Search

Abstract: This paper reports the results of an advanced algorithm for the optimization of electron beam parameters in Free Electron Laser (FEL) Linacs. In the novel approach presented in this paper, the system uses state of the art developments in video games to mimic an operator''s decisions to perform an optimization task when no prior knowledge, other than constraints on the actuators is available. The system was tested for the simultaneous optimization of the energy spread and the transmission of the Australian Synchrotron Linac. The proposed system successfully increased the transmission of the machine from 90% to 97% and decreased the energy spread of the beam from 1.04% to 0.91%. Results of a control experiment performed at the new FERMI@Elettra FEL is also reported, suggesting the adaptability of the scheme for beam-based control. [Copyright &y& Elsevier]

Abstract: The present paper surveys the application of soft computing (SC) techniques in engineering design. Within this context, fuzzy logic (FL), genetic algorithms (GA) and artificial neural networks (ANN), as well as their fusion are reviewed in order to examine the capability of soft computing methods and techniques to effectively address various hard-to-solve design tasks and issues. Both these tasks and issues are studied in the first part of the paper accompanied by references to some results extracted from a survey performed for in some industrial enterprises. The second part of the paper makes an extensive review of the literature regarding the application of soft computing (SC) techniques in engineering design. Although this review cannot be collectively exhaustive, it may be considered as a valuable guide for researchers who are interested in the domain of engineering design and wish to explore the opportunities offered by fuzzy logic, artificial neural networks and genetic algorithms for further improvement of both the design outcome and the design process itself. An arithmetic method is used in order to evaluate the review results, to locate the research areas where SC has already given considerable results and to reveal new research opportunities. [Copyright &y& Elsevier]

A three-phase intelligent technique has been constructed to improve the data-hiding algorithm in colour images with imperceptibility. The first phase of the learning system (LS) has been applied in advance, whereas the other phases have been applied after the hiding process. The first phase has been constructed to estimate the number of bits to be hidden at each pixel (NBH); this phase is based on adaptive neural networks with an adaptive genetic algorithm using upwind adaptive relaxation (LS ANN _ AGAUpAR1 ). The LS of the second phase (LS ANN _ AGAUpAR2 ) has been introduced as a detector to check the performance of the proposed steganographic algorithm by creating a rich images model from available cover and stego images. The LS of the last phase (LS CANN _ AGAUpAR3 ) has been implemented through three steps, and it is based on a concurrent approach to improve the stego image and defend against attacks. The adaptive image filtering and adaptive image segmentation algorithms have been introduced to randomly hide a compressed and encrypted secret message into a cover image. The NBH for each pixel has been estimated cautiously using 32 principle situations (PS) with their 6 branch situations (BS). These situations have been worked through seven layers of security to augment protection from attacks. In this paper, hiding algorithms have been produced to fight three types of attacks: visual, structural, and statistical attacks. The simulation results have been discussed and compared with new literature using data hiding algorithms for colour images. The results of the proposed algorithm can efficiently embed a large quantity of data, up to 12 bpp (bits per pixel), with better image quality. [ABSTRACT FROM AUTHOR]

Abstract: Selection of the optimal neural architecture to solve a pattern classification problem entails to choose the relevant input units, the number of hidden neurons and its corresponding interconnection weights. This problem has been widely studied in many research works but their solutions usually involve excessive computational cost in most of the problems and they do not provide a unique solution. This paper proposes a new technique to efficiently design the MultiLayer Perceptron (MLP) architecture for classification using the Extreme Learning Machine (ELM) algorithm. The proposed method provides a high generalization capability and a unique solution for the architecture design. Moreover, the selected final network only retains those input connections that are relevant for the classification task. Experimental results show these advantages. [Copyright &y& Elsevier]

Abstract: This paper deals with one of the most important keys for economic growth: scientific knowledge and innovation, following the linear Research and Development (R&D) model. Patents, scientific publications and expenditure in R&D as well as the personnel involved in these activities are taken into account as proxy indicators, together with variables related to education and economy in order to classify R&D performance in 25 European Union (EU) Member States. This study classifies these countries using a set of variables which characterize them from 2005 to 2008 and analyses the most relevant ones for this classification. The Multilayer Perceptron Model (MLP) and the Product-Unit Neural Network (EPUNN) models, both trained by evolutionary algorithms (EA), were used to classify yearly country observations in clusters previously defined by employing unsupervised algorithm k-means clustering, obtaining four different classes of national R&D performance: low, moderate, high and innovation driven economies. Finally, our methodology is compared to other classification methods normally used in machine learning. The results show that while various methods of classification exist, our methodology obtains models with a significantly lower number of coefficients without decreasing their accuracy in predicting the classification of other European countries or in these countries in the following years. [Copyright &y& Elsevier]

Abstract: This paper presents an incremental learning algorithm for feed-forward neural networks used as approximators of real world data. This algorithm allows neural networks of limited size to be obtained, providing better performances. The algorithm is compared to two of the main incremental algorithms (Dunkin and cascade correlation) in the respective contexts of synthetic data and of real data consisting of radiation doses in homogeneous environments. [Copyright &y& Elsevier]

Abstract: Email is one of the most ubiquitous and pervasive applications used on a daily basis by millions of people worldwide, individuals and organizations more and more rely on the emails to communicate and share information and knowledge. However, the increase in email users has resulted in a dramatic increase in spam emails during the past few years. It is becoming a big challenge to process and manage the emails efficiently for and individuals and organizations. This paper proposes new email classification models using a linear neural network trained by perceptron learning algorithm and a nonlinear neural network trained by back-propagation learning algorithm. An efficient semantic feature space (SFS) method is introduced in these classification models. The traditional back-propagation neural network (BPNN) has slow learning speed and is prone to trap into a local minimum, so the modified back-propagation neural network (MBPNN) is presented to overcome these limitations. The vector space model based email classification system suffers from a large number of features and ambiguity in the meaning of terms, which will lead to sparse and noisy feature space. So we use the SFS to convert the original sparse and noisy feature space to a semantically richer feature space, which will helps to accelerate the learning speed. The experiments are conducted based on different training set size and extracted feature size. Experimental results show that the models using MBPNN outperform the traditional BPNN, and the use of SFS can greatly reduce the feature dimensionality and improve email classification performance. [Copyright &y& Elsevier]

In this paper, we focus on the experimental analysis on the performance in artificial neural networks with the use of statistical tests on the classification task. Particularly, we have studied whether the sample of results from multiple trials obtained by conventional artificial neural networks and support vector machines checks the necessary conditions for being analyzed through parametrical tests. The study is conducted by considering three possibilities on classification experiments: random variation in the selection of test data, the selection of training data and internal randomness in the learning algorithm. The results obtained state that the fulfillment of these conditions are problem-dependent and indefinite, which justifies the need of using non-parametric statistics in the experimental analysis. [Copyright &y& Elsevier]

Abstract: This paper presents an overview of a data analysis method based on self-organizing maps (SOM), a well-known unsupervised neural network learning algorithm, which was applied to a lead-free wave soldering process. The aim of the study was to determine whether the neural network modeling method could be a useful and time-saving way to analyze data from a discrete manufacturing process, such as wave soldering, which is a widely used technique in the electronics industry to solder components on printed circuit boards. The data variables were mostly various process parameters, but also some solder defect numbers were present in the data as a measure of the product quality. The data analysis procedure went as follows. At first, the process data were modeled using the SOM-algorithm. Next, the neuron reference vectors of the formed map were clustered to reveal the desired dominating elements of each territory of the map. At the final stage, the clusters were utilized as sub-models to indicate variable dependencies in these sub-models. The results show that the method presented here can be a good way to analyze this type of process data because interesting interactions between certain process parameters and solder defects were found by means of this data-driven modeling method. [Copyright &y& Elsevier]

Abstract: This paper presents an identification method based on artificial neural networks, which can be used for the robust fault detection. In particular, a problem of the multi-layer perceptron neural network uncertainty estimation with application of the outer bounding ellipsoid algorithm is considered. The mathematical description of the model uncertainty enables designing robust fault detection system, which effectiveness was verified with the DAMADICS benchmark. [Copyright &y& Elsevier]

Abstract: Minor component analysis (MCA) is an important statistical tool for signal processing and data analysis. Neural networks can be used to extract online minor component from input data. Compared with traditional algebraic approaches, a neural network method has a lower computational complexity. Stability of neural networks learning algorithms is crucial to practical applications. In this paper, we propose a stable MCA neural networks learning algorithm, which has a more satisfactory numerical stability than some existing MCA algorithms. Dynamical behaviors of the proposed algorithm are analyzed via deterministic discrete time (DDT) method and the conditions are obtained to guarantee convergence. Simulations are carried out to illustrate the theoretical results achieved. [Copyright &y& Elsevier]

Abstract: Almost all current training algorithms for neural networks are based on gradient descending technique, which causes long training time. In this paper, we propose a novel fast training algorithm called Fast Constructive-Covering Algorithm (FCCA) for neural network construction based on geometrical expansion. Parameters are updated according to the geometrical location of the training samples in the input space, and each sample in the training set is learned only once. By doing this, FCCA is able to avoid iterative computing and much faster than traditional training algorithms. Given an input sequence in an arbitrary order, FCCA learns “easy” samples first and “confusing” samples are easily learned after these “easy” samples. This sample reordering process is done on the fly based on geometrical concept. In addition, FCCA begins with an empty hidden layer, and adds new hidden neurons when necessary. This constructive learning avoids blind selection of neural network structure. The experimental work for classification problems illustrates the advantages of FCCA, especially in learning speed. [Copyright &y& Elsevier]

This paper presents a new algorithm for on-line artificial neural networks (ANN) training. The network topology is a standard multilayer perceptron (MLP) and the training algorithm is based on the theory of variable structure systems (VSS) and sliding mode control (SMC). The main feature of this novel procedure is the adaptability of the gain (learning rate), which is obtained from sliding mode surface so that system stability is guaranteed. [Copyright &y& Elsevier]

Abstract: In the paper, as an improvement of fuzzy clustering neural network FCNN proposed by Zhang et al., a novel robust fuzzy clustering neural network RFCNN is presented to cope with the sensitive issue of clustering when outliers exist. This new algorithm is based on Vapnik''s ɛ-insensitive loss function and quadratic programming optimization. Our experimental results demonstrate that RFCNN has much better robustness for outliers than FCNN. [Copyright &y& Elsevier]

Abstract: Quantitative characterisation of carotid atherosclerosis and classification into symptomatic or asymptomatic is crucial in planning optimal treatment of atheromatous plaque. The computer-aided diagnosis (CAD) system described in this paper can analyse ultrasound (US) images of carotid artery and classify them into symptomatic or asymptomatic based on their echogenicity characteristics. The CAD system consists of three modules: a) the feature extraction module, where first-order statistical (FOS) features and Laws’ texture energy can be estimated, b) the dimensionality reduction module, where the number of features can be reduced using analysis of variance (ANOVA), and c) the classifier module consisting of a neural network (NN) trained by a novel hybrid method based on genetic algorithms (GAs) along with the back propagation algorithm. The hybrid method is able to select the most robust features, to adjust automatically the NN architecture and to optimise the classification performance. The performance is measured by the accuracy, sensitivity, specificity and the area under the receiver-operating characteristic (ROC) curve. The CAD design and development is based on images from 54 symptomatic and 54 asymptomatic plaques. This study demonstrates the ability of a CAD system based on US image analysis and a hybrid trained NN to identify atheromatous plaques at high risk of stroke. (E-mail: knikita@cc.ece.ntua.gr) [Copyright &y& Elsevier]

Abstract: In this paper, a new subset-based training and pruning (SBTP) algorithm is proposed based on the relationship between node dependence and Jacobian rank deficiency. At each training iteration, the orthogonal factorization with column permutation is applied to the output of the nodes in the same hidden layer to identify the dependent nodes. The output weights of the dependent nodes will be set as zeros, and the output weights of the independent nodes will be recalculated to maintain the original input–output behavior. Then, only the weights of the independent nodes will be trained using the Levenberg–Marquardt (LM) algorithm at this iteration, while keeping the weights of the dependent nodes unchanged. In this way, the computational cost of the LM algorithm will be reduced significantly. After the training process, a unit-based optimal brain surgeon (UB-OBS) pruning method is used to prune the insensitive hidden units to further reduce the size of the neural network, and no retraining is needed. Simulations are presented to demonstrate the effectiveness of the proposed approach. [Copyright &y& Elsevier]

Abstract: This paper presents a new approach to incrementally constructing a neural network that is capable of learning new information without forgetting old knowledge. The proposed neural network, called hyper-spherical ARTMAP network (HS-ARTMAP network), is a synthesis of an RBF-network-like module and an ART-like module. The HS-ARTMAP network is trained via a training algorithm similar to the training algorithm for the fuzzy ARTMAP system. To demonstrate the performance of the proposed HS-ARTMAP network, several pattern recognition and function approximation problems were tested. [Copyright &y& Elsevier]

Abstract: The use of artificial neural networks in various applications related with energy management in buildings has been increasing significantly over the recent years. In this paper the design of inside air temperature predictive neural network models, to be used for predictive control of air-conditioned systems, is discussed. The use of multi-objective genetic algorithms for designing off-line radial basis function neural network models is detailed. The performance of these data-driven models is compared, favourably, with a multi-node physically based model. Climate and environmental data from a secondary school located in the south of Portugal, collected by a remote data acquisition system, are used to generate the models. By using a sliding window adaptive methodology, the good results obtained off-line are extended throughout the whole year. The use of long-range predictive models for air-conditioning systems control is demonstrated, in simulations, achieving a good temperature regulation with important energy savings. [Copyright &y& Elsevier]

Abstract: Feedforward neural networks of multi-layer perceptron type can be used as nonlinear black-box models in data-mining tasks. Common problems encountered are how to select relevant inputs from a large set of variables that potentially affect the outputs to be modeled, as well as high levels of noise in the data sets. In order to avoid over-fitting of the resulting model, the input dimension and/or the number of hidden nodes have to be restricted. This paper presents a systematic method that can guide the selection of both input variables and a sparse connectivity of the lower layer of connections in feedforward neural networks of multi-layer perceptron type with one layer of hidden nonlinear units and a single linear output node. The algorithm is illustrated on three benchmark problems. [Copyright &y& Elsevier]

Abstract: This paper presents a strength model of steel columns under elevated temperatures using the artificial neural network. The many influencing parameters make it difficult to build an analytical steel strength model. Being a flexible model building method, the artificial neural network is an ideal tool to construct the complex relationship between the input and the output parameters accurately. A hybrid neural network, which combines the sigmoid neurons and the radial basis function neurons at the hidden layer, is proposed to better map the input–output relationship both locally and globally. The use of the genetic algorithm approach in searching the best-hidden neurons makes the hybrid neural network less likely to be trapped in local minima than the traditional gradient-based search algorithms. The genetic algorithm based hybrid neural network is applied to model the strength of steel columns under fire. The neural network results are compared with the modified Rankine formula. [Copyright &y& Elsevier]

Abstract: Many constructive learning algorithms have been proposed to find an appropriate network structure for a classification problem automatically. Constructive learning algorithms have drawbacks especially when used for complex tasks and modular approaches have been devised to solve these drawbacks. At the same time, parallel training for neural networks with fixed configurations has also been proposed to accelerate the training process. A new approach that combines advantages of constructive learning and parallelism, output partitioning, is presented in this paper. Classification error is used to guide the proposed incremental-partitioning algorithm, which divides the original data set into several smaller sub-data sets with distinct classes. Each sub-data set is then handled in parallel, by a smaller constructively trained sub-network which uses the whole input vector and produces a portion of the final output vector where each class is represented by one unit. Three classification data sets are used to test the validity of this method, and results show that this method reduces the classification test error. [Copyright &y& Elsevier]

Abstract: Considerable research effort is being devoted to the development of image-enhancement algorithms, which improve the quality of displayed digital pictures. Reliable methods for measuring perceived image quality are needed to evaluate the performances of those algorithms, and such measurements require a univariant (i.e., no-reference) approach. The system presented in this paper applies concepts derived from computational intelligence, and supports an objective quality-assessment method based on a circular back-propagation (CBP) neural model. The network is trained to predict quality ratings, as scored by human assessors, from numerical features that characterize images. As such, the method aims at reproducing perceived image quality, rather than defining a comprehensive model of the human visual system. The connectionist approach allows one to decouple the task of feature selection from the consequent mapping of features into an objective quality score. Experimental results on the perceptual effects of a family of contrast-enhancement algorithms confirm the method effectiveness, as the system renders quite accurately the image quality perceived by human assessors. [Copyright &y& Elsevier]

Abstract: This paper presents a development and implementation of a PC-based maximum power point tracker (MPPT) for PV system using neural networks (NN). The system consists of a PV module via a MPPT supplying a dc motor that drives an air fan. The control algorithm is developed to use the artificial NN for detecting the optimal operating point under different operating conditions, then the control action gives the driving signals to the MPPT. A PC is used for data acquisition, running the control algorithm, data storage, as well as data display and analysis. The system has been implemented and tested under various operating conditions. The experimental results showed that the PV system with MPPT always tracks the peak power point of the PV module under various operating conditions. The MPPT transmits about 97% of the actual maximum power generated by the PV module. The MPPT not only increases the power from the PV module to the load, but also maintains longer operating periods for the PV system. The air velocity and the air mass flow rate of the mechanical load are increased considerably, due to the increase of the PV system power. It is also found that, the increase in the output energy due to using the MPPT is about 45.2% for a clear sunny day. [Copyright &y& Elsevier]

Abstract: In this paper a new approach for short-term load prediction in buildings is shown. The method is based on a special kind of artificial neural network (ANN), which feeds back a part of its outputs. This ANN is trained by means of a hybrid algorithm. The new system uses current and forecasted values of temperature, the current load and the hour and the day as inputs. The performance of this predictor was evaluated using real data and results from international contests. The achieved results demonstrate the high precision reached with this system. [Copyright &y& Elsevier]

Abstract: Marquees and other temporary light structures are connected to the ground by tensile anchors that resist uplift forces. The existing methods for predicting the pullout capacity of these anchors are inaccurate and incomplete. As a result, failures of such structures are not rare and have resulted in deaths and tens of thousands of dollars of damage. This paper aims to increase the safety of temporary light structures, such as marquees, by developing a more accurate pullout capacity prediction method based on artificial neural networks (ANNs). Two types of ANNs are examined, namely, multi-layer perceptrons (MLPs) that are trained with the back-propagation algorithm and B-spline neurofuzzy networks that are trained with the adaptive spline modeling of observation data (ASMOD) algorithm. In order to facilitate the use of the MLP model, it is made available in a tractable equation form. Predictions of pullout capacity from the developed ANN models are obtained and compared with values predicted by traditional methods currently used in practice. The results indicate that ANNs are able to predict accurately the pullout capacity of ground anchors and outperform the existing methods. [Copyright &y& Elsevier]

Abstract: Ensemble algorithms can improve the performance of a given learning algorithm through the combination of multiple base classifiers into an ensemble. In this paper, we attempt to train and combine the base classifiers using an adaptive policy. This policy is learnt through a Q-learning inspired technique. Its effectiveness for an essentially supervised task is demonstrated by experimental results on several UCI benchmark databases. [Copyright &y& Elsevier]

In the past, neural networks have been viewed as classification and regression systems whose internal representations were extremely difficult to interpret. It is now becoming apparent that algorithms can be designed which extract understandable representations from trained neural networks, enabling them to be used for data mining, i.e. the discovery and explanation of previously unknown relationships present in data. This paper reviews existing algorithms for extracting comprehensible representations from neural networks and describes research to generalize and extend the capabilities of one of these algorithms. The algorithm has been generalized for application to bioinformatics datasets, including the prediction of splice site junctions in Human DNA sequences. Results generated on this datasets are compared with those generated by a conventional data mining technique (C5) and conclusions drawn. [Copyright &y& Elsevier]