Search

In-band full duplex communication requires precise self-interference cancellation (SIC) to successfully decode the received desired signal. The existing neural network (NN) based SIC scheme uses offline trained NN to estimate the non-linear component of received self-interference (SI) over a static SI channel without additional NN training. For the time-varying SI channel, the NN-aided SIC method needs to retrain the NN during in-band full duplex communication to adapt time-varying channels. However, NN training is not fast enough to be done during full duplex communication. Thus, the SIC performance degrades. In this paper, we propose a digital SIC scheme using channel robust NN which takes estimates of linear SI channel coefficients as an input. It was found that the NN could learn the static part of the non-linear behavior of the SI channel well. Our solution can adapt the time-varying SI channel with only the channel coefficient estimation of linear components and a pre-trained NN. The proposed scheme can successfully reduce the SI to the noise floor for both time-invariant and time-varying SI channels. [ABSTRACT FROM AUTHOR]

Classifying bank accounts by using transaction data is encouraging in cracking down on illegal financial activities. However, few research simultaneously use heterogenous features, which are embedded in the time series data. In this paper, a two route convolution neural network TRHD-CNN model, fed with two types of heterogeneous feature matrices, is proposed for classifying the bank accounts. TRHD-CNN adopts divide and conquer strategy to extract characteristics from two types of data source independently. The strategy is proved able in mining complementary classification characteristics. We firstly transfer the original log data into a directed and dynamic transaction network. On the basis of that, two feature generation methods are devised for extracting information from local topological structure and time series transaction respectively. A DirectedWalk method is developed in this paper to learning the network vector of vertices used for embedding the neighbor relationship of bank account. The extensive experimental results, conducted on a real bank transaction dataset that contains illegal pyramid selling accounts, show the significant advantage of TRHD-CNN over the existing methods. TRHD-CNN can provide recall scores up to 5.15% higher than competing methods. In addition, the two-route architecture of TRHD-CNN is easy to extend to multi-route scenarios and other fields. [ABSTRACT FROM AUTHOR]

Researchers often use theoretical models which provide a relatively simple, yet concise and effective way of modelling various phenomena. However, it is a well-known fact that the more complex the model, the more complex the mathematical description is. For this reason, theoretical models generally avoid large complexity and aim for the simplest possible definition, which although makes models mathematically more manageable, in practice it also often leads to sub-optimal performance. Furthermore, the data collected during the observations usually contain confounding factors, for which a simple theoretical model can not be prepared. Overall, mathematical models are usually too rigid and sophisticated, and therefore cannot really deal with sudden changes in the environment. The application of artificial intelligence, however, provides a good opportunity to develop complex models that can combine the basic capabilities of the theoretical models with the ability to learn more complex relationships. It has been shown [16] that with neural networks, we can build such models that can approximate mathematical functions. Trained artificial neural networks are thus able to behave like theoretical models developed for different fields, while still retaining their overall flexibility, which guarantees an overall better performance in a complex real-world environment. The aim of our study is to show our notion that we can create an architecture using neural networks, which is able to approximate a given theoretical model, and then further improve it with the help of real data to suit the real world and its various aspects better. In order to validate the functionality of the architecture developed by us, we have selected a simple theoretical model, namely the Kermack-McKendrick one [4] as the base of our research. This is an SIR [2] model, which is a relatively simple compartmental epidemic model, based on differential equations that can be used well for infections that spread very similarly to influenza or COVID. However, on one hand, the SIR model relies too heavily on its parameters, with slight changes in them leading to drastic overall changes of the S, I and R curves, and on the other hand, the simplicity of the SIR model distorts its accuracy in many cases. In our paper, by using the SIR model, we will show that the architecture described above can be a valid approach to modeling the spread of a given disease (such as influenza or COVID-19). To this end, we detail the accuracy of our models with different settings and configurations and show that it performs better than both a simple mathematical model and a plain neural network with randomly initialized weights. [ABSTRACT FROM AUTHOR]

This paper studies neural network models of vehicle dynamics. We consider both models with a generic layer architecture and models with specialised topologies that hard-wire physics principles. Network pre-wiring is limited to universal laws; hence it does not limit the network modelling abilities on one side but allows more robust and interpretable models on the other side. Four different network types (with and without pre-wired structure, recursive and non-recursive) are compared for the longitudinal dynamics of a car with gears and two controls (brake and engine). Results show that pre-wiring effectively improves the performance. Non-recursive networks also look to be preferable for several reasons. [ABSTRACT FROM AUTHOR]

This article addresses why the neural network model has been selected by nature against other computational models to generate behavior in complex multicellular clades. This question, which has not yet been addressed in research, should not be ignored because understanding this issue is necessary to have a complete picture of the evolutionary process of the nervous system. The starting point to discuss the issue is a proposal made 30 years ago: the free-moving hypothesis. This proposal establishes prediction as the main function of the brain and that all multicellular organisms that move require a brain in order to make predictions. This article contains a review contrasting this hypothesis with the discoveries made in the last 30 years within different biological kingdoms. Although none of these discoveries contradict the free-moving hypothesis, it still does not answer the main question. Alternative hypotheses about the origin of the nervous system are discussed in this paper, but they also are not able to answer the question. Six hypotheses are proposed as possible answers, and each of them is discussed by comparing neural processing systems with three other alternative processing systems. The result is that the neural processing system is selected against other kinds of processing systems because it has computational robustness to damage, allowing its function of prediction to be more durable. While this result, called the first neural processing principle, answers the initial question and permits a finished proof of the free-moving hypothesis, it gives rise to the question of how computationally robust a system must be to be selected by nature. This paper claims that the system selected must be computationally robust enough to have enough offspring to allow variation. This answer, named the second neural principle, determines the minimum amount of neurons that a neural processing system must have, but not the maximum. To address this issue, the third and fourth neural processing principles are stated, which determine that the maximum number of neurons is limited by energetic restrictions and body size, respectively. The results presented in this paper show that computational robustness is an important parameter to understand the evolution of nervous system. [ABSTRACT FROM AUTHOR]

This paper mainly studies the globally fixed-time synchronization of a class of coupled neutral-type neural networks with mixed time-varying delays via discontinuous feedback controllers. Compared with the traditional neutral-type neural network model, the model in this paper is more general. A class of general discontinuous feedback controllers are designed. With the help of the definition of fixed-time synchronization, the upper right-hand derivative and a defined simple Lyapunov function, some easily verifiable and extensible synchronization criteria are derived to guarantee the fixed-time synchronization between the drive and response systems. Finally, two numerical simulations are given to verify the correctness of the results. [ABSTRACT FROM AUTHOR]

Pile foundations are usually used when the conditions of the upper soil layers are weak and unable to support the super-structural loads. Piles carry these super-structural loads deep into the ground. Therefore, the safety and stability of pile-supported structures depends largely on the behavior of the piles. In addition, accurate prediction of pile behavior is necessary to ensure appropriate structural and serviceability performance. In this paper, an ANN model is developed for predicting pile behavior based on the results of cone penetration test (CPT) data. Approximately 500 data sets, obtained from the published literature, are used to develop the ANN model. The paper compares the predictions obtained by the ANN with those given by a number of traditional methods and it is observed that the ANN model significantly outperforms the traditional methods. An important advantage of the ANN model is that the complete load-settlement relationship is captured. Finally, the paper proposes a series of charts for predicting pile behavior that will be useful for pile design. [ABSTRACT FROM AUTHOR]

Background: In this paper we present a model of parameters to aesthetically characterize films using a multi-disciplinary approach: by combining film theory, visual low-level video descriptors (modeled in order to supply aesthetic information) and classification techniques using machine and deep learning. Methods: Four different tests have been developed, each for a different application, proving the model's usefulness. These applications are: aesthetic style clustering, prediction of production year, genre detection and influence on film popularity. Results: The results are compared against high-level information to determine the accuracy of the model to classify films without knowing such information previously. The main difference with other film characterization approaches is that we are able to isolate the influence of high-level descriptors to really understand the relevance of low-level features and, accordingly propose a useful set of low-level visual descriptors for that purpose. This model has been tested with a representative number of films to prove that it can be used for different applications. [ABSTRACT FROM AUTHOR]

In this paper, modeling and identification of nonlinear dynamic systems using neuro-fractional Hammerstein model are considered. The proposed model consists of the neural networks (NNs) as the nonlinear subsystem and the fractional-order state space (FSS) as the linear subsystem. The identification procedure consists of a hybrid frequency-/time-domain approach based on the input-output data acquired from the system. First in the frequency domain, the fractional order and fractional degree of the FSS subsystem are determined offline using an iterative linear optimization algorithm. Then, in the time domain, the state-space matrices of the FSS as well as parameters of the NN are estimated using Lyapunov stability theory. Moreover, in order to use only the input-output data from the system, a fractional-order linear observer based on auxiliary model idea is utilized to estimate the system states. The convergence and stability analysis of the proposed method are provided. Simulating and experimental examples show superior performance of the proposed method as compared with the Hammerstein models reported in the literature. [ABSTRACT FROM AUTHOR]

Non-linear processes like conical tank control system is complex because of its non-linear characteristics, long-term interval and time difference between the system input and output. In this context, neural network based controller works since it is able to control and train the non-linear data set of liquid level in order to optimize the network performance. Hence, this article proposes a neural network control using gradient descent with adaptive learning rate that improves the performance and minimizes the errors, by using moving average filter and Hanning window to enhance the non-linear data. The article mainly deals with an application involving ARMA and artificial neural-based network (ANN) to model a conical tank system. To remove the recurrent components and to predict the future values of the process, the present paper employs an Autoregressive Moving Average Model (ARMA) by identifying its time varying parameters and combining with artificial neural network. MATLAB R2016b was applied for the entire simulation and training of non-linear data set. The simulation results indicate a minimization in the difference between the net input to the output and target value with that of error. The results indicated that the simulation took only 13 s to train the entire network for 6,135 iterations with the ARMA based model. [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 focuses on a new kind of artificial neural networks – the Laplace transform artificial neural networks (LTANN). It is proposed to use the Laplace transform instead of ordinary weights and a linear activation function of an artificial neuron. This extension allows to use artificial neural networks in new areas. The ordinary description of artificial neural networks is a special case of the description proposed in this paper. Three models of different geological structures based on the LTANN are discussed in this paper. Using these models, it is possible to classify an unknown geological structure as the structure without anomaly, the structure with a sinkhole or the structure with a loose zone. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the synchronization problem of impulsive fractional-order neural networks with both time-varying and distributed delays. By using the fractional Lyapunov method and Mittag–Leffler function, some sufficient conditions are derived to realize the global Mittag–Leffler synchronization of impulsive fractional-order neural networks and one illustrative example is given to demonstrate the effectiveness of the obtained results. [ABSTRACT FROM AUTHOR]

In this paper, the robust trajectory tracking design of uncertain nonlinear systems is investigated by virtue of a self-learning optimal control formulation. The primary novelty lies in that an effective learning based robust tracking control strategy is developed for nonlinear systems under a general uncertain environment. The augmented system construction is performed by combining the tracking error with the reference trajectory. Then, an improved adaptive critic technique, which does not depend on the initial stabilizing controller, is employed to solve the Hamilton–Jacobi–Bellman (HJB) equation with respect to the nominal augmented system. Using the obtained control law, the closed-loop form of the augmented system is built with stability proof. Moreover, the robust trajectory tracking performance is guaranteed via Lyapunov approach in theory and then through simulation demonstration, where an application to a practical spring–mass–damper system is included. [ABSTRACT FROM PUBLISHER]

In this paper, the sampled-data control is applied to synchronize chaotic neural networks subject to actuator saturation. By employing a time-dependent Lyapunov functional that captures the characteristic information of actual sampling pattern, we derive a local stability condition for the synchronization error systems. By this condition, we design a sampled-data controller to regionally synchronize the drive neural networks and response neural networks subject to actuator saturation. Moreover, an optimization method is given to design the desired sampled-data controller such that the set of admissible initial conditions is maximized. A numerical example is given to demonstrate the effectiveness and merits of the proposed design technique. [ABSTRACT FROM AUTHOR]

Deep learning based land cover classification algorithms have recently been proposed in the literature. In hyperspectral images (HSIs), they face the challenges of large dimensionality, spatial variability of spectral signatures, and scarcity of labeled data. In this paper, we propose an end-to-end deep learning architecture that extracts band specific spectral-spatial features and performs land cover classification. The architecture has fewer independent connection weights and thus requires fewer training samples. The method is found to outperform the highest reported accuracies on popular HSI data sets. [ABSTRACT FROM PUBLISHER]

Two coupled reaction-diffusion neural networks (CRDNNs) with different dimensions of input and output are considered in this paper. The only difference between them is whether time-varying delay is incorporated in the mathematical model of network. We respectively analyze dissipativity and passivity of these CRDNNs. First, for the systems with different dimensions of input and output vectors, two new passivity definitions are proposed. Then, by exploiting some inequality techniques, several dissipativity and passivity criteria for these CRDNNs are established. Furthermore, we analyze stability of passive CRDNNs. Finally, two examples with simulation results are presented to verify the effectiveness of the proposed criteria. [ABSTRACT FROM PUBLISHER]

The most difficult part of an artificial neural network to implement in hardware is the nonlinear activation function. For most implementations, the function used is the hyperbolic tangent. This function has received much attention in relation to hardware implementation. Nevertheless, there is no consensus regarding the best solution. In this paper, we propose a new approach by implementing the hyperbolic tangent in hardware with a polynomial modeling of the fractional exponential part. The results in the paper then demonstrate, through the use of an example, that this solution is faster than the CORDIC algorithm, but slower than the piecewise linear solution with the same error. The advantage over the piecewise linear approach is that it uses less memory. [ABSTRACT FROM AUTHOR]

Recently, nonlinear expectile regression becomes popular because it can not only explore nonlinear relationships among variables, but also describe the complete distribution of a response variable conditional on covariates information. In contrast, the traditional nonlinear expectile regression mainly confronts two shortcomings. First, it is difficult to select an appropriate form of nonlinear function. Second, it ignores the interaction effects among covariates. In this paper, we develop a new expectile regression neural network (ERNN) model by adding a neural network structure to expectile regression approach. The proposed ERNN model is flexible and can be used to explore potential nonlinear effects of covariates on expectiles of the response. The ERNN model can be easily estimated through standard gradient based optimization algorithms and output conditional expectile functions directly. The advantage of ERNN model is illustrated by Monte Carlo simulation studies. The numerical results show that the ERNN model outperforms the conventional expectile regression and support vector machine models in terms of predictive ability with both in-sample and out-of-sample test. We also apply the ERNN model to the predictions of concrete compressive strength and housing price. It turns out the marginal contribution of each predictor to the conditional expectile of a response is useful for decision-making. [ABSTRACT FROM AUTHOR]

In this paper, a novel optimal adaptive radial basis function neural network (RBFNN) control has been investigated for a class of multiple-input-multiple-output (MIMO) nonlinear robot manipulators with uncertain dynamics in discrete time. To facilitate digital implementations of the robot controller, a robot model in discrete time has been employed. A high order uncertain robot model is able to be transformed to a predictor form, and a feedback control system has been then developed without noncausal problem in discrete time. The controller has been designed by an adaptive neural network (NN) based on the feedback system. The adaptive RBFNN robot control system has been investigated by a critic RBFNN and an actor RBFNN to approximate a desired control and a strategic utility function, respectively. The rigorous Lyapunov analysis is used to establish uniformly ultimate boundedness (UUB) of closed-loop signals, and the high-quality dynamic performance against uncertainties and disturbances is obtained by appropriately selecting the controller parameters. Simulation studies validate that the proposed control scheme has performed better than other available methods currently, for robot manipulators. [ABSTRACT FROM AUTHOR]

The present modern power system is getting more complex and dynamic day by day. These Dynamic changes can be effectively handled by integrating renewable sources to the grid. The optimal usage of renewable sources will improve the overall performance of the electrical utility. Renewable energy sources and non-linear loads connected to grid have adverse effects on the power quality of the system. This paper presents I cosine ANFIS control based Dynamic Active Power Filter (DAPF) to improve the power quality of the grid at source side with effective integration of renewable sources. The model presents optimal usage of renewable sources and avoids the usage of battery by replacing with solar energy unit (SEU). DAPF fed by SEU and wind unit serves power to the load during power fluctuations from grid side. The performance of proposed model with I cosine ANFIS controller based DAPF is validated using MATLAB/SIMULINK. [ABSTRACT FROM AUTHOR]

This paper presents a multi-resolution modeling approach using wavelet neural networks. A lithium battery model, which has three resolutions, is developed to depict the modeling approach. By combining the advantages of dyadic activation functions and the orthonormal property of wavelet functions, the developed battery model possesses two salient features. First, the model is built from a coarser approximation to a finer representation by adding more details incrementally. Second, the model at a low resolution is compatible with the model at a high resolution, which means that the parameters used in a low resolution can be directly incorporated into a high resolution without any modification. This paper's results show that this battery modeling provides great flexibility for users to choose a suitable resolution to meet their requirements for model accuracy and model execution speed. [ABSTRACT FROM PUBLISHER]

In this paper, the problem of exponential stability is investigated for a class of stochastic neural networks with both Markovian jump parameters and mixed time delays. The jumping parameters are modeled as a continuous-time finite-state Markov chain. Based on a Lyapunov–Krasovskii functional and the stochastic analysis theory, a linear matrix inequality (LMI) approach is developed to derive some novel sufficient conditions, which guarantee the exponential stability of the equilibrium point in the mean square. The proposed LMI-based criteria are quite general since many factors, such as noise perturbations, Markovian jump parameters, and mixed time delays, are considered. In particular, the mixed time delays in this paper synchronously consist of constant, time-varying, and distributed delays, which are more general than those discussed in the previous literature. In the latter, either constant and distributed delays or time-varying and distributed delays are only included. Therefore, the results obtained in this paper generalize and improve those given in the previous literature. Two numerical examples are provided to show the effectiveness of the theoretical results and demonstrate that the stability criteria used in the earlier literature fail. [ABSTRACT FROM AUTHOR]

In this paper, we present a review of various computational experiments concerning neural network (NN) models developed for regional employment forecasting. NNs are nowadays widely used in several fields because of their flexible specification structure. A series of NN experiments is presented in the paper, using two data sets on German NUTS-3 districts. Individual forecasts are computed by our models for each district in order to answer the following question: How relevant are NN parameters in comparison to NN structure? Comprehensive testing of these parameters is limited in the literature. Building on different specifications of NN models-in terms of explanatory variables and NN structures-we propose a systematic choice of NN learning parameters and internal functions by means of a sensitivity analysis. Our results show that different combinations of NN parameters provide significantly varying statistical performance and forecasting power. Finally, we note that the sets of parameters chosen for a given model specification cannot be light-heartedly applied to different or more complex models. [ABSTRACT FROM AUTHOR]

Abstract: This paper describes the development of neural network models for automatic incident detection on arterial roads, using simulated data derived from inductive loop detectors and probe vehicles. The work reported in this paper extends previous research by comparing the performance of various data fusion neural network architectures and assessing model performance for various probe vehicle penetration rates and loop detector configurations. Data from 108 incidents was collected from loop detectors and probe vehicles using a calibrated and validated traffic simulation model. The best performance was obtained for detector configurations found on most existing road networks, with a detection rate of 86%, false alarm rate of 0.36% and probe vehicle penetration rate of 20%. Fusion of speed data further improved performance, resulting in an incident detection rate of 90% and a false alarm rate of 0.5%. The results reported in this paper demonstrate the feasibility of developing advanced data fusion neural network architectures for detection of incidents on urban arterials using data from existing loop detector configurations and probe vehicles. [ABSTRACT FROM AUTHOR]

Abstract: The probability of occurrence of spread-F can be modeled and predicted using neural networks (NNs). This paper presents a feasibility study into the development of a NN based model for the prediction of the probability of occurrence of spread-F over selected equatorial stations within the Brazilian sector. The input space included the day number (seasonal variation), hour (diurnal variation), sunspot number (measure of the solar activity), magnetic index (measure of the magnetic activity) and magnetic position. Twelve years of spread-F data from Brazil (covering the period 1978–1989) measured at the equatorial site Fortaleza (3.9°S, 38.45°W) and low latitude site Cachoeira Paulista (22.6°S, 45.0°W) are used in the development of an input space and NN architecture for the model. Spread-F data that is believed to be related to plasma bubble developments (range spread-F) was used in the development of the model. The model results show the probability of spread-F occurrence as a function of local time, season and latitude. Results from the Brazilian Sector NN (BSNN) based model are presented in this paper, as well as a comparative analysis with a Brazilian model developed for the same purpose. [Copyright &y& Elsevier]

Abstract: A new neural network (NN) based global empirical model for the foF2 parameter, which represents the peak ionospheric electron density, has been developed using extended temporal and spatial geophysical relevant inputs. It has been proposed that this new model be considered as a suitable replacement for the International Union of Radio Science (URSI) and International Radio Consultative Committee (CCIR) model options currently used within the International Reference Ionosphere (IRI) model for the purpose of F2 peak electron density predictions. The most recent version of the model has incorporated data from 135 global ionospheric stations including a number of equatorial stations. This paper concentrates on the ability of this new model to predict foF2 for the equatorial sector, an area that has been identified as problematic within the current IRI peak prediction setup. The improvement in the predictions of the foF2 parameter by the new model as compared to the URSI and CCIR model options of the IRI is demonstrated and the requirement for additional foF2 data from the equatorial zone for the purpose of global modeling of foF2 is highlighted in this paper. [Copyright &y& Elsevier]

Abstract: This paper illustrates, by a case study, how to apply the conceptual Worst-Case Definition (WCD) model, developed in the methodological paper in the current journal, by Sørensen et al. (2010-this issue). The case is about eco-toxicological risk assessment of pesticides under Danish conditions. Cumulative aspects are included on a conceptual basis as elements of the worst-case conditions. This defines factors that govern the risk assessment, including location in time and space of risk “hotspots”. Two pillars of concern drive the conceptual modelling: (1) What to protect (denoted Protected Units (PUs)) and (2) the reason for increased risk level (denoted Causes of Risks (CRs)). Both PUs and CRs are analysed using hierarchical procedures that facilitate a complete listing of concrete factors governing increased risk for adverse effect due to agricultural usage of pesticide. The factors governing pesticide risk are combined in a context that combines the protection of relevant groupings of organisms with the factors for increased risk level for each of these. Identification of the most important relations between defined types of PUs and CRs is illustrated using expert knowledge. Existing databases are used to form spatial distributed risk indicators as estimators for a selection of important relations between PUs and CRs. This paper illustrates how the WCD model can break down the complex issue of uncertainty into fractions that are more open for evaluations. Finally, it shows application of risk indicators in a multi-criterion analysis using respectively self organizing mapping and partial order technique in a comparative analysis that highlights critical aspects of uncertainty, due to the ambiguity between single risk indicator rankings. [Copyright &y& Elsevier]

It is a common practice to adjust the number of hidden neurons in training, and the removal of neurons in neural networks plays an indispensable role in this architecture manipulation. In this paper, a succinct and unified mathematical form is upgraded to the generic case for removing neurons based on orthogonal projection and crosswise propagation in a feedforward layer with different architectures of neural networks, and further developed for several neural networks with different architectures. For a trained neural network, the method is divided into three stages. In the first stage, the output vectors of the feedforward observation layer are classified to clusters. In the second stage, the orthogonal projection is performed to locate a neuron whose output vector can be approximated by the other output vectors in the same cluster with the least information loss. In the third stage, the previous located neuron is removed and the crosswise propagation is implemented in each cluster. On accomplishment of the three stages, the neural network with the pruned architecture is retrained. If the number of clusters is one, the method is degenerated into its special case with only one neuron being removed. The applications to different architectures of neural networks with an extension to the support vector machine are exemplified. The methodology supports in theory large-scale applications of neural networks in the real world. In addition, with minor modifications, the unified method is instructive in pruning other networks as far as they have similar network structure to the ones in this paper. It is concluded that the unified pruning method in this paper equips us an effective and powerful tool to simplify the architecture in neural networks. [ABSTRACT FROM AUTHOR]

Abstract: Wind energy evaluation is an important goal in the conversion of energy systems to more environmentally friendly solutions. In this paper, we present a novel approach to wind speed spatial estimation on the isle of Sicily (Italy): an incremental self-organizing neural network (Generalized Mapping Regressor – GMR) is coupled with exploratory data analysis techniques in order to obtain a map of the spatial distribution of the average wind speed over the entire region. First, the topographic surface of the island was modelled using two different neural techniques and by exploiting the information extracted from a digital elevation model of the region. Then, GMR was used for automatic modelling of the terrain roughness. Afterwards, a statistical analysis of the wind data allowed for the estimation of the parameters of the Weibull wind probability distribution function. In the last sections of the paper, the expected values of the Weibull distributions were regionalized using the GMR neural network. [Copyright &y& Elsevier]

Aging effects, environmental changes, thermal drifts, and soft and hard faults affect physical systems by changing their nature and behavior over time. To cope with a process evolution adaptive solutions must be envisaged to track its dynamics; in this direction, adaptive classifiers are generally designed by assuming the stationary hypothesis for the process generating the data with very few results addressing nonstationary environments. This paper proposes a methodology based on κ-nearest neighbor (NN) classifiers for designing adaptive classification systems able to react to changing conditions just-in-time (JIT), i.e., exactly when it is needed. κ-NN classifiers have been selected for their computational-free training phase, the possibility to easily estimate the model complexity κ and keep under control the computational complexity of the classifier through suitable data reduction mechanisms. A JIT classifier requires a temporal detection of a (possible) process deviation (aspect tackled in a companion paper) followed by an adaptive management of the knowledge base (KB) of the classifier to cope with the process change. The novelty of the proposed approach resides in the general framework supporting the real-time update of the KB of the classification system in response to novel information coming from the process both in stationary conditions (accuracy improvement) and in nonstationary ones (process tracking) and in providing a suitable estimate of κ. It is shown that the classification system grants consistency once the change targets the process generating the data in a new stationary state, as it is the case in many real applications. [ABSTRACT FROM AUTHOR]

Research involving artificial neural networks has tended to be driven towards efficient computation, especially in the domain of pattern recognition, or towards elucidating biological processes in the brain. Models have become more detailed as our understanding of the biology of the brain has increased, incorporating real-time behaviour of individual neurons interacting within complex system structures and dynamics. There are few examples of abstract and fully formal models of biologically plausible neural networks: in the neural networks literature models are often presented as a mixture of mathematical equations and natural language, supported by simulation code and associated experimental results. The informality often hides or obscures important aspects of a particular model, and leaves a large conceptual gap between the model descriptions and the usually low-level programming code used to simulate them. The main contribution of this paper is formally modelling and analysing a biologically plausible neural network model from the literature that exhibits complex neuron-level behaviour and network-level structure. To achieve this a modelling language ‘Pann’ is developed, based on the process algebras CSP and Hybrid χ . It is designed to be convenient for mixing the behaviour of discrete events (such as a neuron spike) with mutable continuous and discrete variables (representing chemical properties of a neuron, for instance). Its behaviour is defined using an operational semantics, from which a set of general properties of the language is proved. The groundwork for the biological model is laid by first formalising some well-known concepts from the artificial neural networks domain, such as feedforward behaviour, backpropagation, and recurrent neural networks. The Pann model of a feedforward network, comprising a set of communicating processes representing individual neurons, is proved equivalent to the standard one-line calculation of feedforward behaviour. [ABSTRACT FROM AUTHOR]

This paper presents a hybrid neural network approach to model magnetic hysteresis at macro-magnetic scale. That approach aims to be coupled together with numerical treatments of magnetic hysteresis such as FEM numerical solvers of the Maxwell's equations in time domain, as in case of the non-linear dynamic analysis of electrical machines, and other similar devices, allowing a complete computer simulation with acceptable run times. The proposed Hybrid Neural System consists of four inputs representing the magnetic induction and magnetic field components at each time step and it is trained by 2D and scalar measurements performed on the magnetic material to be modeled. The magnetic induction B is assumed as entry point and the output of the Hybrid Neural System returns the predicted value of the field H at the same time step. Within the Hybrid Neural System, a suitably trained neural network is used for predicting the hysteretic behavior of the material to be modeled. Validations with experimental tests and simulations for symmetric, non-symmetric and minor loops are presented. [ABSTRACT FROM AUTHOR]

A radial basis function (RBF) neural network control algorithm can effectively improve the robotic manipulators’ performance against a large amount of uncertainty. The adaptive law can be derived by using the Lyapunov method so that the stability of robotic manipulator control system and the weight self-adaptive convergence of RBF neural networks will be guaranteed. Meanwhile, system fluctuations and even overshot phenomenon under every start-up process, which are caused by the system’s convergence from the given nonoptimal initial weight value to the optimal weight value, can be avoided by using memristors to remember the optimal weight after the system’s first operation. According to the above analysis, this correspondence paper designs a kind of RBF neural network control algorithm based on spintronic memristors, and then analyzes its theoretical derivation process and core design idea. Finally, the system simulation model, which uses a two-link robotic manipulator as control object, is built to prove the algorithm’s validity and feasibility. Simulation results show that the proposed algorithm can satisfy the effect of presupposition. [ABSTRACT FROM PUBLISHER]

Cluster synchronization is a typical collective behavior in coupled dynamical systems, where the synchronization occurs within one group, while there is no synchronization among different groups. In this paper, under event-based mechanism, pinning cluster synchronization in an array of coupled neural networks is studied. A new event-triggered sampled-data transmission strategy, where only local and event-triggering states are utilized to update the broadcasting state of each agent, is proposed to realize cluster synchronization of the coupled neural networks. Furthermore, a self-triggered pinning cluster synchronization algorithm is proposed, and a set of iterative procedures is given to compute the event-triggered time instants. Hence, this will reduce the computational load significantly. Finally, an example is given to demonstrate the effectiveness of the theoretical results. [ABSTRACT FROM AUTHOR]

Despite the advantage of global coverage at high spatiotemporal resolutions, satellite remotely sensed precipitation estimates still suffer from insufficient accuracy that needs to be improved for weather, climate, and hydrologic applications. This paper presents a framework of a deep neural network (DNN) that improves the accuracy of satellite precipitation products, focusing on reducing the bias and false alarms. The state-of-the-art deep learning techniques developed in the area of machine learning specialize in extracting structural information from a massive amount of image data, which fits nicely into the task of retrieving precipitation data from satellite cloud images. Stacked denoising autoencoder (SDAE), a widely used DNN, is applied to perform bias correction of satellite precipitation products. A case study is conducted on the Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks Cloud Classification System (PERSIANN-CCS) with spatial resolution of 0.08° × 0.08° over the central United States, where SDAE is used to process satellite cloud imagery to extract information over a window of 15 × 15 pixels. In the study, the summer of 2012 (June-August) and the winter of 2012/13 (December-February) serve as the training periods, while the same seasons of the following year (summer of 2013 and winter of 2013/14) are used for validation purposes. To demonstrate the effectiveness of the methodology outside the study area, three more regions are selected for additional validation. Significant improvements are achieved in both rain/no-rain ( R/NR) detection and precipitation rate quantification: the results make 33% and 43% corrections on false alarm pixels and 98% and 78% bias reductions in precipitation rates over the validation periods of the summer and winter seasons, respectively. [ABSTRACT FROM AUTHOR]

Although artificial neural networks have recently gained importance in time series applications, some methodological shortcomings still continue to exist. One of these shortcomings is the selection of the final neural network model to be used to evaluate its performance in test set among many neural networks. The general way to overcome this problem is to divide data sets into training, validation, and test sets and also to select a neural network model that provides the smallest error value in the validation set. However, it is likely that the selected neural network model would be overfitting the validation data. This paper proposes a new model selection strategy (IHTS) for forecasting with neural networks. The proposed selection strategy first determines the numbers of input and hidden units, and then, selects a neural network model from various trials caused by different initial weights by considering validation and training performances of each neural network model. It is observed that the proposed selection strategy improves the performance of the neural networks statistically as compared with the classic model selection method in the simulated and real data sets. Also, it exhibits some robustness against the size of the validation data. [ABSTRACT FROM AUTHOR]

Spoken dialog systems have been proposed as a solution to facilitate a more natural human–machine interaction. In this paper, we propose a framework to model the user׳s intention during the dialog and adapt the dialog model dynamically to the user needs and preferences, thus developing more efficient, adapted, and usable spoken dialog systems. Our framework employs statistical models based on neural networks that take into account the history of the dialog up to the current dialog state in order to predict the user׳s intention and the next system response. We describe our proposal and detail its application in the Let׳s Go spoken dialog system. [ABSTRACT FROM AUTHOR]

Acceptance sampling, a category of statistical quality control, deals with the confidence of the product's quality. In certain times, it is necessary to deal with the error in the demanding distribution counting on the sample size and the pertained population size, in determining the necessitated sample size for the acute exactitude. Further this sample size with minimized error is utilized in deriving the most beneficial OC curve. Neural networks have been used to train the data with the resulting error and their matching toleration level for the sample sizes of different population sizes. This trained network can be used to foster automated acceptance or rejection of the sample size to be used for a better OC curve based on the minimized error, ensuing time reduction of the burdened work. It is better explained in this paper with the geo-statistics data, using SAS program. [ABSTRACT FROM PUBLISHER]

In a paper on quantum neural networks, Zhou and Ding (Int. J. Theor. Phys. 46(12):3209-3215 ([])) proposed a new model of quantum perceptron denoted quantum M-P neural network and showed its functionality by an example. In this letter, we show that the proposed learning algorithm does not follow an unitary evolution and the proposed neuron can be efficiently simulated by a classical single layer neural network. [ABSTRACT FROM AUTHOR]

Data based modeling applications require the complete automation of model creation of, in general, nonlinear processes. Numerous model architectures are available to approximate complex data structures, however, creating and selecting the best model provides a present challenge for application. Model ensembles provide excellent strategies if the prediction performance of the models can be assessed in some way. Information criteria approaches, trading off goodness of fit criteria against the average variance error of the model structures, are theoretically applicable, but demonstratively perform poorly in settings with sparse data sets and complex model structures, settings which are present for many industrial purposes. This paper proposes and discusses a methodology how to regularise the weight calculation building model ensembles. Thereby, the weights trade off goodness of fit criteria against empirical measures of risk, increasing the model ensemble prediction performance. The methodology is independent of the model class, applicable to all black box models, and improves prediction performance for a variety of data in several industrial application areas. [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]

Machine learning is a very important approach to pattern classification. This paper provides a better insight into Incremental Attribute Learning (IAL) with further analysis as to why it can exhibit better performance than conventional batch training. IAL is a novel supervised machine learning strategy, which gradually trains features in one or more chunks. Previous research showed that IAL can obtain lower classification error rates than a conventional batch training approach. Yet the reason for that is still not very clear. In this study, the feasibility of IAL is verified by mathematical approaches. Moreover, experimental results derived by IAL neural networks on benchmarks also confirm the mathematical validation. [ABSTRACT FROM AUTHOR]

Nonlinear system identification tends to provide highly accurate models these last decades; however, the user remains interested in finding a good balance between high-accuracy models and moderate complexity. In this paper, four balanced accuracy-complexity identification model families are proposed. These models are derived, by selecting different combinations of activation functions in a dedicated neural network design presented in our previous work (Romero-Ugalde et al. in Neurocomputing 101:170-180. doi:, ). The neural network, based on a recurrent three-layer architecture, helps to reduce the number of parameters of the model after the training phase without any loss of estimation accuracy. Even if this reduction is achieved by a convenient choice of the activation functions and the initial conditions of the synaptic weights, it nevertheless leads to a wide range of models among the most encountered in the literature. To validate the proposed approach, three different systems are identified: The first one corresponds to the unavoidable Wiener-Hammerstein system proposed in SYSID2009 as a benchmark; the second system is a flexible robot arm; and the third system corresponds to an acoustic duct. [ABSTRACT FROM AUTHOR]

This paper proposes the use of online retrained metamodels for the optimization of water distribution system (WDS) design. In these metamodels, artificial neural networks (ANNs) are used to replace the full hydraulic and water quality simulation models and differential evolution (DE) is utilized to carry out the optimization. The ANNs in the proposed online DE-ANN model are retrained periodically during the optimization in order to improve their approximation to the appropriate portion of the search space. In addition, a local search strategy is used to further polish the final solution obtained by the online DE-ANN model. Three case studies are used to verify the effectiveness of the proposed online retrained DE-ANN model for which both hydraulic and water quality constraints are considered. In order to enable a performance comparison, a model in which a DE is combined with a full hydraulic and water quality simulation model (DE-EPANET2.0) and an offline DE-ANN model (ANNs are trained only once at the beginning of optimization) are established and applied to each case study. The results obtained show that the proposed online retrained DE-ANN model consistently outperforms the offline DE-ANN model for each case study in terms of efficiency and solution quality. Compared with the DE-EPANET2.0 model, the proposed online DE-ANN model exhibits a substantial improvement in computational efficiency, while still producing reasonably good quality solutions. [ABSTRACT FROM AUTHOR]

Scale is highly detrimental to surface quality for tinplate products. There are a large number of process variables at a typical hot mill and principal component analysis is a well-known technique for reducing the number of process variables. This paper estimates the principal components associated with the hot mill process variables and puts these through an Adaptive Neuro Fuzzy Inference System (ANFIS) to find those hot mill running conditions that will minimise the amount of scale observed on the bottom of the rolled strip. It was found that the variation observed in all the hot mill process variables could be captured through the use of just six principal components, and that using just three of these in an ANFIS was sufficient to identify those operating conditions leading to coils being produced with a consistently low scale count. Specifically, it was found that the best operating conditions for the hot mill were when the first component was lower than -0.098 the second lower than 0.8058 and the third higher than -0.482. These ranges in turn corresponded to certain hot mill temperatures that depended to some extent on the base chemistry of the incoming slab. [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]

One of the main limitations of artificial neural networks (ANN) is their high inability to know in an explicit way the relations established between explanatory variables (input) and dependent variables (output). This is a major reason why they are usually called 'black boxes.' In the last few years, several methods have been proposed to assess the relative importance of each explanatory variable. Nevertheless, it has not been possible to reach a consensus on which is the best-performing method. This is largely due to the different relative importance obtained for each variable depending on the method used. This importance also varies with the designed network architecture and/or with the initial random weights used to train the ANN. This paper proposes a procedure that seeks to minimize these problems and provides consistency in the results obtained from different methods. Essentially, the idea is to work with a set of neural networks instead of a single one. The proposed procedure is validated using a database collected from a customer satisfaction survey, which was conducted on the public transport system of Granada (Spain) in 2007. The results show that, when each method is applied independently, the variable's importance rankings are similar and, in addition, coincide with the hierarchy established by researchers who have applied other techniques. [ABSTRACT FROM AUTHOR]