DC Algorithm for Extended Robust Support Vector Machine

2017 ◽  
Vol 29 (5) ◽  
pp. 1406-1438 ◽  
Author(s):  
Shuhei Fujiwara ◽  
Akiko Takeda ◽  
Takafumi Kanamori
Keyword(s):  
Support Vector Machine ◽  
Numerical Experiments ◽  
Support Vector ◽  
Nonconvex Problem ◽  
Dc Algorithm ◽  
Special Cases ◽  
Vector Machines ◽  
Extended Range ◽  
Nonconvex Constraint ◽  
Robust Variant

Nonconvex variants of support vector machines (SVMs) have been developed for various purposes. For example, robust SVMs attain robustness to outliers by using a nonconvex loss function, while extended [Formula: see text]-SVM (E[Formula: see text]-SVM) extends the range of the hyperparameter by introducing a nonconvex constraint. Here, we consider an extended robust support vector machine (ER-SVM), a robust variant of E[Formula: see text]-SVM. ER-SVM combines two types of nonconvexity from robust SVMs and E[Formula: see text]-SVM. Because of the two nonconvexities, the existing algorithm we proposed needs to be divided into two parts depending on whether the hyperparameter value is in the extended range or not. The algorithm also heuristically solves the nonconvex problem in the extended range. In this letter, we propose a new, efficient algorithm for ER-SVM. The algorithm deals with two types of nonconvexity while never entailing more computations than either E[Formula: see text]-SVM or robust SVM, and it finds a critical point of ER-SVM. Furthermore, we show that ER-SVM includes the existing robust SVMs as special cases. Numerical experiments confirm the effectiveness of integrating the two nonconvexities.

scholarly journals Research on Parallel Support Vector Machine Based on Spark Big Data Platform

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yao Huimin
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Big Data ◽  
Support Vector Machines ◽  
Cross Validation ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Lambda Architecture ◽  
Vector Machines ◽  
Data Platform

With the development of cloud computing and distributed cluster technology, the concept of big data has been expanded and extended in terms of capacity and value, and machine learning technology has also received unprecedented attention in recent years. Traditional machine learning algorithms cannot solve the problem of effective parallelization, so a parallelization support vector machine based on Spark big data platform is proposed. Firstly, the big data platform is designed with Lambda architecture, which is divided into three layers: Batch Layer, Serving Layer, and Speed Layer. Secondly, in order to improve the training efficiency of support vector machines on large-scale data, when merging two support vector machines, the “special points” other than support vectors are considered, that is, the points where the nonsupport vectors in one subset violate the training results of the other subset, and a cross-validation merging algorithm is proposed. Then, a parallelized support vector machine based on cross-validation is proposed, and the parallelization process of the support vector machine is realized on the Spark platform. Finally, experiments on different datasets verify the effectiveness and stability of the proposed method. Experimental results show that the proposed parallelized support vector machine has outstanding performance in speed-up ratio, training time, and prediction accuracy.

Support Vector Machine Classification applied on Weaning Trials Patients

2008 ◽  
pp. 1277-1282
Author(s):  
B.F. Giraldo ◽  
A. Garde ◽  
C. Arizmendi ◽  
R. Jané ◽  
I. Diaz ◽  
...  
Keyword(s):  
Mechanical Ventilation ◽  
Support Vector Machine ◽  
Support Vector Machines ◽  
Work Of Breathing ◽  
Selection Procedure ◽  
Respiratory Pattern ◽  
Support Vector ◽  
Vector Machines ◽  
Leave One Out ◽  
Pattern Variability

The most common reason for instituting mechanical ventilation is to decrease a patient’s work of breathing. Many attempts have been made to increase the effectiveness on the evaluation of the respiratory pattern by means of respiratory signal analysis. This work suggests a method of studying the lying differences in respiratory pattern variability between patients on weaning trials. The core of the proposed method is the use of support vector machines to classify patients into two groups, taking into account 35 features of each one, previously extracted from the respiratory flow. 146 patients from mechanical ventilation were studied: Group S of 79 patients with Successful trials, and Group F of 67 patients that Failed on the attempt to maintain spontaneous breathing and had to be reconnected. Applying a feature selection procedure based on the use of the support vector machine with leave-one-out cross-validation, it was obtained 86.67% of well classified patients into the Group S and 73.34% into Group F, using only eight of the 35 features. Therefore, support vector machines can be an interesting classification method in the study of the respiratory pattern variability.

scholarly journals Forecast of Power Grid Investment Scale Based on Support Vector Machine

2020 ◽  
Vol 165 ◽  
pp. 06026
Author(s):  
Yongli Wang ◽  
Yanchao Lu ◽  
Jingyan Wang ◽  
Xiaohui Wang ◽  
Shuo Wang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Power Grid ◽  
Economic Transformation ◽  
Single Parameter ◽  
Support Vector ◽  
Vector Machines ◽  
New Situation ◽  
Fitting Accuracy

Economic transformation creates a new environment for grid investment. In the situation of high quality development, the traditional investment scale prediction model is no longer applicable. Aiming at the problems of single parameter of grid-driven investment scale prediction model and poor linear fitting accuracy, a provincial medium- and long-term investment scale prediction model based on support vector machine was proposed. Aiming at the single parameter and poor line fitting accuracy of the grid-driven investment scale prediction model under the new situation, the new environment, new directions and new requirements for grid investment are analyzed. Based on the support vector machine algorithm, a medium-and long-term investment scale prediction model for provincial grids based on support vector machines is proposed. The scale of provincial grid investment is expected from 2019 to 2022. The empirical results show that the prediction model constructed in this paper is effective and feasible. It is of great significance to explore the prediction model of medium and long-term investment scale of power grid enterprises in the new situation.

scholarly journals A Novel Sparse Least Squares Support Vector Machines

2013 ◽  
Vol 2013 ◽  
pp. 1-10 ◽  
Author(s):  
Xiao-Lei Xia ◽  
Weidong Jiao ◽  
Kang Li ◽  
George Irwin
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Regularization Parameter ◽  
Support Vector ◽  
Training Algorithm ◽  
Least Squares Approximation ◽  
Generalization Ability ◽  
Vector Machines ◽  
Training Cost ◽  
Benchmark Datasets

The solution of a Least Squares Support Vector Machine (LS-SVM) suffers from the problem of nonsparseness. The Forward Least Squares Approximation (FLSA) is a greedy approximation algorithm with a least-squares loss function. This paper proposes a new Support Vector Machine for which the FLSA is the training algorithm—the Forward Least Squares Approximation SVM (FLSA-SVM). A major novelty of this new FLSA-SVM is that the number of support vectors is the regularization parameter for tuning the tradeoff between the generalization ability and the training cost. The FLSA-SVMs can also detect the linear dependencies in vectors of the input Gramian matrix. These attributes together contribute to its extreme sparseness. Experiments on benchmark datasets are presented which show that, compared to various SVM algorithms, the FLSA-SVM is extremely compact, while maintaining a competitive generalization ability.

Study on Prediction of Chaotic Time Series Using Least Squares Support Vector Machines

2014 ◽  
Vol 1061-1062 ◽  
pp. 935-938
Author(s):  
Xin You Wang ◽  
Guo Fei Gao ◽  
Zhan Qu ◽  
Hai Feng Pu
Keyword(s):  
Time Series ◽  
Support Vector Machine ◽  
Support Vector Machines ◽  
Least Squares ◽  
Prediction Accuracy ◽  
Chaotic Time Series ◽  
Support Vector ◽  
Vector Machines ◽  
Online Prediction ◽  
Better Than

The predictions of chaotic time series by applying the least squares support vector machine (LS-SVM), with comparison with the traditional-SVM and-SVM, were specified. The results show that, compared with the traditional SVM, the prediction accuracy of LS-SVM is better than the traditional SVM and more suitable for time series online prediction.

Optimal Reduced-Set Vectors for Support Vector Machines with a Quadratic Kernel

2004 ◽  
Vol 16 (9) ◽  
pp. 1769-1777 ◽  
Author(s):  
Thorsten Thies ◽  
Frank Weber
Keyword(s):  
Support Vector Machine ◽  
Support Vector Machines ◽  
Discriminant Function ◽  
Explicit Solution ◽  
Computational Cost ◽  
One Dimension ◽  
Support Vector ◽  
Homogeneous Kernel ◽  
Vector Machines

To reduce computational cost, the discriminant function of a support vector machine (SVM) should be represented using as few vectors as possible. This problem has been tackled in different ways. In this article, we develop an explicit solution in the case of a general quadratic kernel k(x, x′) = (C + Dx⊺x′)2. For a given number of vectors, this solution provides the best possible approximation and can even recover the discriminant function if the number of used vectors is large enough. The key idea is to express the inhomogeneous kernel as a homogeneous kernel on a space having one dimension more than the original one and to follow the approach of Burges (1996).

SUPPORT VECTOR MACHINES FOR THAI PHONEME RECOGNITION

2001 ◽  
Vol 09 (06) ◽  
pp. 803-813 ◽  
Author(s):  
NUTTAKORN THUBTHONG ◽  
BOONSERM KIJSIRIKUL
Keyword(s):  
Support Vector Machine ◽  
Dimensional Space ◽  
High Dimensional ◽  
Support Vector ◽  
Phoneme Recognition ◽  
Classification Technique ◽  
Separating Hyperplane ◽  
Vector Machines ◽  
Tone Recognition ◽  
Vowel Recognition

The Support Vector Machine (SVM) has recently been introduced as a new pattern classification technique. It learns the boundary regions between samples belonging to two classes by mapping the input samples into a high dimensional space, and seeking a separating hyperplane in this space. This paper describes an application of SVMs to two phoneme recognition problems: 5 Thai tones, and 12 Thai vowels spoken in isolation. The best results on tone recognition are 96.09% and 90.57% for the inside test and outside test, respectively, and on vowel recognition are 95.51% and 87.08% for the inside test and outside test, respectively.

Parameters of Support Vector Machines Model Optimized Method Based on Genetic Algorithm

2014 ◽  
Vol 989-994 ◽  
pp. 1873-1876
Author(s):  
Yu Zhen Xie ◽  
Zhao Gang Wang ◽  
Xiao Wei Dai
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Support Vector Machine Model ◽  
Optimization Problems ◽  
Support Vector ◽  
Machine Model ◽  
Penalty Factor ◽  
Vector Machines ◽  
Cross Validation Error ◽  
Function Selection

In order to obtain more accurate parameters of support vector machine model, using genetic algorithm to optimize the parameters is an effective method. This paper analyzes the principle of support vector machine for regression, support vector machine kernel function selection, kernel parameters, penalty factor selection and adjustment methods, taking into account genetic algorithm is effective in solving optimization problems, proposed a method using genetic algorithm to optimize the parameters of support vector machine, which uses genetic algorithms to make cross-validation error minimized. The simulation results demonstrate the effectiveness of this method.

scholarly journals Prediksi Konsumsi Energi Pada Bangunan Menggunakan Metode Support Vector Machice Berbasis Algoritma Genetika

2017 ◽  
Vol 2 (1) ◽  
pp. 1
Author(s):  
Wida Prima Mustika
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Feature Selection ◽  
Energy Consumption ◽  
Support Vector Machines ◽  
Energy Use ◽  
Building Energy ◽  
Support Vector ◽  
Vector Machines ◽  
Optimization Parameters

Energy consumption is a demand for the amount of energy that must supply the building at any given time. Building energy consumption has continued increased over the last few decades all over the world, and Heating, Ventilating, and Air-Conditioning (HVAC), which has a catalytic role in regulating the temperature in the room, mostly accounted for of building energy use. Models created for in this study support vector machine and support vector machine-based models of genetic algorithm to obtain the value of accuracy or error rate or the smallest error value Root Mean Square Error (RMSE) in predicting energy consumption in buildings is more accurate. After testing the two models of support vector machines and support vector machines based on the genetic algorithm is the testing results obtained by using support vector machines where RMSE value obtained was 2,613. Next was the application of genetic algorithms to the optimization parameters C and γ values obtained RMSE error of 1.825 and a genetic algorithm for feature selection error RMSE values obtained for 1,767 of the 7 predictor variables and the selection attribute or feature resulting in the election of three attributes used. After that is done the optimization parameters and the importance of the value of feature selection mistake or error of the smallest RMSE of 1.537. Thus the support vector machine algorithm based on genetic algorithm can give a solution to the problems in the prediction of energy consumption rated the smallest mistake or error.

scholarly journals A New Support Vector Machine Based on Convolution Product

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-19
Author(s):  
Wei-Chang Yeh ◽  
Yunzhi Jiang ◽  
Shi-Yi Tan ◽  
Chih-Yen Yeh
Keyword(s):  
Neural Networks ◽  
Support Vector Machine ◽  
Classification Accuracy ◽  
Numerical Experiments ◽  
Classification Problem ◽  
Support Vector ◽  
Convolution Product ◽  
Swarm Optimization ◽  
New Information ◽  
Short Time

The support vector machine (SVM) and deep learning (e.g., convolutional neural networks (CNNs)) are the two most famous algorithms in small and big data, respectively. Nonetheless, smaller datasets may be very important, costly, and not easy to obtain in a short time. This paper proposes a novel convolutional SVM (CSVM) that has the advantages of both CNN and SVM to improve the accuracy and effectiveness of mining smaller datasets. The proposed CSVM adapts the convolution product from CNN to learn new information hidden deeply in the datasets. In addition, it uses a modified simplified swarm optimization (SSO) to help train the CSVM to update classifiers, and then the traditional SVM is implemented as the fitness for the SSO to estimate the accuracy. To evaluate the performance of the proposed CSVM, experiments were conducted to test five well-known benchmark databases for the classification problem. Numerical experiments compared favorably with those obtained using SVM, 3-layer artificial NN (ANN), and 4-layer ANN. The results of these experiments verify that the proposed CSVM with the proposed SSO can effectively increase classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document