Search

Traditional computing architecture (Von Neumann) that requires data transfer between the off-chip memory and processor consumes a large amount of energy when running machine learning (ML) models. Memristive synaptic devices are employed to eliminate this inevitable inefficiency in energy while solving cognitive tasks. However, the performances of energy-efficient neuromorphic systems, which are expected to provide promising results, need to be enhanced in terms of accuracy and test error rates for classification applications. Improving accuracy in such ML models depends on the optimal learning parameter changes from a device to algorithm-level optimisation. To do this, this paper considers the Adadelta, an adaptive learning rate technique, to achieve accurate results by reducing the losses and compares the accuracy, test error rates, and energy consumption of stochastic gradient descent (SGD), Adagrad and Adadelta optimisation methods integrated into the Ag:a-Si synaptic device neural network model. The experimental results demonstrated that Adadelta enhanced the accuracy of the hardware-based neural network model by up to 4.32% when compared to the Adagrad method. The Adadelta method achieved the best accuracy rate of 94%, while DGD and SGD provided an accuracy rate of 68.11 and 75.37%, respectively. These results show that it is vital to select a proper optimisation method to enhance performance, particularly the accuracy and test error rates of the neuro-inspired nano-synaptic device-based neural network models. [ABSTRACT FROM AUTHOR]

English expression, language characteristics and usage norms are quite special, which is quite different from Chinese. This has special requirements for auxiliary teaching tools that use computer technology for English text processing. Based on neural network algorithm, this paper combines the actual needs of English grammar error correction to construct an English grammar error correction model based on neural network. In data processing, after feature selection, logistic regression model is used to analyze the influence of different features on article error correction. The article error correction incorporating word vector features mainly explores how to effectively express the features in English grammar error correction. In addition, this paper proposes two methods to optimize the feature representation in article error correction. One is to directly use the word vector corresponding to the word as a feature, replacing the original One-hot encoding, and the other uses a clustering method to compress the article features. Finally, this paper designs experiments to study the performance of the model constructed in this paper. The results obtained show that the model constructed in this paper has a certain effect. [ABSTRACT FROM AUTHOR]

The operation of the mobile interactive autonomous learning system injects advanced management technology and scientific and reasonable management system for the effective management and arrangement of the school's teaching, enables students to conduct autonomous learning in their spare time, makes full use of students' fragmented time, and improves students' learning enthusiasm and efficiency. Based on the neural network algorithm, this paper constructs an English network learning interactive evaluation model, studies the influence of the flattening layer in the convolutional neural network structure on the structural complexity, and then proposes spatial pyramid weighted average pooling to optimize the traditional flattened layer. Moreover, this paper evaluates RSPP from three aspects: space complexity, training time-consuming, and accuracy. In addition, this paper designs two types of integrated convolutional neural networks, namely Bagging integration and snapshot integration. Finally, this paper evaluates the performance of the model through experiments and counts the experimental results. The research results show that the model constructed in this paper has a certain effect. [ABSTRACT FROM AUTHOR]

How to build a football match prediction model and use scientific methods to solve the prediction problem has become a key point in the application of artificial intelligence in the sports industry. In this paper, we choose a BP neural network model that is powerful in processing nonlinear data to perform research. According to the demand, this paper constructs a gray fuzzy prediction model based on neural network, a gray extreme learning machine prediction model, and a gray fuzzy extreme learning machine prediction combination model based on neural network. Moreover, this paper tests the neural network model by comparing actual results with predicted results. In addition, by predicting and analyzing the football league data, this article tests the three models in terms of match result prediction accuracy, data processing speed, data transmission accuracy, match analysis scores, etc., and uses statistical analysis methods to process data, and uses intuitive statistical graphs to obtain the processing results. The research results show that the gray fuzzy extreme learning machine prediction combination model based on neural network constructed in this paper can retain the advantages of a single model and effectively improve the prediction accuracy of the model and the performance of the system. [ABSTRACT FROM AUTHOR]

In order to overcome the shortcomings of the current English network learning system, based on the neural network algorithm, this paper constructs an intelligent English network learning system based on the improved algorithm. Moreover, by analyzing the coupling between recurrent neural networks by contrast methods, this paper infers the coupling between recurrent neural networks. Moreover, this paper studies the continuous attractors of the autoencoder neural network and studies the continuous attractors of different types of autoencoder models. On this basis, this paper expands the existing model, adds the module of the interaction between the external input and the visible layer and studies the conditions required for the continuous attractor of the autoencoder model. In addition, on the basis of actual needs, this paper constructs the basic structure of the model and integrates it into the improved algorithm proposed in this paper to realize English online intelligent learning. Finally, this paper designs experiments to analyze the practical effects of this model and analyzes the experimental results through mathematical statistics. The research results show that the English network learning system constructed in this paper is effective. [ABSTRACT FROM AUTHOR]

In this paper, the spatial-temporal dynamics of a delayed reaction-diffusion Hopfield's neural network model (HNNM) under a Neumann boundary condition is considered. Our main concern is the absolute, also called the delay-independent, global or local stability of the trivial and nontrivial steady states of the HNNM with non-monotone activation functions. The dissipativity of the semiflow generated by HNNM is first proved and then the absolute attractivity of both the trivial and the nontrivial steady states is obtained by adopting the idea of connecting the spatial-temporal dynamics of the HNNM with the asymptotic behaviors of a finite-dimensional discrete dynamical system. Specifically, it is shown that the strong attractors of the finite-dimensional discrete dynamical system generated by the nonlinear activation function of the HNNM are indeed the attractors of the corresponding delayed reaction-diffusion HNNM. Numerical simulations are also conducted at last to illustrate the effectiveness of our established results. [ABSTRACT FROM AUTHOR]

Experience shows that cooperating and communicating computing systems, comprising segregated single processors, have severe performance limitations, which cannot be explained using von Neumann's classic computing paradigm. In his classic "First Draft," he warned that using a "too fast processor" vitiates his simple "procedure" (but not his computing model!); furthermore, that using the classic computing paradigm for imitating neuronal operations is unsound. Amdahl added that large machines, comprising many processors, have an inherent disadvantage. Given that artificial neural network's (ANN's) components are heavily communicating with each other, they are built from a large number of components designed/fabricated for use in conventional computing, furthermore they attempt to mimic biological operation using improper technological solutions, and their achievable payload computing performance is conceptually modest. The type of workload that artificial intelligence-based systems generate leads to an exceptionally low payload computational performance, and their design/technology limits their size to just above the "toy" level systems: The scaling of processor-based ANN systems is strongly nonlinear. Given the proliferation and growing size of ANN systems, we suggest ideas to estimate in advance the efficiency of the device or application. The wealth of ANN implementations and the proprietary technical data do not enable more. Through analyzing published measurements, we provide evidence that the role of data transfer time drastically influences both ANNs performance and feasibility. It is discussed how some major theoretical limiting factors, ANN's layer structure and their methods of technical implementation of communication affect their efficiency. The paper starts from von Neumann's original model, without neglecting the transfer time apart from processing time, and derives an appropriate interpretation and handling for Amdahl's law. It shows that, in that interpretation, Amdahl's law correctly describes ANNs. [ABSTRACT FROM AUTHOR]

This paper presents an approach for the optimisation of geological disposal canister loadings, combining high resolution simulations of used nuclear fuel characteristics with an articial neural network and a genetic algorithm. The used nuclear fuels (produced in an open fuel cycle without reprocessing) considered in this work come from a Swiss Pressurised Water Reactor, taking into account their realistic lifetime in the reactor core and cooling periods, up to their disposal in the final geological repository. The case of 212 representative used nuclear fuel assemblies is analysed, assuming a loading of 4 fuel assemblies per canister, and optimizing two safety parameters: the fuel decay heat (DH) and the canister effective neutron multiplication factor k eff . In the present approach, a neural network is trained as a surrogate model to evaluate the k eff value to substitute the time-consuming-code Monte Carlo transport & depletion SERPENT for specific canister loading calculations. A genetic algorithm is then developed to optimise simultaneously the canister k eff and DH values. The k eff computed during the optimisation algorithm is using the previously developed artificial neural network. The optimisation algorithm allows (1) to minimize the number of canisters, given assumed limits for both DH and k eff quantities and (2) to minimize DH and k eff differences among canisters. This study represents a proof-of-principle of the neural network and genetic algorithm capabilities, and will be applied in the future to a larger number of cases. [ABSTRACT FROM AUTHOR]

One of the most important problems in teleoperation systems is time delay and packet loss in the communication channel, which can affect transparency and stability. One way to overcome the time delay effects in a teleoperation system is to predict the master-side motion. In this way, when data is received in the slave side, it will be considered as the current position of the master robot and, thus, complete transparency could be achieved. The majority of the previous works regarding operator position prediction have considered known and constant time delay in the system; however, in the real applications, time delay is unknown and variable. In this paper, an adaptive online prediction approach based on artificial neural network (NN) is proposed. The time delay of the communication channel is estimated using an observer based on the dynamics of the master and slave sides. Then an artificial NN predicts the master-side motion based on the current available data of the master robot and the variable time delay estimated by the observer. This adaptive prediction approach is utilized in simulations and experiments on Phantom Omni haptic devices. The simulation results indicate the feasibility of this approach. It is revealed that this approach can predict an alternative human's hand motion in a teleoperation system with unknown and variable time delay. Finally, the simulation results would be supported by experimental results. [ABSTRACT FROM AUTHOR]

Semantic understanding is an essential research issue for many applications, such as social network analysis, collective intelligence and content computing, which tells the inner meaning of language form. Recently, Abstract Meaning Representation (AMR) is attracted by many researchers for its semantic representation ability on an entire sentence. However, due to the non-projectivity and reentrancy properties of AMR graphs, they lose some important semantic information in parsing from sentences. In this paper, we propose a general AMR parsing model which utilizes a two-stack-based transition algorithm for both Chinese and English datasets. It can incrementally parse sentences to AMR graphs in linear time. Experimental results demonstrate that it is superior in recovering reentrancy and handling arcs while is competitive with other transition-based neural network models on both English and Chinese datasets. [ABSTRACT FROM AUTHOR]

Lane–Emden differential equations describe different physical and astrophysical phenomena that include forms of stellar structure, isothermal gas spheres, gas spherical cloud thermal history, and thermionic currents. This paper presents a computational approach to solve the problems related to fractional Lane–Emden differential equations based on neural networks. Such a solution will help solve the fractional polytropic gas spheres problems which have different applications in physics, astrophysics, engineering, and several real-life issues. We used artificial neural network (ANN) framework in its feed-forward back-propagation learning scheme. The efficiency and accuracy of the presented algorithm are checked by testing it on four fractional Lane–Emden equations and compared with the exact solutions for the polytropic indices n = 0,1,5 and those of the series expansions for the polytropic index n = 3. The results we obtained prove that using the ANN method is feasible and accurate and may outperform other methods. [ABSTRACT FROM AUTHOR]

Brain–computer interface (BCI) is the current trend in technology expansion as it provides an easy interface between human brain and machine. The demand for BCI-based applications is growing tremendously, and efforts are in progress to deploy BCI devices for real-world applications. One of the widely known applications of BCI technology is rehabilitation in which BCI devices can provide various types of assistance to specially abled persons. In this paper, the effect of hand actions on objects is analyzed for motor-related mental task. The proposed approach analyzes electroencephalogram (EEG)-based brain activity which was captured for images shown with different gripping actions on objects. The EEG recordings are first pre-processed, followed by extraction of epochs and frequency bands using discrete wavelet transform; afterward, feature extraction followed by training and classification steps is performed for classifying the grip action into congruent (correct) and incongruent (incorrect) grip categories. The proposed work makes use of average power and relative wavelet energy as discriminating features which are then fed to train an artificial neural network for automatically classifying the incoming EEG patterns into correct or incorrect object hand grips. The performance evaluation of the proposed system is done on real EEG dataset obtained from 14 subjects. Experimental results have shown an accuracy of 75%. Also, to evaluate the effectiveness of our work, a comparison of our work with other state-of-the-art works reported by different authors is presented at the end. The results show the effectiveness of proposed approach and suggest further that the system can be used to analyze and train subjects having motor-related disabilities for perceiving correct or incorrect hand grips on objects. [ABSTRACT FROM AUTHOR]

The key to the coordination of photovoltaic power generation and conventional energy power load lies in the accurate prediction of photovoltaic power generation. At present, prediction models have problems with accuracy and system operation stability. Based on the neural network algorithm, this research carries the prediction of energy photovoltaic power generation and establishes a BP neural network prediction model and a wavelet neural network prediction model. Moreover, this research studies the influence of various factors on the prediction t of photovoltaic power generation, and analyzes the relationship between the various factors. In addition, in this study, a comparative test is constructed to analyze the model performance, and a statistical graph is drawn to take a visual comparison of performance. The research shows that the model proposed in this paper has certain effects and has certain advantages in the prediction of photovoltaic power generation. [ABSTRACT FROM AUTHOR]

This paper investigates the ability of four artificial intelligence techniques, including artificial neural network (ANN), radial basis neural network (RBNN), adaptive neuro-fuzzy inference system (ANFIS) with grid partitioning, and ANFIS with fuzzy c-means clustering, to predict the peak and residual conditions of actively confined concrete. A large experimental test database that consists of 377 axial compression test results of actively confined concrete specimens was assembled from the published literature, and it was used to train, test, and validate the four models proposed in this paper using the mentioned artificial intelligence techniques. The results show that all of the neural network and ANFIS models fit well with the experimental results, and they outperform the conventional models. Among the artificial intelligence models investigated, RBNN model is found to be the most accurate to predict the peak and residual conditions of actively confined concrete. The predictions of each proposed model are subsequently used to study the interdependence of critical parameters and their influence on the behavior of actively confined concrete. [ABSTRACT FROM AUTHOR]

Containers are shaping the new era of cloud applications due to their key benefits such as lightweight, very quick to launch, consuming minimum resources to run an application which reduces cost, and can be easily and rapidly scaled up/down as per workload requirements. However, container-based cloud applications require sophisticated auto-scaling methods that automatically and in a timely manner provision and de-provision cloud resources without human intervention in response to dynamic fluctuations in workload. To address this challenge, in this paper, we propose a proactive machine learning-based approach to perform auto-scaling of Docker containers in response to dynamic workload changes at runtime. The proposed auto-scaler architecture follows the commonly abstracted four steps: monitor, analyze, plan, and execute the control loop. The monitor component continuously collects different types of data (HTTP request statistics, CPU, and memory utilization) that are needed during the analysis and planning phase to determine proper scaling actions. We employ in analysis phase a concise yet fast, adaptive, and accurate prediction model based on long short-term memory (LSTM) neural network to predict future HTTP workload to determine the number of containers needed to handle requests ahead of time to eliminate delays caused by starting or stopping running containers. Moreover, in the planning phase, the proposed gradually decreasing strategy avoids oscillations which happens when scaling operations are too frequent. Experimental results using realistic workload show that the prediction accuracy of LSTM model is as accurate as auto-regression integrated moving average model but offers 600 times prediction speedup. Moreover, as compared with artificial neural network model, LSTM model performs better in terms of auto-scaler metrics related to provisioning and elastic speedup. In addition, it was observed that when LSTM model is used, the predicted workload helped in using the minimum number of replicas to handle future workload. In the experiments, the use of GDS showed promising results in keeping the desired performance at reduced cost to handle cases with sudden workload increase/decrease. [ABSTRACT FROM AUTHOR]

Due to its technical and economic advantages, the use of explosives in underground rock excavation is widely adopted. However, some safety and, especially, environmental issues arise when using this technique, mainly concerning ground vibrations induced by blasts. Thus, to minimize dynamic environmental impacts, prediction of blast-induced vibrations is imperative. In the last few years, artificial neural networks (ANNs) have been applied to model blast-induced ground vibrations. Nevertheless, ANN's architecture, mainly the number of neurons in the hidden layer, has been selected manually concerning ANN's performance parameters. To avoid over-fitting and reduce model's complexity, this paper presents a bilevel optimization of ANN architecture, considering two transfer functions, based on the maximization of quality of the adjustment and model's complexity, this last one as a penalty criterion. An ANN approach based on this bilevel optimization was successfully applied on a database of 1188 samples obtained from underground blast-induced ground vibration monitoring in a granitic rock mass. A residual analysis of the best-fitted model is performed to ensure the quality of the adjustment. It is demonstrated that the determined ANN model offers much higher generalization ability than the traditional prediction models usually used for blast-induced ground vibration amplitude predictions and other ANN architectures applied to ground vibration prediction. [ABSTRACT FROM AUTHOR]

In order to improve the prediction accuracy and modeling speed of railway freight volume, this paper combines the cargo floating price prediction model with the neural network algorithm (hereinafter referred to as NNA) to establish a prediction model. The railway cargo floating price based on neural network (hereinafter referred to as PMBCFP) relies on the random forest regression algorithm (hereinafter referred to as RFRA). Through the neural network operator in the prediction model of the floating price of goods, the randomness of the original sequence is weakened, and the implicit rules in the series are mined. The characteristics of neural networks are computationally very simple. In addition, a random forest regression algorithm is applied to the optimization, RFRA's choice. Case studies of China's rail freight volume show that RMSE and other indicators are faster. The MAE, MPE and Tell inequality coefficients obtained from this model were 0.0628, 0.0523, 0.0162 and 0.0107, respectively. This model has good prediction results. The time to search for the best parameters of RFRA using the NNA algorithm is 55.656 s, which is 10.462 s less than the time required for traditional cross-validation methods. Therefore, it is suitable for short-term forecasting of railway freight volume. [ABSTRACT FROM AUTHOR]

With the increasing severity of air pollution, PM2.5 in aerosols, as the most important air pollutant, has adversely affected people's normal production, life and work, and has caused harm to people's health. Scientific and effective prediction of PM2.5 can enable people to take precautions in advance to avoid or reduce harm to the human body. Therefore, the prediction of PM2.5 concentration has become a topic of great practical significance. This paper selects the air quality data released in real time, obtains the historical monitoring data of air environmental pollutants, and normalizes the data, then divides the sample data, and divides it into training data set and test data set in appropriate proportion. Design the optimal network structure based on BP neural network. An improved neural network is proposed, and the neural network is optimized using genetic algorithms. The preprocessed data are input into the network for training and testing. The fitting and prediction results were statistically and comparatively analyzed. The data results show that the neural network optimized by genetic algorithm has better performance in PM2.5 mass concentration prediction, which improves the accuracy of prediction results and reduces the error rate. [ABSTRACT FROM AUTHOR]

This paper proposes a neural network model for solving convex nonlinear optimization problems (CNOP) with equality and inequality constraints, whose equilibrium point coincides with the solution of Karush–Kuhn–Tucker points of the CNOP. Based on equality transformation and a Fischer–Burmeister function, we first transform the CNOP into a unconstrained minimization problem via a merit function. Then, using the steepest descent method, the neural network is constructed. On the basis of the convex analysis theory, Lyapunov stability theory and LaSalle invariance principle, the proposed network is proved to be stable in the sense of Lyapunov and converges to the optimal solution of the CNOP. Moreover, the proposed neural network is proved to be exponentially stable. Comparing with the existing models, the proposed neural network has fewer variables and neurons, which makes circuit realization easier. Simulation results show the feasibility and efficiency of the proposed network. [ABSTRACT FROM AUTHOR]

This paper is mainly aimed at developing an off-line supervision approach geared to complex processes. This approach consists of two parts: the first part is the fault detection and isolation and the second one is the process control. The first part is devoted to the implementation of the multilayer neural PCA which combines the advantage of data reduction provided by the principal component analysis and the power of neural network linearization. The transition to control is conditioned by the absence of faults in the process; if there is a defect, it must be isolated by identifying the defected variables. The second part rests on the combination of two control tools: both the gain scheduling and the feedback linearization yield a new approach called nonlinear gain scheduling. To have our work validated, we applied it to a photovoltaic system and it gave effective results. [ABSTRACT FROM AUTHOR]

Image segmentation is a process of segregating foreground object from background object in an image. This paper proposes a method to perform image segmentation for the color and textured images with a two-step approach. In the first step, self-organizing neurons based on neural networks are used for clustering the input image, and in the second step, multiphase active contour model is used to get various segments of an image. The contours are initialized in the active contour model with the help of the self-organizing maps obtained as a result of first step. From the results, it is inferred that the proposed method provides better segmentation result for all types of images. [ABSTRACT FROM AUTHOR]

Traffic identification is currently an important challenge for network management and security. In this paper, we propose a novel application identification method named as MPNN to improve the efficiency and flexibility of application identification. MPNN is based on a structure of multiple neural networks, and it uses an individual neural network module to handle a single application; therefore, it can effectively utilize the characteristics of every application; meanwhile, the minimum Bayes method is used in every neural network module. The MPNN method has the following advantages: it can handle more complex network behavior and extend the identified object from complete TCP flows to all TCP+UDP flows. It can improve the identification accuracy of every application, especially for those applications which containing much less traffic than others. The process of changing identified applications become much easier. Due to adopting parallel processing, it has much lower time and space complexity. The theoretical analysis and experimental results show that MPNN could achieve 95% identification accuracy. [ABSTRACT FROM AUTHOR]

Recently, using of the intelligent technologies in the field of clinical decision making is increased rapidly to improve the lifestyles of patients and to help for reducing the workload and cost concerned in their healthcare. Heart diseases are one of the primary causes of death. However, if the diseases are identified at the early stage, the rate of death can be decreased. Thus, the disease identification process has become a matter of concern. An efficient medical recommendation system has been proposed in this paper, namely Fourier transformation-based heart disease prediction system (FTHDPS) by using Fourier transformation and machine learning technique to predict the chronic heart diseases effectively. Here, the input sequences rely on the patient's time series details or data, which are crumbled by Fourier transformation for extracting the frequency information. In FTHDPS, a bagging model is utilized for predicting the conditions of the patients in advance to produce the absolute recommendation. In FTHDPS, three classifiers are used, namely artificial neural network, Naive Bayes and support vector machine, and real-life time series chronic heart disease data are used to evaluate the proposed model. The experimental results demonstrate that FTHDPS is much efficient to provide a reliable and accurate recommendation to the heart patients. [ABSTRACT FROM AUTHOR]

In Indian economy, agriculture is the prime vocation that avails in the overall development of the country. Tamil Nadu occupies approximately 7% of the nation's population, with 3% of water resources and 4% of land resources at the country level. The crop suitability prediction is of prime importance to enhance the nutritional security to the developing country. Based on several crops grown in a particular place, and the availability of natural resources, one can identify the suitability of crops that can be grown in a particular place. To this end, many mathematical tools were developed, but they failed to include processing of uncertainties present in the accumulated data. Therefore, in this paper an effort has been made to process the uncertainties by hybridizing rough set on fuzzy approximation space and neural network. The rough set on fuzzy approximation space identifies the almost indiscernibility among the natural resources and helps in minimizing the computational procedure on employing data reduction techniques, whereas neural network helps in prediction process. The proposed model is analysed on agriculture data of Vellore District of Tamil Nadu, India, and achieved 93% of classification accuracy in validation. The model is compared with an earlier model and achieved 8% more accuracy while predicting unseen associations. [ABSTRACT FROM AUTHOR]

The determination of the energy characteristics of a Kaplan hydraulic turbine is based on numerous measuring points during extensive and expensive experimental model tests in laboratory and on-site prototype tests at the hydropower plant. The results of those experimental researches are valuable insofar as they are detailed and comprehensive. In order to reduce the number of modes, in which the double-regulated turbine has to be tested with the aim of obtaining the off-cam energy characteristics in unknown operating modes, the application of contemporary artificial neural networks models is presented in the paper. The rationalization of the turbine test conditions may not be at the expense of the quality of the obtained characteristics. Two types of neural networks, feedforward neural networks and adaptive network-based fuzzy inference system with different partitioning methods, were used. The reliability of applied method was considered by analyzing and validating the predicted turbine energy parameters with the results obtained in the highly sophisticated laboratory. [ABSTRACT FROM AUTHOR]

As a consequence of increasing wind power penetration level, it will be a big challenge to control and operate the power system because of the inherent uncertainty of the wind energy. One of the ways to deal with the wind power variability is to predict it accurately and reliably. The traditional point forecasting-based technique cannot notably solve the uncertainty in power system operation. In order to compute the probabilistic forecasting, which yields information on the uncertainty of wind power, a novel hybrid intelligent method that incorporates the wavelet transform, neural network (NN), and improved krill herd optimization algorithm (IKHOA), is used in this paper. Also, the extreme learning machine is exerted to train NN and calculates point forecasts, and IKHOA is applied to forecast the noise variance. The robust method called bootstrap is regarded to create prediction intervals and calculate the model uncertainty. The efficiency of proposed forecasting engine is evaluated by usage of wind power data from the Alberta, Canada. [ABSTRACT FROM AUTHOR]

The global synchronization of coupled neural networks with hybrid coupling has been studied in this paper. The hybrid coupling is formed from constant coupling, discrete-delay coupling, and distributed-delay coupling. In this regard, a larger class and more complicated coupled neural networks lead in the synchronization problem procedure. According to the new augmented Lyapunov-Krasovskii functional and the idea of M-segmentation of delay length, a less conservative delay-dependent criterion is obtained and expressed in the form of linear matrix inequalities. In many cases, due to the increasing segmentation number, the delay length M-segmentation method could give an opportunity to the user to find a bigger upper bound of the maximum allowable time delay. The effectiveness of suggested method above is proved by simulating a numerical example on a typical chaotic cellular neural network. The results show that the above-mentioned method is less conservative than the other methods reviewed in this article. [ABSTRACT FROM AUTHOR]

In this paper, we consider the challenging problem of finding shared information in multiple data streams simultaneously. The standard statistical method for doing this is the well-known canonical correlation analysis (CCA) approach. We begin by developing an online version of the CCA and apply it to reservoirs of an echo state network in order to capture shared temporal information in two data streams. We further develop the proposed method by forcing it to ignore shared information that is created from static values using derivative information. We finally develop a novel multi-set CCA method which can identify shared information in more than two data streams simultaneously. The comparative effectiveness of the proposed methods is illustrated using artificial and real benchmark datasets. [ABSTRACT FROM AUTHOR]

This paper proposes a novel approach for the evolution of artificial creatures which moves in a 3D virtual environment based on the neuroevolution of augmenting topologies (NEAT) algorithm. The NEAT algorithm is used to evolve neural networks that observe the virtual environment and respond to it, by controlling the muscle force of the creature. The genetic algorithm is used to emerge the architecture of creature based on the distance metrics for fitness evaluation. The damaged morphologies of creature are elaborated, and a crossover algorithm is used to control it. Creatures with similar morphological traits are grouped into the same species to limit the complexity of the search space. The motion of virtual creature having 2-3 limbs is recorded at three different angles to check their performance in different types of viscous mediums. The qualitative demonstration of motion of virtual creature represents that improved swimming of virtual creatures is achieved in simulating mediums with viscous drag 1-10 arbitrary unit. [ABSTRACT FROM AUTHOR]

In this paper, we present a new solving approach for a class of multi-leader-follower games. For the problem studied, we firstly propose a neural network model. Then, based on Lyapunov and LaSalle theories, we prove that the trajectory of the neural network model can converge to the equilibrium point, which corresponds to the Nash equilibrium of the problem studied. The numerical results show that the proposed neural network approach is feasible to the problem studied. [ABSTRACT FROM AUTHOR]

The image semantic segmentation has been extensively studying. The modern methods rely on the deep convolutional neural networks, which can be trained to address this problem. A few years ago networks require the huge dataset to be trained. However, the recent advances in deep learning allow training networks on the small datasets, which is a critical issue for medical images, since the hospitals and research organizations usually do not provide the huge amount of data. In this paper, we address medical image semantic segmentation problem by applying the modern CNN model. Moreover, the recent achievements in deep learning allow processing the whole image per time by applying concepts of the fully convolutional neural network. Our qualitative and quantitate experiment results demonstrated that modern CNN can successfully tackle the medical image semantic segmentation problem. [ABSTRACT FROM AUTHOR]

This paper proposes a simplified neural network for generalized least absolute deviation by transforming its optimization conditions into a system of double projection equations. The proposed network is proved to be stable in the sense of Lyapunov and converges to an exact optimization solution of the original problem for any starting point. Compared with the existing neural networks for generalized least absolute deviation, the new model has the least neurons and low complexity and is suitable to parallel implementation. The validity and transient behavior of the proposed neural network are demonstrated by numerical examples. [ABSTRACT FROM AUTHOR]

A finite element model of commercial vehicles was firstly built in the paper to study the virtual reality of vibration characteristics, and the top 6-order modal was then computed and compared with the experimental results to verify the reliability of the computational model. Then, a neural network model of the cabin was built. Through road tests, the excitation signal at the cabin suspension point and the response signal of interior vibration noise were measured under the idle condition and constant speed condition. The measured excitation signal was applied to the prediction model for frequency response analysis, in order to compute the interior noise within the range 20-200 Hz. The obtained simulation result of the vibration noise was compared with the experimental result and analyzed. As indicated from the analysis, the influence of excitation spectrum and the model can be reflected by the simulation response spectrum, which is consistent with the experimental result. The higher precision can be also obtained when the model is applied to predict the interior noise. [ABSTRACT FROM AUTHOR]

In spite of advanced material cutting technology, there are still some problems due to unpredicted vibrations on horizontal and vertical directions on column drilling machines. This paper presents an investigation for drilling condition of drill column machines performance using proposed neural networks. The investigation is divided into two parts. First, the drill column machine is employed to analyze vibrations with steel and aluminum materials for increased drilling speeds. During the working of the system, some measuring points are indicated to analyses of drilling conditions. Finally, two types of proposed neural networks predictors are used to predict vibration variation for both cases of steel and aluminum materials of drilling systems. The experimental and simulation result is improved that radial basis neural network has superior performance to adapt experimental applications for drill column machines. [ABSTRACT FROM AUTHOR]

This paper investigates the feasibility of using artificial neural networks (ANNs) modeling to predict the properties of self-compacting concrete (SCC) containing fly ash as cement replacement. For the purpose of constructing this model, a database of experimental data was gathered from the literature and used for training and testing the model. The data used in the artificial neural network model are arranged in a format of six input parameters that cover the total binder content, fly ash replacement percentage, water-binder ratio, fine aggregates, coarse aggregates and superplasticizer. Four outputs parameters are predicted based on the ANN technique as the slump flow, the L-box ratio, the V-funnel time and the compressive strength at 28 days of SCC. To demonstrate the utility of the proposed model and improve its performance, a comparison of the ANN-based prediction model with other researcher's experimental results was carried out, and a good agreement was found. A sensitivity analysis was also conducted using the trained and tested ANN model to investigate the effect of fly ash on SCC properties. This study shows that artificial neural network has strong potential as a feasible tool for predicting accurately the properties of SCC containing fly ash. [ABSTRACT FROM AUTHOR]

The paper documents a concept of ocean forecasting system for ocean surface currents based on self-organizing map (SOM) trained by high-resolution numerical weather prediction (NWP) model and high-frequency (HF) radar data. Wind and surface currents data from the northern Adriatic coastal area were used in a 6-month long training phase to obtain SOM patterns. Very high correlation between current and joined current and wind SOM patterns indicated the strong relationship between winds and currents and allowed for creation of a prediction system. Increasing SOM dimensions did not increase reliability of the forecasting system, being limited by the amount of the data used for training and achieving the lowest errors for 4 × 4 SOM matrix. As the HF radars and high-resolution NWP models are strongly expanding in coastal oceans, providing reliable and long-term datasets, the applicability of the proposed SOM-based forecasting system is expected to be high. [ABSTRACT FROM AUTHOR]

This paper studies the performance of an artificial neural network (ANN) with teaching-learning-based optimization (TLBO) for modeling electric energy demand (EED) in Turkey. The ANN with TLBO (ANN-TLBO) was compared to the ANN with backpropagation (ANN-BP) and the ANN with artificial bee colony algorithm (ANN-ABC) models. Gross domestic product, population, import, and export were selected as independent variables in the models. The results reveal that the ANN-TLBO models perform better than the ANN-BP and ANN-ABC models in EED estimation. The average root-mean-square error of the ANN-BP and ANN-ABC models was decreased by 42.3 and 39.3 % using the ANN-TLBO model, respectively. Different scenarios have been studied over a projected 6-year period, from 2013 to 2018, to forecast Turkey's EED. The results of the proposed model give excellent clues with regards to its use in future energy studies. [ABSTRACT FROM AUTHOR]

In this paper, an adaptive robust finite-time neural control scheme is proposed for uncertain permanent magnet synchronous motor servo system with nonlinear dead-zone input. According to the differential mean value theorem, the dead zone is represented as a linear time-varying system, and the model uncertainty including the dead zone is approximated by using a simple neural network. Then, an adaptive finite-time controller is designed based on a fast terminal sliding mode control principle, and the singularity problem in the initial TSMC is circumvented by modifying the terminal sliding manifold. Comparative experiments are conducted to validate the effectiveness and superior performance of the proposed method. [ABSTRACT FROM AUTHOR]

In the last decades, a plethora of advanced computational models and techniques have been proposed on the modeling, assessment and design of masonry structures. The successful application of such sophisticated models necessitates the development of reliable analytical models capable of describing the failure of masonry materials. Nevertheless, there is a lack of analytical models due to the anisotropic and brittle nature exhibited by the masonry materials. In the present paper, the use of neural networks (NNs) is proposed to approximate the failure surface of masonry materials in dimensionless form. The comparison of the derived results with experimental findings as well as analytical results demonstrates the promising potential of using NNs for the reliable and robust approximation of the masonry failure surface under biaxial stress. [ABSTRACT FROM AUTHOR]

Artificial neural networks have been widely used in time series prediction. In this paper, multi-layer feedforward neural networks with optimized structures, using particle swarm optimization (PSO) algorithm, are used for hourly load prediction based on load time series of IEEE Reliability Test System. To have a small and appropriate feature subset, a hybrid method is used for feature selection in this paper. This hybrid method uses the combination of genetic algorithm (GA) and ant colony optimization (ACO) algorithm. The season, day of the week, time of the day and history load are considered as load influencing factors in this study based on the mentioned standard load dataset. The optimized number of neurons in the hidden layers of multi-layer perceptron (MLP) is determined using PSO algorithm. Experimental results show that the proposed hybrid model offers superior performance, in terms of mean absolute percentage error (MAPE), in time series prediction as compared to some recent researches in this field. [ABSTRACT FROM AUTHOR]

This paper illustrates the application of an adaptive flight control architecture to a scale quad-rotor. For autonomous vertical takeoff and landing flight, it is common to separate the control problem into an inner fast loop that controls attitude and an outer slow loop that controls the trajectory tracking. In this paper, we augment a conventional proportional and derivative controller conceived mainly for hovering, with an adaptive element using a real-time tuning single hidden layer neural network in a inner–outer loop combined architecture to account for model inversion error cancelation, issued in the feedback linearization process. The results shown in simulations reveal the superior performance of the augmented controller in tracking maneuvers. [ABSTRACT FROM AUTHOR]

Automated classification systems have allowed for the rapid development of exploratory data analysis. Such systems increase the independence of human intervention in obtaining the analysis results, especially when inaccurate information is under consideration. The aim of this paper is to present a novel approach, a neural networking, for use in classifying interval information. As presented, neural methodology is a generalization of probabilistic neural network for interval data processing. The simple structure of this neural classification algorithm makes it applicable for research purposes. The procedure is based on the Bayes approach, ensuring minimal potential losses with regard to that which comes about through classification errors. In this article, the topological structure of the network and the learning process are described in detail. Of note, the correctness of the procedure proposed here has been verified by way of numerical tests. These tests include examples of both synthetic data, as well as benchmark instances. The results of numerical verification, carried out for different shapes of data sets, as well as a comparative analysis with other methods of similar conditioning, have validated both the concept presented here and its positive features. [ABSTRACT FROM AUTHOR]

The auto-encoder model plays a crucial role in the success of deep learning. During the pre-training phase, auto-encoders learn a representation that helps improve the performance of the entire neural network during the fine-tuning phase of deep learning. However, the learned representation is not always meaningful and the network does not necessarily achieve higher performance with such representation because auto-encoders are trained in an unsupervised manner without knowing the specific task targeted in the fine-tuning phase. In this paper, we propose a novel approach to train auto-encoders by adding an explicit guiding term to the traditional reconstruction cost function that encourages the auto-encoder to learn meaningful features. Particularly, the guiding term is the classification error with respect to the representation learned by the auto-encoder, and a meaningful representation means that a network using the representation as input has a low classification error in a classification task. In our experiments, we show that the additional explicit guiding term helps the auto-encoder understand the prospective target in advance. During learning, it can drive the learning toward a minimum with better generalization with respect to the particular supervised task on the dataset. Over a range of image classification benchmarks, we achieve equal or superior results to baseline auto-encoders with the same configuration. [ABSTRACT FROM AUTHOR]

The present paper deals with modeling of AC resistance of twisted litz wires used for high-frequency inverter-fed induction cooker. Several traditional approaches are available, most of which have concentrated in deriving the analytical relationships between the AC resistances with the parameters of the wire. However, it is very difficult to get the exact relationship, due to several reasons. An attempt is made in this paper to model the AC resistance using a three-layered feed-forward Neural Network. For this purpose, four inputs (wire type, number of strand, number of spiral turn and operating frequency) and one output as AC resistance have been considered. Since the performance of Neural Network alone might not be optimal; it is optimized using a binary-coded Genetic Algorithm. Performances of the proposed approach were compared with the method of AC resistance computation proposed by Ferreira. Genetic-neural system has given a very close accuracy, and the computational complexity was found to be very low. Thus, it is suitable for online implementations. [ABSTRACT FROM AUTHOR]

This paper investigates adaptive neural network (NN) prescribed performance output tracking control problem for a class of strict-feedback nonlinear systems with output dead zone. By introducing a Nussbaum function, the problem of unknown virtual control coefficient is resolved, which is caused by the nonlinearity in the output dead zone. By designing the state observer and utilizing backstepping recursive design technique, a new adaptive NN control method is proposed. It is shown that all the signals of the resulting closed-loop system are bounded and the tracking error remains an adjustable neighborhood of the origin with the predefined performance under the effect of output dead zone. Finally, a simulation example is given at the simulation part, which further demonstrate the effectiveness of proposed control method. [ABSTRACT FROM AUTHOR]

Concurrency control (CC) algorithms guarantee the correctness and consistency criteria for concurrent execution of a set of transactions in a database. A precondition that is seen in many CC algorithms is that the writeset (WS) and readset (RS) of transactions should be known before the transaction execution. However, in real operational environments, we know the WS and RS only for a fraction of transaction set before execution. However, optional knowledge about WS and RS of transactions is one of the advantages of the proposed CC algorithm in this paper. If the WS and RS are known before the transaction execution, the proposed algorithm will use them to improve the concurrency and performance. On the other hand, the concurrency control algorithms often use a specific static or dynamic equation in making decision about granting a lock or detection of the winner transaction. The proposed algorithm in this paper uses an adaptive resonance theory (ART)-based neural network for such a decision making. In this way, a parameter called health factor (HF) is defined for transactions that is used for comparing the transactions and detecting the winner one in accessing the database objects. HF is calculated using ART2 neural network. Experimental results show that the proposed neural-based CC (NCC) algorithm increases the level of concurrency by decreasing the number of aborts. The performance of proposed algorithm is compared with strict two-phase locking (S2PL) algorithm, which has been used in most commercial database systems. Simulation results show that the performance of proposed NCC algorithm, in terms of number of aborts, is better than S2PL algorithm in different transaction rates. [ABSTRACT FROM AUTHOR]

This paper addresses the decentralized adaptive output-feedback control problem for a class of interconnected stochastic strict-feedback uncertain systems described by It $$\hat{\hbox{o}}$$ differential equation using neural networks. Compared with the existing literature, this paper removes the commonly used assumption that the interconnections are bounded by known functions multiplying unknown parameters, and all unknown interconnections are lumped in a suitable function which is compensated by only a neural network in each subsystem. So, the controller is simpler even than that for the strict-feedback systems described by the ordinary differential equation. Moreover, the circle criterion is applied to designing nonlinear observers for the estimates of system states. A simulation example is used to illustrate the effectiveness of control scheme proposed in this paper. [ABSTRACT FROM AUTHOR]

Nonlinear feature extraction of speech signals has been the main concern of many researches in recent years. In this paper, feature extraction of phonemes using NPC (neural predictive coding) model is generalized to a combination of time and DCT domains. Two main ideas were proposed and evaluated in this paper. First, a frame-wise DCT-based NPC feature extractor is proposed to overcome the computational complexity deficiency of the system. The basis of this approach is the application of a DCT pre-feature extractor to remove unwanted additional data. In this approach, the extracted features are the output of the hidden layer. It is shown that the use of a pre-processing stage can improve both computational complexity efficiency and accuracy issues. At the second approach, we proposed a complementary role for DCT domain features in classic NPC modeling. This approach uses the signal residual of the predicted signal in the DCT domain. The experiments were conducted on voiced plosive phonemes of TIMIT database. Simulations showed that the performance of the combined method is good at the plosive phonemes. The achieved accuracy that was resulted from the proposed method was 70.3% recognition rate on /b/d/g/ phonemes, which is higher than the results of traditional NPC approaches. [ABSTRACT FROM AUTHOR]

This paper describes a novel method of facial representation and recognition based upon adaptive processing of tree structures. Instead of the conventional flat vector representation for a face, a neural network approach-based technique is proposed to transform the Localised Gabor Feature (LGF) vectors extracted from human facial components into Human Face Tree Structure (HFTS) to represent a human face. A structural training algorithm is assigned to train and recognize the face identity in this HFTS representation with the corresponding LGF vectors. By benchmarking using the tested public face databases presented in this paper, our approach is able to achieve accuracy up to 90% under different scenarios of lighting conditions and posture orientations. [ABSTRACT FROM AUTHOR]

There are many performance based techniques that aim to improve the safety of neural networks for safety critical applications. However, many of these approaches provide inadequate forms of safety assurance required for certification. As a result, neural networks are typically restricted to advisory roles in safety-related applications. Neural networks have the ability to operate in unpredictable and changing environments. It is therefore desirable to certify them for highly-dependable roles in safety critical systems. This paper outlines the safety criteria which are safety requirements for the behaviour of neural networks. If enforced, the criteria can contribute to justifying the safety of ANN functional properties. Characteristics of potential neural network models are also outlined and are based upon representing knowledge in interpretable and understandable forms. The paper also presents a safety lifecycle for artificial neural networks. This lifecycle focuses on managing behaviour represented by neural networks and contributes to providing acceptable forms of safety assurance. [ABSTRACT FROM AUTHOR]