Search

The radial basis function neural network (RBFNN) is a widely used tool for interpolation and prediction problems. In this paper, we propose to improve the traditional RBFNN by automatically identifying core neurons in the hidden layer, based on the l 1 regularization. Our proposed approach will greatly reduce the number of neurons required, which will save the memory and also the computational cost. To determine the radial parameter in the RBFs, we propose to use the K -fold cross-validation method. Moreover, the principal component analysis (PCA) method is used to reconstruct the distance between samples for high-dimensional data sets. Numerical experiments are provided to demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

In the rapid development of high and new technology, the intelligence and integration of modern equipment are constantly improving. Power electronics technology is one of the indispensable key technologies in any high and new technology. In this paper, a power electronics circuit fault diagnosis based on improved particle swarm optimization neural network is proposed, the algorithm design of particle swarm optimization algorithm neural network is introduced, and the improved PS0 algorithm, standard PS0 algorithm, and BP algorithm optimized neural network are applied to the fault diagnosis classification system of rectifier circuits. The results show that the parameters of the basic (particle swarm optimization) algorithm are as follows: the parameter value of the basic PSO algorithm is the number of particles is 30, W decreases from 0.9 to 0.4 linearly with the increase of iterations, and the number of iterations is 300. The BP algorithm uses the traingdx training function. The transfer functions of the hidden layer and the output layer are hyperbolic tangent sigmoid and Purelin function, respectively. The target error e = 0.01. The superiority and effectiveness of the neural network diagnosis model of the improved PS0 algorithm are shown in this paper. This method can solve the fault diagnosis problem of the double-bridge parallel rectifier circuit. [ABSTRACT FROM AUTHOR]

The nonlinear filtering problem is a hot spot in robot navigation research. As an advanced method that can effectively improve the robustness and accuracy of the system, the progressive Gaussian approximate filter with variable step size (PGAFVS) still has some shortcomings, how to resolve the nonlinear filtering problem in the application of tightly coupled integration under the premise of the prior uncertainty and further promote robustness high measurement accuracy, which becomes the purpose of this paper. This paper formulates the processing of trajectory tracking measurement noise problem as a Kalman filtering procedure and the measurement noise covariance matrix in controller, is jointly estimated based on the progressive Gaussian approximate filter (PGAF), after that, PGAFVS can be deduced. Then we proposed an adaptive fuzzy and backpropagation neural network controller based on PGAFVS (AFNPGA-VS) that can improve the application of tightly coupled integration under the premise of the prior uncertainty and further promote robustness high measurement accuracy. The simulation results show that the proposed algorithm outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, a top-k pseudo labeling method for semi-supervised self-learning is proposed. Pseudo labeling is a key technology in semi-supervised self-learning. Briefly, the quality of the pseudo label generated largely determined the convergence of the neural network and the accuracy obtained. In this paper, the authors use a method called top-k pseudo labeling to generate pseudo label during the training of semi-supervised neural network model. The proposed labeling method helps a lot in learning features from unlabeled data. The proposed method is easy to implement and only relies on the neural network prediction and hyper-parameter k. The experiment results show that the proposed method works well with semi-supervised learning on CIFAR-10 and CIFAR-100 datasets. Also, a variant of top-k labeling for supervised learning named top-k regulation is proposed. The experiment results show that various models can achieve higher accuracy on test set when trained with top-k regulation. [ABSTRACT FROM AUTHOR]

In distributed generation systems, islanding detection is a necessary function of grid-connected inverters. In view of the performance disadvantages of traditional passive and active islanding detection methods, this paper proposes a novel passive islanding detection method. The proposed method first extracts characteristic parameters from the inverter output voltage signal and inverter output current signal through lifting wavelet transform, and then conducts the pattern recognition of these extracted characteristic parameters via BP neural network, so as to judge if there is an islanding phenomenon. As verified by the simulation and experiment results, the islanding detection method proposed in this paper is effective, and is featured by high detection speed and small non-detection zone, without affecting electric energy quality; its detection performance has been remarkably improved in comparison with that of traditional islanding detection methods. [ABSTRACT FROM AUTHOR]

Convolution-based recurrent neural networks and convolutional neural networks have been used extensively in spatiotemporal prediction. However, these methods tend to concentrate on fixed-scale spatiotemporal state transitions and disregard the complexity of spatiotemporal motion. Through statistical analysis, we found that the distribution of the spatiotemporal sequence and the variety of spatiotemporal motion state transitions exhibit some regularity. In light of these statistics and observations, we propose the Multi-scale Spatiotemporal Neural Network (MSSTNet), an end-to-end neural network based on 3D convolution. It can be separated into three major child modules: a distribution feature extraction module, a multi-scale motion state capture module, and a feature decoding module. Furthermore, the MSST unit is designed to model multi-scale spatial and temporal information in the multi-scale motion state capture module. We first conduct the experiments on the MovingMNIST dataset, which is the most commonly used dataset in the field of spatiotemporal prediction, MSSTNet can achieve state-of-the-art results for this dataset, and ablation experiments demonstrate that the MSST unit has positive significance for spatiotemporal prediction. In addition, this paper applies the model to valuable precipitation nowcasting, due to efficiently capturing the multi-scale information of distribution and motion, the new MSSTNet model can predict the real-world radar echo more accurately. [ABSTRACT FROM AUTHOR]

Accurately predicting tunnel boring machine (TBM) performance is beneficial for excavation efficiency enhancement and risk mitigation of TBM tunneling. In this paper, we develop a long short-term memory (LSTM) based hybrid intelligent model to predict two key TBM performance parameters (advance rate and cutterhead torque). The model combines the LSTM, BN, Dropout and Dense layers to process the raw data and improve the fitting quality. The features, including the ground formation properties, tunnel route curvature, tunnel location and TBM operational parameters, are divided into historical/real-time time-varying parameters, time-invariant parameters and historical/real-time output prediction data. The effectiveness of the proposed model is verified based on a large monitoring database of the Baimang River Tunnel Project in Shenzhen, south China. We then discuss the influence of the prediction mode, neural network structure and time division interval length of historical data on the prediction accuracy. The significance evaluation of input features shows that the historical output prediction has the largest influence on the prediction accuracy, and the influence of ground properties is secondary. It is also found that the correlations between input features and the output prediction are coincident with their interrelationships with the ground properties and ease of TBM excavation. Finally, it is found that the prediction results are most affected by the total propulsion force followed by the rotation speed of the cutterhead. The established model can provide useful guidance for construction personnel to roughly grasp the possible TBM status from the prediction results when adjusting the operational parameters. [ABSTRACT FROM AUTHOR]

This paper addresses the design of an observer-based adaptive neural network chaos synchronization scheme for a general class of uncertain chaotic systems. The controller consists of an adaptive neural network control law and an extended state observer. The parameterization of the designed extended observer and the sufficient stability conditions are derived in the light of the singular perturbation theory. The extended observer is incorporated into the controller to reconstruct the synchronization error vector as well as to estimate the error between an ideal control law and the actual control. These estimated error signals are utilized in the adaptation mechanism of the neural network weight vector. In the presented chaos synchronization method, the knowledge of the models of the master–slave systems is not required and the controller only needs the projective synchronization error for its implementation. Numerical simulations are performed along with a comparative study to demonstrate the efficiency and effectiveness of the suggested chaos synchronization approach. [ABSTRACT FROM AUTHOR]

This paper describes some biologically-inspired processes that could be used to build the sort of networks that we associate with the human brain. New to this paper, a 'refined' neuron will be proposed. This is a group of neurons that by joining together can produce a more analogue system, but with the same level of control and reliability that a binary neuron would have. With this new structure, it will be possible to think of an essentially binary system in terms of a more variable set of values. The paper also shows how recent research can be combined with established theories, to produce a more complete picture. The propositions are largely in line with conventional thinking, but possibly with one or two more radical suggestions. An earlier cognitive model can be filled in with more specific details, based on the new research results, where the components appear to fit together almost seamlessly. The intention of the research has been to describe plausible 'mechanical' processes that can produce the appropriate brain structures and mechanisms, but that could be used without the magical 'intelligence' part that is still not fully understood. There are also some important updates from an earlier version of this paper. [ABSTRACT FROM AUTHOR]

Detection of computer-generated (CG) images can reveal the authenticity and originality of digital images. However, recent cutting-edge image generation methods make it very difficult to distinguish CG images from natural photographs. In this paper, a novel method based on color patterns and enhanced texture learning is proposed to tackle this problem. We designed and implemented the backbone network with a separation-fusion learning strategy by constructing a multi-branch neural network. The luminance and chrominance patterns in dual-color spaces (RGB and YCbCr) are leveraged to achieve a robust representation of image differences. A channel-spatial attention module and a global texture enhancement module are also integrated into a backbone network to enhance the learning of inherent traces. Experiments on several commonly used benchmark datasets and a newly constructed dataset with more realistic and diverse images demonstrate that the proposed algorithm outperforms state-of-the-art competitors by a large margin. [ABSTRACT FROM AUTHOR]

Recently, various applications and services are used in the Internet. Load balancing the increasing network traffic in real time can improve the network quality. The flow control technologies become much more important than before. Our research proposes an intelligent network flow identifying method, which is based on the neural network algorithm, GHSOM. In this paper, we suggest to utilize the structural classification of GHSOM for training the properties of packets, such as timestamp, source and destination. Based on our proposed normalization, IP network flows can be formed autonomously during the learning process. The combination use of the new normalization with the GHSOM can divide a flow to several sub-IP flows. This paper indicates that a flow shall consist of several sub-IP flows, and sub-IP flow shall consist of several IP packets. The experiments show that IP packets can be divided to flow and sub-IP flow classes properly. Furthermore, those repeated jumbo sub-IP flows can be used to discover communicating errors or abnormal attacks. [ABSTRACT FROM AUTHOR]

Neural synchronization is considered as a key role in several neurological diseases, such as Parkinson's and Epilepsy's disease. During these diseases, there is increased synchronization of massive numbers of neurons. In addition, evidences show that astrocytes modulate the synaptic interactions of the neuronal population. The Astrocyte is an important part of a neural network that can be involved in the desynchronization of the neuronal population. In this paper, we design a new analog neuromorphic circuit to implement the effect of astrocyte in the desynchronization of neural networks. The simulation results demonstrate that the astrocyte circuit as a feedback path can be desynchronized to a synchronized neural population. In this circuit, as a first step, the population of twenty neurons is synchronized with the same input currents. Next, by involving an astrocyte feedback circuit, the synchronization of the neural network is disturbed. Then, the neuronal population will be desynchronized. The proposed circuit is designed and simulated using HSPICE simulator in 0.35 µm standard CMOS technology. [ABSTRACT FROM AUTHOR]

Manufactured sand has high potential for replacing natural sand and reducing the negative impact of the construction industry on the environment. This paper aims at developing a novel deep learning-based approach for estimating the compressive strength of manufactured-sand concrete. The deep neural networks are trained by the advanced optimizers of Root Mean Squared Propagation, Adaptive Moment Estimation, and Adaptive Moment Estimation with Nesterov momentum (Nadam). In addition, the activation functions of logistic sigmoid, hyperbolic tangent sigmoid, and rectified linear unit activation are employed. A dataset including 132 samples has been used to train and verify the deep neural networks. Stone powder content, sand ratio, quantity of cement, quantity of water, quantity of coarse aggregate, quantity of water-reducer, quantity of manufactured sand, concrete slump, unit weight of concrete, and curing age are utilized as predictor variables. Based on experiments, the Nadam-optimized model used with the sigmoid activation function has achieved the most desired performance with root mean square error (RMSE) = 1.95, mean absolute percentage error (MAPE) = 3.04%, and coefficient of determination (R²) = 0.97. Thus, this neural computing model is recommended for practical purposes because it can help to mitigate the time and cost dedicated to laboratory work. [ABSTRACT FROM AUTHOR]

Road sign recognition is one of the most important steps drivers can take to avoid dangerous roads or accidents. The purpose of the research work is to develop a recognition system, increasing the classification accuracy of the model, using deep learning methods of Road sign recognition system for drivers in real time on the road. Stages of road sign image classification were carried out, and other authors' solutions were analyzed. In addition, in this work, the convolutional neural network (CNN) method with the help of deep learning was used to create a system for identifying and recognizing road signs. The proposed road sign recognition system can work in real time to recognize the image of road signs. In this paper, a model is trained using deep learning of 43 different road signs using existing datasets and collected local road signs. A traffic sign detection and recognition system is presented using an 8-layer convolutional neural network, which acquires different functions by training different types of traffic signs. In previous studies, models were trained using simple machine learning algorithms, but the relevance of this study is that a CNN model was trained for a classification task based on convolutional neural networks using deep learning. As a result of the study, classification accuracy of 95% was obtained using deep learning methods. As a novelty of the work, it is possible to note the diversity of the convolutional network methods used to increase the efficiency of the used data set and model training algorithms, the variety of received road signs and algorithms for its recognition, as well as the achievement of a high accuracy rate. This allowed the system to overcome the limited accuracy and performance issues caused by environmental factors, and to be more versatile and accurate than most modern systems. [ABSTRACT FROM AUTHOR]

Uncertainty of target motion, limited perception ability of onboard cameras, and constrained control have brought new challenges to unmanned aerial vehicle (UAV) dynamic target tracking control. In virtue of the powerful fitting ability and learning ability of the neural network, this paper proposes a new deep reinforcement learning (DRL)-based end-to-end control method for UAV dynamic target tracking. Firstly, a DRL-based framework using onboard camera image is established, which simplifies the traditional modularization paradigm. Secondly, neural network architecture, reward functions, and soft actor-critic (SAC)-based speed command perception algorithm are designed to train the policy network. The output of the policy network is denormalized and directly used as speed control command, which realizes the UAV dynamic target tracking. Finally, the feasibility of the proposed end-to-end control method is demonstrated by numerical simulation. The results show that the proposed DRL-based framework is feasible to simplify the traditional modularization paradigm. The UAV can track the dynamic target with rapidly changing of speed and direction. [ABSTRACT FROM AUTHOR]

The target's threat prediction is an essential procedure for the situation analysis in an aerial defense system. However, the traditional threat prediction methods mostly ignore the effect of commander's emotion. They only predict a target's present threat from the target's features itself, which leads to their poor ability in a complex situation. To aerial targets, this paper proposes a method for its potential threat prediction considering commander emotion (PTP-CE) that uses the Bi-directional LSTM (BiLSTM) network and the backpropagation neural network (BP) optimized by the sparrow search algorithm (SSA). Furthermore, we use the BiLSTM to predict the target's future state from real-time series data, and then adopt the SSA-BP to combine the target's state with the commander's emotion to establish a threat prediction model. Therefore, the target's potential threat level can be obtained by this threat prediction model from the predicted future state and the recognized emotion. The experimental results show that the PTP-CE is efficient for aerial target's state prediction and threat prediction, regardless of commander's emotional effect. [ABSTRACT FROM AUTHOR]

This paper presents the development and evaluation of neural network models using a small input–output dataset to predict the thermal behavior of a high-speed motorized spindles. Different neural multi-output regression models were developed and evaluated using Keras, one of the most popular deep learning frameworks at the moment. ANN was developed and evaluated considering the following: the influence of the topology (number of hidden layers and neurons within), the learning parameter, and validation techniques. The neural network was simulated using a dataset that was completely unknown to the network. The ANN model was used for analyzing the effect of working conditions on the thermal behavior of the motorized grinder spindle. The prediction accuracy of the ANN model for the spindle thermal behavior ranged from 95% to 98%. The results show that the ANN model with small datasets can accurately predict the temperature of the spindle under different working conditions. In addition, the analysis showed a very strong effect of type coolant on spindle unit temperature, particularly for intensive cooling with water. [ABSTRACT FROM AUTHOR]

Neural networks generally require significant memory capacity/bandwidth to store/access a large number of synaptic weights. This paper presents design of an energy-efficient neural network inference engine based on adaptive weight compression using a JPEG image encoding algorithm. To maximize compression ratio with minimum accuracy loss, the quality factor of the JPEG encoder is adaptively controlled depending on the accuracy impact of each block. With 1% accuracy loss, the proposed approach achieves $63.4{\times }$ compression for multilayer perceptron (MLP) and $31.3 {\times }$ for LeNet-5 with the MNIST dataset, and $15.3 {\times }$ for AlexNet and $10.2 {\times }$ for ResNet-50 with ImageNet. The reduced memory requirement leads to higher throughput and lower energy for neural network inference ($3 {\times }$ effective memory bandwidth and $22 {\times }$ lower system energy for MLP). [ABSTRACT FROM AUTHOR]

Purpose: This paper aims at predicting skin diseases using Neural Network, Decision Tree and Ensemble method based on majority voting. Design/Methodology/Approach: The study employed three selected machine learning algorithms (classifiers) to predict skin diseases in WEKA data mining tool environment. Dermatological dataset was used to evaluate the predictive system. The performance evaluation was done based on accuracy, precision, true positive, false positive and recall. Comparative analysis was conducted on the three data mining techniques. Findings: Each individual classifier and the ensemble method was put through training and testing phase using N-fold cross validation technique (N value was set to 10) and J48 gave accuracy of 93.9891% while Multi-layer Perceptron gave 96.9945%. The accuracy of 95.3552% was obtained in ensemble method using majority voting. Precision and recall rate of 0.94 for J48, 0.97 for precision and recall values for MLP and 0.95 for precision / recall values for ensemble method. Practical Implications: The paper provides a better skin disease predictive model with much higher accuracy and generalization that avoids both over-fitting and under-fitting by combining two machine learning algorithms via the majority voting method. The developed skin disease predictive system will help the medical personnel to effectively predict skin disease accurately. Originality/Value: Several works have been proposed by researchers in data mining for diagnosis or prediction of skin diseases, but this study's major concern is on the performance evaluation in term of over-fitting, under-fitting and generalization of individual base classifier and ensemble based approach in predicting skin diseases. [ABSTRACT FROM AUTHOR]

Machine learning approaches have recently been applied to the study of various problems in physics. Most of these studies are focused on interpreting the data generated by conventional numerical methods or the data on an existing experimental database. An interesting question is whether it is possible to use a machine learning approach, in particular a neural network, for solving the many-body problem. In this paper, we present a neural network solver for the single impurity Anderson model, the paradigm of an interacting quantum problem in small clusters. We demonstrate that the neural-network-based solver provides quantitative accurate results for the spectral function as compared to the exact diagonalization method. This opens the possibility of utilizing the neural network approach as an impurity solver for other many-body numerical approaches, such as the dynamical mean field theory. [ABSTRACT FROM AUTHOR]

Pipeline transportation of crude oil has great advantages over traditional oil transmission methods, in terms of economic and environmental protection. The main costs in the oilfield surface system are the fuel costs for heating the crude oil during transportation and the electricity costs for the pumping units. In the northeast of China, where winter temperatures are extremely low and the oil has a high freezing point and high viscosity, higher temperatures, and pressures are required to transport crude oil. With machine learning widely used in many industries and achieving better results, the digital management of oil pipelines has stored a large amount of production and operation data, which has laid the foundation for the research of oil pipeline process calculation using machine learning methods. In this paper, a crude oil pressure drop calculation of an oil pipeline in Northeast China is carried out based on a neural network. For pipeline pressure drop calculation, the back propagation neural network (BP) pressure drop calculation model and particle swarm optimization for back propagation neuron network (PSO-BP) pressure drop calculation model are established. Two models were used to calculate and compare the measured data, and the average absolute error of the PSO-BP model was the smallest, which was 0.015%. Compared with the BP model, the average relative error is reduced by 13.16%. Therefore, The PSO-BP pressure drop calculation model has high accuracy and is of practical significance for predicting pipeline pressure drop. [ABSTRACT FROM AUTHOR]

In this paper, the problem of adaptive neural network asymptotical tracking is investigated for a class of nonlinear system with unknown function, external disturbances and input quantisation. Based on neural network technique, an adaptive asymptotical tracking controller is provided for an uncertain nonlinear system via backstepping method. In order to reduce complexity of the control algorithm in the backstepping design process, a sliding mode differentiator is employed to estimate the virtual control law and only two parameters need to be estimated via adaptive control technique. The stability of the closed-loop system is analysed by using Lyapunov function method and zero-tracking error performance is obtained in the presence of unknown nonlinear function, external disturbances and input quantisation. Finally, an application example is employed to demonstrate the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

Estimation of power system parameter plays an important role in the modern power system. In this paper, estimation of harmonics components in a power system synthetic signal is done by an improved estimation technique called as ADALINE. This neural estimator basically uses an adaptive interpreted linear neuron. Learning parameter is adjusted to keep the difference between the Real and Expected values to satisfy the difference that arises due to error equation. Tracking of the fourier co-efficent of the proposed signal, which also constitutes a noise, and DC decaying component can be done easily and accurately using the proposed algorithm. To verify the effectiveness of the proposed algorithm, estimation of amplitude as well as Phase of fundamental and harmonics is carried out. The simulation results obtained are encouraging to work more on the estimation of signals. [ABSTRACT FROM AUTHOR]

The paper aims to present the research methodology of metalworking with a toroidal milling machine. It focuses on monitoring the different variables in the processing process. The paper presents the type of tool to be used in the experimental processing as well as the direct control of the tool. The paper also shows how experiments will be performed with the numeric control center type. Different parameters will be monitored during experiments and these monitoring procedures will be presented in this paper. The main parameters monitored will be surface quality, electricity consumption, tool wear, vibration level and acoustic emission level. After obtaining these parameters in the future researches, they will try their mathematical modeling, in this paper presenting the applicability of the neural network for roughness. [ABSTRACT FROM AUTHOR]

In this paper, a missing wind speed data temporal interpolation and extrapolation method in the wind energy industry was investigated. Given that traditional methods have previously ignored part of mixed uncertainty of wind speed, a concrete granular computing method is constructed and a new Measure-Correlate-Predict (MCP) method of wind speed data temporal interpolation and extrapolation considering all mixed uncertainties is proposed, based on granular computing theory by adopting the cloud model method, support vector regression method, artificial neural network, genetic algorithm, and fuzzy c-means clustering algorithm as tools. The importance of considering mixed wind speed uncertainty and the suitability of using granular computing method are illustrated, and wind speed mixed uncertainty analysis is implemented, then, recommended values and estimation tools for wind speed measurement uncertainty and combined uncertainty are provided. An interpolation case of two practical meteorological sites in central Southern China was used to implement and validate the method proposed in this paper. The following conclusions are reached: (a) by using the method proposed in this paper, mixed uncertainty of wind speed can be considered, comparing to other MCP methods used for purposes of comparison, a better estimation of the wind speed is provided, and most evaluation metrics employed in this analysis were superior to other methods, that is to say, the accuracy of the wind resource assessment improved, and the risks of wind farm construction were reduced; (b) granular computing method is suitable for the issue of wind speed data interpolation and extrapolation considering wind speed mixed uncertainty; (c) mixed uncertainty of wind speed can be divided into three levels, and recommended values of granularity are minimum interval of records, 0.3-0.8 m/s, and 1-3 m/s, respectively. [ABSTRACT FROM AUTHOR]

In view of the bad performance of standard BP neural network algorithm in soybean appearance quality discrimination, this paper put forward a BP neural network optimized by improved LP algorithm. It firstly combines the principal component analysis with BP neural network, using the principal component analysis method to preprocess the high-dimensional input variables to construct the low-dimensional principal variables which reflects the process information, then using the global properties of Gradientdescent and local properties of Gaussian- Newton algorithm built in LM algorithm to train the BP neural network. The simulation experiment shows that the BP neural network optimized by LM algorithm in this paper has better convergent performance and image identification ability compared with standard BP neural network. The proposed BP algorithm shows good performance in soybean appearance quality identification. [ABSTRACT FROM AUTHOR]

The cognitive radio (CR) has been recently proposed as an auspicious technology to effectively utilize the radio band to allow unlicensed users by allocating the spectrum dynamically on a non-interfering basis. The main challenge of the CR system is control channel overhead when the number of secondary users (SUs) becomes very large in cooperative spectrum sensing (CSS) scenario. To mitigate this problem, Cluster based CSS approach is useful to avoid the crowding on the control channel. Therefore, in this paper, neural network approach based on supervised learning algorithm is applied at the fusion center (FC) for proposed clustering technique. The simulation results prove that proposed clustering approach enhance the accuracy of the system. Also, it is more robust than other conventional schemes. [ABSTRACT FROM AUTHOR]

This paper proposes a step-by-step technique for combining basic models that forecast electricity consumption in an artificial neural network by the method of preliminary selection and further hybridization. The reported experiments were conducted using data on hourly electricity consumption at the metallurgical plant AO ArcelorMittal Temirtau in the period from January 1, 2019, to November 30, 2021. The current research is related to the planned introduction of a balancing electricity market. 96 combinations of basic models were compiled, differing in the type of neural network, the set of initial data, the order of lag, the learning algorithm, and the number of neurons in the hidden layer. It has been determined that the NARX-type network is the most optimal architecture to forecast electricity consumption. Based on experimental studies, the number of hidden neurons needed to form a planned daily profile should equal 3 or 4; it is recommended to use the conjugate gradient method as a learning algorithm. When selecting models from three groups, it was revealed that the conjugate gradient method produces better results compared to the LevenbergMarquardt algorithm. It is determined that the values of the selected RMSE error indicator take values of 23.17, 22.54, and 22.56, respectively, for the first, second, and third data groups. The adaptive hybridization method has been shown to reduce the RMSE error rate to 21.73. However, the weights of the best models with values of 0.327 for the first group of data, and 0.336 for the second and third ones, show that the individual use of a separate combination of models is also applicable. The devised forecasting electricity consumption model can be integrated into an automated electricity metering system. [ABSTRACT FROM AUTHOR]

Network dynamics with point-process-based interactions are of paramount modeling interest. Unfortunately, most relevant dynamics involve complex graphs of interactions for which an exact computational treatment is impossible. To circumvent this difficulty, the replica-mean-field approach focuses on randomly interacting replicas of the networks of interest. In the limit of an infinite number of replicas, these networks become analytically tractable under the so-called 'Poisson hypothesis'. However, in most applications this hypothesis is only conjectured. In this paper we establish the Poisson hypothesis for a general class of discrete-time, point-process-based dynamics that we propose to call fragmentation-interaction-aggregation processes, and which are introduced here. These processes feature a network of nodes, each endowed with a state governing their random activation. Each activation triggers the fragmentation of the activated node state and the transmission of interaction signals to downstream nodes. In turn, the signals received by nodes are aggregated to their state. Our main contribution is a proof of the Poisson hypothesis for the replica-mean-field version of any network in this class. The proof is obtained by establishing the propagation of asymptotic independence for state variables in the limit of an infinite number of replicas. Discrete-time Galves–Löcherbach neural networks are used as a basic instance and illustration of our analysis. [ABSTRACT FROM AUTHOR]

In this paper, a new feature selection and forecast engine is presented for day ahead prediction of electricity prices, which are so valuable for both producers and consumers in the new competitive electric power markets. In a competitive electricity market, forecast of energy prices is a key information for the market participants. However, price signal usually has a complex behavior due to its nonlinearity, non-stationary, and time variance. Also, an appropriate feature selection is crucial for accurate forecasting. In this paper, a two-step approach that identifies a set of candidate features based on the data characteristics proposed and then selects a subset of them using correlation and instance-based feature selection methods, applied in a systematic way. Then, a combination of wavelet transform (WT) and a hybrid forecast method is presented based on neural network (NN) and an optimization algorithms. The proposed method is examined on PJM electricity market and compared with some of the most recent price forecast methods. These comparisons illustrate effectiveness of the proposed strategy. [ABSTRACT FROM AUTHOR]

In this paper, an integrated algorithm has been proposed for ranking contingencies in the deregulated network. The network security and economical indices should be considered when dealing with market environment. Locational marginal price and congestion cost indices are the best signals to completely illustrate the market operation. In this paper, voltage violation, line flow violation, locational marginal price and congestion cost indices have been simultaneously considered to rank the contingencies. This algorithm uses neural networks method to estimate the power system parameters (locational marginal price, bus voltage magnitudes and angles). The efficiency of each of contingencies was calculated using data envelopment analysis and this index was employed for ranking. The efficiency of each contingency shows its severity and indicates that it affects network security and economic indices concurrently. Considering the proposed formulation for data envelopment analysis, the efficiency of a contingency will be higher if the calculated indices for that contingency are higher. More efficiency leads to increased severity of the contingency and shows that the contingency has concurrently more affected network security and economic indices. The proposed algorithm has been tested on IEEE 30-bus test power system. Simulation results show the high efficiency of the algorithm. [ABSTRACT FROM AUTHOR]

Copyright of Materialwissenschaft und Werkstoffechnik is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Automatic eye localization is a crucial part of many computer vision algorithms for processing face images. Some of the existing algorithms can be very accurate, albeit at the cost of computational complexity. In this paper, a new solution to the problem of automatic eye localization is proposed. Eye localization is posed as a nonlinear regression problem solved by two feed-forward multilayer perceptrons (MLP) working in a cascade. The input feature vector of the first network is constructed from coefficients of a two dimensional discrete cosine transform(DCT) of a face image. The second network generates corrections based on small image patches. Feature extraction and neural network prediction have known and efficient implementations, thus the entire procedure can be very fast. The paper hints at the neural network structure and the procedure for generating artificial training samples from a low number of face images. In terms of accuracy, the method is comparable to state-of-the-art techniques; however it is based on numerical procedures that could be highly optimized (fast Fourier transform and matrix multiplication). [ABSTRACT FROM AUTHOR]

The aim of this paper is to explore the mechanisms for implementing a risk management process into an organisation. A way of exploring the mechanisms for implementing a risk management process is to break it down into its component parts and examine what each part should contribute to the overall risk management process. The main aim of the empirical part of the paper is on the other hand to present empirical research of risk management focusing on forecasting sales using a neural network method. A neural network is a powerful data modeling tool that is able to capture and represent complex input/output relationships. Integrating an overall risk management process into an organisation can significantly improve the response of the organisation to unplanned events (good or bad) and enhances its ability to compete, not to mention that the objectives of an organisation are easier to achieve and that resources areeffectively allocated. Applying neural network method produces consistently accurate sales forecast. However, effort should be put in proper preparation of dataset. This paper has a tremendous added value for all risk management officers, CFOs and all others involved in risk management process. The added value is shown in the description of theoretical risk management model which is upgraded with a practical approach example. [ABSTRACT FROM AUTHOR]

Summary: This paper develops a novel adaptive neural integral sliding‐mode control to enhance the tracking performance of fully actuated uncertain surface vessels. The proposed method is built based on an integrating between the benefits of the approximation capability of neural network (NN) and the high robustness and precision of the integral sliding‐mode control (ISMC). In this paper, the design of NN, which is used to approximate the unknown dynamics, is simplified such that just only one simple adaptive rule is needed. The ISMC, which can eliminate the reaching phase and offer higher tracking performance compared to the conventional sliding‐mode control, is designed such that the system robust against the approximation error and stabilize the whole system. The design procedure of the proposed controller is constructed according to the backstepping control technique so that the stability of the closed‐loop system is guaranteed based on Lyapunov criteria. The proposed method is then tested on a simulated vessel system using computer simulation and compared with other state‐of‐the‐art methods. The comparison results demonstrate the superior performance of the proposed approach. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Qadisiyah Computer Science & Mathematics is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The objective of this review paper is to summarize some of the wellknown methods used in various stages of a pattern recognition system. Pattern recognition has become more and more popular and important to us and it induces attractive attention coming from wider areas. The general processing steps of pattern recognition are discussed, starting with the pre-processing, then the feature extraction, and classification. In this paper we have reviewed methods used in pattern recognition. This review paper introduces the basic concepts of pattern recognition, different methods used for pattern recognition like statistical and structural techniques, template matching, neural network and provides the understanding of various methods and related algorithms for classification. [ABSTRACT FROM AUTHOR]

Contrary to the single pier, due to the complexity of the scour mechanism around pile groups, empirical methods do not give a satisfactory prediction for the scour depth around pier with multiple piles. It was shown recently that artificial neural networks (NNs) have better prediction performance than empirical methods. In order to exploit the full potential of the NN procedure for predicting the scour depth around pile groups, a ‘Bagging’ technique is adopted in this paper. The comparison between several different approaches for improving the generalization performance of NNs shows that ‘Bagging’ is the most reliable method. Furthermore, the sensitivity analysis is performed on the data to determine the effect of different inputs on the scour depth around pile groups. This analysis shows that pile diameter and pile spacing are dominant contributors. [ABSTRACT FROM AUTHOR]

Abstract: In order to study the working conditions of condensing heat exchangers under non-rated load conditions, the orthogonal test method was conducted on the condensing gas water heaters by experiment firstly in this paper. Eighty groups of the experimental data about the relationship between the design variables and the object functions were obtained, among them, the design variables include excess air coefficient, flue gas flow, water flow and water flow temperature, and the objective functions include heat exchanger efficiency, NOx and CO emission concentration. The above experimental data were divided into two groups for the training and prediction of neural networks. Here two neural networks of BP artificial neural network (BPNN) and generalized regression neural network (GRNN) will be used to predict the heat efficiency and pollutant emission of condensate heat exchanger at partial load rate. The results show that both BPNN and GRNN structures achieve the required prediction accuracy, and the prediction accuracy of GRNN is higher than that of BPNN. The condensing heat exchanger can achieve higher heat exchanger efficiency and lower concentration of NOx and CO emission at the 90-100% load rate. When the load rate is lower than 30% or higher than 100%, the heat efficiency of the heat exchanger is decreased, and the concentration of pollutant emission is increased rapidly.Graphical abstract: [ABSTRACT FROM AUTHOR]

One of the well-known issues in the field of network routing is the Shortest Path Routing (SPR). The objective is to find the least-cost path with minimum delay and link breaks. Even though there are many algorithms to solve SPR, the cost, as well as link breaks, are indeed more thought-provoking in the real-time application. This paper intends to develop a routing approach that solves the challenges like route establishment and route recovery. The selection of the optimal route is done by adopting a generalized multi-purpose optimization algorithm named Grey Wolf Optimizer. Along with this, this paper adopts Neural Network (NN) to predict the node movements in the ad hoc network. The proposed routing algorithm is compared to the conventional approaches, and the significance of the approach is described clearly. [ABSTRACT FROM AUTHOR]

The contribution is focused on technical implementation of controlling a small mobile 3Pi robot in a maze along a predefined guide line where the control of the acquired direction of the robot's movement was provided by a neural network. The weights (memory) of the neuron were calculated using a feedforward neural network learning via the Back-propagation method. This article fastens on the paper by the title "Movement control of a small mobile 3-pi robot in a maze using artificial neural network", where Hebbian learning was used for a single-layer neural network. The reflectance infra-red sensors performed as input sensors. The result of this research is the evaluation based on the experiments that served to compare different training sets with the learning methods when moving a mobile robot in a maze. [ABSTRACT FROM AUTHOR]

In this paper, we extend our previous results on continuous multi-time scales dynamic neural networks identification to the discrete domain. A robust on-line identification algorithm is proposed for nonlinear systems identification via discrete multi-time scales dynamic neural networks. The main contribution of the paper is that the input-to-state stability (ISS) approach is used to tune the weights of the discrete multi-time scales dynamic neural networks in the sense of L1. The commonly used robustifying techniques, such as dead-zone ors-modification in the weight tuning, are not necessary for the proposed identification algorithm. The stability of the proposed identifier is proved by Lyapunov function and ISS theory. Two examples are given to demonstrate the correctness of the theoretical results. [ABSTRACT FROM AUTHOR]

This paper mainly considers the complex dynamics of a discrete-time ring neural network with multiple time delays. By transforming the network system into a system of difference equations, one can obtain a chaotic neural network. More specifically, by projection method one can determine a closed invariant set of the system governed by some difference equations, and prove that some invariant subsystem is topologically conjugate to the two-sided symbolic dynamical system. Moreover, numerical simulations are presented to verify the theoretical results. [ABSTRACT FROM AUTHOR]

The power quality compensator chosen in this paper is a DSTATCOM which integrates a three phase four leg Voltage Source Converter (VSC) with a DC capacitor. The major role of the DSTATCOM is to mitigate the components of harmonic/reactive current present in the line current thereby shapes the grid current to be sinusoidal and improves the power factor nearly unity under varying conditions. In addition DSATATCOM mitigates neutral current (Isn) and balances the load currents under unbalanced conditions in three phase four wire (3P4W) distribution system. The control strategy proposed for the DSTATCOM is a Neural Network (NN) based p-q-r theory with two Artificial Neural Network (ANN) controllers for a 3P4W distribution system. The reference signal for 3P3W Shunt Active Power Filter (SAPF) is calculated by implementing an ANN controller. The alleviation of Isn under unbalanced condition is achieved by another ANN controller which produces reference signal for the 1Φ APF. The performance of the proposed DSTATCOM is analysed for various conditions through simulations in MATLAB SIMULINK and the simulation results justify the effectiveness of the propounded NN based control algorithm for DSTATCOM. [ABSTRACT FROM AUTHOR]