process has been developed and successfully applied to the parallelisation of sequential codes.

Neural network controlled three-phase four-wire shunt active powerfilter

A three-phase four-wire shunt active power filter for harmonic mitigation and reactive power compensation in power systems supplying nonlinear loads is presented. Three adaptive linear neurons are used to tackle the desired three-phase filter current templates. Another feedforward three-layer neural network is adopted to control the output filter compensating currents online. This is accomplished by producing the appropriate switching patterns of the converter's legs IGBTs. Adequate tracking of the filter current references is obtained by this method. The active filter injects the current required to compensate for the harmonic and reactive components of the line currents, Simulation results of the proposed active filter indicate a remarkable improvement in the source current waveforms. This is reflected in the enhancement of the unified power quality index defined. Also, the filter has exhibited quite a high dynamic response for step variations in the load current, assuring its potential for real-time applications