Optimization Of Tuning Parameters Research Articles

Predicting the Bond Resistance of Glass Fiber Bars in Hinged Beams Employing Enhanced Soft Computing Techniques

One of the principal parameters which affect the behavior of reinforced concrete (RC) elements is the bond of the bar to concrete. Considering the corrosion of steel bars and the widespread use of glass fiber reinforced polymer (GFRP) bars, it is necessary to study the bond between concrete and GFRP rebars. The hinged beam is one of the tests which simulates the relatively actual stress of RC members. In this study, a database containing 116 GFRP reinforced hinged beams with pull-out failure mode has been collected. To predict the bond resistance, Kriging, multivariate adaptive regression splines (MARS), and nonlinear regression techniques are utilized. K-fold cross-validation, sensitivity analysis of input variables, and optimization of tuning parameters for soft computing methods have been used to increase the precision, efficiency, and generality of the proposed models. Also, using the nonlinear regression method, a practical and straightforward relationship is suggested to forecast the bond resistance. The proposed Kriging, MARS, and nonlinear regression models outperformed the other models with determination coefficients of 0.98, 0.96, and 0.78, respectively. Parametric analysis of the variables has also been performed to investigate the influence of various input parameters on the bond resistance of GFRP bars in hinged beams.

Improved estimation of rail–wheel contact forces from instrumented wheel-set data through higher harmonic cancellation and a back-propagation neural network scheme

Instrumented wheelsets, equipped with numbers of strain gauges, are widely used to estimate the rail–wheel contact parameters. The accuracy in estimation of rail–wheel contact parameters from the measured strain signals depends on the layout of the strain gauges and correlation techniques adopted for processing measured signals. Harmonic components estimation is the most widely used conventional correlation technique. However, its accuracy in estimation of rail–wheel contact parameters is limited to the order of 80%–90%. This study proposes a signal modification algorithm, initially utilizing cancellation of next significant higher harmonics than those considered in the existing algorithms and then further, a novel Artificial Neural Network architecture for the same purpose.The signal modification approach is based on the realization that the seventh harmonic has significant contribution on the strain signals. The proposed algorithm is aimed at estimating and cancelling the effects of the seventh harmonic in strain signals. The accuracy thus improves to 91% in vertical contact force estimates, while the accuracy in estimation of lateral contact force and lateral contact position are improved to 97% and 95%, respectively. Due to the highly non-linear nature of the rail–wheel contact parameters, an optimized nonlinear mapping is required for further improvement in the accuracy.The viability of using artificial neural networks in estimation of rail–wheel contact parameters have been explored earlier. The proposed architectures are complicated and require extensive manual optimization of tuning parameters. A simple back-propagation artificial neural network architecture, using Bayesian regularization training function with Levenberg–Marquardt optimization technique is proposed in this study. The proposed neural network consists of 18 measured strain signals as input, three hidden layers with 20, 6 and 3 neurons, respectively, and vertical force, lateral force and lateral contact position as three outputs. Accuracies of the order of 99%, 99% and 96% are achieved in the estimation of vertical contact force, lateral contact force and lateral contact position respectively. The input and training data is generated from the multi-body dynamics and finite element simulations.

Fractional-Order PID and Active Disturbance Rejection Control with Tuning Parameter Optimization for Induction Heating

Induction heating systems are characterized by model uncertainty, nonlinearity, and external disturbances, and the control accuracy of the system directly affects the performance of the heated workpiece. In order to improve the temperature control accuracy and anti-interference performance of induction heating systems, this paper proposes a composite control strategy combining fractional-order PID (FOPID) and active disturbance rejection control (ADRC). Meanwhile, for the problem of too many controller tuning parameters, an improved quantum behavior particle swarm optimization (QPSO) algorithm is used to transform the nine parameters to be tuned in fractional-order PID active disturbance rejection control (FOPID-ADRC) into a minimization value optimization problem for solving. The simulation results show that the FOPID-ADRC controller improves the anti-interference capability and control accuracy of the temperature control system, and the improved QPSO algorithm has better global search capability and local optimal adaptation value.

Global optimization control for nonlinear full‐car active suspension system with multi‐performances

In this article, based on feedback linearized approach and linear quadratic regulator optimization control approach using particle swarm optimization, the almost disturbance decoupling, input amplitude reduction, tuning parameter optimization, controllable convergence rate, improved suspension and globally exponential stability multi-performances of highly nonlinear multi-input multi-output full-car uncertain system are simultaneously achieved without applying any nonlinear function approximator including neural network approach and fuzzy logic approach. The article proposes a new method to achieve the optimal control matrices of LQR such that the composite controller can reduce the amplitudes of system control inputs. Determination of the LQR tuning parameters is conventionally determined via trial and error approach. In addition to being very troublesome, it is difficult to find the globally best tuning matrices with LQR method. This study has first proposed the convergence rate formula of the nonlinear system response as the fitness function of LQR approach by using PSO optimization algorithm to take the place of the conventional trial and error method and locally Jacobian linearized approach under the guarantee of globally exponential stability. The simulation results show how the full-car system can be controlled optimally and satisfactorily and confirm the superiority of the proposed method.

Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics

Selecting the right tuning parameters for algorithms is a pravelent problem in machine learning that can significantly affect the performance of algorithms. Data-efficient optimization algorithms, such as Bayesian optimization, have been used to automate this process. During experiments on real-world systems such as robotic platforms these methods can evaluate unsafe parameters that lead to safety-critical system failures and can destroy the system. Recently, a safe Bayesian optimization algorithm, called SafeOpt, has been developed, which guarantees that the performance of the system never falls below a critical value; that is, safety is defined based on the performance function. However, coupling performance and safety is often not desirable in practice, since they are often opposing objectives. In this paper, we present a generalized algorithm that allows for multiple safety constraints separate from the objective. Given an initial set of safe parameters, the algorithm maximizes performance but only evaluates parameters that satisfy safety for all constraints with high probability. To this end, it carefully explores the parameter space by exploiting regularity assumptions in terms of a Gaussian process prior. Moreover, we show how context variables can be used to safely transfer knowledge to new situations and tasks. We provide a theoretical analysis and demonstrate that the proposed algorithm enables fast, automatic, and safe optimization of tuning parameters in experiments on a quadrotor vehicle.

Feedback Linearized Optimal Control Design for Quadrotor With Multi-Performances

Design of tracking controller for quadrotor is an important issue for many engineering fields such as COVID-19 epidemic prevention, intelligent agriculture, military photography and rescue nowadays. This study applies the feedback linearized method and linear quadratic regulator (LQR) method using particle swarm optimization (PSO) to analysis and stabilize the highly nonlinear quadrotor system without applying any nonlinear function approximator that includes neural network approach and fuzzy approach. The article proposes a new method based on the firstly proposed convergence rate formula to achieve the optimal weighting matrices of LQR such that the composite controller can reduce the amplitudes of system control inputs. Determination of the LQR tuning parameters is conventionally achieved via trial and error approach. In addition to being very troublesome, it is difficult to find the globally best tuning matrices with LQR method. This article firstly uses the convergence rate formula of the nonlinear system as the fitness function of LQR approach by using PSO to take the place of the trial and error method. The generalities and implications of proposed approach are globally valid, whereas the Jacobian linearized approach is locally valid due to the Taylor expansion theorem. In addition to these two major achievements, the significant innovation of the proposed method is to possess “simultaneously” additional performances including the almost disturbance decoupling, input amplitude reduction, tuning parameter optimization and globally exponential stability performances. Comparative examples show that the convergence rate with our proposed optimal controller using the PSO algorithm is larger than the fuzzy method, and better than the singular perturbation method with high-gain feedback.

Generalized Cross-Validation for Simultaneous Optimization of Tuning Parameters in Ridge Regression

When multicollinearity exists in the context of robust regression, ridge rank regression estimator can be used as an alternative to the rank estimator. Performance of the ridge rank regression estimator is highly dependent on the ridge parameter, here the tuning parameter. On the other hand, suppose we are provided with some non-sample uncertain prior information (UPI) about regression coefficients. Shrinkage estimation is a well-known strategy to improve estimation, under the UPI, where the amount of shrinkage is controlled by a tuning parameter. Hence, optimization of both tuning parameters can be a problem of interest. In this study, theoretical development of the generalized cross-validation (GCV) is considered and some numerical illustrations are given to validate the theoretical findings. Our results demonstrated that using the proposed GCV criterion, the shrinkage ridge rank regression estimator behaves well in the sense of minimum risk function.

An On-Board Model-Based Condition Monitoring for Lithium-Ion Batteries

A model-based condition monitoring for lithium-ion (Li-ion) batteries involves estimating critical model parameters (e.g., capacity and impedance) and operational states [e.g., state of charge (SOC) and state of health]. This is important to design high-performance and safety-critical battery systems. Moreover, the tuning parameters of the condition monitoring algorithms significantly influence the performance of the algorithms. This paper proposes a real-time model-based condition monitoring for Li-ion batteries based on a real-time second-order resistor–capacitor electrical circuit battery model. The proposed method consists of an extended Kalman filter based online parameter identification and a smooth variable structure filter based state estimation. The two filters are systematically integrated to cooperate with each other and named hybrid filter (HF). Furthermore, a proposed particle swarm optimization based tuning parameter optimization is employed to find the optimal tuning parameters of the HF. The proposed method is compared with the dual extended Kalman filter (DEKF) via simulations and validated by experiments using a low-priced microcontroller. The results show that the proposed method can effectively choose the tuning parameters and has less computational complexity and higher accuracy of the SOC and capacity estimation than those of the conventional DEKF. Therefore, the proposed HF can be suitable for use in real-time embedded battery management system applications.

Modeling Dissociation Pressure of Semi-Clathrate Hydrate Systems Containing CO2, CH4, N2, and H2S in the Presence of Tetra-n-butyl Ammonium Bromide

Abstract In this study, the phase equilibria of semi-clathrate hydrates of methane (CH4), carbon dioxide (CO2), nitrogen (N2), and hydrogen sulfide (H2S) in an aqueous solution of tetra-n-butyl ammonium bromide (TBAB) were modeled using a correlation based on a two-stage formation mechanism: a quasi-chemical reaction that forms basic semi-clathrate hydrates and adsorption of guest molecules in the linked cavities of the basic semi-clathrate hydrate. The adsorption of guest molecules was described by the Langmuir adsorption theory and the fugacity of the gas phase was calculated by Peng–Robinson (PR) equation of state (EOS). The water activity in the presence of TBAB was calculated using a correlation, dependent on temperature, the TBAB mass fraction, and the nature of the guest molecule. These equations were coupled together and form a correlation which was linked to a genetic algorithm for optimization of tuning parameters. The results showed an excellent agreement between model results and experimental data. In addition, an outlier diagnostic was performed for finding any possible doubtful data and assessing the applicability of the model. The results showed that more than 97 % of the data were reliable and they were in the applicability domain of the model.

Differential-Evolution Control Parameter Optimization for Unmanned Aerial Vehicle Path Planning

The differential evolution algorithm has been widely applied on unmanned aerial vehicle (UAV) path planning. At present, four random tuning parameters exist for differential evolution algorithm, namely, population size, differential weight, crossover, and generation number. These tuning parameters are required, together with user setting on path and computational cost weightage. However, the optimum settings of these tuning parameters vary according to application. Instead of trial and error, this paper presents an optimization method of differential evolution algorithm for tuning the parameters of UAV path planning. The parameters that this research focuses on are population size, differential weight, crossover, and generation number. The developed algorithm enables the user to simply define the weightage desired between the path and computational cost to converge with the minimum generation required based on user requirement. In conclusion, the proposed optimization of tuning parameters in differential evolution algorithm for UAV path planning expedites and improves the final output path and computational cost.

PI Stabilization for Congestion Control of AQM Routers with Tuning Parameter Optimization

This work is builds on the study of the 10 top data mining algorithms identified by the IEEE International Conference on Data Mining (ICDM) community in December 2006. We address the same study, but with the application of statistical tests to establish, a more appropriate and justified ranking classifier for classification tasks. Current studies and practices on theoretical and empirical comparison of several methods, approaches, advocated tests that are more appropriate. Thereby, recent studies recommend a set of simple and robust non-parametric tests for statistical comparisons classifiers. In this paper, we propose to perform non-parametric statistical tests by the Friedman test with post-hoc tests corresponding to the comparison of several classifiers on multiple data sets. The tests provide a better judge for the relevance of these algorithms.

A measure of the impact of CV incompleteness on prediction error estimation with application to PCA and normalization.

BackgroundIn applications of supervised statistical learning in the biomedical field it is necessary to assess the prediction error of the respective prediction rules. Often, data preparation steps are performed on the dataset—in its entirety—before training/test set based prediction error estimation by cross-validation (CV)—an approach referred to as “incomplete CV”. Whether incomplete CV can result in an optimistically biased error estimate depends on the data preparation step under consideration. Several empirical studies have investigated the extent of bias induced by performing preliminary supervised variable selection before CV. To our knowledge, however, the potential bias induced by other data preparation steps has not yet been examined in the literature. In this paper we investigate this bias for two common data preparation steps: normalization and principal component analysis for dimension reduction of the covariate space (PCA). Furthermore we obtain preliminary results for the following steps: optimization of tuning parameters, variable filtering by variance and imputation of missing values.MethodsWe devise the easily interpretable and general measure CVIIM (“CV Incompleteness Impact Measure”) to quantify the extent of bias induced by incomplete CV with respect to a data preparation step of interest. This measure can be used to determine whether a specific data preparation step should, as a general rule, be performed in each CV iteration or whether an incomplete CV procedure would be acceptable in practice. We apply CVIIM to large collections of microarray datasets to answer this question for normalization and PCA.ResultsPerforming normalization on the entire dataset before CV did not result in a noteworthy optimistic bias in any of the investigated cases. In contrast, when performing PCA before CV, medium to strong underestimates of the prediction error were observed in multiple settings.ConclusionsWhile the investigated forms of normalization can be safely performed before CV, PCA has to be performed anew in each CV split to protect against optimistic bias.Electronic supplementary materialThe online version of this article (doi:10.1186/s12874-015-0088-9) contains supplementary material, which is available to authorized users.

MrBayes 3.2: efficient Bayesian phylogenetic inference and model choice across a large model space.

Since its introduction in 2001, MrBayes has grown in popularity as a software package for Bayesian phylogenetic inference using Markov chain Monte Carlo (MCMC) methods. With this note, we announce the release of version 3.2, a major upgrade to the latest official release presented in 2003. The new version provides convergence diagnostics and allows multiple analyses to be run in parallel with convergence progress monitored on the fly. The introduction of new proposals and automatic optimization of tuning parameters has improved convergence for many problems. The new version also sports significantly faster likelihood calculations through streaming single-instruction-multiple-data extensions (SSE) and support of the BEAGLE library, allowing likelihood calculations to be delegated to graphics processing units (GPUs) on compatible hardware. Speedup factors range from around 2 with SSE code to more than 50 with BEAGLE for codon problems. Checkpointing across all models allows long runs to be completed even when an analysis is prematurely terminated. New models include relaxed clocks, dating, model averaging across time-reversible substitution models, and support for hard, negative, and partial (backbone) tree constraints. Inference of species trees from gene trees is supported by full incorporation of the Bayesian estimation of species trees (BEST) algorithms. Marginal model likelihoods for Bayes factor tests can be estimated accurately across the entire model space using the stepping stone method. The new version provides more output options than previously, including samples of ancestral states, site rates, site dN/dS rations, branch rates, and node dates. A wide range of statistics on tree parameters can also be output for visualization in FigTree and compatible software.

Elastic SCAD as a novel penalization method for SVM classification tasks in high-dimensional data

BackgroundClassification and variable selection play an important role in knowledge discovery in high-dimensional data. Although Support Vector Machine (SVM) algorithms are among the most powerful classification and prediction methods with a wide range of scientific applications, the SVM does not include automatic feature selection and therefore a number of feature selection procedures have been developed. Regularisation approaches extend SVM to a feature selection method in a flexible way using penalty functions like LASSO, SCAD and Elastic Net.We propose a novel penalty function for SVM classification tasks, Elastic SCAD, a combination of SCAD and ridge penalties which overcomes the limitations of each penalty alone.Since SVM models are extremely sensitive to the choice of tuning parameters, we adopted an interval search algorithm, which in comparison to a fixed grid search finds rapidly and more precisely a global optimal solution.ResultsFeature selection methods with combined penalties (Elastic Net and Elastic SCAD SVMs) are more robust to a change of the model complexity than methods using single penalties. Our simulation study showed that Elastic SCAD SVM outperformed LASSO (L1) and SCAD SVMs. Moreover, Elastic SCAD SVM provided sparser classifiers in terms of median number of features selected than Elastic Net SVM and often better predicted than Elastic Net in terms of misclassification error.Finally, we applied the penalization methods described above on four publicly available breast cancer data sets. Elastic SCAD SVM was the only method providing robust classifiers in sparse and non-sparse situations.ConclusionsThe proposed Elastic SCAD SVM algorithm provides the advantages of the SCAD penalty and at the same time avoids sparsity limitations for non-sparse data. We were first to demonstrate that the integration of the interval search algorithm and penalized SVM classification techniques provides fast solutions on the optimization of tuning parameters.The penalized SVM classification algorithms as well as fixed grid and interval search for finding appropriate tuning parameters were implemented in our freely available R package 'penalizedSVM'.We conclude that the Elastic SCAD SVM is a flexible and robust tool for classification and feature selection tasks for high-dimensional data such as microarray data sets.

Using cross-validation to evaluate predictive accuracy of survival risk classifiers based on high-dimensional data

Developments in whole genome biotechnology have stimulated statistical focus on prediction methods. We review here methodology for classifying patients into survival risk groups and for using cross-validation to evaluate such classifications. Measures of discrimination for survival risk models include separation of survival curves, time-dependent ROC curves and Harrell's concordance index. For high-dimensional data applications, however, computing these measures as re-substitution statistics on the same data used for model development results in highly biased estimates. Most developments in methodology for survival risk modeling with high-dimensional data have utilized separate test data sets for model evaluation. Cross-validation has sometimes been used for optimization of tuning parameters. In many applications, however, the data available are too limited for effective division into training and test sets and consequently authors have often either reported re-substitution statistics or analyzed their data using binary classification methods in order to utilize familiar cross-validation. In this article we have tried to indicate how to utilize cross-validation for the evaluation of survival risk models; specifically how to compute cross-validated estimates of survival distributions for predicted risk groups and how to compute cross-validated time-dependent ROC curves. We have also discussed evaluation of the statistical significance of a survival risk model and evaluation of whether high-dimensional genomic data adds predictive accuracy to a model based on standard covariates alone.

Modified technique of automatic and automated tuning of thermal-engineering process controllers

A technique of automatic optimization of tuning parameters of the closed-loop automatic control system in the course of operation of the latter is presented. This technique is based on the use of a new correlation for calculating tuning parameters of controllers from the coefficients of a transfer function of the object to be controlled. Simple analytical dependences are given that do not require large computer capacities and can easily be incorporated into a microprocessor-based controller, which in this case is converted into a self-tuning device.

PI Control for Second Order Delay System with Tuning Parameter Optimization

In this paper, we consider the control of time delay sys- tem by Proportional-Integral (PI) controller. By Using the Hermite- Biehler theorem, which is applicable to quasi-polynomials, we seek a stability region of the controller for first order delay systems. The essence of this work resides in the extension of this approach to second order delay system, in the determination of its stability region and the computation of the PI optimum parameters. We have used the genetic algorithms to lead the complexity of the optimization problem.

Bayesian mass spectra peak alignment from mass charge ratios.

Proteomics studies based on mass spectrometry (MS) are gaining popular applications in biomedical research for protein identification/quantification and biomarker discovery, especially for potential early diagnosis and prognosis of severe disease before the occurrence of symptoms. However, MS data collected using current technologies are very noisy and appropriate data preprocessing is critical for successful applications of MS-based approaches. Among various data preprocessing steps, peak alignment from multiple spectra based on detected peak sample locations presents special statistical challenges when effective experimental calibration is not feasible due to relatively large peak location variation. To avoid intensive tuning parameter optimization, we propose a simple novel Bayesian algorithm "random grafting-pruning Markov chain Monte Carlo (RGPMCMC)" that can be applied to global MS peak alignment and to follow certain model-based sample classification criterion for using aligned peaks to classify spectrum samples. The usefulness of our approach is demonstrated through simulation study by making extensive comparison with other algorithms in the literature. Its application to an ovarian cancer MALDI-MS data set achieves a smaller 10-fold cross validation error rate than other current large scale methodologies.

Bayesian Mass Spectra Peak Alignment from Mass Charge Ratios

Proteomics studies based on mass spectrometry (MS) are gaining popular applications in biomedical research for protein identification/quantification and biomarker discovery, especially for potential early diagnosis and prognosis of severe disease before the occurrence of symptoms. However, MS data collected using current technologies are very noisy and appropriate data preprocessing is critical for successful applications of MS-based approaches. Among various data preprocessing steps, peak alignment from multiple spectra based on detected peak sample locations presents special statistical challenges when effective experimental calibration is not feasible due to relatively large peak location variation. To avoid intensive tuning parameter optimization, we propose a simple novel Bayesian algorithm “random grafting-pruning Markov chain Monte Carlo (RGPMCMC)” that can be applied to global MS peak alignment and to follow certain modelbased sample classification criterion for using aligned peaks to classify spectrum samples. The usefulness of our approach is demonstrated through simulation study by making extensive comparison with other algorithms in the literature. Its application to an ovarian cancer MALDI-MS data set achieves a smaller 10-fold cross validation error rate than other current large scale methodologies.

Spectral embedding finds meaningful (relevant) structure in image and microarray data

BackgroundAccurate methods for extraction of meaningful patterns in high dimensional data have become increasingly important with the recent generation of data types containing measurements across thousands of variables. Principal components analysis (PCA) is a linear dimensionality reduction (DR) method that is unsupervised in that it relies only on the data; projections are calculated in Euclidean or a similar linear space and do not use tuning parameters for optimizing the fit to the data. However, relationships within sets of nonlinear data types, such as biological networks or images, are frequently mis-rendered into a low dimensional space by linear methods. Nonlinear methods, in contrast, attempt to model important aspects of the underlying data structure, often requiring parameter(s) fitting to the data type of interest. In many cases, the optimal parameter values vary when different classification algorithms are applied on the same rendered subspace, making the results of such methods highly dependent upon the type of classifier implemented.ResultsWe present the results of applying the spectral method of Lafon, a nonlinear DR method based on the weighted graph Laplacian, that minimizes the requirements for such parameter optimization for two biological data types. We demonstrate that it is successful in determining implicit ordering of brain slice image data and in classifying separate species in microarray data, as compared to two conventional linear methods and three nonlinear methods (one of which is an alternative spectral method). This spectral implementation is shown to provide more meaningful information, by preserving important relationships, than the methods of DR presented for comparison.Tuning parameter fitting is simple and is a general, rather than data type or experiment specific approach, for the two datasets analyzed here. Tuning parameter optimization is minimized in the DR step to each subsequent classification method, enabling the possibility of valid cross-experiment comparisons.ConclusionResults from the spectral method presented here exhibit the desirable properties of preserving meaningful nonlinear relationships in lower dimensional space and requiring minimal parameter fitting, providing a useful algorithm for purposes of visualization and classification across diverse datasets, a common challenge in systems biology.