Search

The quality of scientific publications can be measured by quantitative indices such as the h‐index, Source Normalized Impact per Paper, or g‐index. However, these measures lack to explain the function or reasons for citations and the context of citations from citing publication to cited publication. We argue that citation context may be considered while calculating the impact of research work. However, mining citation context from unstructured full‐text publications is a challenging task. In this paper, we compiled a data set comprising 9,518 citations context. We developed a deep learning‐based architecture for citation context classification. Unlike feature‐based state‐of‐the‐art models, our proposed focal‐loss and class‐weight‐aware BiLSTM model with pretrained GloVe embedding vectors use citation context as input to outperform them in multiclass citation context classification tasks. Our model improves on the baseline state‐of‐the‐art by achieving an F1 score of 0.80 with an accuracy of 0.81 for citation context classification. Moreover, we delve into the effects of using different word embeddings on the performance of the classification model and draw a comparison between fastText, GloVe, and spaCy pretrained word embeddings. [ABSTRACT FROM AUTHOR]

Mathematical modeling of many natural and physical phenomena in industry, engineering sciences and basic sciences lead to linear and non-linear devices. In many cases, the coefficients of these devices, taking into account qualitative or linguistic concepts, show their complexity in the form of Z-numbers. Since Z-number involves both fuzziness and reliability or probabilistic uncertainty, it is difficult to obtain the exact solution to the problems with Z-number. In this work, a method and an algorithm are proposed for the approximate solution of a Z-number linear system of equations as an important case of such problems. The paper is devoted to solving linear systems where the coefficients of the variables and right hand side values are Z-numbers. An algorithm is presented based on a ranking scheme and the neural network technique to solve the obtained system. Moreover, two examples are included to describe the procedure of the method and results. [ABSTRACT FROM AUTHOR]

Combining computational technologies and humanities is an ongoing effort aimed at making resources such as texts, images, audio, video, and other artifacts digitally available, searchable, and analyzable. In recent years, deep neural networks (DNN) dominate the field of automatic text analysis and natural language processing (NLP), in some cases presenting a super‐human performance. DNNs are the state‐of‐the‐art machine learning algorithms solving many NLP tasks that are relevant for Digital Humanities (DH) research, such as spell checking, language detection, entity extraction, author detection, question answering, and other tasks. These supervised algorithms learn patterns from a large number of "right" and "wrong" examples and apply them to new examples. However, using DNNs for analyzing the text resources in DH research presents two main challenges: (un)availability of training data and a need for domain adaptation. This paper explores these challenges by analyzing multiple use‐cases of DH studies in recent literature and their possible solutions and lays out a practical decision model for DH experts for when and how to choose the appropriate deep learning approaches for their research. Moreover, in this paper, we aim to raise awareness of the benefits of utilizing deep learning models in the DH community. [ABSTRACT FROM AUTHOR]

The nanoindentation technique is employed to characterize the behaviors of biomaterials. Nevertheless, there is a lack of development of a miniaturized precise positioner for in situ nanoindentation. Besides, modeling behaviors of the positioner are restricted due to its complex kinematic characteristics. Therefore, this paper proposes a novel compliant two degrees of freedom (dof) stage for positioning a biomaterial sample in in situ nanoindentation. In addition, a new modeling and dimensional optimization synthesis method of the stage is developed. The proposed effective methodology is developed based on a kinetostatic analysis-based calculation method, the Lagrange approach, and a neural network algorithm. With an increased advance in artificial intelligence, a neural network algorithm is proposed to extend the applicability of artificial neural networks in optimizing the parameters of the stage. First, the 2-dof stage is built via a combination of an eight-lever displacement amplifier and a symmetric parallelogram mechanism. Second, a chain of mathematical equations of the 2-dof stage is constructed using a kinetostatic analysis-based method to calculate the ratio of displacement amplification and the input stiffness of the 2-dof stage. Then, the Lagrange method is utilized to formulate the dynamic equation of the 2-dof stage. Finally, a neural network algorithm is adopted to maximize the natural first frequency of the proposed stage. The optimal results determined that the frequency of the stage can achieve a high value of 112.0995 Hz. Besides, the formed mathematical models were relatively precise by comprising the simulation verifications. [ABSTRACT FROM AUTHOR]

As the competition between enterprises intensifies, employees have witnessed a decline of psychological health year by year and severe anxiety and depression. To ensure the normal work of employees, it is important to implement psychological occupational therapy intervention (POTI). The previous studies on corporate occupational values focus on the behavioral variables and attitude variables related to occupations. The research paradigm does not suit a specific group of employees. Therefore, this paper explores the individual differences in POTI guided by the realization of occupational values. For a specific group of employees, the correlations of the psychological problems with job attitude, job involvement, and psychological health level were reasoned logically, a theoretical model was established, and the full-model map was plotted to illustrate the influence of the realization of occupational values over POTI. Then, the evaluation data on the psychological intervention effect of 2,800 employees were explored based on multikernel learning, and an individual difference prediction model was constructed through multikernel learning. Finally, the predicted results of different groups of employees were compared, revealing the effectiveness of our algorithm. [ABSTRACT FROM AUTHOR]

In view of the poor performance of the original mathematical model of assembly construction project precost budget, a mathematical model of assembly construction project precost budget based on improved neural network algorithm is proposed. This paper investigates the cost content of assembly construction project and analyzes its early cost. It finds that the early cost of assembly construction project includes component production cost, transportation component cost, and installation component cost. Based on the improved neural network algorithm to build an improved neural network model, the improved neural network model to mine the cost data in the early stage of assembly construction project is used. In this paper, the earned value variable is introduced to transform the project duration and project cost in the early stage of the prefabricated construction project into quantifiable cost data, and the earned value analysis method is used to estimate the implementation cost of the prefabricated construction project. According to the result of cost estimation, the mathematical model of precost budget of prefabricated construction project is built based on the project parameters. In order to prove that the cost budget performance of the mathematical model based on the improved neural network algorithm in the early stage of assembly construction project is better, the original mathematical model is compared with the mathematical model, the experimental results show that the cost budget performance of the model is better than the original model, and the cost budget performance is improved. [ABSTRACT FROM AUTHOR]

In this paper, the problem of temperature distribution for convective straight fins with constant and temperature-dependent thermal conductivity is solved by using artificial neural networks trained by the biogeography-based heterogeneous cuckoo search (BHCS) algorithm. We have solved the integer and noninteger order energy balance equation in order to analyse the temperature distribution in convective straight fins. We have compared our results with homotopy perturbation method (HPM), variational iteration method (VIM), and homotopy perturbation Sumudu transform method (HPSTM). The results show that the ANN–BHCS algorithm gives better results than other analytical techniques. We have further checked the efficiency of the ANN–BHCS algorithm by using the performance metrics MAD, TIC, and ENSE. We have calculated the values of MAD, TIC, and ENSE for case 1 of the problem, and histograms of these metrics show the efficiency of our algorithm. [ABSTRACT FROM AUTHOR]

The spiculation sign is one of the main signs to distinguish benign and malignant pulmonary nodules. In order to effectively extract the image feature of a pulmonary nodule for the spiculation sign distinguishment, a new spiculation sign recognition model is proposed based on the doctors' diagnosis process of pulmonary nodules. A maximum density projection model is established to fuse the local three-dimensional information into the two-dimensional image. The complete boundary of a pulmonary nodule is extracted by the improved Snake model, which can take full advantage of the parallel calculation of the Spike Neural P Systems to build a new neural network structure. In this paper, our experiments show that the proposed algorithm can accurately extract the boundary of a pulmonary nodule and effectively improve the recognition rate of the spiculation sign. [ABSTRACT FROM AUTHOR]

In this paper, neural algorithms, including the multi-layered perceptron (MLP) differential approximator, generalized hybrid power series, discrete Hopfield neural network, and the hybrid numerical, are used for constructing models that incorporate a priori knowledge in the form of differential equations for dynamic engineering processes. The properties of these approaches are discussed and compared to each other in terms of efficiency and accuracy. The presented algorithms have a number of advantages over other traditional mesh-based methods such as reduction of the computational cost, speed up of the execution time, and data integration with the a priori knowledge. Furthermore, the presented techniques are applicable when the differential equations governing a system or dynamic engineering process are not fully understood. The proposed algorithms learn to compute the unknown or free parameters of the equation from observations of the process behavior, hence a more precise theoretical description of the process is obtained. Additionally, there will be no need to solve the differential equation each time the free parameters change. The parallel nature of the approaches outlined in this paper make them attractive for parallel implementation in dynamic engineering processes. [ABSTRACT FROM AUTHOR]

This paper presents a competitive co-evolutionary (ComCoE) that engages a double elimination tournament (DET) to evolve artificial neural networks (ANNs) for undertaking data classification problems. The proposed model performs a global search by a ComCoE approach to find near optimal solutions. During the global search process, two populations of different ANNs compete and fitness evaluation of each ANN is made in a subjective manner based on their participations throughout a DET which promotes competitive interactions among individual ANNs. The adaptation and fitness evaluation processes drive the global search for a more competent ANN classifier. A winning ANN is identified from the global search. Then, the Scaled Conjugate Backpropagation algorithm, which is a local search, is performed to further train the winning ANN to obtain a precise solution. The performance of the proposed classification model is evaluated rigorously; its performance is compared with the baseline ANNs of the proposed model as well as other classifiers. The results indicate that the proposed model could construct an ANN which could produce high classification accuracy rates with a compact network structure. [ABSTRACT FROM AUTHOR]

The focus in this paper embraces the hybrid models whose components are nonparametric regression and artificial neural networks. Smoothing spline, regression spline and additive regression models are considered as the nonparametric regression components. Furthermore, various multilayer perceptron algorithms and radial basis function network model are regarded as the artificial neural networks components. The performances of these models are compared by forecasting three real Turkish data sets: Domestic product per capita (GDP), the number of cars produced and the number of tourist arrivals. The results obtained by experimental evaluations show that hybrid models proposed in this paper have performed much better in comparison to hybrid models discussed in literature. [ABSTRACT FROM AUTHOR]

This paper investigates the data-based optimal control for a class of networked industrial processes with a double-layer architecture. Without knowing the dynamics of subsystems at the device layer, the index prediction function is constructed via the input/output signals, and radial basis function neural networks. The tuning laws for the index prediction function are obtained through the optimal control strategy. Then, by treating the network-induced phenomenon as random round-trip time delay and introducing the predictive algorithm, the compensation scheme is designed at the operation layer to dynamically decompose the setpoints. Finally, two simulation examples are given to further illustrate the effectiveness of the proposed compensation strategy. [ABSTRACT FROM AUTHOR]

Abstract: Incremental learning of neural networks has attracted much interest in recent years due to its wide applicability to large scale data sets and to distributed learning scenarios. Moreover, nonstationary learning paradigms have also emerged as a subarea of study in Machine Learning literature due to the problems of classical methods when dealing with data set shifts. In this paper we present an algorithm to train single layer neural networks with nonlinear output functions that take into account incremental, nonstationary and distributed learning scenarios. Moreover, it is demonstrated that introducing a regularization term into the proposed model is equivalent to choosing a particular initialization for the devised training algorithm, which may be suitable for real time systems that have to work under noisy conditions. In addition, the algorithm includes some previous models as special cases and can be used as a block component to build more complex models such as multilayer perceptrons, extending the capacity of these models to incremental, nonstationary and distributed learning paradigms. In this paper, the proposed algorithm is tested with standard data sets and compared with previous approaches, demonstrating its higher accuracy. [Copyright &y& Elsevier]

Accuracy is a critical factor in predictive modeling. A predictive model such as a decision tree must be accurate to draw conclusions about the system being modeled. This research aims at analyzing and improving the performance of classification and regression trees (CART), a decision tree algorithm, by evaluating and deriving a new methodology based on the performance of real-world data sets that were studied. This paper introduces a new approach to tree induction to improve the efficiency of the CART algorithm by combining the existing functionality of CART with the addition of artificial neural networks (ANNs). Trained ANNs are utilized by the tree induction algorithm by generating new, synthetic data, which have been shown to improve the overall accuracy of the decision tree model when actual training samples are limited. In this paper, traditional decision trees developed by the standard CART methodology are compared with the enhanced decision trees that utilize the ANN's synthetic data generation, or CART+. This research demonstrates the improved accuracies that can be obtained with CART+, which can ultimately improve the knowledge that can be extracted by researchers about a system being modeled. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel feature-based neural network (NN) approach for estimation of blood pressure (BP) from wrist oscillometric measurements. Unlike previous methods that use the raw oscillometric waveform envelope (OMWE) as input to the NN, in this paper, we propose to use features extracted from the envelope. The OMWE is mathematically modeled as a sum of two Gaussian functions. The optimum parameters of this model are found by minimizing the least squares error between the model and the OMWE using the Levenberg–Marquardt algorithm and are used as features. Two separate feed-forward NNs (FFNNs) are then designed to estimate the systolic and diastolic BPs using these features. The FFNNs are trained using the resilient backpropagation learning algorithm and tested on a data set of BP measurements recorded from 85 subjects. The performance is then compared with that of the conventional maximum amplitude algorithm, adaptive neuro-fuzzy inference system, and already published NN-based methods. It is found that the proposed approach achieves lower values of mean absolute error and standard deviation of error in the estimation of BP. In addition, the proposed approach has the following advantages: lower complexity with respect to the design parameters, smaller training data set, and lower computational load. [ABSTRACT FROM PUBLISHER]

Abstract: The focus of this paper is to propose a hybrid neural network model for associative recall of analog and digital patterns. This hybrid model consists of self-feedback neural network structures (SFNN) in parallel with generalized regression neural networks (GRNN). Using a new one-shot learning algorithm developed in the paper, pattern representations are first stored as the asymptotically stable fixed points of the SFNN. Then in the retrieving process, each pattern is applied to the GRNN to make the corresponding initial condition and to initiate the dynamical equations of the SFNN that should in turn output the corresponding representation. In this way, the corresponding stored patterns are retrieved even under high noise degradation. Moreover, contrary to many associative memories, the proposed hybrid model is without any spurious attractors and can store both binary and real-value patterns without any preprocessing. Several simulations confirm the theoretical analyses of the model. Results indicate that the performance of the hybrid model is better than that of recurrent associative memory and competitive with other classes of networks. [Copyright &y& Elsevier]

Abstract: This paper presents a nonlinear modeling approach of a proton exchange membrane fuel cell (PEMFC) based on the hybrid particle swarm optimization with Levenberg–Marquardt algorithm neural network (PSO-LM NN). The PSO algorithm converges rapidly during the initial stages of a global search, while it becomes extremely slow around the global optimum. On the contrary, the LM algorithm can achieve faster convergent speed around the global optimum, while it is prone to being trapped in the local minimum. Therefore the hybrid algorithm with a transition from PSO search to LM training is proposed to train the weights and thresholds of neural network, which aims to exploit the advantage of the both algorithms. An accurate mathematical model is an extremely useful tool for the fuel cell design, and neural network is an excellent optional tool for complex nonlinear dynamic system modeling such as PEMFC. In the paper, firstly a highly reduced PEMFC dynamic physical model is established to generate the data for the PSO-LM NN model training and validation, and then the neural network nonlinear autoregressive model based on the PSO-LM algorithm is applied in modeling PEMFC voltage and temperature model, and finally the validation test result demonstrates that the trained PSO-LM NN model can efficiently approach the dynamic behavior of a PEMFC. [Copyright &y& Elsevier]

A Centroid Neural Network with Weighted Features (CNN-WF) is proposed and presented in this paper. The proposed CNN-WF is based on a Centroid Neural Network (CNN), an effective clustering tool that has been successfully applied to various problems. In order to evaluate the importance of each feature in a set of data, a feature weighting concept is introduced to the Centroid Neural Network in the proposed algorithm. The weight update equations for CNN-WF are derived by applying the Lagrange multiplier procedure to the objective function constructed for CNN-WF in this paper. The use of weighted features makes it possible to assess the importance of each feature and to reject features that can be considered as noise in data. Experiments on a synthetic data set and a typical image compression problem show that the proposed CNN-WF can assess the importance of each feature and the proposed CNN-WF outperforms conventional algorithms including the Self-Organizing Map (SOM) and CNN in terms of clustering accuracy. [ABSTRACT FROM AUTHOR]

This paper describes the comparison of the burr size predictive models based on artificial neural networks (ANN) and response surface methodology (RSM). The models were developed based on three-level full factorial design of experiments conducted on AISI 316L stainless steel work material with cutting speed, feed, and point angle as the process parameters. The ANN predictive models of burr height and burr thickness were developed using a multilayer feed forward neural network, trained using an error back propagation learning algorithm (EBPA), which is based on the generalized delta rule. The performance of the developed ANN models were compared with the second-order RSM mathematical models of burr height and thickness. The comparison clearly indicates that the ANN models provide more accurate prediction compared to the RSM models. The details of experimentation, model development, testing, and performance comparison are presented in the paper. [ABSTRACT FROM AUTHOR]

Steady State models of Evolutionary Algorithms are widely used, yet surprisingly little attention has been paid to the effects arising from different replacement strategies. This paper explores the use of mathematical models to characterise the selection pressures arising in a selection-only environment. The first part brings together models for the behaviour of seven different replacement mechanisms and provides expressions for various proposed indicators of Evolutionary Algorithm behaviour. Some of these have been derived elsewhere, and are included for completeness, but the majority are new to this paper. These theoretical indicators are used to compare the behaviour of the different strategies. The second part of this paper examines the practical relevance of these indicators as predictors for algorithms' relative performance in terms of optimisation time and reliability. It is not the intention of this paper to come up with a "one size fits all" recommendation for choice of replacement strategy. Although some strategies may have little to recommend them, the relative ranking of others is shown to depend on the intended use of the algorithm to be implemented, as reflected in the choice of performance metrics. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have now demonstrated state-of-the-art detection performance on pedestrian datasets. However, because of their high computational complexity, detection efficiency is still a frustrating problem even with the help of Graphics Processing Units (GPUs). To improve detection efficiency, this paper proposes to share features across a group of DNNs that correspond to pedestrian models of different sizes. By sharing features, the computational burden for extracting features from an image pyramid can be significantly reduced. Simultaneously, we can detect pedestrians of several different scales on one single layer of an image pyramid. Furthermore, the improvement of detection efficiency is achieved with negligible loss of detection accuracy. Experimental results demonstrate the robustness and efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Background: Although Pneumatic Artificial Muscle (PAM) has a promising future in rehabilitation robots, it's difficult to realize accurate position control due to its highly nonlinear properties.Objective: This paper deals with position control of PAM.Methods: To describe the hysteresis inside PAM, a polynomial based phenomenological function is developed. Based on the phenomenological model for PAM and analysis of pressure dynamics within PAM, an adaptive cascade controller is proposed. Both outer loop and inner loop employ BP Neural Network tuned PID algorithm. The outer loop is to handle high nonlinearities and unmodeled dynamics of PAM, while the inner loop is responsible for nonlinearities caused by pressure dynamics.Results: Experimental results show high tracking accuracy as compared with a convention PID controller.Conclusion: The proposed controller is effective in improving performance of PAM and will be implemented in a rehabilitation robot. [ABSTRACT FROM AUTHOR]

This paper proposes an algorithm for creating rules of a fuzzy logic system using a neuro-fuzzy approach. The proposal is based on the results of Juang and Tsao who use a Fuzzy Neural Network (FNN) to generate rules and fuzzy sets from input data. A time series example is solved using our proposal, which is tested using statistical analysis of the residuals of the model. [ABSTRACT FROM AUTHOR]

Input Variable Selection (IVS) is an essential step in the development of data-driven models and is particularly relevant in environmental modelling. While new methods for identifying important model inputs continue to emerge, each has its own advantages and limitations and no single method is best suited to all datasets and modelling purposes. Rigorous evaluation of new and existing input variable selection methods would allow the effectiveness of these algorithms to be properly identified in various circumstances. However, such evaluations are largely neglected due to the lack of guidelines or precedent to facilitate consistent and standardised assessment. In this paper, a new framework is proposed for the evaluation and inter-comparison of IVS methods which takes into account: (1) a wide range of dataset properties that are relevant to real world environmental data, (2) assessment criteria selected to highlight algorithm suitability in different situations of interest, and (3) a website for sharing data, algorithms and results ( http://ivs4em.deib.polimi.it/ ). The framework is demonstrated on four IVS algorithms commonly used in environmental modelling studies and twenty-six datasets exhibiting different typical properties of environmental data. The main aim at this stage is to demonstrate the application of the proposed evaluation framework, rather than provide a definitive answer as to which of these algorithms has the best overall performance. Nevertheless, the results indicate interesting differences in the algorithms' performance that have not been identified previously. [ABSTRACT FROM AUTHOR]

Abstract: Achieving a low Noise-to-Signal Ratio (NSR) is one of the major concerns when implementing hardware-based neural networks. Continuous Valued Number System (CVNS) features have been exploited to improve the NSR. The efficiency of the network model in terms of area, power consumption, and NSR is measured using the product of the total number of neurons in the network multiplied by the network NSR, which indicates the number of neurons required for a specific NSR. The network proposed in this paper stores the weights in digital registers while the processing is done in the analog domain using CVNS arithmetic. The mathematical analysis and comparison between the proposed network and the previous structures prove that the proposed architecture improves upon in terms of both the NSR and the product of neuron multiplied by NSR. [Copyright &y& Elsevier]

This paper introduces a new algorithm for solving ordinary differential equations (ODEs) with initial or boundary conditions. In our proposed method, the trial solution of differential equation has been used in the regression-based neural network (RBNN) model for single input and single output system. The artificial neural network (ANN) trial solution of ODE is written as sum of two terms, first one satisfies initial/boundary conditions and contains no adjustable parameters. The second part involves a RBNN model containing adjustable parameters. Network has been trained using the initial weights generated by the coefficients of regression fitting. We have used feed-forward neural network and error back propagation algorithm for minimizing error function. Proposed model has been tested for first, second and fourth-order ODEs. We also compare the results of proposed algorithm with the traditional ANN algorithm. The idea may very well be extended to other complicated differential equations. [ABSTRACT FROM AUTHOR]

A new force tracking control algorithm of partial actuated lower limb exoskeleton suit, which is designed for enhancing human motion is presented in this paper. Firstly, a mathematical model of the electro-hydraulic servo system was created, and equations for the frictions in the hydraulic valve and actuator were obtained. Secondly, the appropriate observer based on the estimated functions and the measurement error equations are presented for the sliding mode control algorithm. Thirdly, a sliding mode controller with applicable surface coefficient has been designed for force tracking control of the servo system. Fourthly so as to reduce the error caused by the unchangeable surface of the sliding mode control, a radial basis functions (RBF) neural network control algorithm has been introduced to offset the disadvantage of the sliding mode control by moving the sliding surface effectively Finally, the simulation results under conditions of different frequencies and the trial results based on the human motion of sliding mode control and the RBF based sliding control are presented, which indicate that RBF based sliding control provides a better performance than regular sliding mode control. [ABSTRACT FROM AUTHOR]

Abstract: Individuals from Pittsburgh rule-based classifiers represent a complete solution to the classification problem and each individual is a variable-length set of rules. Therefore, these systems usually demand a high level of computational resources and run-time, which increases as the complexity and the size of the data sets. It is known that this computational cost is mainly due to the recurring evaluation process of the rules and the individuals as rule sets. In this paper we propose a parallel evaluation model of rules and rule sets on GPUs based on the NVIDIA CUDA programming model which significantly allows reducing the run-time and speeding up the algorithm. The results obtained from the experimental study support the great efficiency and high performance of the GPU model, which is scalable to multiple GPU devices. The GPU model achieves a rule interpreter performance of up to 64 billion operations per second and the evaluation of the individuals is speeded up of up to 3.461×when compared to the CPU model. This provides a significant advantage of the GPU model, especially addressing large and complex problems within reasonable time, where the CPU run-time is not acceptable. [Copyright &y& Elsevier]

Abstract: Neural networks have been successfully used to model nonlinear dynamic systems. However, when a static neural network model is used in system fault detection and the model prediction error is used as the residual, the residual is insensitive to the fault if the neural network used is in dependent mode. This paper proposed the use of a radial basis function network in independent mode as the system model for fault detection, and it was found that the residual is sensitive to the fault. To enhance the signal to noise ratio of the detection the recursive orthogonal least squares algorithm is employed to train the network weights. Another radial basis function network is used to isolate fault using the information in the residual signal. The developed method is applied to a benchmark simulation model of the proton exchange membrane fuel cell stacks developed at the Michigan University. One component fault, one actuator fault and three sensor faults were simulated on the benchmark model. The simulation results show that the developed approach is able to detect and isolate the faults to a fault size of ±10% of nominal values. These results are promising and indicate the potential of the method to be applied to the real world of fuel cell stacks for dynamic monitoring and reliable operations. [Copyright &y& Elsevier]

Stock index forecasting is an important tool for both the investors and the government organizations. However, due to the inherent large volatility, high noise, and nonlinearity of the stock index, stock index forecasting has been a challenging task for a long time. This paper aims to develop a novel hybrid stock index forecasting model named BSO-GNN based on the brain storm optimization (BSO) approach and the grey neural network (GNN) model by taking full advantage of the grey model in dealing with data with small samples and the neural network in handling nonlinear fitting problems. Moreover, the new developed BSOGNN, which initializes the parameters in grey neural network with the BSO algorithm, has great capability in overcoming the deficiencies of the traditional GNN model with randomly initialized parameters through solving the local optimum and low forecasting accuracy problems. The performance of the proposed BSO-GNN model is evaluated under the normalization and nonnormalization preprocessing situations. Experimental results from the Shanghai Stock Exchange (SSE) Composite Index, the Shenzhen Composite Index, and the HuShen 300 Index opening price forecasting show that the proposed BSO-GNN model is effective and robust in the stock index forecasting and superior to the individual GNN model. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we propose a novel method that performs dynamic action classification by exploiting the effectiveness of the Extreme Learning Machine (ELM) algorithm for single hidden layer feedforward neural networks training. It involves data grouping and ELM based data projection in multiple levels. Given a test action instance, a neural network is trained by using labeled action instances forming the groups that reside to the test sample’s neighborhood. The action instances involved in this procedure are, subsequently, mapped to a new feature space, determined by the trained network outputs. This procedure is performed multiple times, which are determined by the test action instance at hand, until only a single class is retained. Experimental results denote the effectiveness of the dynamic classification approach, compared to the static one, as well as the effectiveness of the ELM in the proposed dynamic classification setting. [Copyright &y& Elsevier]

Abstract: Pulse Coupled Neural Network (PCNN) is suitable for dealing with the classical shortest path problem, because of its autowave characteristic. However, most methods suggest that the autowave of PCNN models should keep a constant speed in finding the shortest paths. This paper proposes a novel self-adaptive autowave pulse-coupled neural network (SAPCNN) model for the shortest path problem. The autowave generated by SAPCNN propagates adaptively according to the current network state, which guarantees it spreads more effectively in finding the shortest paths. Our experiments, which have been carried out for both the shortest paths problem and K shortest paths problem, show that our proposed algorithm outperforms classical algorithms. [Copyright &y& Elsevier]

This paper presents a new overall system for state-of-available-power (SoAP) prediction for a lithium-ion battery pack. The essential part of this method is based on an adaptive network architecture which utilizes both fuzzy model (FIS) and artificial neural network (ANN) into the framework of adaptive neuro-fuzzy inference system (ANFIS). While battery aging proceeds, the system is capable of delivering accurate power prediction not only for room temperature, but also at lower temperatures at which power prediction is most challenging. Due to design property of ANN, the network parameters are adapted on-line to the current battery states (state-of-charge (SoC), state-of-health (SoH), temperature). SoC is required as an input parameter to SoAP module and high accuracy is crucial for a reliable on-line adaptation. Therefore, a reasonable way to determine the battery state variables is proposed applying a combination of several partly different algorithms. Among other SoC boundary estimation methods, robust extended Kalman filter (REKF) for recalibration of amp hour counters was implemented. ANFIS then achieves the SoAP estimation by means of time forward voltage prognosis (TFVP) before a power pulse occurs. The trade-off between computational cost of batch-learning and accuracy during on-line adaptation was optimized resulting in a real-time system with TFVP absolute error less than 1%. The verification was performed on a software-in-the-loop test bench setup using a 53 Ah lithium-ion cell. [ABSTRACT FROM AUTHOR]

Abstract: Brand choice models, used for describing the process of choosing mutually exclusive alternatives, attracted a large amount of attention from researchers in the early of the recent decade. These models can be used as a market response simulator for simulating marketing strategies and assessing how changes in marketing variables such as pricing and promotions will influence consumer behavior and thus perform ‘what-if’ simulations. So a reliable and relevant brand choice model can be very useful and effective, which, in fact, represents a worthwhile opportunity to improve the efficiency of the marketing decisions. In this paper we offer a new approach by integrating of Probabilistic Neural Network (PNN) and Data preprocessing for brand choice modeling and constructing a market response simulator. This approach, called Preprocessed-Probabilistic Neural Network (PPNN), consists of two main stages. First, a robust Genetic Based Instance Selection Model (GBIS) employed to look for a representative data subset of instances in training data set. The second stage ends up with a relevant brand choice model, using a probabilistic neural network trained by Dynamic Decay Adjustment Algorithm (DDA). The evaluation process is carried out using the same data set been used in literature for modeling individual consumer choices in a retail coffee market. The evaluation results show that the offered approach outperforms all previous methods, so it can be considered as an effective tool for consumer behavior modeling and simulation. [Copyright &y& Elsevier]

Abstract: This paper uses an artificial neural network (ANN) and Levenberg–Marquardt training algorithm to model the nonlinear relationship between refractive index and energy gap in semiconductors. The predicted simulation values of the ANN are in accordance with the experimental data. An error deviation (Δn) was estimated for different models. The lowest deviation is given by the ANN model. The ANN model performance was also tested for some compounds not included in the training and was found to be in good agreement with the experimental data. High precision of the NN model is demonstrated as well as good generalization performance. [Copyright &y& Elsevier]

Abstract: This study aims to develop a PD control system based on the neural network algorithm to reduce the ship rolling motion in the desired track through rudder and fin actions. The mathematical model including sea-keeping and maneuvering characteristics is developed in the present paper and the nonlinear time history of ship motions is solved by the fourth order Runge–Kutta method. In order to achieve the purpose of roll reduction and track keeping, the rudder and fin stabilizer are used as the control tools for the ship advancing in the seaway. In addition, the PD controller based on the self-tuning neural network algorithm is applied to achieve the goals of multi-input and multi-output in the control system. Four different types of control modes on a container ship model are studied and the performances are investigated in different sea states. The results indicate that the PD controller based on the self-tuning neural network algorithm applying to the stabilizer fin control for roll reduction and the rudder control for track keeping in the seaway would be suggested. [Copyright &y& Elsevier]

Abstract: Neural network systems are highly capable of deriving knowledge from complex data, and they are used to extract patterns and trends which are otherwise hidden in many applications. Preserving the privacy of sensitive data and individuals'' information is a major challenge in many of these applications. One of the most popular algorithms in neural network learning systems is the back-propagation (BP) algorithm, which is designed for single-layer and multi-layer models and can be applied to continuous data and differentiable activation functions. Another recently introduced learning technique is the extreme learning machine (ELM) algorithm. Although it works only on single-layer models, ELM can out-perform the BP algorithm by reducing the communication required between parties in the learning phase. In this paper, we present new privacy-preserving protocols for both the BP and ELM algorithms when data is horizontally and vertically partitioned among several parties. These new protocols, which preserve the privacy of both the input data and the constructed learning model, can be applied to online incoming records and/or batch learning. Furthermore, the final model is securely shared among all parties, who can use it jointly to predict the corresponding output for their target data. [Copyright &y& Elsevier]

Abstract: An artificial neural network (ANN) model is used to forecast the annual and monthly solar irradiation in Morocco. Solar irradiation data are taken from the new Satellite Application Facility on Climate Monitoring (CM-SAF)-PVGIS database. The database represents a total of 12 years of data from 1998 to 2010. In this paper, the data are inferred using an ANN algorithm to establish a forward/reverse correspondence between the longitude, latitude, elevation and solar irradiation. Specifically, for the ANN model, a three-layered, back-propagation standard ANN classifier is considered consisting of three layers: input, hidden and output layer. The learning set consists of the normalised longitude, latitude, elevation and the normalised mean annual and monthly solar irradiation of 41 Moroccan sites. The testing set consists of patterns just represented by the input component, while the output component is left unknown and its value results from the ANN algorithm for that specific input. The results are given in the form of the annual and monthly maps. They indicate that the method could be used by researchers or engineers to provide helpful information for decision makers in terms of sites selection, design and planning of new solar plants. [Copyright &y& Elsevier]

Abstract: In this paper, a novel self-organizing radial basis function (SORBF) neural network is proposed for nonlinear identification and modeling. The proposed SORBF consists of simultaneous network construction and parameter optimization. It offers two important advantages. First, the hidden neurons in the SORBF neural network can be added or removed, based on the neuron activity and mutual information (MI), to achieve the appropriate network complexity and maintain overall computational efficiency for identification and modeling. Second, the model performance can be significantly improved through the parameter optimization. The proposed parameter-adjustment-based optimization algorithm, utilizing the forward-only computation (FOC) algorithm instead of the traditionally forward-and-backward computation, simplifies neural network training, and thereby significantly reduces computational complexity. Additionally, the convergence of the SORBF is analyzed in both the structure organizing process phase and the phase following the modification. Lastly, the proposed approach is applied to model and identify the nonlinear dynamical systems. Simulation results demonstrate its effectiveness. [Copyright &y& Elsevier]

Based on information theory, the single neuron adaptive control problem for stochastic systems with non-Gaussian noises is investigated in this paper. Here, the statistic information of the output within a receding window rather than the output value is used for the tracking problem. Firstly, the single neuron controller structure, which has the ability of self-learning and self-adaptation, is established. Then, an improved performance criterion is given to train the weights of the single neuron. Furthermore, the mean-square convergent condition of the proposed control algorithm is formulated. Finally, comparative simulation results are presented to show that the proposed algorithm is superior to the PID controller. The contributions of this work are twofold: (1) the optimal control algorithm is formulated in the data-driven framework, which needn't the precise system model that is usually difficult to obtain; (2) the control problem of non-Gaussian systems can be effectively dealt with by the simple single neuron controller under improved minimum entropy criterion. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a rule-based approach for the classification of power quality disturbances. The disturbed signal is first characterized using the multi-resolution S-transform, which acts as a feature extraction tool. Then, a simple but robust rule-based classification algorithm is used to identify disturbances. This algorithm uses linear and parabolic rules as pattern classifiers where decision boundaries are established by a heuristic search. The classification algorithm has a modular structure where each module works separately to detect specific disturbances. The most common types of disturbances, including sags, interruptions, swells, harmonics and oscillatory transients, were analyzed. Moreover, complex disturbances consisting of combinations of two simple events (simultaneous or consecutive in the same interval) were also analyzed. In both cases, noise, ranging from 40 to 20dB, was also considered. The tested data set contains power quality signals obtained using mathematical models, power quality events obtained from power network''s simulations using PSCAD/EMTDC and measured signals at electrical installations. Finally, evaluation results verifying the accuracy of the proposed method are presented and compared to those obtained from a classification system based on an artificial neural network. [Copyright &y& Elsevier]

Recently, artificial neural networks, especially feedforward neural networks, have been widely used for the identification and control of nonlinear dynamical systems. However, the determination of a suitable set of structural and learning parameter value of the feed-forward neural networks still remains a difficult task. This paper is concerned with the use of extended Kalman filter and unscented Kalman filter based feedforward neural networks training algorithms. The comparisons of the performances of both algorithms are discussed and illustrated using a simulated example. The simulation results show that in terms of mean squared errors, unscented Kalman filter algorithm is superior to the extended Kalman filter and back-propagation algorithms since there are improvements between 2.45-21.48% (for training) and 8.35-29.15% (for testing). This indicates that unscented Kalman filter based feedforward neural networks learning could be a good alternative in artificial neural network models based applications for nonlinear dynamical systems. [ABSTRACT FROM AUTHOR]

Abstract: Dynamic pricing is a pricing strategy where price for the product changes according to the expected demand for it. Some work on using neural network for dynamic pricing have been previously reported, such as for forecasting the demand and modelling consumer choices. However, little work has been done in using them for optimising pricing policies. In this paper, we describe how neural networks and evolutionary algorithms can be combined together to optimise pricing policies. Particularly, we build a neural network based demand model and use evolutionary algorithms to optimise policy over build model. There are two key benefits of this approach. Use of neural network makes it flexible enough to model a range of different demand scenarios occurring within different products and services, and the use of evolutionary algorithm makes it versatile enough to solve very complex models. We also evaluate the pricing policies found by neural network based model to that found by other widely used demand models. Our results show that proposed model is more consistent, adapts well in a range of different scenarios, and in general, finds more accurate pricing policy than other three compared models. [Copyright &y& Elsevier]

Neural tree model has been successfully applied to solving a variety of interesting problems. In most previous studies, optimization of the neural tree model was divided into two steps: first structure optimization, then parameter optimization. One major problem in the evolution of structure without parameter information was noisy fitness evaluation. In this paper, an improved breeder genetic programming algorithm is proposed to the synthesis of neural tree model. The effectiveness and performance of the method are evaluated on time series prediction problems and compared with those of related methods. Simulation results show that the proposed algorithm is a potential method with better performance and effectiveness. [ABSTRACT FROM AUTHOR]

Abstract: Bruise damage is a major cause of fruit quality loss. Bruises occur under dynamic and static loading when stress induced in the fruit exceeds the failure stress of the fruit tissue. In this article the potential of an artificial neural network (ANN) technique has evaluated as an alternative method for the prediction of apple bruise volume. Neural bruise estimation models were constructed to calculate Golden Delicious apple bruise volume with respect to fruit properties. The neural models were built based upon impact force and impact energy as the main input parameters including fruit curvature radius, temperature and acoustical stiffness. Optimal parameters for the network were selected via a trial and error procedure on the available data. In this paper, the performance of Basic Backpropagation (BB) training algorithm was also compared with Backpropagation with Declining Learning Rate Factor algorithm (BDLRF). It was found that BDLRF has a better performance for the prediction of apple bruise volume. It is concluded that ANN represents a promising tool for predicting apple bruise volume in comparison to regression model. [Copyright &y& Elsevier]

Abstract: In this paper a neural detector of internal parameter changes in a stationary, non-linear SISO dynamic system is considered. A dynamic system is usually described by an input–output relation or by a set of state equations. Each change of parameter values creates a new non-nominal model of a dynamic system (sometimes with different values of parameters, sometimes with different structure and different values of parameters). Thus the detection of parameter changes can be formulated as a multi-model classification. The LVQ (Learning Vector Quantisation) neural network has been proposed as a classifier. Selected aggregated properties of discrete wavelet decomposition coefficients of the system output have been chosen as the inputs of the LVQ classifier. The output of the classifier points out the current model. The proposed approach to classification can be adopted as a fault detection method where faults are represented by changes of values of internal parameters of a system. The algorithm has been evaluated on the example of a non-linear fluid system with a non-ideal pipe which internal state is characterised by one value of a parameter, chosen from the known set. [Copyright &y& Elsevier]

Abstract: This paper proposes accurate partial shading modeling of photovoltaic (PV) system. The main contribution of this work is the utilization of the two-diode model to represent the PV cell. This model requires only four parameters and known to have better accuracy at low irradiance level, allowing for more accurate prediction of PV system performance during partial shading condition. The proposed model supports a large array simulation that can be interfaced with MPPT algorithms and power electronic converters. The accurateness of the modeling technique is validated by real time simulator data and compared with the three other types of modeling, namely Neural Network, P&O and single-diode model. It is envisaged that the proposed work is very useful for PV professionals who require simple, fast and accurate PV model to design their systems. [Copyright &y& Elsevier]