A new Jacobian matrix for optimal learning of single-layer neural networks

This paper investigates the learning of a wide class of single-hidden-layer feedforward neural networks (SLFNs) with two sets of adjustable parameters, i.e., the nonlinear parameters in the hidden nodes and the linear output weights. The main objective is to both speed up the convergence of second-order learning algorithms such as Levenberg-Marquardt (LM), as well as to improve the network performance. This is achieved here by reducing the dimension of the solution space and by introducing a new Jacobian matrix. Unlike conventional supervised learning methods which optimize these two sets of parameters simultaneously, the linear output weights are first converted into dependent parameters, thereby removing the need for their explicit computation. Consequently, the neural network (NN) learning is performed over a solution space of reduced dimension. A new Jacobian matrix is then proposed for use with the popular second-order learning methods in order to achieve a more accurate approximation of the cost function. The efficacy of the proposed method is shown through an analysis of the computational complexity and by presenting simulation results from four different examples.

Genetic algorithms for local controller network construction

Local Controller Networks (LCNs) provide nonlinear control by interpolating between a set of locally valid, subcontrollers covering the operating range of the plant. Constructing such networks typically requires knowledge of valid local models. This paper describes a new genetic learning approach to the construction of LCNs directly from the dynamic equations of the plant, or from modelling data. The advantage is that a priori knowledge about valid local models is not needed. In addition to allowing simultaneous optimisation of both the controller and validation function parameters, the approach aids transparency by ensuring that each local controller acts independently of the rest at its operating point. It thus is valuable for simultaneous design of the LCNs and identification of the operating regimes of an unknown plant. Application results from a highly nonlinear pH neutralisation process and its associated neural network representation are utilised to illustrate these issues.

Neural modelling, control and optimisation of an industrial grinding process

This paper describes the development of neural model-based control strategies for the optimisation of an industrial aluminium substrate disk grinding process. The grindstone removal rate varies considerably over a stone life and is a highly nonlinear function of process variables. Using historical grindstone performance data, a NARX-based neural network model is developed. This model is then used to implement a direct inverse controller and an internal model controller based on the process settings and previous removal rates. Preliminary plant investigations show that thickness defects can be reduced by 50% or more, compared to other schemes employed. (c) 2004 Elsevier Ltd. All rights reserved.

System oriented neural networks - Problem formulation, methodology and application

A novel methodology is proposed for the development of neural network models for complex engineering systems exhibiting nonlinearity. This method performs neural network modeling by first establishing some fundamental nonlinear functions from a priori engineering knowledge, which are then constructed and coded into appropriate chromosome representations. Given a suitable fitness function, using evolutionary approaches such as genetic algorithms, a population of chromosomes evolves for a certain number of generations to finally produce a neural network model best fitting the system data. The objective is to improve the transparency of the neural networks, i.e. to produce physically meaningful

Estimation of ternary liquid-liquid equilibria for arene/alkane/ionic liquid mixtures using neural networks

Neural network models have been explored for the prediction of the liquid-liquid equilibrium data and aromatic/aliphatic selectivity values. Four ternary systems composed of toluene, heptane, and the ionic liquids 1-ethyl-3-methylimidazolium ethylsulfate, or 1,3-dimethylimidazolium methylsulfate were investigated at 313.2 and 348.2 K.

Robust face recognition using posterior union model based neural networks

Face recognition with unknown, partial distortion and occlusion is a practical problem, and has a wide range of applications, including security and multimedia information retrieval. The authors present a new approach to face recognition subject to unknown, partial distortion and occlusion. The new approach is based on a probabilistic decision-based neural network, enhanced by a statistical method called the posterior union model (PUM). PUM is an approach for ignoring severely mismatched local features and focusing the recognition mainly on the reliable local features. It thereby improves the robustness while assuming no prior information about the corruption. We call the new approach the posterior union decision-based neural network (PUDBNN). The new PUDBNN model has been evaluated on three face image databases (XM2VTS, AT&T and AR) using testing images subjected to various types of simulated and realistic partial distortion and occlusion. The new system has been compared to other approaches and has demonstrated improved performance.

Integrated structure selection and parameter optimisation for eng-genes neural models

The eng-genes concept involves the use of fundamental known system functions as activation functions in a neural model to create a 'grey-box' neural network. One of the main issues in eng-genes modelling is to produce a parsimonious model given a model construction criterion. The challenges are that (1) the eng-genes model in most cases is a heterogenous network consisting of more than one type of nonlinear basis functions, and each basis function may have different set of parameters to be optimised; (2) the number of hidden nodes has to be chosen based on a model selection criterion. This is a mixed integer hard problem and this paper investigates the use of a forward selection algorithm to optimise both the network structure and the parameters of the system-derived activation functions. Results are included from case studies performed on a simulated continuously stirred tank reactor process, and using actual data from a pH neutralisation plant. The resulting eng-genes networks demonstrate superior simulation performance and transparency over a range of network sizes when compared to conventional neural models. (c) 2007 Elsevier B.V. All rights reserved.

Application of auto-associative neural networks to transient fault detection in an IC engine

The tailpipe emissions from automotive engines have been subject to steadily reducing legislative limits. This reduction has been achieved through the addition of sub-systems to the basic four-stroke engine which thereby increases its complexity. To ensure the entire system functions correctly, each system and / or sub-systems needs to be continuously monitored for the presence of any faults or malfunctions. This is a requirement detailed within the On-Board Diagnostic (OBD) legislation. To date, a physical model approach has been adopted by me automotive industry for the monitoring requirement of OBD legislation. However, this approach has restrictions from the available knowledge base and computational load required. A neural network technique incorporating Multivariant Statistical Process Control (MSPC) has been proposed as an alternative method of building interrelationships between the measured variables and monitoring the correct operation of the engine. Building upon earlier work for steady state fault detection, this paper details the use of non-linear models based on an Auto-associate Neural Network (ANN) for fault detection under transient engine operation. The theory and use of the technique is shown in this paper with the application to the detection of air leaks within the inlet manifold system of a modern gasoline engine whilst operated on a pseudo-drive cycle. Copyright © 2007 by ASME.

Automated nonlinear system modelling with multiple neural networks

This article discusses the identification of nonlinear dynamic systems using multi-layer perceptrons (MLPs). It focuses on both structure uncertainty and parameter uncertainty, which have been widely explored in the literature of nonlinear system identification. The main contribution is that an integrated analytic framework is proposed for automated neural network structure selection, parameter identification and hysteresis network switching with guaranteed neural identification performance. First, an automated network structure selection procedure is proposed within a fixed time interval for a given network construction criterion. Then, the network parameter updating algorithm is proposed with guaranteed bounded identification error. To cope with structure uncertainty, a hysteresis strategy is proposed to enable neural identifier switching with guaranteed network performance along the switching process. Both theoretic analysis and a simulation example show the efficacy of the proposed method.

Improved structure optimization for fuzzy-neural networks

Fuzzy-neural-network-based inference systems are well-known universal approximators which can produce linguistically interpretable results. Unfortunately, their dimensionality can be extremely high due to an excessive number of inputs and rules, which raises the need for overall structure optimization. In the literature, various input selection methods are available, but they are applied separately from rule selection, often without considering the fuzzy structure. This paper proposes an integrated framework to optimize the number of inputs and the number of rules simultaneously. First, a method is developed to select the most significant rules, along with a refinement stage to remove unnecessary correlations. An improved information criterion is then proposed to find an appropriate number of inputs and rules to include in the model, leading to a balanced tradeoff between interpretability and accuracy. Simulation results confirm the efficacy of the proposed method.

Earthmoving trucks condition level prediction using neural networks

Purpose: The purpose of this paper is to present an artificial neural network (ANN) model that predicts earthmoving trucks condition level using simple predictors; the model’s performance is compared to the respective predictive accuracy of the statistical method of discriminant analysis (DA).

Design/methodology/approach: An ANN-based predictive model is developed. The condition level predictors selected are the capacity, age, kilometers travelled and maintenance level. The relevant data set was provided by two Greek construction companies and includes the characteristics of 126 earthmoving trucks.

Findings: Data processing identifies a particularly strong connection of kilometers travelled and maintenance level with the earthmoving trucks condition level. Moreover, the validation process reveals that the predictive efficiency of the proposed ANN model is very high. Similar findings emerge from the application of DA to the same data set using the same predictors.

Originality/value: Earthmoving trucks’ sound condition level prediction reduces downtime and its adverse impact on earthmoving duration and cost, while also enhancing the maintenance and replacement policies effectiveness. This research proves that a sound condition level prediction for earthmoving trucks is achievable through the utilization of easy to collect data and provides a comparative evaluation of the results of two widely applied predictive methods.

Neural basis of language switching in the brain: fMRI evidence from Korean-Chinese early bilinguals

Using fMRI, we conducted two types of property generation task that involved language switching, with early bilingual speakers of Korean and Chinese. The first is a more conventional task in which a single language (L1 or L2) was used within each trial, but switched randomly from trial to trial. The other consists of a novel experimental design where language switching happens within each trial, alternating in the direction of the L1/L2 translation required. Our findings support a recently introduced cognitive model, the 'hodological' view of language switching proposed by Moritz-Gasser and Duffau. The nodes of a distributed neural network that this model proposes are consistent with the informative regions that we extracted in this study, using both GLM methods and Multivariate Pattern Analyses: the supplementary motor area, caudate, supramarginal gyrus and fusiform gyrus and other cortical areas. 

Intelligent potentiostat for identification of heavy metals in situ

This article presents a low-cost portable electrochemical instrument capable of on-site identification of heavy metals. The instrument acquires metal-specific voltage and current signals by the application of differential pulse anodic stripping voltammetry. This technique enhances the analytical current and rejects the background current, resulting in a higher signal-to-noise ratio for a better detection limit. The identification of heavy metals is based on an intelligent machine-based method using a multilayer perceptron neural network consisting of three layers of neurons. The neural network is implemented using a 16 bit microcontroller. The system is developed for use in the field in order to avoid expensive and time-consuming procedures and can be used in a variety of situations to help environmental assessment and control. 

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.