A neural network approach to estimating rainfall from spacebornemicrowave data

Various techniques use microwave (MW) brightness temperature (BT) data, obtained from remote sensing orbiting platforms, to calculate rain rates. The most commonly used techniques are based on regressions or other statistical methods. An emerging tool in rainfall estimation using satellite data is artificial neural networks (NNs), NNs are mathematical models that are capable of learning complex relationships. They consist of highly interconnected, interactive data processing units. NNs are implemented in this study to estimate rainfall, and backpropagation is used as a learning scheme. The inputs for the training phase are BTs and the outputs are rainfall rates, all generated by three-dimensional (3D) simulations based on a 3D stochastic, space-time rainfall model, and a 3D radiative transfer model. Once training is complete the NNs are presented with multi-frequency and polarized (horizontal and vertical) BT data, obtained from the Special Sensor Microwave/Imager (SSM/I) instrument onboard the F10 and F11 polar-orbiting meteorological satellites. Hence, rainrates corresponding to real BT measurements are generated. The rainfall rates are also estimated using a log-linear regression model. Comparison of the two approaches, using simulated data, shows that the NN can represent more accurately the underlying relationship between BT and rainrate than the regression model, Comparison of the rates, estimated by both methods, with radar-estimated rainrates shows that NNs outperform the regression model. This study demonstrates the great potential of NNs in estimating rainfall from remotely sensed data     

Fast adaptive digital equalization by recurrent neural networks

Neural networks (NNs) have been extensively applied to many signal processing problems. In particular, due to their capacity to form complex decision regions, NNs have been successfully used in adaptive equalization of digital communication channels. The mean square error (MSE) criterion, which is usually adopted in neural learning, is not directly related to the minimization of the classification error, i.e., bit error rate (BER), which is of interest in channel equalization. Moreover, common gradient-based learning techniques are often characterized by slow speed of convergence and numerical ill conditioning. In this paper, we introduce a novel approach to learning in recurrent neural networks (RNNs) that exploits the principle of discriminative learning, minimizing an error functional that is a direct measure of the classification error. The proposed method extends to RNNs a technique applied with success to fast learning of feedforward NNs and is based on the descent of the error functional in the space of the linear combinations of the neurons (the neuron space); its main features are higher speed of convergence and better numerical conditioning w.r.t. gradient-based approaches, whereas numerical stability is assured by the use of robust least squares solvers. Experiments regarding the equalization of PAM signals in different transmission channels are described, which demonstrate the effectiveness of the proposed approach     

Infinite-Mode Networks for Motion Control

In this paper, a novel multiple-input-multiple-output network model entitled "infinite-mode networks" (IMNs) is explained. The model proposes a new and challenging design concept. It is a dual structure and combines neural networks (NNs) to linear models. It has mathematically clear input-output relationship as compared to NNs. The model has a desired embedded internal function, which roughly determines a route for the whole system to follow as DNA does for biological systems. By this model, infinitely many error dimensions can be defined, and each error converges to zero in a stable manner. The network outputs include logical combinations of infinite modes of reference states, which consequently result in a substantial improvement of the control system performance. In order to support the network theory, time-delay and noise-suppression experiments on a four-channel haptic bilateral teleoperation control system are analyzed. An analysis between NNs, sliding-mode NNs, and IMNs is introduced. Possible future applications of IMNs are discussed.     

Neural-Network Application for Mechanical Variables Estimation of a Two-Mass Drive System

This paper deals with the application of neural networks (NNs) to the mechanical state estimation of the drive system with elastic joint. The torsional vibrations of the two-mass system are damped using the control structure with additional feedbacks from the torsional torque and the load-side speed. These feedbacks signals are obtained using NN estimators. The learning procedure of the NNs is described, and the influence of the input vector size to the accuracy of the state-variable estimation is investigated. The neural estimators of the torsional torque and the load machine speed are tested with open-loop and closed-loop control structures. The simulation results are confirmed by laboratory experiments     

A neurocomputing controller for bandwidth allocation in ATMnetworks

We propose a new neurocomputing call admission control (CAC) algorithm for asynchronous transfer mode (ATM) networks. The proposed algorithm employs neural networks (NNs) to calculate the bandwidth required to support multimedia traffic with multiple quality-of-service (QoS) requirements. The NN controller calculates the bandwidth required percall using on-line measurements of the traffic via its count process, instead of relying on simple parameters such as the peak, average bit rate and burst length. Furthermore, to enhance the statistical multiplexing gain, the controller calculates the gain obtained from multiplexing multiple streams of traffic supported on separate virtual paths (i.e., class multiplexing). In order to simplify the design and obtain a small reaction time, the controller is realized using a hierarchical structure of a bank of small size, parallel NN units. Each unit is a feed-forward back-propagation NN that has been trained to, learn the complex nonlinear function relating different traffic patterns and QoS, with the corresponding received capacity. The reported results prove that the neurocomputing approach is effective in achieving more accurate results than other conventional methods that are based upon mathematical or simulation analysis. This is primarily due to the unique learning and adaptive capabilities of NNs that enable them to extract and memorize rules from previous experience. Evidently such unique capabilities poise NNs to solve many of the problems encountered in the development of a coherent ATM traffic management strategy     

Support vector machines for quality monitoring in a plastic injection molding process

Support vector machines (SVMs) are receiving increased attention in different application domains for which neural networks (NNs) have had a prominent role. However, in quality monitoring little attention has been given to this more recent development encompassing a technique with foundations in statistic learning theory. In this paper, we compare C-SVM and /spl nu/-SVM classifiers with radial basis function (RBF) NNs in data sets corresponding to product faults in an industrial environment concerning a plastics injection molding machine. The goal is to monitor in-process data as a means of indicating product quality and to be able to respond quickly to unexpected process disturbances. Our approach based on SVMs exploits the first part of this goal. Model selection which amounts to search in hyperparameter space is performed for study of suitable condition monitoring. In the multiclass problem formulation presented, classification accuracy is reported for both strategies. Experimental results obtained thus far indicate improved generalization with the large margin classifier as well as better performance enhancing the strength and efficacy of the chosen model for the practical case study.     

Intelligent traffic control for ATM broadband networks

Performance results prove that a neural networks approach achieves better results, simpler and faster, than algorithmic approaches. The focus of this paper is to shed light on how neural networks (NNs) can be used to solve many of the serious problems encountered in the development of a coherent traffic control strategy in ATM networks. The main philosophy that favors neural networks over conventional programming approaches is their learning and adaptive capabilities, which can be utilized to construct adaptive (and computationally intelligent) algorithms for allocation of resources (e.g., bandwidth, buffers), thus providing highly effective tools for congestion control     

A novel neural network traffic enforcement mechanism for ATMnetworks

ATM has been recommended by the CCITT as the transport vehicle for the future B-ISDN networks. In ATM-based networks, a set of user declared parameters that describes the traffic characteristics, is required for the connection acceptance control (CAC) and traffic enforcement (policing) mechanisms. At the call set-up phase, the CAC algorithm uses those parameters to make a call acceptance decision. During the call progress, the policing mechanism uses the same parameters to control the user's traffic within its declared values in order to protect the network's resources and avoid possible congestion problems. A novel policing mechanism using neural networks (NNs) is presented. This is based upon an accurate estimation of the probability density function (pdf) of the traffic via its count process and implemented using NNs. The pdf-based policing is made possible only by NNs because pdf policing requires complex calculations, in real-time, at very high speeds. The architecture of the policing mechanism is composed of two interconnected NNs. The first one is trained to learn the pdf of “ideal nonviolating” traffic, whereas the second is trained to capture the “actual” characteristics of the “actual” offered traffic during the progress of the call. The output of both NNs is compared. Consequently, an error signal is generated whenever the pdf of the offered traffic violates its “ideal” one. The error signal is then used to shape the traffic back to its original values     

Evolutionary fuzzy neural networks for hybrid financial prediction

In this paper, an evolutionary fuzzy neural network using fuzzy logic, neural networks (NNs), and genetic algorithms (GAs) is proposed for financial prediction with hybrid input data sets from different financial domains. A new hybrid iterative evolutionary learning algorithm initializes all parameters and weights in the five-layer fuzzy NN, then uses GA to optimize these parameters, and finally applies the gradient descent learning algorithm to continue the optimization of the parameters. Importantly, GA and the gradient descent learning algorithm are used alternatively in an iterative manner to adjust the parameters until the error is less than the required value. Unlike traditional methods, we not only consider the data of the prediction factor, but also consider the hybrid factors related to the prediction factor. Bank prime loan rate, federal funds rate and discount rate are used as hybrid factors to predict future financial values. The simulation results indicate that hybrid iterative evolutionary learning combining both GA and the gradient descent learning algorithm is more powerful than the previous separate sequential training algorithm described in.     

Neuro sliding mode control of robotic manipulators

In this paper, a synergistic combination of neural networks with sliding mode control (SMC) methodology is proposed. As a result, the chattering is eliminated and error performance of SMC is improved. In the approach, two parallel Neural Networks (NNs) are utilized to realize a neuro-SMC. The equivalent control and the corrective control terms of SMC are the outputs of the NNs. The weight adaptations of NNs are based on the SMC equations in such a way that the use of the gradient descent method minimizes the control activity and the amount of chattering while optimizing the error performance. The approach is almost model-free, requiring a minimal amount of a priori knowledge and robust in the face of parameter changes. Experimental studies carried out on a direct drive arm are presented, indicating that the proposed approach is a good candidate for trajectory control applications.     

基于神经网络集成的微带天线谐振频率建模

谐振频率是微带天线设计过程中最重要的一个参数,直接决定设计的成败.提出基于十进制粒子群优化(DePSO)算法和二进制粒子群优化(BiPSO)算法的选择性神经网络集成方法,通过粒子群优化(PSO)算法合理选择组成神经网络集成的各个神经网络,使个体间保持较大的差异度,减小"多维共线性"和样本噪声的影响.为有效保证PSO算法的粒子多样性,在迭代过程中加入混沌变异策略.仿真试验表明:混沌PSO算法可以有效提高神经网络集成的泛化能力,基于混沌PSO算法的选择性神经网络集成所建立的微带天线的谐振频率模型好于此问题的已有结论.     

Neural-Network-Based Sensor Fusion of Optical Emission and Mass Spectroscopy Data for Real-Time Fault Detection in Reactive Ion Etching

To achieve timely and accurate fault detection in reactive ion etching, neural networks (NNs) have been applied for the fusion of data generated by two in-situ sensors: optical emission spectroscopy (OES) and residual gas analysis (RGA). While etching is performed, OES and RGA data are simultaneously collected in real time. Several pre-determined, statistically significant wavelengths (for OES data) and atomic masses (for RGA signals) are monitored. These data are subsequently used for training NN-based time series models of process behavior. Such models, referred to herein as time series NNs (TSNNs), are realized using multilayered perceptron NNs. Results indicate that the TSNNs not only predict process parameters of interest, but also efficiently perform as sensor fusion of the in-situ sensor data.     

Geometrical Error Modeling and Compensation Using Neural Networks

This paper describes an approach based on neural networks (NNs) for geometrical error modeling and compensation for precision motion systems. A laser interferometer is used to obtain the systematic error measurements of the geometrical errors, based on which an error model may be constructed and, consequently, a model-based compensation may be incorporated in the motion-control system. NNs are used to approximate the components of geometrical errors, thus dispensing with the conventional lookup table. Apart from serving as a more adequate model due to its inherent nonlinear characteristics, the use of NNs also results in less memory requirements to implement the error compensation for a specified precision compared to the use of lookup table. The adequacy and clear benefits of the proposed approach are illustrated via applications to various configurations of precision-positioning stages, including a single-axis, a gantry, and a complete XY stage     

Network traffic prediction based on INGARCH model

In this paper, we introduce the integer-valued generalized autoregressive conditional heteroscedasticity (INGARCH) as a network traffic prediction model. As the INGARCH is known as a non-linear analytical model that could capture the characteristics of network traffic such as Poisson packet arrival and long-range dependence property, INGARCH seems to be an adequate model for network traffic prediction. Based on the investigation for the traffic arrival process in various network topologies including IoT and VANET, we could confirm that assuming the Poisson process as packet arrival works for some networks and environments of networks. The prediction model is generated by estimating parameters of the INGARCH process and predicting the Poisson parameters of future-steps ahead process using the conditional maximum likelihood estimation method and prediction procedure, respectively. Its performance is compared with those of three different models; autoregressive integrated moving average, GARCH, and long short-term memory recurrent neural network. Anonymized passive traffic traces provided by the Center for Applied Internet Data Analysis are used in the experiment. Numerical results show that the proposed model predicts better than the three models in terms of measurements used in prediction models. Based on the study, we can conclude the followings: INGARCH can capture the characteristics of network traffic better than other statistic models, it is more tractable than neural networks (NNs) overcoming the black-box nature of NNs, and the performances of some statistical models are comparable or even superior to those of NNs, especially when the data is insufficient to apply deep NNs.

     

Prediction model for the diffusion length in silicon-based solar cells

A novel approach to compute diffusion lengths in solar cells is presented. Thus, a simulation is done; it aims to give computational support to the general development of a neural networks （NNs）, which is a very powerful predictive modelling technique used to predict the diffusion length in mono-crystalline silicon solar cells. Furthermore, the computation of the diffusion length and the comparison with measurement data, using the infrared injection method, are presented and discussed.     

Neural networks for intelligent multimedia processing

This paper reviews key attributes of neural processing essential to intelligent multimedia processing (IMP). The objective is to show why neural networks (NNs) are a core technology for the following multimedia functionalities: (1) efficient representations for audio/visual information, (2) detection and classification techniques, (3) fusion of multimodal signals, and (4) multimodal conversion and synchronization. It also demonstrates how the adaptive NN technology presents a unified solution to a broad spectrum of multimedia applications. As substantiating evidence, representative examples where NNs are successfully applied to IMP applications are highlighted. The examples cover a broad range, including image visualization, tracking of moving objects, image/video segmentation, texture classification, face-object detection/recognition, audio classification, multimodal recognition, and multimodal lip reading     

On the Direction of Arrival (DoA) Estimation for a Switched-Beam Antenna System Using Neural Networks

A generic direction of arrival (DoA) estimation methodology is presented that is based on neural networks (NNs) and designed for a switched-beam system (SBS). The method incorporates the benefits of NNs and SBSs to achieve DoA estimation in a less complex and expensive way compared to the corresponding widely known super resolution algorithms. The proposed technique is step-by-step developed and thoroughly studied and explained, especially in terms of the beam pattern structure and the neuro-computational procedures. Emphasis is given on the direct sequence code division multiple access (DS-CDMA) applications, and particularly the Universal Mobile Telecommunication System (UMTS). Extensive simulations are realized for each step of the method, demonstrating its performance. It is shown that a properly trained NN can accurately find the signal of interest (SoI) angle of arrival at the presence of a varying number of mobile users and a varying SoI to interference ratio. The proposed NN-SBS DoA estimation method can be applied to current cellular communications base stations, promoting the wider use of smart antenna beamforming.      

Neural network modeling and identification of nonlinear channelswith memory: algorithms, applications, and analytic models

This paper proposes a neural network (NN) approach for modeling nonlinear channels with memory. Two main examples are given: (1) modeling digital satellite channels and (2) modeling solid-state power amplifiers (SSPAs). NN models provide good generalization performance (in terms of output signal-to-error ratio). NN modeling of digital satellite channels allows the characterization of each channel component. Neural net models represent the SSPA as a system composed of a linear complex filter followed by a nonlinear memoryless neural net followed by a linear complex filter. If the new algorithms are to be used in real systems, it is important that the algorithm designer understands their learning behavior and performance capabilities. Some simplified neural net models are analyzed in support of the simulation results. The analysis provides some theoretical basis for the usefulness of NNs for modeling satellite channels and amplifiers. The analysis of the simplified adaptive models explains the simulation results qualitatively but not quantitatively. The analysis proceeds in several steps and involves several novel ideas to avoid solving the more difficult general nonlinear problem     

System-level training of neural networks for counting white bloodcells

Neural networks (NNs) that are trained to perform classification may not perform as well when used as a module in a larger system. We introduce a novel, system-level method for training NNs with application to counting white blood cells. The idea is to phrase the objective function in terms of total count error rather than the traditional class-coding approach because the goal of this particular recognition system is to accurately count white blood cells of each class, not to classify them. An objective function that represents the sum of the squared counting errors (SSCE) is defined. A batch-mode training scheme based on back-propagation and gradient descent is derived. Sigma and crisp counts are used to evaluate the counting performance. The testing results show that the network trained to minimize SSCE performs better in counting than a classification network with the same structure even though both are trained a comparable number of iterations. This result is consistent with the principle of least commitment of D. Marr (1982)     

Hybrid soft computing systems: industrial and commercialapplications

Soft computing (SC) is an association of computing methodologies that includes as its principal members fuzzy logic, neurocomputing, evolutionary computing and probabilistic computing. We present a collection of methods and tools that can be used to perform diagnostics, estimation, and control. These tools are a great match for real-world applications that are characterized by imprecise, uncertain data and incomplete domain knowledge. We outline the advantages of applying SC techniques and in particular the synergy derived from the use of hybrid SC systems. We illustrate some combinations of hybrid SC systems, such as fuzzy logic controllers (FLCs) tuned by neural networks (NNs) and evolutionary computing (EC), NNs tuned by EC or FLCs, and EC controlled by FLCs. We discuss three successful real-world examples of SC applications to industrial equipment diagnostics, freight train control, and residential property valuation