Linear Radial Basis Research Articles

Groundwater Depth Prediction Using Data-Driven Models with the Assistance of Gamma Test

Prediction of the groundwater dynamics via models can help better manage the groundwater resources and guarantee their sustainable use. Three types of data-driven models are built for groundwater depth prediction in the plain of Shijiazhuang, the capital of Hebei Province in North China. The data-driven models include the Power Function Model (PFM), Back-Propagation Artificial Neural Network (BPANN) and Support Vector Machines (SVM) with two kernel functions of linear kernel function (LKF) and radial basis function (RBF). Five classes of factors (including 12 indices) are considered as potential model input variables. The Gamma Test (GT) is adopted in this study to help identify the relative importance of the input indices and tackle the tricky issue of the optimal input combinations for the data-driven models. The established models are evaluated in both fitting and testing procedures based on the root mean squared error (RMSE) and Nash-Sutcliffe efficiency (E) for different input combination schemes. The results show that SVM (RBF) performs the best. It is interesting to find that the natural factors (i.e., precipitation and evaporation) are less relevant to the groundwater depth variations. The methods used in this study have much significance for groundwater depth prediction in areas lacking hydrogeological data.

Enhancement of a text-independent speaker verification system by using feature combination and parallel structure classifiers

Speaker verification (SV) systems involve mainly two individual stages: feature extraction and classification. In this paper, we explore these two modules with the aim of improving the performance of a speaker verification system under noisy conditions. On the one hand, the choice of the most appropriate acoustic features is a crucial factor for performing robust speaker verification. The acoustic parameters used in the proposed system are: Mel Frequency Cepstral Coefficients, their first and second derivatives (Deltas and Delta–Deltas), Bark Frequency Cepstral Coefficients, Perceptual Linear Predictive, and Relative Spectral Transform Perceptual Linear Predictive. In this paper, a complete comparison of different combinations of the previous features is discussed. On the other hand, the major weakness of a conventional support vector machine (SVM) classifier is the use of generic traditional kernel functions to compute the distances among data points. However, the kernel function of an SVM has great influence on its performance. In this work, we propose the combination of two SVM-based classifiers with different kernel functions: linear kernel and Gaussian radial basis function kernel with a logistic regression classifier. The combination is carried out by means of a parallel structure approach, in which different voting rules to take the final decision are considered. Results show that significant improvement in the performance of the SV system is achieved by using the combined features with the combined classifiers either with clean speech or in the presence of noise. Finally, to enhance the system more in noisy environments, the inclusion of the multiband noise removal technique as a preprocessing stage is proposed.

QSPR study on the flash point of organic binary mixtures by using electrotopological state index

The quantitative structure property relationship (QSPR) for the flash point of 288 organic binary mixtures was investigated. The electrotopological state (E-state) index of the components in each mixture was calculated and weight summed to generate the quantitative descriptor of the investigated mixtures. Multivariable linear regression (MLR), stepwise regression and radial basis function artificial neural network (RBF-ANN) was respectively used to build the calibration model. The weight summed E-state index was used as the independent variable of the established models. The prediction performance of the developed models were assessed with external test validation, k-fold cross validation and Monte Carlo cross validation (MCCV). The results of the three validations demonstrate that the RBF-ANN model which includes five input variables is the best one among the developed models. The prediction root mean square relative error (RMSRE) of the external test validation, k-fold cross validation and MCCV is 1.86, 1.11 and 1.07 respectively for this model. It is demonstrated that there is a quantitative relationship between the E-state index and flash point of the investigated mixtures. MLR, stepwise regression and RBF-ANN are all practicable for modeling this relationship. The developed RBF-ANN model involving five input variables is the most promising method for predicting the flash point of organic binary mixtures.

Prediction of peak ground acceleration using ϵ-SVR, ν-SVR and Ls-SVR algorithm

ABSTRACTIn this paper, a prediction model is developed using support vector machine for forecasting the parameter associated with ground motion of a seismic signal. The prediction model is developed using three learning algorithms, ϵ-support vector regression, ν-support vector regression and least square-support vector regression (Ls-SVR) for forecasting peak ground acceleration (PGA), a parameter associated with ground motion of a seismic signal. The prediction model is developed for each of the algorithms with different kernel functions, namely linear kernel, polynomial kernel and radial basis function kernel. The ground motion parameter is related to four seismic parameters, namely faulting mechanism, average soil shear wave velocity, earthquake magnitude and source to site distance. The database used for modelling is NGA flatfile released by Pacific Earthquake Engineering Research Center. The experimental results show that the optimal prediction model for forecasting PGA is Ls-SVR with RBF kernel. It is observed that the developed prediction model is better compared to the existing conventional models and benchmark models in the same database. This paper further compares the three variations of SVR algorithm for ground motion parameter prediction model. The learning effectiveness of each algorithm is measured in terms of accuracy, testing error and overfitness measure.

Three-Dimensional Eigenbrain for the Detection of Subjects and Brain Regions Related with Alzheimer's Disease.

Considering that Alzheimer's disease (AD) is untreatable, early diagnosis of AD from the healthy elderly controls (HC) is pivotal. However, computer-aided diagnosis (CAD) systems were not widely used due to its poor performance. Inspired from the eigenface approach for face recognition problems, we proposed an eigenbrain to detect AD brains. Eigenface is only for 2D image processing and is not suitable for volumetric image processing since faces are usually obtained as 2D images. We extended the eigenbrain to 3D. This 3D eigenbrain (3D-EB) inherits the fundamental strategies in either eigenface or 2D eigenbrain (2D-EB). All the 3D brains were transferred to a feature space, which encoded the variation among known 3D brain images. The feature space was named as the 3D-EB, and defined as eigenvectors on the set of 3D brains. We compared four different classifiers: feed-forward neural network, support vector machine (SVM) with linear kernel, polynomial (Pol) kernel, and radial basis function kernel. The 50x10-fold stratified cross validation experiments showed that the proposed 3D-EB is better than the 2D-EB. SVM with Pol kernel performed the best among all classifiers. Our "3D-EB + Pol-SVM" achieved an accuracy of 92.81% ± 1.99% , a sensitivity of 92.07% ± 2.48% , a specificity of 93.02% ± 2.22% , and a precision of 79.03% ± 2.37% . Based on the most important 3D-EB U1, we detected 34 brain regions related with AD. The results corresponded to recent literature. We validated the effectiveness of the proposed 3D-EB by detecting subjects and brain regions related to AD.

The dual reciprocity boundary elements method for the linear and nonlinear two‐dimensional time‐fractional partial differential equations

In this paper, we apply the dual reciprocity boundary elements method for the numerical solution of two‐dimensional linear and nonlinear time‐fractional modified anomalous subdiffusion equations and time‐fractional convection–diffusion equation. The fractional derivative of problems is described in the Riemann–Liouville and Caputo senses. We employ the linear radial basis function for interpolation of the nonlinear, inhomogeneous and time derivative terms. This method is improved by using a predictor–corrector scheme to overcome the nonlinearity which appears in the nonlinear problems under consideration. The accuracy and efficiency of the proposed schemes are checked by five test problems. The proposed method is employed for solving some examples in two dimensions on unit square and also in complex regions to demonstrate the efficiency of the new technique. Copyright © 2016 John Wiley & Sons, Ltd.

APPLICATION OF RADIAL BASIS FUNCTION NETWORK ON PARKINSON DATA

Radial basis function networks have many uses, including the function approximation, time series production, classification and system control. Radial basis function based diagnosis of medical diseases has been taken into great consideration in recent studies. The real data from UCI Machine Learning websites that used 500 Parkinson’s patients and 7 different attributes as the subject were analyzed by using Statistical Package for Social Sciences (SPSS) 21.0. Next, the result of SPSS software will be used and run by MATLAB software. From the research that has been done by other researchers, it was found that MATLAB software is much better in producing the best results for Radial Basis Function. The value of R2 for Multiple Linear Regression and Radial Basis Function is 0.7450 and 0.9702 respectively. Hence, the Radial Basis Function method shows that there is more variability is explained by this model

Joint rough sets and Karhunen-Loève transform approach to seismic attribute selection for porosity prediction in a Chinese sandstone reservoir

The Paleogene Lower Dongying Formation of the Bohai Bay Basin, China, consists of a series of vertically stacked sand-filled delta distributary channels. These laterally complex sandstones create the need for a precise interwell estimation of reservoir porosity. In this study, we integrated wireline logs from 101 wells and [Formula: see text] of seismic data to directly predict porosity in the area of an existing heavy-oil field in the middle of the Liaoxi Uplift, Bohai Bay Basin. The top and the bottom horizons of the target oil unit interpreted on high-quality 3D seismic data are used to constrain the time window for 41 horizon-based attribute extractions. Next, we used the joint rough sets and Karhunen-Loève transform (K-L transform) selection method to choose the optimal number and the type of seismic attributes that exhibit a high correlation with porosity. Finally, a method combinings multiple linear regression and radial basis function neural network was used to predict porosity based on the selected attribute subsets. After error analysis of the 101 wells, the results from the joint attribute selection approach showed the least prediction error at well locations because the joint attribute selection captured the linear and nonlinear relationship between attributes and porosities. We obtained a geologically realistic predicted porosity distribution using the joint approach, which suggested a network of main distributary channel sands characterized by high-porosity zones (approximately 32%).

The dual reciprocity boundary integral equation technique to solve a class of the linear and nonlinear fractional partial differential equations

In this paper, we apply the boundary integral equation technique and the dual reciprocity boundary elements method (DRBEM) for the numerical solution of linear and nonlinear time‐fractional partial differential equations (TFPDEs). The main aim of the present paper is to examine the applicability and efficiency of DRBEM for solving TFPDEs. We employ the time‐stepping scheme to approximate the time derivative, and the method of linear radial basis functions is also used in the DRBEM technique. This method is improved by using a predictor–corrector scheme to overcome the nonlinearity that appears in the nonlinear problems under consideration. To confirm the accuracy of the new approach, several examples are presented. The convergence of the DRBEM is studied numerically by comparing the exact solutions of the problems under investigation. Copyright © 2015 John Wiley & Sons, Ltd.

Fire detection and identification method based on visual attention mechanism

The method of traditional fire detection has many deficiencies. Not only being susceptible to been interference by environmental factors, but also not to find a lot of information timely and effectively from the fire inspection information. At the same time also not to record the specific details when the fire breaks out. These make it difficult for subsequent fire cause investigation. Therefore, this paper puts forward a new method for fire detection and identification by using visual attention mechanism. That is, through simulation of the human visual system, visual attention mechanism can help us from a lot of complex images to quickly find the information “been worth noting” of the image to find critical information, and to eliminate a lot of useless information. The method can significantly speed up image processing and improve the accuracy of image recognition. Several experiments have been designed to verify the effectiveness of the method by using SVM learning and training. The experimental results denote that the novel algorithms based on visual attention mechanism and been mixed linear function nuclear and radial basis function nuclear improve the accuracy and speed of recognition, significantly reduces the false negative rate of fire recognition and improves the accuracy of fire detection.

Comparison of modified teaching–learning-based optimization and extreme learning machine for classification of multiple power signal disturbances

This paper presents a modified TLBO (teaching---learning-based optimization) approach for the local linear radial basis function neural network (LLRBFNN) model to classify multiple power signal disturbances. Cumulative sum average filter has been designed for localization and feature extraction of multiple power signal disturbances. The extracted features are fed as inputs to the modified TLBO-based LLRBFNN for classification. The performance of the proposed modified TLBO-based LLRBFNN model is compared with the conventional model in terms of convergence speed and classification accuracy. Also, an extreme learning machine (ELM) approach is used to optimize the performance of the proposed LLRBFNN and is compared with the TLBO method in classifying the multiple power signal disturbances. The classification results reveal that although the TLBO approach produces slightly better accuracy in comparison with the ELM approach, the latter is much faster in implementation, thus making it suitable for processing large quantum of power signal disturbance data.

An adaptive local linear optimized radial basis functional neural network model for financial time series prediction

For financial time series, the generation of error bars on the point of prediction is important in order to estimate the corresponding risk. In recent years, optimization techniques-driven artificial intelligence has been used to make time series approaches more systematic and improve forecasting performance. This paper presents a local linear radial basis functional neural network (LLRBFNN) model for classifying finance data from Yahoo Inc. The LLRBFNN model is learned by using the hybrid technique of backpropagation and recursive least square algorithm. The LLRBFNN model uses a local linear model in between the hidden layer and the output layer in contrast to the weights connected from hidden layer to output layer in typical neural network models. The obtained prediction result is compared with multilayer perceptron and radial basis functional neural network with the parameters being trained by gradient descent learning method. The proposed technique provides a lower mean squared error and thus can be considered as superior to other models. The technique is also tested on linear data, i.e., diabetic data, to confirm the validity of the result obtained from the experiment.

Selection of Methods for Predicting Tidal Levels with a Typhoon Surge Effect

ABSTRACT Yuan, H.; Tan, M., and Wang, W., 2015. Selection of methods for predicting tidal levels with a typhoon surge effect. Accurate prediction of tidal level with strong meteorological effects is very important for human activities in oceanic and coastal areas. Under severe weather, such as typhoons, the contribution of non-astronomical components to tidal level may be as significant as that of astronomical components. The traditional harmonic analysis method and other models based on the analysis of astronomical components do not work well in these situations. The objective of this paper is to select an effective method for predicting the tidal level under the influence of typhoons at Luchaogang, China. The linear regression, back-propagation (BP) and radial basis function neural network methods are compared. Based on the typhoon data and tidal-level data gathered from Pudong Hydrological Bureau, seven parameters of typhoon are extracted and employed as input parameters while the corresponding tidal-l...

Prediction of subacute ruminal acidosis based on milk fatty acids: A comparison of linear discriminant and support vector machine approaches for model development

Subacute ruminal acidosis (SARA), characterized by low rumen pH, is one of the most important metabolic disorders in dairy cattle. As dairy cows experiencing SARA often do not exhibit overt clinical symptoms, diagnostic biomarkers in milk are of interest. Data of six acidosis induction experiments with rumen-fistulated dairy cows were combined to assess the potential of milk fatty acids (FA) to identify acidotic cases, based on three threshold values often reported in literature, i.e. time pH<5.6 of 180min/d and 283min/d and time pH below 5.8 of 475min/d (N=442 cases, of which 111–165 acidotic cases, depending on the applied threshold value). Both linear discriminant analysis (LDA) as well as support vector machines (SVM) were used to develop classification models, with SVM based on two common types of kernel functions (linear kernels and Gaussian radial basis function kernels) and including either the whole milk FA profile (41–69 milk FA, depending on the experiment) or a selected number of milk FA (i.e. both odd and branched chain FA and biohydrogenation derivates of poly-unsaturated FA, 13–16 FA). Both evaluation of the performance of individual classification models as well as comparison of models was based on the area under the receiver operating characteristic (ROC) curve. Non-linear models developed through a radial kernel based SVM approach seemed of particular interest when including all milk FA as model features. However, linear models based on the selected group of milk FA most often performed as good as the non-linear models including all milk FA, with the former being least time consuming and more cost-effective, both from a computational as well as an analytical perspective. However, combination of all data sets only resulted in good classification models when including data of each dataset upon training the model, whereas model performance decreased dramatically in case of cross-dataset cross-validation. This indicates an important impact of the origin of the datasets on the performance of the model which should be taken into account in further exploration of prediction models of SARA.

A comparative study between fuzzy linear regression and support vector regression for global solar radiation prediction in Iran

Energy is fundamental to, and plays a prominent role in the quality of life. Sustainable energy is important for the benefits it yields. Sustainable energy technologies are clean sources of energy that have a much lower environmental impact than conventional energy technologies. Among the different forms of clean energy, solar energy has attracted a lot of attention as it is not only sustainable, but is also renewable. Because the number of meteorological stations where global solar radiation (GSR) is recorded is limited in Iran, the aim was to develop three distinctive models in order to prognosticate GSR in Tehran Province, Iran. Accordingly, the fuzzy linear regression (FLR), polynomial and radial basis function (RBF) were applied as the kernel function of support vector regression (SVR). Input energies from different meteorological data obtained from the only station in the study region were selected as the model inputs while GSR was chosen as the model output. Instead of minimizing the observed training error, SVR_poly and SVR_rbf attempted to minimize the generalization error bounds so as to achieve generalized performance. The experimental results show that it is possible to achieve enhanced predictive accuracy and capability of generalization via the proposed approach. The calculated root mean square error and correlation coefficient disclosed that SVR_rbf performed well in predicting GSR compared with FLR.

Noninvasive prostate cancer screening based on serum surface-enhanced Raman spectroscopy and support vector machine

This study aims to present a noninvasive prostate cancer screening methods using serum surface-enhanced Raman scattering (SERS) and support vector machine (SVM) techniques through peripheral blood sample. SERS measurements are performed using serum samples from 93 prostate cancer patients and 68 healthy volunteers by silver nanoparticles. Three types of kernel functions including linear, polynomial, and Gaussian radial basis function (RBF) are employed to build SVM diagnostic models for classifying measured SERS spectra. For comparably evaluating the performance of SVM classification models, the standard multivariate statistic analysis method of principal component analysis (PCA) is also applied to classify the same datasets. The study results show that for the RBF kernel SVM diagnostic model, the diagnostic accuracy of 98.1% is acquired, which is superior to the results of 91.3% obtained from PCA methods. The receiver operating characteristic curve of diagnostic models further confirm above research results. This study demonstrates that label-free serum SERS analysis technique combined with SVM diagnostic algorithm has great potential for noninvasive prostate cancer screening.

Automatic Moving Object Extraction Through a Real-World Variable-Bandwidth Network for Traffic Monitoring Systems

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 F <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> and Similarity metrics for the proposed approach were, respectively, up to 92.23% and 88.24% higher than those produced for other previous methods.

A new approach of audio emotion recognition

A new architecture of intelligent audio emotion recognition is proposed in this paper. It fully utilizes both prosodic and spectral features in its design. It has two main paths in parallel and can recognize 6 emotions. Path 1 is designed based on intensive analysis of different prosodic features. Significant prosodic features are identified to differentiate emotions. Path 2 is designed based on research analysis on spectral features. Extraction of Mel-Frequency Cepstral Coefficient (MFCC) feature is then followed by Bi-directional Principle Component Analysis (BDPCA), Linear Discriminant Analysis (LDA) and Radial Basis Function (RBF) neural classification. This path has 3 parallel BDPCA+LDA+RBF sub-paths structure and each handles two emotions. Fusion modules are also proposed for weights assignment and decision making. The performance of the proposed architecture is evaluated on eNTERFACE’05 and RML databases. Simulation results and comparison have revealed good performance of the proposed recognizer.

A new approach to radial basis function approximation and its application to QSAR.

We describe a novel approach to RBF approximation, which combines two new elements: (1) linear radial basis functions and (2) weighting the model by each descriptor’s contribution. Linear radial basis functions allow one to achieve more accurate predictions for diverse data sets. Taking into account the contribution of each descriptor produces more accurate similarity values used for model development. The method was validated on 14 public data sets comprising nine physicochemical properties and five toxicity endpoints. We also compared the new method with five different QSAR methods implemented in the EPA T.E.S.T. program. Our approach, implemented in the program GUSAR, showed a reasonable accuracy of prediction and high coverage for all external test sets, providing more accurate prediction results than the comparison methods and even the consensus of these methods. Using our new method, we have created models for physicochemical and toxicity endpoints, which we have made freely available in the form of an online service at http://cactus.nci.nih.gov/chemical/apps/cap.

Application of radial basis function neural network and DFT quantum mechanical calculations for the prediction of the activity of 2-biarylethylimidazole derivatives as bombesin receptor subtype-3 (BRS-3) agonists

Two quantitative structure–activity relationship (QSAR) models, multiple linear regression (MLR) and radial basis function neural network (RBFNN), have been developed for predicting agonist activity of a series of potent and selective bombesin receptor subtype-3 (BRS-3) containing a biarylethylimidazole pharmacophore by performing density functional theory calculations at the B3LYP/6-311G(d,p) level. The investigated results have demonstrated that the excitation activity of investigated compounds can be reflected by quantum descriptors such as hardness, the total dipole moment, electrophilicity, the highest occupied molecular orbital energy (E HOMO), and the lowest unoccupied molecular orbital energy (E LUMO). The results showed that the pEC50 values calculated by RBFNN model are in good agreement with the experimental data, and the performance of the RBFNN regression model is superior to the MLR-based model. The developed RBFNN model was applied for the prediction of the biological activities of biarylethylimidazole derivatives, which were not in the modeling procedure. The resulted model showed high prediction ability with root mean square error of prediction of 0.224 for RBFNN. Therefore, the QSAR models based on quantum descriptors are reliable in predicting BRS-3 agonist activity for unknown biarylethylimidazole derivatives.