Abstract: A novel model-free adaptive control method is proposed for a class of discrete-time single input single output (SISO) nonlinear systems, where the equivalent dynamic linearization technique is used on the ideal nonlinear controller. With radial basis function neural network, the controller parameters are tuned on-line directly using the measured input and output data of the plant, when the plant model is unavailable. The stability of the proposed method is guaranteed by rigorous theoretical analysis, and the effectiveness and applicability are verified by numerical simulation and further demonstrated by the experiment on three tanks water level control process.

Abstract: Water temperature directly affects the physical, biological and chemical characteristics of the river and determines the fitness and life of all aquatic organisms. It has direct and indirect effects on nearly all aspects of stream ecology. Accurately estimating water temperature is a complex problem. The purpose of this article is to analyze the relationship between the air and water temperature of the River Drava by constructing an artificial neural network (ANN) model and choosing appropriate network architectures for the River Drava’s daily river water temperature as well as demonstrating its application in improving the interpretation of the results. A linear regression model, as well as a stochastic model are also constructed and compared to ANN models consisting of a multilayer perceptron neural network and a radial basis function network. The results indicate that the ANN models are much better models and that ANNs are powerful tools that can be used for the estimation of daily mean river temperature.

Abstract: An improved neural network of time series predicting is presented in this paper. We introduce a random data-time effective radial basis function neural network in determination of the output weights, the center vectors and the widths in the hidden layer of the network. In the training modeling, we consider that the historical data on the financial market is key to the investors' decision-making for their investing positions, and the impact of historical data depends closely on the time. We develop a random data-time effective function to describe this impact strength, and a weight is given to each of the historical data, where a drift function and a random Brownian volatility function are applied to express the behavior of the time strength. Further, this neural network is applied to the prediction of financial price series of crude oil, SSE, N225 and DAX. The empirical experiments show that the proposed neural network results in better performance in financial time series forecasting and is advantageous in increasing the forecasting precision.

Abstract: Automated motion detection has become an increasingly important subject in traffic surveillance systems Video communication in traffic surveillance systems may experience network congestion or unstable bandwidth over real-world networks with limited bandwidth, which is harmful in regard to motion detection in video streams of variable bit rate In this paper, we propose a unique Fisher's linear discriminant-based radial basis function network motion detection approach for accurate and complete detection of moving objects in video streams of both high and low bit rates The proposed approach is accomplished through a combination of two stages: adaptive pattern generation (APG) and moving object extraction (MOE) For the APG stage, the variable-bit-rate video stream properties are accommodated by the proposed approach, which subsequently distinguishes the moving objects within the regions belonging to the moving object class by using two devised procedures during the MOE stage Qualitative and quantitative detection accuracy evaluations show that the proposed approach exhibits superior efficacy when compared to previous methods For example, accuracy rates produced by F1 and Similarity metrics for the proposed approach were, respectively, up to 9223% and 8824% higher than those produced for other previous methods

Abstract: In this paper, a new study based on machine learning technique, specifically artificial neural network, is investigated to predict the systolic blood pressure by correlated variables (BMI, age, exercise, alcohol, smoke level etc.). The raw data are split into two parts, 80% for training the machine and the remaining 20% for testing the performance. Two neural network algorithms, back-propagation neural network and radial basis function network, are used to construct and validate the prediction system. Based on a database with 498 people, the probabilities of the absolute difference between the measured and predicted value of systolic blood pressure under 10mm Hg are 51.9% for men and 52.5% for women using the back-propagation neural network With the same input variables and network status, the corresponding results based on the radial basis function network are 51.8% and 49.9% for men and women respectively. This novel method of predicting systolic blood pressure contributes to giving early warnings to young and middle-aged people who may not take regular blood pressure measurements. Also, as it is known an isolated blood pressure measurement is sometimes not very accurate due to the daily fluctuation, our predictor can provide another reference value to the medical staff. Our experimental result shows that artificial neural networks are suitable for modeling and predicting systolic blood pressure.

Abstract: Artificial neural networks (ANNs) method is widely used in reliability analysis. However, the performance of ANNs cannot be guaranteed due to the fitting problems because there is no efficient constructive method for choosing the structure and the learning parameters of the network. To mitigate these difficulties, this article presents a new adaptive wavelet frame neural network method for reliability analysis of structures. The new method uses the single-scaling multidimensional wavelet frame as the activation function in the network to deal with the multidimensional problems in reliability analysis. Because the wavelet frame is highly redundant, the time–frequency localization and matching pursuit algorithm are respectively utilized to eliminate the superfluous wavelets, thus the obtained wavelet frame neural network can be implemented efficiently. Five examples are given to demonstrate the application and effectiveness of the proposed method. Comparisons of the new method and the classical radial basis function network method are made.

Abstract: This paper proposes an online learning adaptive radial basis function neural network (RBFNN) to deal with measurement errors and environment disturbances to improve control performance. Since the weight matrix of the adaptive neural network can be updated online by the state error information, the adaptive neural network can be constructed directly without prior training. Moreover, with the parameter optimization rule, the residual approximation error can be reduced by the maximum absolute position error, average position error, and mean square position error in sampling windows. The applicability of the proposed method is validated by a series of simulations and flight tests. The adaptive RBFNN control method can realize hovering, straight flight, and autonomous landing control under wind disturbances.

Abstract: Experimental validation of software metrics in fault prediction for object-oriented methods using statistical and machine learning methods is necessary. By the process of validation the quality of software product in a software organization is ensured. Object-oriented metrics play a crucial role in predicting faults. This paper examines the application of linear regression, logistic regression, and artificial neural network methods for software fault prediction using Chidamber and Kemerer (CK) metrics. Here, fault is considered as dependent variable and CK metric suite as independent variables. Statistical methods such as linear regression, logistic regression, and machine learning methods such as neural network (and its different forms) are being applied for detecting faults associated with the classes. The comparison approach was applied for a case study, that is, Apache integration framework (AIF) version 1.6. The analysis highlights the significance of weighted method per class (WMC) metric for fault classification, and also the analysis shows that the hybrid approach of radial basis function network obtained better fault prediction rate when compared with other three neural network models.

Abstract: Many current model reference adaptive control methods employ parametric adaptive elements in which the number of parameters are fixed a priori and the hyperparameters, such as the bandwidth, are predefined, often through expert judgment. As an alternative to these methods, a nonparametric model using Gaussian processes was recently proposed. Using Gaussian processes, it is possible to maintain constant coverage over the operating domain by adaptively selecting new kernel locations as well as adapt hyperparameters in an online setting to improve model prediction. In this work, the first extensive experimental flight results are presented using Gaussian process/model reference adaptive control. Experimental results show that Gaussian process/model reference adaptive control outperforms traditional model reference adaptive control methods that use radial basis function neural networks in terms of tracking error as well as transient behavior on trajectory following using a quadrotor. Results show an improveme...

Abstract: Artificial neural networks (ANNs) are known as “universal approximators” and “computational models” with particular characteristics such as the ability to learn or adapt, to organize or to generalize data. Because of their automatic (self-adaptive) process and capability to learn complex, nonlinear surfaces, ANN classifiers have become a popular choice for many machine intelligence and pattern recognition applications. In this chapter, we shall present a technique for automatic design of Artificial Neural Networks (ANNs) by evolving to the optimal network configuration(s) within an architecture space (AS), which is a family of ANNs. The AS can be formed according to the problem in hand encapsulating indefinite number of network configurations. The evolutionary search technique is entirely based on multidimensional Particle Swarm Optimization (MD PSO). With a proper encoding of the network configurations and parameters into particles, MD PSO can then seek positional optimum in the error space and dimensional optimum in the AS. The optimum dimension converged at the end of a MD PSO process corresponds to a unique ANN configuration where the network parameters (connections, weights, and biases) can then be resolved from the positional optimum reached on that dimension. In addition to this, the proposed technique generates a ranked list of network configurations, from the best to the worst. This is indeed a crucial piece of information, indicating what potential configurations can be alternatives to the best one, and which configurations should not be used at all for a particular problem. In this chapter, the architecture space is defined over feed-forward, fully connected ANNs so as to use the conventional techniques such as back-propagation and some other evolutionary methods in this field. We shall then apply the evolutionary ANNs over the most challenging synthetic problems to test its optimality on evolving networks and over the benchmark problems to test its generalization capability as well as to make comparative evaluations with the several competing techniques. We shall demonstrate that MD PSO evolves to optimum or near-optimum networks in general and has a superior generalization capability. In addition, MD PSO naturally favors a low-dimension solution when it exhibits a competitive performance with a high dimension counterpart and such a native tendency eventually steers the evolution process toward the compact network configurations in the architecture space instead of more complex ones, as long as optimality prevails.

Abstract: This paper proposes a parallel fixed point radial basis function (RBF) artificial neural network (ANN), implemented in a field programmable gate array (FPGA) trained online with a least mean square (LMS) algorithm. The processing time and occupied area were analyzed for various fixed point formats. The problems of precision of the ANN response for nonlinear classification using the XOR gate and interpolation using the sine function were also analyzed in a hardware implementation. The entire project was developed using the System Generator platform (Xilinx), with a Virtex-6 xc6vcx240t-1ff1156 as the target FPGA.

Abstract: The current work involves both modeling and optimization approaches to achieve minimum spring-back in V-die bending process of heat treated CK67 sheets. Number of 36 experimental tests have been conducted with various levels of sheet orientation, punch tip radius and sheet thickness. Firstly, various predictive models based on statistical analysis, back-propagation neural network (BPNN), counter propagation neural network (CPNN) and radial basis function network (RBFNN) have been developed using experimental observations. Then the accuracy of the developed models has been compared based on values of mean absolute error (MAE), and root mean square error (RMSE). Secondly, the model with lowest values of MAE, and RMSE has been applied as objective function for optimization of process using imperialist competitive algorithm (ICA). After selection of optimal bending parameters, a confirmation test has been conducted to prove the optimal solutions. Results indicated that the radial basis network fulfills precise prediction of process rather than the other developed models. Also, confirmation tests proved that both RBFNN and ICA could predict and optimize the process vigorously.

Abstract: The autonomous vehicle is an automated system equipped with features like environment perception, decision-making, motion planning, and control and execution technology. Navigating in an unstructured and complex environment is a huge challenge for autonomous vehicles, due to the irregular shape of road, the requirement of real-time planning, and the nonholonomic constraints of vehicle. This paper presents a motion planning method, based on the Radial Basis Function (RBF) neural network, to guide the autonomous vehicle in unstructured environments. The proposed algorithm extracts the drivable region from the perception grid map based on the global path, which is available in the road network. The sample points are randomly selected in the drivable region, and a gradient descent method is used to train the RBF network. The parameters of the motion-planning algorithm are verified through the simulation and experiment. It is observed that the proposed approach produces a flexible, smooth, and safe path that can fit any road shape. The method is implemented on autonomous vehicle and verified against many outdoor scenes; furthermore, a comparison of proposed method with the existing well-known Rapidly-exploring Random Tree (RRT) method is presented. The experimental results show that the proposed method is highly effective in planning the vehicle path and offers better motion quality.

Abstract: In this work, we apply the radial basis functions for solving the time fractional diffusion-wave equation defined by Caputo sense for 2) <  . The problem is discretized in the time direction based on finite difference scheme and is continuously approximated by using the radial basis functions in the space direction which achieves the semi-discrete solution. Numerical results show the accuracy and efficiency of the presented method.

Abstract: In this study, a new heuristic based intelligent algorithm is proposed for the elimination of harmonics in diode-clamped inverters. Numerous methods have been introduced for optimising harmonics in diode-clamped inverter such as Newton-Raphson method. These methods are not sometimes applicable because of difficulty of initializing algorithm parameters and singularity problems in Jacobian-based methods. Radial basis function neural network is used in the proposed method which is one of the most useful members of the neural networks family, because of their capability in the approximation problems. They work on the basis of this fact that, it has been proved that any arbitrary non-linear function can be exactly modelled by a combination of some non-linear basis functions. The proposed algorithm can be applied to solve the selective harmonic elimination problem of any multilevel inverters with any number of levels. The method has the benefit of high rate of convergence and accuracy besides simplicity in implementation. Theoretical results are authorised by experiments and simulations for a seven-level diode-clamped inverter. The obtained results prove efficiency and capability of the proposed method.

Abstract: The invention relates to an adaptive learning control method of a piezoelectric ceramics driver. The adaptive learning control method of the piezoelectric ceramics driver comprises the following steps of (1), building a dynamic hysteretic model of the piezoelectric ceramics driver and designing a control method with the artificial neural network and a PID combined, (2), adopting a reinforcement learning algorithm to achieve adaptive setting of PID parameters on line, (3), adopting a three-layer radial basis function network to approach a strategic function of an actuator in the reinforcement learning algorithm and a value function of an evaluator in the reinforcement learning algorithm; (4), inputting a system error, an error first-order difference and an error second-order difference through a first layer of the radial basis function network, (5), achieving mapping of the system state to the three PID parameters through the actuator in the reinforcement learning algorithm, and (6), judging the output of the actuator and generating an error signal through the evaluator in the reinforcement learning algorithm, and updating system parameters through the signal. The adaptive learning control method of the piezoelectric ceramics driver solves the hysteresis nonlinear problem of the piezoelectric ceramics driver, improves the repeated locating accuracy of a piezoelectric ceramics drive platform, and eliminates influence on a system from hysteresis nonlinearity of piezoelectric ceramics.

Abstract: The Swarm Intelligence Algorithms are (Meta-Heuristic) development Algorithms, which attracted much attention and appeared its ability in the last ten years within many applications such as data mining, scheduling, improve the performance of artificial neural networks (ANN) and classification. In this research was the work of a comparative study between Bat Algorithm (BA) and Particle Swarm Optimization Algorithm (PSO) to train Radial Basis function network (RBF) to classify types of benchmarking data. Results showed that Bat Algorithm (BA) is overcome on (PSO )Algorithm in terms of improving the weights of (RBF) network and accelerate the training time and good convergence of optimal solutions, which led to increase network efficiency and reduce falling mistakes and nonoccurrence. General Terms Bat Algorithm, Radial Basis Function, Particle Swarm Optimization Algorithm, Neural Network, Classification.

Abstract: This paper introduces the concept and practice of Neural Network architectures for wind speed prediction in wind farms. The wind speed prediction method has been analyzed by using back propagation network and radial basis function network. Artificial neural network is used to develop suitable architecture for predicting wind speed in wind farms. The key of wind speed prediction is rational selection of forecasting model and effective optimization of model performance. To verify the effectiveness of neural network architecture, simulations were conducted on real time wind data with different heights of wind mill. Due to fluctuation and nonlinearity of wind speed, accurate wind speed prediction plays a major role in the operational control of wind farms. The key advantages of Radial Basis Function Network include higher accuracy, reduction of training time and minimal error. The experimental results show that compared to existing approaches, proposed radial basis function network performs better in terms of minimization of errors.

Abstract: The paper discusses how Spiking Wavelet Radial Basis Neural Network can be effectively used for the classification of gene expression data. A new spiking function has been proposed in the non-linear integrate and fire model and its inter spike interval is derived and used in the Wavelet Radial Basis Neural Network for the classification of gene expression data. The proposed model is termed as Spiking Wavelet Radial Basis Neural Network (SWRNN). The classification accuracy has been evaluated on various benchmark gene expression datasets. A comparative performance evaluation of the proposed model has been made with the Wavelet Radial Basis Neural Network (WRNN) and the standard available results in terms of classification accuracy. The comparison of the proposed SWRNN and WRNN has also been done in terms of execution time. It has been observed that the increase in classification accuracy for the proposed SWRNN is highly statistically significant for most of the gene expression datasets when compared with WRNN and the standard results. Thus incorporating a spiking function in an artificial neural network can make it more powerful for classification.

Abstract: The success of software development depends on the proper estimation of the effort required to develop the software. Project managers require a reliable approach for software effort estimation. It is especially important during the early stages of the software development life cycle. Accurate software effort estimation is a major concern in software industries. Stochastic Gradient Boosting (SGB) is one of the machine learning techniques that helps in getting improved estimated values. SGB is used for improving the accuracy of models built on decision trees. In this paper, the main goal is to estimate the effort required to develop various software projects using the class point approach. Then, optimization of the effort parameters is achieved using the SGB technique to obtain better prediction accuracy. Further- more, performance comparisons of the models obtained using the SGB technique with the Multi Layer Perceptron and the Radial Basis Function Network are presented in order to highlight the performance achieved by each method.

Abstract: The paper presents a multi-objective optimization of circumferential casing grooves geometries for the NASA Rotor 37 transonic compressor. The depth normalized by the tip clearance and the width normalized by the tip chord are selected as the design variables. The stall margin and peak efficiency are used as the objective functions. The Latin Hypercube Sampling technique was used to select the sample points in the design space. Based on the numerical results of the sample points, the radial basis function network model of the artificial neural network was constructed. The NSGA-II multi-objective evolutionary algorithm is then employed to search for Pareto-optimal solutions. The leave-one-out cross validation method was also used to evaluate the precision of the radial basis function network model. The results of the optimization show the present method can be effectively used for the design of circumferential casing grooves to take account of the stall margin and efficiency. From the Pareto-optimal soluti...

Abstract: In this work, we present the method based on radial basis functions to solve partial integro-differential equations. We focus on the parabolic type of integro-differential equations as the most common forms including the ``\emph{memory}'' of the systems. We propose to apply the collocation scheme using radial basis functions to approximate the solutions of partial integro-differential equations. Due to the presented technique, system of linear or nonlinear equations is made instead of primary problem. The method is efficient because the rate of convergence of collocation method based on radial basis functions is exponential. Some numerical examples and investigation of the experimental results show the applicability and accuracy of the method.

Abstract: A new approach for adaptively sampling a design parameter space using an error estimate through the reconstruction of flow field by a combination of proper orthogonal decomposition (POD) and radial basis function network (RBFN) is presented It differs from other similar approaches in that it does not use the reconstructed flow field by POD for the evaluation of objective functions, and thus it can be a subset of the flow field Advantages of this approach include the ease of constructing a chain of simulation codes as well as the flexibility of choosing where and what to reconstruct within the solution domain An improvement in achieving a good prediction quality, with respect to other adaptive sampling methods, has been demonstrated using supersonic impulse turbine optimization as the test case A posteriori validation of the surrogate models were also carried out using a set of separately-evaluated samples, which showed a similar trend as the Leave-One-Out (LOO) cross-validation The progressively enriched surrogate model was then used to achieve the more uniformly populated Pareto front with fewer number of function evaluationsCopyright © 2014 by ASME