Different Types Of Kernels Research Articles

Variable hyperparameterized Gaussian kernel using displaced squeezed vacuum state

There are machine learning schemes for realizing different types of kernels by quantum states of light. It is particularly interesting to realize a Gaussian kernel due to its wider applicability. A multimode coherent state can generate the Gaussian kernel with a constant value of hyperparameter. However, this constancy has limited the application of the Gaussian kernel when it is applied to complex learning problems. We improve it by introducing a variable hyperparameterized Gaussian kernel with a multimode-displaced squeezed vacuum state. The learning capacity of this kernel is tested with the support vector machines over some synthesized data sets, as well as public benchmark data sets. We establish that the proposed variable hyperparameterized Gaussian kernel offers better accuracy over the constant Gaussian kernel.

Explaining the predictions of kernel SVM models for neuroimaging data analysis

Machine learning methods have shown great performance in many areas, including neuroimaging data analysis. However, model performance is only one objective in neuroimaging analysis. Gaining insight from the data is also critical in this field, such as identifying regions where detected signals are relevant to cognitive and diagnostic tasks. To fulfill this need, enabling the explainability of a model’s decision-making process is critical. Predictions of complex machine learning models are notoriously difficult to explain. This limits the use of complex models like kernel support vector machines (SVM) in neuroimaging analysis. Recently, several permutation-based methods have been developed to explain these complex models. However, the explanation results are affected by class-irrelevant features like suppressor variables and high background noise variables. This problem may also happen when explaining linear models. One possible reason is that the permutation process will produce unrealistic data instances when features are not independent, e.g. correlated. These unrealistic data instances will influence the explanation results. In neuroimaging analysis, the activation pattern, the estimated weight of the assumed generative model corresponding to the current classifier, is used to deal with this problem for linear models. This method does not rely on a permutation process but rather on the available data information. In this paper, we propose a novel method of Explanation through Activation Pattern (EAP) to explain the SVM models with different types of kernels for neuroimaging data analysis. Our method can generate a global feature importance score by estimating the activation pattern of kernel SVM models. We evaluate our method against three popular methods on both simulation datasets and a publicly available EEG/MEG dataset on visual tasks. The experimental results demonstrate that the proposed EAP method can provide explanations with low computational cost and is less affected by class-irrelevant features than the other three methods. In the experiment using the MEG/EEG dataset of visual tasks, the proposed EAP method provides agreement results with the brain’s electrical activity patterns reported in the literature on the visual tasks EEG/MEG data and is significantly faster than the other explanation methods.

Comparison of Discriminant Analysis and Support Vector Machine on Mixed Categorical and Continuous Independent Variables for COVID-19 Patients Data

Purpose: Numerous factors can affect the duration of COVID-19 recovery. One method involves utilizing natural herbal medication. This study seeks to determine the variables influencing the duration of COVID-19 recovery and to compare discriminant analysis and support vector machine models using COVID-19 patient data from West Sumatra.Methods: Two data mining methods, Discriminant Analysis and Support Vector Machine with different types of kernels (linear, polynomial, and radial basis function), were employed to categorize the time of COVID-19 recovery in this work. The study utilized 428 data points, with 75% allocated for training data and 25% for testing data. The independent factors were evaluated by determining the selection variables' information value (IV) to gauge their influence on the dependent variable. Data resampling techniques were employed to tackle the problem of data imbalance. This study employs data resampling techniques, including undersampling, oversampling, and SMOTE. The balancing accuracy of Discriminant Analysis and Support Vector Machine was examined.Result: The Discriminant Analysis with SMOTE achieved a balanced accuracy of 66.50%, outperforming the linear kernel Support Vector Machine with SMOTE, which had a balanced accuracy of 63.20% in this dataset.Novelty: This study assessed the novelty, originality, and value by comparing Discriminant Analysis and SVM algorithms with categorical and continuous independent variables. This research explores techniques for managing imbalanced data using undersampling, oversampling, and SMOTE, with variable selection based on information value assessment.

Non-Standard Finite Difference and Vieta-Lucas Orthogonal Polynomials for the Multi-Space Fractional-Order Coupled Korteweg-de Vries Equation

This paper focuses on examining numerical solutions for fractional-order models within the context of the coupled multi-space Korteweg-de Vries problem (CMSKDV). Different types of kernels, including Liouville-Caputo fractional derivative, as well as Caputo-Fabrizio and Atangana-Baleanu fractional derivatives, are utilized in the examination. For this purpose, the nonstandard finite difference method and spectral collocation method with the properties of the Shifted Vieta-Lucas orthogonal polynomials are employed for converting these models into a system of algebraic equations. The Newton-Raphson technique is then applied to solve these algebraic equations. Since there is no exact solution for non-integer order, we use the absolute two-step error to verify the accuracy of the proposed numerical results.

Improvements in adverse drug reaction prediction

This report investigates prediction on adverse drug reactions (ADR) with kernel and imbalance data mechanisms. The hypothesis is that different types of kernel lead to different prediction results, which suggests deciding the best-fit kernel might be a critical way of improving prediction accuracy. Besides, it was also hypothesized that edge cases in real-life setting would cause imbalance in the dataset, thus further causing inaccuracy in prediction. Similarly, attempting to add class weight to various machine learning models could also be a way to improve prediction accuracy. Hence, these hypotheses are being explored in this study.

NA

NA

HBCA: A Toolchain for High-Accuracy Branch-Fused CNN Accelerator on FPGA with Dual-Decimal-Fused Technique

The programmability of FPGA suits the constantly changing convolutional neural network (CNN). However, several challenges arise when the previous FPGA-based accelerators update CNN. Firstly, although the model of RepVGG can balance accuracy and speed, it solely supports two types of kernels. Meanwhile, 8-bit integer-only quantization of PyTorch which can support various CNNs is seldom successfully supported by the FPGA-based accelerators. In addition, Winograd F(4 × 4, 3 × 3) uses less multiplication, but its transformation matrix contains irregular decimals, which could lead to accuracy problems. To tackle these issues, this paper proposes High-accuracy Branch-fused CNN Accelerator (HBCA): a toolchain and corresponding FPGA-based accelerator. The toolchain proposes inception-based branch–fused technique, which can support more types of kernels. Meanwhile, the accelerator proposes Winograd-quantization dual decimal–fuse techniques to balance accuracy and speed. In addition, this accelerator supports multi-types of kernels and proposes Winograd decomposed-part reuse, multi-mode BRAM & DSP and data reuse to increase power efficiency. Experiments show that HBCA is capable of supporting seven CNNs with different types of kernels and more branches. The accuracy loss is within 0.1% when compared to the quantized model. Furthermore, the power efficiency (GOPS/W) of Inception, ResNet and VGG is up to 226.6, 188.1 and 197.7, which are better than other FPGA-based CNN accelerators.

A 2D-GRAPPA Algorithm with a Boomerang Kernel for 3D MRI Data Accelerated along Two Phase-Encoding Directions

For the reconstruction of 3D MRI data that are accelerated along the two phase-encoding directions, the 2D-generalized autocalibrating partially parallel acquisitions (GRAPPA) algorithm can be used to estimate the missing data in the k-space. We propose a new boomerang-shaped kernel based on theoretic and systemic analyses of the shape and dimensions of the kernel. The reconstruction efficiency of the 2D-GRAPPA algorithm with the proposed boomerang-shaped kernel (i.e., boomerang kernel (BK)-2D-GRAPPA) was compared with other 2D-GRAPPA algorithms that utilize different types of kernels (i.e., EX-2D-GRAPPA and SK-2D-GRAPPA) based on computer simulation, phantom and in vivo experiments. The proposed method was validated for different sets of ACS lines with acceleration factors from four to eight and various sizes of the kernels. A quantitative analysis was also performed by comparing the normalized root mean squared error (nRMSE) in the images and the undersampled edges. Computer simulation, in vivo and phantom experiments, and the quantitative analysis, showed that the proposed method could reduce aliasing artifacts without reducing the SNRs of the reconstructed images.

Laplace Transform for Solving System of Integro-Fractional Differential Equations of Volterra Type with Variable Coefficients and Multi-Time Delay

This study is the first to use Laplace transform methods to solve a system of Caputo fractional Volterra integro-differential equations with variable coefficients and a constant multi-time delay. This technique is based on different types of kernels, which we will explain in this paper. Symmetry kernels, which have properties of difference kernels or simple degenerate kernels, are able to compute analytical work. These are demonstrated by solving certain examples and analyzing the effectiveness and precision of cause techniques.

Prediction of Postoperative Speech Dysfunctions in Neurosurgery Based on Cortico-Cortical Evoked Potentials and Machine Learning Technology.

Intraoperative recording of cortico-cortical evoked potentials (CCEPs) enables studying effective connections between various functional areas of the cerebral cortex. The fundamental possibility of postoperative speech dysfunction prediction in neurosurgery based on CCEP signal variations could serve as a basis to develop the criteria for the physiological permissibility of intracerebral tumors removal for maximum preservation of the patients’ quality of life.The aim of the study was to test the possibility of predicting postoperative speech disorders in patients with glial brain tumors by using the CCEP data recorded intraoperatively before the stage of tumor resection.Materials and MethodsCCEP data were reported for 26 patients. To predict the deterioration of speech functions in the postoperative period, we used four options for presenting CCEP data and several machine learning models: a random forest of decision trees, logistic regression, and support vector machine method with different types of kernels: linear, radial, and polynomial. Twenty variants of models were trained: each in 300 experiments with resampling. A total of 6000 tests were performed in the study.ResultsThe prediction quality metrics for each model trained in 300 tests with resampling were averaged to eliminate the influence of “successful” and “unsuccessful” data grouping. The best result with F1-score = 0.638 was obtained by the support vector machine with a polynomial kernel. In most tests, a high sensitivity score was observed, and in the best model, it reached a value of 0.993; the specificity of the best model was 0.370.ConclusionThis pilot study demonstrated the possibility of predicting speech dysfunctions based on CCEP data taken before the main stage of glial tumors resection; the data were processed using traditional machine learning methods. The best model with high sensitivity turned out to be insufficiently specific. Further studies will be aimed at assessing the changes in CCEP during the operation and their relationship with the development of postoperative speech deficit.

General Fractional Calculus: Multi-Kernel Approach

For the first time, a general fractional calculus of arbitrary order was proposed by Yuri Luchko in 2021. In Luchko works, the proposed approaches to formulate this calculus are based either on the power of one Sonin kernel or the convolution of one Sonin kernel with the kernels of the integer-order integrals. To apply general fractional calculus, it is useful to have a wider range of operators, for example, by using the Laplace convolution of different types of kernels. In this paper, an extended formulation of the general fractional calculus of arbitrary order is proposed. Extension is achieved by using different types (subsets) of pairs of operator kernels in definitions general fractional integrals and derivatives. For this, the definition of the Luchko pair of kernels is somewhat broadened, which leads to the symmetry of the definition of the Luchko pair. The proposed set of kernel pairs are subsets of the Luchko set of kernel pairs. The fundamental theorems for the proposed general fractional derivatives and integrals are proved.

Modeling Student’s Academic Performance During Covid-19 Based on Classification in Support Vector Machine

This study proposed a statistical investigate the pattern of students’ academic performance before and after online learning due to the Movement Control Order (MCO) during pandemic outbreak and a modelling students’ academic performance based on classification in Support Vector Machine (SVM). Data sample were taken from undergraduate students of Faculty of Science and Mathematics, Universiti Pendidikan Sultan Idris (UPSI). Student’s Grade Point Average (GPA) were obtained to developed model of academic performances during Covid-19 outbreak. The prediction model was used to predict the academic performances of university students when online classes was conducted. The algorithm of Support Vector Machine (SVM) was used to develop a model of students’ academic performance in university. For the Support Vector Machine (SVM) algorithm, there are two important parameters which are C (misclassification tolerance parameter) and epsilon need to identify before proceed the further analysis. The parameters was applied to four different types of kernel which is linear kernel, radial basis function kernel, polynomial kernel and sigmoid kernel and the result was found that the best accuracy achieved by SVM are 73.68% by using linear kernel and the worst accuracy obtained from a sigmoid kernel which is 67.99% with parameter of misclassification tolerance C is 128 and epsilon is 0.6.

Numerical simulation of the fractal-fractional reaction diffusion equations with general nonlinear

<abstract> In this paper a new approach to the use of kernel operators derived from fractional order differential equations is proposed. Three different types of kernels are used, power law, exponential decay and Mittag-Leffler kernels. The kernel's fractional order and fractal dimension are the key parameters for these operators. The main objective of this paper is to study the effect of the fractal-fractional derivative order and the order of the nonlinear term, $ 1 &lt; q &lt; 2 $, in the equation on the behavior of numerical solutions of fractal-fractional reaction diffusion equations (FFRDE). Iterative approximations to the solutions of these equations are constructed by applying the theory of fractional calculus with the help of Lagrange polynomial functions. In key parameter regimes, all these iterative solutions based on a power kernel, an exponential kernel and a generalized Mittag-Leffler kernel are very close. Hence, iterative solutions obtained using one of these kernels are compared with full numerical solutions of the FFRDE and excellent agreement is found. All numerical solutions in this paper were obtained using Mathematica. </abstract>

Joint Distribution Adaptation for Drift Correction in Electronic Nose Type Sensor Arrays

This research deal with the drift compensation problem in sensor arrays named electronic noses. The drift problem occurs in this kind of sensor when they are exposed to an analyte for long periods, which may cause that the response of the sensor varies with time. Some approaches in the literature have tackled the drift compensation problem from the point of view of signal processing algorithms to obtain high rates of accuracy independently of time. In this work, the drift problem is solved using transfer learning with the joint distribution adaptation (JDA) method, which adapts both marginal and conditional distributions between domains, and requires no labeled data in the target domain to perform a classification task with a machine learning algorithm. The developed methodology for drift compensation is validated by measuring accuracy in the classification process. Validation considers a data set that measured six volatile organic compounds during a period of three years under strongly controlled operating conditions using a series of 16 metal oxide gas (MOX) sensors. JDA and Kernel JDA are used with three different types of kernels to determine the best behavior in terms of accuracy to correct the drift in electronic noses. As a result, it can be concluded that the approach using JDA outperforms standard learners like K-Nearest Neighbor (KNN) method.

Heart Sounds Classification for a Medical Diagnostic Assistance

In order to develop the assessment of phonocardiogram “PCG” signal for discrimination between two of people classes – individuals with heart disease and healthy one- we have adopted the database provided by "The PhysioNet/Computing in Cardilogy Challenge 2016", which contains records of heart sounds 'PCG '. This database is chosen in order to compare and validate our results with those already published. We subsequently extracted 20 features from each provided record. For classification, we used the Generalized Linear Model (GLM), and the Support Vector Machines (SVMs) with its different types of kernels (i.e.; Linear, polynomial and MLP). The best classification accuracy obtained was 88.25%, using the SVM classifier with an MLP kernel.

Movie films consumption in Brazil: an analysis of support vector machine classification

We employ the support vector machine (SVM) classifier, over different types of kernels, to investigate whether observable variables of individuals and their household information are able to describe their consumption decision of film at theaters in Brazil. Using a very big dataset of 340,000 individuals living in metropolitan areas of a whole large developing economy, we performed a Knowledge Discovery in Databases to classify the film consumers, which results in 80% instances correctly classified. To reduce the degrees of freedom for SVM and to learn the more important determinants of film consumption, we apply the Linear Discriminant Analysis that allows us to identify the key determinants of this consumption. The main individual characteristics are age, education (that merges to be a student), income, and preferences for cultural goods. Regarding the main geographic characteristics, these are the timing of sample, population concentration, and supply of movie theaters. The results point to an ineffective policy for the sector at the time investigated.

SURAA: A Novel Method and Tool for Loadbalanced and Coalesced SpMV Computations on GPUs

Sparse matrix-vector (SpMV) multiplication is a vital building block for numerous scientific and engineering applications. This paper proposes SURAA (translates to speed in arabic), a novel method for SpMV computations on graphics processing units (GPUs). The novelty lies in the way we group matrix rows into different segments, and adaptively schedule various segments to different types of kernels. The sparse matrix data structure is created by sorting the rows of the matrix on the basis of the nonzero elements per row ( n p r) and forming segments of equal size (containing approximately an equal number of nonzero elements per row) using the Freedman–Diaconis rule. The segments are assembled into three groups based on the mean n p r of the segments. For each group, we use multiple kernels to execute the group segments on different streams. Hence, the number of threads to execute each segment is adaptively chosen. Dynamic Parallelism available in Nvidia GPUs is utilized to execute the group containing segments with the largest mean n p r, providing improved load balancing and coalesced memory access, and hence more efficient SpMV computations on GPUs. Therefore, SURAA minimizes the adverse effects of the n p r variance by uniformly distributing the load using equal sized segments. We implement the SURAA method as a tool and compare its performance with the de facto best commercial (cuSPARSE) and open source (CUSP, MAGMA) tools using widely used benchmarks comprising 26 high n p r v a r i a n c e matrices from 13 diverse domains. SURAA outperforms the other tools by delivering 13.99x speedup on average. We believe that our approach provides a fundamental shift in addressing SpMV related challenges on GPUs including coalesced memory access, thread divergence, and load balancing, and is set to open new avenues for further improving SpMV performance in the future.

Voice Assessments for Detecting Patients with Parkinson’s Diseases in Different Stages

&lt;p class="IJASEITParagraph"&gt;Recently, a wide range of speech signal processing algorithms (dysphonia measures) aiming to detect patients with Parkinson’s disease (PD). So we have computed 19 dysphonia measures from sustained vowels collected from 375 voice samples from healthy and people suffer from PD. All the features are analysed and the more relevant ones are selected by the Principal component analysis (PCA) to classify the subjects in 4 classes according to the UPDRS (unified Parkinson’s disease Rating Scale) score. We used k-folds cross validation method with (k=4) validation scheme; 75% for training and 25% for testing, along with the Support Vector Machines (SVM) with its different types of kernels. The best result obtained was 92.5% using the PCA and the linear SVM.&lt;/p&gt;

Some Problems of Distributed and Boundary Control for Systems with Integral Aftereffect

We consider the problem of exact control for a system described by an equation with integral “memory.” It is shown that, under certain conditions, this system can be brought to rest in finite time by distributed control bounded in absolute value, and, in a special one-dimensional case, by control applied to an end-point of the interval. We consider different types of kernels in the integral term of the equation and describe some relationships between problems of controllability of some hyperbolic and parabolic systems.

Training Very Deep CNNs for General Non-Blind Deconvolution.

Non-blind image deconvolution is an ill-posed problem. The presence of noise and band-limited blur kernels makes the solution of this problem non-unique. Existing deconvolution techniques produce a residual between the sharp image and the estimation that is highly correlated with the sharp image, the kernel, and the noise. In most cases, different restoration models must be constructed for different blur kernels and different levels of noise, resulting in low computational efficiency or highly redundant model parameters. Here we aim to develop a single model that handles different types of kernels and different levels of noise: general non-blind deconvolution. Specifically, we propose a very deep convolutional neural network that predicts the residual between a pre-deconvolved image and the sharp image rather than the sharp image. The residual learning strategy makes it easier to train a single model for different kernels and different levels of noise, encouraging high effectiveness and efficiency. Quantitative evaluations demonstrate the practical applicability of the proposed model for different blur kernels. The model also shows state-of-the-art performance on synthesized blurry images.