Parameter selection of support vector machine for function approximation based on chaos optimization

The support vector machine （SVM） is a novel machine learning method, which has the ability to approximate nonlinear functions with arbitrary accuracy. Setting parameters well is very crucial for SVM learning results and generalization ability, and now there is no systematic, general method for parameter selection. In this article, the SVM parameter selection for function approximation is regarded as a compound optimization problem and a mutative scale chaos optimization algorithm is employed to search for optimal paraxneter values. The chaos optimization algorithm is an effective way for global optimal and the mutative scale chaos algorithm could improve the search efficiency and accuracy. Several simulation examples show the sensitivity of the SVM parameters and demonstrate the superiority of this proposed method for nonlinear function approximation.

Piezoelectric transducer parameter selection for exciting a single mode from multiple modes of Lamb waves

Excitation and propagation of Lamb waves by using rectangular and circular piezoelectric transducers surface- bonded to an isotropic plate are investigated in this work. Analytical stain wave solutions are derived for the two transducer shapes, giving the responses of these transducers in Lamb wave fields. The analytical study is supported by a numericM simulation using the finite element method. Symmetric and antisymmetric components in the wave propagation responses are inspected in detail with respect to test parameters such as the transducer geometry, the length and the excitation frequency. By placing only one piezoelectric transducer on the top or the bottom surface of the plate and weakening the strength of one mode while enhancing the strength of the other modes to find the centre frequency, with which the peak wave amplitude ratio between the SO and A0 modes is maximum, a single mode excitation from the multiple modes of the Lamb waves can be achieved approximately. Experimental data are presented to show the validity of the analyses. The results are used to optimize the Lamb wave detection system.

Parameter selection and model research on remote sensing evaluation for nearshore water quality

Using remote sensing technology for water quality evaluation is an inevitable trend in marine environmental monitoring. However, fewer categories of water quality parameters can be monitored by remote sensing technology than the 35 specified in GB3097-1997 Marine Water Quality Standard. Therefore, we considered which parameters must be selected by remote sensing and how to model for water quality evaluation using the finite parameters. In this paper, focused on Leizhou Peninsula nearshore waters, we found N, P, COD, PH and DO to be the dominant parameters of water quality by analyzing measured data. Then, mathematical statistics was used to determine that the relationship among the five parameters was COD〉DO〉P〉N〉pH. Finally, five-parameter, fourparameter and three-parameter water quality evaluation models were established and compared. The results showed that COD, DO, P and N were the necessary parameters for remote sensing evaluation of the Leizhou Peninsula nearshore water quality, and the optimal comprehensive water quality evaluation model was the four- parameter model. This work may serve as a reference for monitoring the quality of other marine waters by remote sensing.

TV/L2-based image denoisingalgorithm with automaticparameter selection

In order to improve the adaptiveness of TV/L2-based image denoising algorithm in differ- ent signal-to-noise ratio （SNR） environments, an iterative denoising method with automatic parame- ter selection is proposed. Based upon the close connection between optimization function of denois- ing problem and regularization parameter, an updating model is built to select the regularized param- eter. Both the parameter and the objective function are dynamically updated in alternating minimiza- tion iterations, consequently, it can make the algorithm work in different SNR environments. Mean- while, a strategy for choosing the initial regularization parameter is presented. Considering Morozov discrepancy principle, a convex function with respect to the regularization parameter is modeled. Via the optimization method, it is easy and fast to find the convergence value of parameter, which is suitable for the iterative image denoising algorithm. Comparing with several state-of-the-art algo- rithms, many experiments confirm that the denoising algorithm with the proposed parameter selec- tion is highly effective to evaluate peak signal-to-noise ratio （PSNR） and structural similarity

Convolution Neural Network-based Load Model Parameter Selection Considering Short-term Voltage Stability

The recently proposed ambient signal-based load modeling approach offers an important and effective idea to study the time-varying and distributed characteristics of power loads.Meanwhile,it also brings new problems.Since the load model parameters of power loads can be obtained in real-time for each load bus,the numerous identified parameters make parameter application difficult.In order to obtain the parameters suitable for off-line applications,load model parameter selection(LMPS)is first introduced in this paper.Meanwhile,the convolution neural network(CNN)is adopted to achieve the selection purpose from the perspective of short-term voltage stability.To begin with,the field phasor measurement unit(PMU)data from China Southern Power Grid are obtained for load model parameter identification,and the identification results of different substations during different times indicate the necessity of LMPS.Meanwhile,the simulation case of Guangdong Power Grid shows the process of LMPS,and the results from the CNNbased LMPS confirm its effectiveness.

Scaling parameters selection principle for the scaled unscented Kalman filter

The paper deals with the state estimation of the widely used scaled unscented Kalman filter（UKF）. In particular, the stress is laid on the scaling parameters selection principle for the scaled UKF. Several problems caused by recommended constant scaling parameters are highlighted. On the basis of the analyses, an effective scaled UKF is proposed with self-adaptive scaling parameters,which is easy to understand and implement in engineering. Two typical strong nonlinear examples are given and their simulation results show the effectiveness of the proposed principle and algorithm.

Novel Method for Selection of Regularization Parameter in the Near-field Acoustic Holography

Because of the ill-posedness of the near-field acoustic holography（NAH）,the regularization method is required to stabilize the computational process of NAH.The regularization effect is related to how to select the parameter correctly and effectively.However the L-curve method commonly used for the selection of regularization parameters has the disadvantages of wrong selection and incorrect selection,which influences the application of NAH.For the purpose of solving the problems existed in the L-curve method,the （？）-curve method is introduced into the field of NAH,and the performance applied to NAH directly is analyzed on the basis of equivalent source method-based NAH.However,it is found out via investigations that the（？）-curve method in NAH also has the problem of wrong selection and is unable to choose the regularization parameter correctly.In order to select the parameter correctly and effectively,a novel method for selecting regularization parameters is proposed based on the original（？）-curve method,which can be called improved （？）-curve method.In the proposed method the regularization parameters are discretized linearly between the largest singular value and the smallest singular value,and the solution norm and the residual norm corresponding to these regularization parameters are also described in a linear coordinate instead of in a lg-lg coordinate,which are the two main differences compared with the L-curve and with the original（？）-curve method.In linear coordinate and using the linearly discretized regularization parameters,the solution norm is a monotonically decreasing function of the residual norm as the increase of the regularization parameter,moreover the curve is convex everywhere.So the regularization parameters can be selected correctly and effectively based on the improved（？）-curve method.Then a numerical simulation is done with a simply supported plate to verify the validity of the proposed method.Experiments with two actual sources,a clamped plate and the double speakers,are carried out to do a further demonstration.The simulation result as well as the experimental result shows that the improved（？）-curve method is efficacious and has some advantages over the L-curve method and the original（？）-curve method.The proposed novel method is able to avoid the problem of wrong selection and to select the regularization parameter correctly even if the curve is smooth.

Numerical estimation of choice of the regularization parameter for NMR T2 inversion

Nuclear Magnetic inversion is the basis of NMR Resonance （NMR） T2 logging interpretation. The regularization parameter selection of the penalty term directly influences the NMR T2 inversion result. We implemented both norm smoothing and curvature smoothing methods for NMR T2 inversion, and compared the inversion results with respect to the optimal regular- ization parameters （（Xopt） which were selected by the dis- crepancy principle （DP）, generalized cross-validation （GCV）, S-curve, L-curve, and the slope of L-curve methods, respectively. The numerical results indicate that the DP method can lead to an oscillating or oversmoothed solution which is caused by an inaccurately estimated noise level. The （Xopt selected by the L-curve method is occa- sionally small or large which causes an undersmoothed or oversmoothed T2 distribution. The inversion results from GCV, S-curve and the slope of L-curve methods show satisfying inversion results. The slope of the L-curve method with less computation is more suitable for NMR T2 inversion. The inverted T2 distribution from norm smoothing is better than that from curvature smoothing when the noise level is high.

Parameter selecting and quality predicting of spot welding based on artificial neural networks

This paper proposes a procedure for using artificial neural networks (ANN) in spot welding , and establishes spot welding parameter selecting ANN systems and spot welding joint quality predicting ANN systems . It has been proved that the ANN systems have high prediction precision , providing a new way of parameter selecting and quality predicting in spot welding .

Association among Geomagnetic Activity, Atmospheric Electric Field and Selected Meteorological Parameters

The association among the geomagnetic activity (Ap index) and atmospheric electric field, meteorological parameters was investigated using a long series of continuous data set available tor Colaba (18 ° 53'N, 72 ° 48'E, 11m ASL) for the period 1936-1966. The meteorological parameters used for the investigation are the surface pressure, temperature, wind velocity and relative humidity. The results of the above study indicate that the atmospheric electric field and the meteorological parameters are associated with the geomagnetic storms with Ap > 100 . The atmospheric electric field shows an increasing trend after the geomagnetic storm. The surface pressure dips and surface temperatures increase after a geomagnetic storm. The wind velocity shows a decreasing trend and the relative humidity shows an increasing trend after the geomagnetic storm.

Deep Learning-Based Stacked Auto-Encoder with Dynamic Differential Annealed Optimization for Skin Lesion Diagnosis

Intelligent diagnosis approaches with shallow architectural models play an essential role in healthcare.Deep Learning(DL)models with unsupervised learning concepts have been proposed because high-quality feature extraction and adequate labelled details significantly influence shallow models.On the other hand,skin lesionbased segregation and disintegration procedures play an essential role in earlier skin cancer detection.However,artefacts,an unclear boundary,poor contrast,and different lesion sizes make detection difficult.To address the issues in skin lesion diagnosis,this study creates the UDLS-DDOA model,an intelligent Unsupervised Deep Learning-based Stacked Auto-encoder(UDLS)optimized by Dynamic Differential Annealed Optimization(DDOA).Pre-processing,segregation,feature removal or separation,and disintegration are part of the proposed skin lesion diagnosis model.Pre-processing of skin lesion images occurs at the initial level for noise removal in the image using the Top hat filter and painting methodology.Following that,a Fuzzy C-Means(FCM)segregation procedure is performed using a Quasi-Oppositional Elephant Herd Optimization(QOEHO)algorithm.Besides,a novel feature extraction technique using the UDLS technique is applied where the parameter tuning takes place using DDOA.In the end,the disintegration procedure would be accomplished using a SoftMax(SM)classifier.The UDLS-DDOA model is tested against the International Skin Imaging Collaboration(ISIC)dataset,and the experimental results are examined using various computational attributes.The simulation results demonstrated that the UDLS-DDOA model outperformed the compared methods significantly.

Local Radial Basis Function Methods: Comparison, Improvements, and Implementation

Radial Basis Function methods for scattered data interpolation and for the numerical solution of PDEs were originally implemented in a global manner. Subsequently, it was realized that the methods could be implemented more efficiently in a local manner and that the local approaches could match or even surpass the accuracy of the global implementations. In this work, three localization approaches are compared: a local RBF method, a partition of unity method, and a recently introduced modified partition of unity method. A simple shape parameter selection method is introduced and the application of artificial viscosity to stabilize each of the local methods when approximating time-dependent PDEs is reviewed. Additionally, a new type of quasi-random center is introduced which may be better choices than other quasi-random points that are commonly used with RBF methods. All the results within the manuscript are reproducible as they are included as examples in the freely available Python Radial Basis Function Toolbox.

Parameter value selection strategy for complete coverage path planning based on the Lüsystem to perform specific types of missions

We propose a novel parameter value selection strategy for the Lüsystem to construct a chaotic robot to accomplish the complete coverage path planning(CCPP)task.The algorithm can meet the requirements of high randomness and coverage rate to perform specific types of missions.First,we roughly determine the value range of the parameter of the Lüsystem to meet the requirement of being a dissipative system.Second,we calculate the Lyapunov exponents to narrow the value range further.Next,we draw the phase planes of the system to approximately judge the topological distribution characteristics of its trajectories.Furthermore,we calculate the Pearson correlation coefficient of the variable for those good ones to judge its random characteristics.Finally,we construct a chaotic robot using variables with the determined parameter values and simulate and test the coverage rate to study the relationship between the coverage rate and the random characteristics of the variables.The above selection strategy gradually narrows the value range of the system parameter according to the randomness requirement of the coverage trajectory.Using the proposed strategy,proper variables can be chosen with a larger Lyapunov exponent to construct a chaotic robot with a higher coverage rate.Another chaotic system,the Lorenz system,is used to verify the feasibility and effectiveness of the designed strategy.The proposed strategy for enhancing the coverage rate of the mobile robot can improve the efficiency of accomplishing CCPP tasks under specific types of missions.

Partition region-based suppressed fuzzy C-means algorithm

Aimed at the problem that the traditional suppressed fuzzy C-means clustering algorithms ignore the real needs of different objects, applying the same suppressed parameter for modifying membership degrees of all the objects, a novel partition region-based suppressed fuzzy C-means clustering algorithm with better capacity of adaptability and robustness is proposed in this paper. The model based on the real needs of different objects is built, making it clear to decide whether to proceed with further determination; in addition, the external user-defined suppressed parameter is automatically selected according to the intrinsic structural characteristic of each dataset, making the proposed method become robust to the fluctuations in the incoming dataset and initial conditions. Experimental results show that the proposed method is more robust than its counterparts and overcomes the weakness of the original suppressed clustering algorithm in most cases.

Two-dimensional NMR inversion based on fast norm smoothing method

Two-dimensional(2D)nuclear magnetic resonance(NMR)inversion operates with massive echo train data and is an ill-posed problem.It is very important to select a suitable inversion method for the 2D NMR data processing.In this study,we propose a fast,robust,and effective method for 2D NMR inversion that improves the computational efficiency of the inversion process by avoiding estimation of some unneeded regularization parameters.Firstly,a method that combines window averaging(WA)and singular value decomposition(SVD)is used to compress the echo train data and obtain the singular values of the kernel matrix.Subsequently,an optimum regularization parameter in a fast manner using the signal-to-noise ratio(SNR)of the echo train data and the maximum singular value of the kernel matrix are determined.Finally,we use the Butler-Reeds-Dawson(BRD)method and the selected optimum regularization parameter to invert the compressed data to achieve a fast 2D NMR inversion.The numerical simulation results indicate that the proposed method not only achieves satisfactory 2D NMR spectra rapidly from the echo train data of different SNRs but also is insensitive to the number of the final compressed data points.

CHARACTERISTICS OF STRENGTH CONTROL OF ADAPTIVE STRUCTURE WITH ELECTROMECHANICAL COUPLING

Based on the programming method, an electromechanical coupling adaptive statically indeterminate truss structure is controlled for increasing its load capacity. Several main parameters during the process of design of the adaptive structure are selected for a study of its characteristic during the control stage. The curves of each parameter for the effect of control results are plotted and corresponding conclusions are drawn. Thus, the theoretical basis is presented for optimal design, manufacture and control of the adaptive structure.

COMPARISON OF MODELING TECHNIQUES FOR SELECTING OPTIMIZED AND AUTOMATED PLASMA CUTTING PROCESS PARAMETERS

The advancement in technologies made the entire manufacturing system,to be operated with more efficient,flexible,user friendly,more productive and cost effective.One such a system to be focused for advancement is plasma cutting system,which has wider industrial applications.There are many researches pursuing at various area of plasma cutting technology,still the automated and optimized parameters value selection is challenging.The work is aimed to eliminate the manual mode of feeding the input parameters for cutting operation.At present,cutting parameters are fed by referring the past cut data information or with the assistance of experienced employers.The cutting process parameters selections will have direct impact on the quality of the material being cut,and life of the consumables.This paper is intended to automate the process parameters selection by developing the mathematical model with existing cutting process parameters database.In this,three different approaches,multiple regression,multiple polynomial regression and AI technique,are selected and analyzed with the mathematical relations developed between the different cutting process parameters.The accuracy and reliability of those methods are detailed.The advantage and disadvantage of those methods for optimal setting conditions are discussed.The appropriate method that can be preferred for automated and optimal settings are elucidated.Finally,the selected technique is checked for accuracy and reliability for the existing cut data.

An adaptive turbo-shaft engine modeling method based on PS and MRR-LSSVR algorithms

In order to establish an adaptive turbo-shaft engine model with high accuracy, a new modeling method based on parameter selection （PS） algorithm and multi-input multi-output recursive reduced least square support vector regression （MRR-LSSVR） machine is proposed. Firstly, the PS algorithm is designed to choose the most reasonable inputs of the adaptive module. During this process, a wrapper criterion based on least square support vector regression （LSSVR） machine is adopted, which can not only reduce computational complexity but also enhance generalization performance. Secondly, with the input variables determined by the PS algorithm, a mapping model of engine parameter estimation is trained off-line using MRR-LSSVR, which has a satisfying accuracy within 5＆. Finally, based on a numerical simulation platform of an integrated helicopter/ turbo-shaft engine system, an adaptive turbo-shaft engine model is developed and tested in a certain flight envelope. Under the condition of single or multiple engine components being degraded, many simulation experiments are carried out, and the simulation results show the effectiveness and validity of the proposed adaptive modeling method.

A fast and adaptive method for complex-valued SAR image denoising based on l_k norm regularization

This paper developed a fast and adaptive method for SAR complex image denoising based on lk norm regularization, as viewed from parameters estimation. We firstly establish the relationship between denoising model and ill-posed inverse problem via convex half-quadratic regularization, and compare the difference between the estimator variance obtained from the iterative formula and biased CramerRao bound, which proves the theoretic flaw of the existent methods of parameter selection. Then, the analytic expression of the model solution as the function with respect to the regularization parameter is obtained. On this basis, we study the method for selecting the regularization parameter through minimizing mean-square error of estimators and obtain the final analytic expression, which resulted in the direct calculation, high processing speed, and adaptability. Finally, the effect of regularization parameter selection on the resolution of point targets is analyzed. The experiment results of simulation and real complex-valued SAR images illustrate the validity of the proposed method.