Search

Self-assembling amphiphilic peptides have recently received special attention in medicine. Nonetheless, testing the myriad of combinations generated from at least 20 coded and several hundreds of noncoded amino acids to obtain candidate sequences for each application, if possible, is time-consuming and expensive. Therefore, rapid and accurate approaches are needed to select candidates from countless combinations. In the current study, we examined three conventional descriptor sets along with a novel descriptor set derived from the simulated aggregation propensity of di- and tripeptides to model the critical aggregation concentration (CAC) of amphiphilic peptides. In contrast to the conventional descriptors, the radial kernel model derived from the novel descriptor set accurately predicted the critical aggregation concentration of the test set with a residual standard error of 0.10. The importance of aromatic side chains, as well as neighboring amino acids in the self-assembly, was emphasized by analysis of the influential descriptors. The addition of very long peptides (70–100 residues) to the data set decreased the model accuracy and changed the influential descriptors. The developed model can be used to predict the CAC of self-assembling amphiphilic peptides and also to derive rules to apply in designing novel amphiphilic peptides with desired properties.

Carbon financial futures have both the characteristics of commodity futures and environmental protection and its price is affected by many factors. It is hard and complex for traditional analysis methods to get precise prediction results effectively. How to effectively predict the price trend of carbon financial futures has been focused on by both academia and traders. This study addresses the high prediction error of European allowance (EUA) futures price by constructing a novel approach by combining the support vector machine (SVM) and particle swarm optimization (PSO) algorithm. This article introduces a parameters optimization method, which provides the best parameters for SVM to improve the prediction performance of the EUA futures price. Furthermore, this research uses the realistic trading dataset containing 30,762 EUA futures closing prices to verify the effectiveness and efficiency of the PSO-SVM prediction model. The empirical results show that the prediction performance of the model, especially the radial kernel function, is significantly improved. And this approach can determine the parameters according to the characteristics of the dataset and input the parameters for training and prediction automatically. The PSO-SVM algorithm can effectively predict extreme price fluctuations and overcome the problem of high prediction error caused by parameter constraints.

Tourism in Bali is one of the major industries which play an important role in developing the global economy in Indonesia. Good forecasting of tourist arrival, especially from foreign countries, is needed to predict the number of tourists based on past information to minimize the prediction error rate. This study compares the performance of SVM and Backpropagation to find the model with the best prediction algorithm using data from foreign tourists in Bali Province. The results of this study recommend the best forecasting using the SVM model with the radial kernel function. The best accuracy of the SVM model obtained the lowest error values of MSE 0.0009, MAE 0.0186, and MAPE 0.0276, compared to Backpropagation which obtained MSE 0.0170, MAE 0.1066, and MAPE 0.1539.

Due to the concentration effect, there is a major challenge for the electronic nose system to identify different odor samples with multiple concentrations. The development of artificial intelligence provides new ways to solve such problems. This article attempts to use support vector machine (SVM) technology to distinguish four fragrance samples with three concentrations, including roman chamomile, jasmine, lavender, and orange. The responses of these samples were collected by an 11-sensor electronic nose. After baseline correction, data smoothing, and removal of non-responsive sensors, the signals of 8 sensors were used for subsequent model analysis. Due to the concentration effect, when the primary signal intensities were used as features, the electronic nose cannot distinguish between different aroma types (accuracy less than 50%). When the normalized maximum signal intensity Xmr was used, the accuracy of the model was greatly improved. Graphic analysis and PCA showed that the normalized feature effectively eliminates the concentration effect, and appropriately reducing some sensors can enhance the ability to distinguish odors. The SVM correctly classified all 14 aromas when feeding 8 sets of data to train the radial kernel C-classification SVM. This showed that the cross-interference of the sensors was reduced, and the resolving power of the electronic nose was enhanced after the feature reduction.

Objective Early diagnosis of many diseases is essential for their treatment. Furthermore, the existence of abundant and unknown variables makes more complicated decision making. For this reason, the diagnosis and classification of diseases using machine learning algorithms have attracted a lot of attention. Therefore, this study aimed to design a support vector machine (SVM) based decision-making support system to diagnosis various periodontal diseases. Data were collected from 300 patients referring to Periodontics department of Hamadan University of Medical Sciences, west of Iran. Among these patients, 160 were Gingivitis, 60 were localized periodontitis and 80 were generalized periodontitis. In the designed classification model, 11 variables such as age, sex, smoking, gingival index, plaque index and so on used as input and output variable show the individual’s status as a periodontal disease. Results Using different kernel functions in the design of the SVM classification model showed that the radial kernel function with an overall correct classification accuracy of 88.7% and the overall hypervolume under the manifold (HUM) value was to 0.912 has the best performance. The results of the present study show that the designed classification model has an acceptable performance in predicting periodontitis.

Tuberculosis is a contagious disease that is generally transmitted through a sufferer’s cough and is deadly. Tuberculosis usually attacks the lungs but can also affect other parts of the body. Treatment of tuberculosis patients who do not recover with those who can recover is different, mishandling can cause death in patients. Therefore, we need a system that can predict whether the patient’s condition can recover normally, or the lungs cannot be recovered. Support vector machine is a learning system that uses a hypothetical linear function in a high dimensional space and is trained with an algorithm based on optimization theory by applying learning bias derived from statistical theory. In this study, the kernel function is used, namely the radial kernel and the polynomial. Based on the analysis and discussion that has been done, it can be concluded from this study that the performance of the radial and polynomial kernels is the same with an accuracy of 85% and a sensitivity value of 94%.

Autism Spectrum Disorder (ASD) is on the rise and constantly growing. Earlier identify of ASD with the best outcome will allow someone to be safe and healthy by proper nursing. Humans are hard to estimate the present condition and stage of ASD by measuring primary symptoms. Therefore, it is being necessary to develop a method that will provide the best outcome and measurement of ASD. This paper aims to show several measurements that implemented in several classifiers. Among them, Support Vector Machine (SVM) provides the best result and under SVM, there are also some kernels to perform. Among them, the Gaussian Radial Kernel gives the best result. The proposed classifier achieves 95% accuracy using the publicly available standard ASD dataset.

In this work, the estimation of the characteristic impedance of a microstrip transmission line with the aid of support vector machines was conducted. In the estimation, first data was obtained by using empirical analytical formulas and this data was used for training and testing in support vector machine. Both classification and regression analysis were conducted using different kernel functions. Kernel functions used in this case were linear kernel and radial kernel. In the analysis, different regression techniques as ν-regression and e-regression were also used. It is concluded that using radial kernels produce more accurate results. Moreover, it can be concluded that support vector machines can be efficiently used in determining the characteristic impedance of microstrip lines.

This research introduces a new and effective asymmetric dual regression model by combining the advantages of possibilistic regression model and paired nu support vector machine (pair-v SVM). Our algorithm is able to best examine the ambiguity in a given data set from internal and external sides. Our algorithm estimates the outer boundary and inner boundary of the uncertain area for the predicted output. Based on the strategy of pair-v SVM, our algorithm find the solutions of four smaller SVM types of quadratic programming problems (QPP) instead of one big QPP to seek the up and down limits of the necessity and possibility model. This scheme greatly speeds up the training speed for our algorithm. Our model adopts the radial kernel, which offers a unified structure for the proposed method, which can handle crisp and vague input at the same time. The experimental results prove the efficiency and effectiveness of our algorithm.

Student dropout is a significant problem affecting higher education institutions. This phenomenon is the result of multiple causes and has different forms. The aim of this work was to predict which students of the Departamento de Ingenieria Informatica, Universidad de Santiago de Chile, will migrate to a different programme. For this purpose, we considered logistic regression models and support vector machines (SVM) with linear and radial kernels. Results showed that radial kernel SVM can satisfactorily predict this phenomenon, with an accuracy of 88.0% for the 6-year programme and of 66.67% for the 4-year programme.

The objective of this paper is to compare the accuracy of different kernel functions of the SVM method for text classification. As a basis for the research film reviews are used. The authors try to detect the kernel functions and their parameters to achieve high accuracy in movie reviews classification. The studied kernel functions are: polynomial kernel of degree 2, a linear kernel and a radial base kernel. The achieved accuracy is higher than 83%. The experiments show that the sigmoid radial kernel is an inappropriate choice in text classification.

Music recommendations are one of the important things, such as music streaming platforms. Classification of music genres is one of the important initial stages in the process of music recommendation based on genre. Many music classifications are proposed by extracting audio features that require a not light computing process. This research aims to analyze and test the performance of music genre classification based on metadata using three different classifiers, namely Support Vector Machine (SVM) with radial kernel base function (RBF), K Nearest Neighbors (K-NN), and Naive Bayes (NB). The Spotify music dataset was chosen because it has complete metadata on each of its music. Based on the results of tests conducted by the SVM classifier has the best classification performance with 80% accuracy, then followed by KNN with 77.18% and NB with 76.08%. The accuracy results are relatively the same as music classification based on audio feature extraction, so the classification with the extraction of metadata features can continue to be developed if the metadata in the dataset is well managed.

The paper presents the application of support vector regression technique for the modelling of antennas. Two different antennas were modelled with different properties. The first modelling was for a helical antenna with varying parameters to determine the gain of antenna. In the second modelling, an equilateral triangular patch antenna with varying properties for the design was considered for the determination of the directivity of the antenna. The support vector regression modelled both of the antennas very well. In helical antenna, the radial kernel with ν-regression produced only 0.143 dBi average error. In equilateral triangular patch antenna, the radial kernel with e-regression produced only 0.126 dBi average error.

In this work, we modelled the exchange rates using Support Vector Regression (SVR). The currency selected in this work was Turkish Lira (TRY) and compared the rates between United States Dollars (USD), Euro (EUR), and British Pounds (GBP). The modelling was done for the period of January 2018 till October 2019 data, with the aim to investigate three different issues. The difference in using ν-regression and e–regression was investigated. The effect of using different kernel functions was examined. Also, the effect of using multiple different exchange rates together (multi-rate) compared with modeling only one rate (single-rate) was explored. The results showed very successful modelling of the currencies producing very accurate results using the ν-regression modelling with radial kernel and using multi-rate modelling.

This paper explores new notions of approximate minimality in set optimization using aset approach. We propose characterizations of several approximate minimal elements of familiesof sets in real linear spaces by means of general functionals, which can be unified in an inequalityapproach. As particular cases, we investigate the use of the prominent Tammer&ndash, Weidner nonlinearscalarizing functionals, without assuming any topology, in our context. We also derive numericalmethods to obtain approximate minimal elements of families of finitely many sets by means of ourobtained results.

Building occupancy maps of the environment is a fundamental problem for robot autonomy. A common assumption in early work was that the occupancy states of different map elements are independent. Recently, Gaussian Process (GP) techniques were proposed to capture correlation, which is important not only for improved accuracy but also for uncertainty quantification and autonomous exploration based on the predicted occupancy of nearby unexplored areas. Despite these desirable properties, current GP mapping techniques are limited to small maps and slow inference speeds. This paper proposes an information space formulation of the GP mapping problem. If a decomposable radial kernel is evaluated over a latent grid of pseudo-input points, the resulting kernel matrix has a Kronecker-product-of-Toeplitz-matrices structure that allows very efficient representation of the occupancy distribution. We utilize this structure to design an information filter occupancy mapping algorithm with linear time and memory complexity that still permits continuous space observations and predictions.

Skin condition closely reflects human health, and skin roughness is one of the factors to analyze skin condition. This paper presents a classification algorithm of skin roughness based on improved support vector machine. The improved gray co-occurrence matrix, Tamura texture feature, fractal dimension, Gabor feature and other 24 properties affecting skin roughness were extracted by using human skin samples captured by visible light as data sources. Genetic algorithm was used to optimize the feature space, and the most important feature combinations were selected according to the fitness values. In order to improve the performance of classifier, the improved particle swarm optimization algorithm is used to optimize the penalty factor C and radial kernel function coefficient Gamma of support vector machine. The experiment shows that the model established in this paper has an obvious effect on the classification of skin roughness.

Article focuses on the prediction of bankruptcy of the 850 medium-sized retail business companies in EU from which 48 companies gone bankrupt in 2014 with respect to lag of the used features. From various types of classification models we chose Support vector machines method with linear, polynomial and radial kernels to acquire best results. Pre-processing is enhanced with filter based feature selection like Gain ratio, Chi-square and Relief algorithm to acquire attributes with the best information value. On this basis we deal with random samples of financial data to measure prediction accuracy with the confusion matrices and area under curve values for different kernel types and selected features. From the results it is obvious that with the rising distance to the bankruptcy there drops precision of bankruptcy prediction. The last year (2013) with avaible financial data offers best total prediction accuracy, thus we also infer both the Error I and II types for better recognizance. The 3rd order polynomial kernel offers better accuracy for bankruptcy prediction than linear and radial versions. But in terms of the total accuracy we recommend to use radial kernel without feature selection.

Log-based reservoir characterization is one of the widely used techniques to estimate the reservoir properties and make decisions about future plans for hydrocarbon production. Use of the machine learning tools is becoming a more accessible approach for predictive model development in oil and gas engineering. The objective of this research is to identify and rank the most contributing log variables for estimation of water saturation using the machine learning tools. The multilayer perception artificial neural network (MLP-ANN) and kernel function-based least-squares support vector machine (LS-SVM) techniques are employed to develop predictive models for water saturation. The model can capture the non-linear behaviors and high-dimensional complex relationships among field log data variables. Based on the prediction performance of the models, the Levenberg-Marquardt algorithm-based MLP-ANN and the radial kernel function-based LS-SVM model optimized with coupled simulated annealing optimization technique were found to perform better compared to other models. The MLP-ANN and radial kernel function-based LS-SVM approaches lead to the same feature ranking of predictor variables. It was found that the significance order (higher to lower) of influential log variables are the true resistivity, bulk density, neutron porosity, photoelectric factor, gamma-ray, and sonic travel time based on their relative contribution to the water saturation. The strategy introduced in this study assists to forecast water saturation with a relatively few number of log variables, and thus, reduces the number of necessary logs to run during exploration stage, considerably lowering the exploration costs.

In this paper, the author has proposed the combination of deep convolutional neural networks as feature learning and long short-term memory as time series forecasting algorithm to forecast appliances energy consumption in residential houses using 28 data features collected from IoT sensors database. It is shown in experiment that the forecasting performance can be improved with comparison methods such as GBM (Gradient Boosting Machine), Support vector Machine with Radial Kernel, and RF (Random Forest).

—Metal oxide (MOX) gas detectors based on SnO2 provide low-cost solutions for real-time sensing of complex gas mixtures for indoor ambient monitoring. With high sensitivity under ideal conditions, MOX detectors may have poor longterm response accuracy due to environmental factors (humidity and temperature) along with sensor aging, leading to calibration drifts. Finding a simple and efficient solution to correct such calibration drifts has been the subject of numerous studies but remains an open problem. In this work, we present an efficient approach to MOX calibration using active and transfer sampling techniques coupled with non-linear machine learning algorithms, namely neural networks, extreme gradient boosting (XGBoost) and radial kernel support vector machines (SVM). Applied on the UCI’s HT detectors dataset, the study evaluates methods for active sampling, makes an assessment of suitable neural networks architectures and compares the performance of neural networks, XGBoost and radial kernel SVM to classify gas mixtures (banana and wine odours, clean air) in the presence of humidity and temperature changes. The results show high classification accuracy levels (above 90%) and confirm that active sampling can provide a suitable solution. Index Terms—Neural Networks, Extreme Gradient Boosting, XGBoost, Support Vector Machines, Non-Linear Learning Methods, Machine Learning

As inorganic nitrogen compounds are essential for basic building blocks of life (e.g., nucleotides and amino acids), the role of biological nitrogen-fixation (BNF) is indispensible. All nitrogen fixing microbes rely on the same nitrogenase enzyme for nitrogen reduction, which is in fact an enzyme complex consists of as many as 20 genes. However, the occurrence of six genes viz., nifB, nifD, nifE, nifH, nifK, and nifN has been proposed to be essential for a functional nitrogenase enzyme. Therefore, identification of these genes is important to understand the mechanism of BNF as well as to explore the possibilities for improving BNF from agricultural sustainability point of view. Further, though the computational tools are available for the annotation and phylogenetic analysis of nifH gene sequences alone, to the best of our knowledge no tool is available for the computational prediction of the above mentioned six categories of nitrogen-fixation (nif) genes or proteins. Thus, we proposed an approach, which is first of its kind for the computational identification of nif proteins encoded by the six categories of nif genes. Sequence-derived features were employed to map the input sequences into vectors of numeric observations that were subsequently fed to the support vector machine as input. Two types of classifier were constructed: (i) a binary classifier for classification of nif and non-nitrogen-fixation (non-nif) proteins, and (ii) a multi-class classifier for classification of six categories of nif proteins. Higher accuracies were observed for the combination of composition-transition-distribution (CTD) feature set and radial kernel, as compared to the other feature-kernel combinations. The overall accuracies were observed >90% in both binary and multi-class classifications. The developed approach further achieved >92% accuracy, while evaluated with blind (independent) test datasets. The developed approach also produced higher accuracy in identifying nif proteins, while evaluated using proteome-wide datasets of several species. Furthermore, we established a prediction server nifPred (http://webapp.cabgrid.res.in/nifPred) to assist the scientific community for proteome-wide identification of six categories of nif proteins. Besides, the source code of nifPred is also available at https://github.com/PrabinaMeher/nifPred. The developed web server is expected to supplement the transcriptional profiling and comparative genomics studies for the identification and functional annotation of genes related to BNF.

The objective of this research was to recognize the hand gestures of Arabic Sign Language (ArSL) words using two depth sensors. The researchers developed a model to examine 143 signs gestured by 10 users for 5 ArSL words (the dataset). The sensors captured depth images of the upper human body, from which 235 angles (features) were extracted for each joint and between each pair of bones. The dataset was divided into a training set (109 observations) and a testing set (34 observations). The support vector machine (SVM) classifier was set using different parameters on the gestured words’ dataset to produce four SVM models, with linear kernel (SVMLD and SVMLT) and radial kernel (SVMRD and SVMRT) functions. The overall identification accuracy for the corresponding words in the training set for the SVMLD, SVMLT, SVMRD, and SVMRT models was 88.92%, 88.92%, 90.88%, and 90.884%, respectively. The accuracy from the testing set for SVMLD, SVMLT, SVMRD, and SVMRT was 97.059%, 97.059%, 94.118%, and 97.059%, respectively. Therefore, since the two kernels in the models were close in performance, it is far more efficient to use the less complex model (linear kernel) set with a default parameter.

To date, no systematic study has assessed the effect of random experimental errors on the predictive power of QSAR models. To address this shortage, we have benchmarked the noise sensitivity of 12 learning algorithms on 12 data sets (15,840 models in total), namely the following: Support Vector Machines (SVM) with radial and polynomial (Poly) kernels, Gaussian Process (GP) with radial and polynomial kernels, Relevant Vector Machines (radial kernel), Random Forest (RF), Gradient Boosting Machines (GBM), Bagged Regression Trees, Partial Least Squares, and k-Nearest Neighbors. Model performance on the test set was used as a proxy to monitor the relative noise sensitivity of these algorithms as a function of the level of simulated noise added to the bioactivities from the training set. The noise was simulated by sampling from Gaussian distributions with increasingly larger variances, which ranged from zero to the range of pIC50 values comprised in a given data set. General trends were identified by designing a full-factorial experiment, which was analyzed with a normal linear model. Overall, GBM displayed low noise tolerance, although its performance was comparable to RF, SVM Radial, SVM Poly, GP Poly, and GP Radial at low noise levels. Of practical relevance, we show that the bag fraction parameter has a marked influence on the noise sensitivity of GBM, suggesting that low values (e.g., 0.1-0.2) for this parameter should be set when modeling noisy data. The remaining 11 algorithms display a comparable noise tolerance, as a smooth and linear degradation of model performance is observed with the level of noise. However, SVM Poly and GP Poly display significant noise sensitivity at high noise levels in some cases. Overall, these results provide a practical guide to make informed decisions about which algorithm and parameter values to use according to the noise level present in the data.

This contribution discusses the construction of kernel-based adaptive particle methods for numerical flow simulation, where the finite volume particle method (FVPM) is used as a prototype. In the FVPM, scattered data approximation algorithms are required in the recovery step of the WENO reconstruction. We first show how kernel-based approximation schemes can be used in the recovery step of particle methods, where we give preference to the radial polyharmonic spline kernel. Then we discuss important aspects concerning the numerical stability and approximation behaviour of polyharmonic splines. Moreover, we propose customized coarsening and refinement rules for the adaptive resampling of the particles. Supporting numerical examples and comparisons with other radial kernels are provided.

Invariant Moment is an important method for image representation for its invariant for shift, rotation, scale, and intensity distortion of an image. According to drawbacks of state-of-the-art methods, the criteria of designing radial kernels were summarized in this paper. And also a new invariant moment-Non-Uniform Cube Fourier Moment was proposed. The zeros are distributed non-uniformly, and the amplitudes of vibration are descending along the radial orientation. And also information redundancy was used to design the radial kernel, so the base functions of it are non-orthogonal. Those features make them more reasonable for image representation, especially small images. Finally image reconstruction with those new moments was experimented, to prove those new moments perform better in image representation.

We discuss interior point methods for large-scale linear programming, with an emphasis on methods that are useful for problems arising in telecommunications. We give the basic framework of a primal-dual interior point method, and consider the numerical issues involved in calculating the search direction in each iteration, including the use of factorization methods and/or preconditioned conjugate gradient methods. We also look at interior point column generation methods which can be used for very large scale linear programs or for problems where the data is generated only as needed.

The conventional wisdom states that the interior problem (reconstruction of an interior region from projection data along lines only through that region) is NOT uniquely solvable. While it remains correct, our recent theoretical and numerical results demonstrated that this interior problem CAN be solved in a theoretically exact and numerically stable fashion if a sub-region within the interior region is known. In contrast to the well-established lambda tomography, the studies on this type of exact interior reconstruction are referred to as "interior tomography". In this paper, we will overview the development of interior tomography, involving theory, algorithms and applications. The essence of interior tomography is to find the unique solution from highly truncated projection data via analytic continuation. Such an extension can be done either in the filtered backprojection or backprojection filtration formats. The key issue for the exact interior reconstruction is how to invert the truncated Hilbert transform. We have developed a projection onto convex set (POCS) algorithm and a singular value decomposition (SVD) method and produced excellent results in numerical simulations and practical applications.

Design of an interior point method for linear programming is discussed, and results of a simulation study reported. Emphasis is put on guessing the optimal vertex at as early a stage as possible.

We derive optimal radial kernel in the radial basis function network applied in nonlinear function learning and classification.

We describe a new general approach for interior points algorithms in nonlinear constrained optimization. It consists on the iterative solution, in the primal and dual variables, of Karush — Kuhn — Tucker first order optimality conditions. Based on this approach, different algorithms can be stated by taking advantage of the particular characteristics of the problem in consideration and of the order of the available information. This method is very strong and efficient, since at each iteration it only requires the solution of two linear systems with the same matrix. It is also particularly appropriated for Engineering Design Optimization, since feasible designs are obtained. We present a basic algorithm for inequality constrained problems and two of the possible particular versions. The first one is a first order algorithm and the second one uses a quasi — Newton approximation of the second derivative of the Lagrangian, in order to have superlinear asymptotic convergence. Equality constraints are introduced later.

A method based on adaptive kernel probablity density estimators is proposed in order to design optimal receivers from finite sets of examples. Performances are shown for the classification of underwater transient signals.

In the literature there are multiple machine learning techniques that have been used successfully in clinical data analysis. However, there is little information about the parameter configurations, the required data transformations to prepare the data used to train and evaluate the models and the impact of these decisions in the accuracy of the predictive model. This research tackles these issues, using the clinical data of MIMICII to build features from physiological measure patterns to predict the decease of patients inside the hospital in the next 24 hours, building predictive models based on Logistic Regression, Neural Networks, Decision Trees and Nearest Neighbors. In particular, we use data associated to physiological measures of 3220 patients, where 2385 left the hospital alive and 835 passed in the hospital. The results show that the chosen strategy for building features from physiological data gives good results with Neural Networks and Logistic Regression with radial kernel models and the parameter configuration plays a fundamental role in the models performance.