Statistical learning: regression by support vector niachines

2005 ◽  
Author(s):  
S.S. Stankovic
Keyword(s):  
Statistical Learning ◽  
Support Vector

Combining statistical learning and geostatistical approaches in a spatiotemporal framework for low flow estimation

2021 ◽  
Author(s):  
Johannes Laimighofer ◽  
Michael Melcher ◽  
Juraj Parajka ◽  
Gregor Laaha
Keyword(s):  
Statistical Learning ◽  
Mean Squared Error ◽  
Temporal Structure ◽  
Empirical Orthogonal Functions ◽  
Regression Coefficients ◽  
Low Flow ◽  
Support Vector ◽  
Spatiotemporal Model ◽  
Residual Field ◽  
The Mean

<p><span>This paper aims to develop a spatiotemporal model to estimate monthly low flow quantiles Q95 [P(Q<Q95=0.05)] standardized by catchment area in Austria. Our dataset consists of 325 gauging stations that where consistently monitored between 1976 to 2015, and it covers about 60% of the national territory of Austria. </span></p><p><span>In a first step we are adapting a spatiotemporal model initially designed for modeling air pollution data. This approach is based on empirical orthogonal functions (EOF), that should capture the temporal structure of the spatiotemporal model. The EOFs are weighted by regression coefficients estimated by universal kriging. We extend the model by using GLM-boosting, LASSO, Principal Component Regression (PCR) and Random Forest (RF) for selecting the regression coefficients of the EOFs. Furthermore, we do not limit the kriging structure of the residual field to geographical coordinates but use a broader approach of physiographic kriging. In a second step we implement separate models for the mean parts of the model and the residual parts of the model. The mean field is defined by statistical learning methods as RF, GAM-boosting, LASSO and Support Vector Machines (SVM). For the residual field we define two different approaches, either the </span><span>method developed in the first step</span><span> or spatiotemporal kriging.</span></p><p><span>Model performance is evaluated by cross validation and the best model is selected by the mean squared error (MSE). </span></p><p> </p>

Study on Prediction of Mackey-Glass Chaotic Time Series Using Support Vector Machines

2014 ◽  
Vol 1051 ◽  
pp. 1009-1015 ◽  
Author(s):  
Ya Li Ning ◽  
Xin You Wang ◽  
Xi Ping He
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Support Vector Machines ◽  
Statistical Learning ◽  
Chaotic Time Series ◽  
Support Vector ◽  
Machine Type ◽  
Type Selection ◽  
Vector Machines ◽  
New Generation

Support Vector Machines (SVM), which is a new generation learning method based on advances in statistical learning theory, is characterized by the use of many standard technologies of machine learning such as maximal margin hyperplane, Mercel kernels and the quadratic programming. Because the best performance is obtained in many currently challenging applications, SVM has sustained wide attention, and has been become the standard tools of machine learning and data mining. But as a developing technology, SVM still have some problems and its applications are limited. In this paper, SVM and its applications in chaotic time series including predicting chaotic time series, focus on comparison in regression type selection, and kernel type selection in the same regression machine type.

A Computer Method for Validating Traditional Chinese Medicine Herbal Prescriptions

2005 ◽  
Vol 33 (02) ◽  
pp. 281-297 ◽  
Author(s):  
J. F. Wang ◽  
C. Z. Cai ◽  
C. Y. Kong ◽  
Z. W. Cao ◽  
Y. Z. Chen
Keyword(s):  
Chinese Medicine ◽  
Traditional Chinese Medicine ◽  
Statistical Learning ◽  
Conventional Medicine ◽  
Computer Method ◽  
Support Vector ◽  
Random Combination ◽  
System A ◽  
Statistical Learning Method

Traditional Chinese medicine (TCM) has been widely practiced and is considered as an alternative to conventional medicine. TCM herbal prescriptions contain a mixture of herbs that collectively exert therapeutic actions and modulating effects. Traditionally defined herbal properties, related to the pharmacodynamic, pharmacokinetic and toxicological, as well as physicochemical properties of their principal ingredients, have been used as the basis for formulating TCM multi-herb prescriptions. These properties are used in this work to develop a computer program for predicting whether a multi-herb recipe is a valid TCM prescription. This program is based on a statistical learning method, support vector machine (SVM), and it is trained by using 575 well-known TCM prescriptions and 1961 non-TCM recipes generated by random combination of TCM herbs. Testing results by using 72 well-known TCM prescriptions and 5039 non-TCM recipes showed that 73.6% of the TCM prescriptions and 99.9% of non-TCM recipes are correctly classified by this system. A further test by using 48 TCM prescriptions published in recent years found that 68.7% of these are correctly classified. These accuracies are comparable to those of SVM classification of other biological systems. Our study indicates the potential of SVM for facilitating the analysis of TCM prescriptions.

A Novel Filtering Algorithm Based on Least Square Support Vector

2012 ◽  
Vol 532-533 ◽  
pp. 1732-1735
Author(s):  
Ya Qin Li ◽  
Yang Hua Xu
Keyword(s):  
Statistical Learning ◽  
Seismic Data ◽  
Least Square ◽  
Support Vector ◽  
Machine Learning Method ◽  
Learning Method ◽  
Central Frequency ◽  
Filtering Algorithm ◽  
Ricker Wavelet ◽  
Better Than

In this paper, we proposed a novel filtering algorithm that using the Ricker wavelet kernel to reduce the noise. The algorithm based on Support vector machine (SVM) which is a machine learning method on the base of statistical learning theory. Those parameters of the new algorithm affect the rising edge, the band width and central frequency of passband. The experimental results of synthetic seismic data show that the filter with the Ricker wavelet kernel works better than other methods．

scholarly journals The Novel Quantitative Technique for Assessment of Gait Symmetry Using Advanced Statistical Learning Algorithm

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Jianning Wu ◽  
Bin Wu
Keyword(s):  
Statistical Learning ◽  
Learning Algorithm ◽  
Lower Limbs ◽  
Classification Method ◽  
Support Vector ◽  
Accurate Identification ◽  
Index Method ◽  
Gait Symmetry ◽  
Significant Difference ◽  
Gait Asymmetry

The accurate identification of gait asymmetry is very beneficial to the assessment of at-risk gait in the clinical applications. This paper investigated the application of classification method based on statistical learning algorithm to quantify gait symmetry based on the assumption that the degree of intrinsic change in dynamical system of gait is associated with the different statistical distributions between gait variables from left-right side of lower limbs; that is, the discrimination of small difference of similarity between lower limbs is considered the reorganization of their different probability distribution. The kinetic gait data of 60 participants were recorded using a strain gauge force platform during normal walking. The classification method is designed based on advanced statistical learning algorithm such as support vector machine algorithm for binary classification and is adopted to quantitatively evaluate gait symmetry. The experiment results showed that the proposed method could capture more intrinsic dynamic information hidden in gait variables and recognize the right-left gait patterns with superior generalization performance. Moreover, our proposed techniques could identify the small significant difference between lower limbs when compared to the traditional symmetry index method for gait. The proposed algorithm would become an effective tool for early identification of the elderly gait asymmetry in the clinical diagnosis.

scholarly journals Machine Learning Approaches for Accurate Prediction of Relative Humidity based on Temperature and Wet-Bulb Depression

2020 ◽  
Author(s):  
Mahdi Ghadiri ◽  
Azam Marjani ◽  
Samira Mohammadinia ◽  
Manouchehr Shokri
Keyword(s):  
Relative Humidity ◽  
Statistical Learning ◽  
Air Conditioning ◽  
Fuzzy Inference ◽  
Least Square ◽  
Support Vector ◽  
Cooling Towers ◽  
Learning Approaches ◽  
Inference System ◽  
Data Points

The main parameters for calculation of relative humidity are the wet-bulb depression and dry bulb temperature. In this work, easy-to-used predictive tools based on statistical learning concepts, i.e., the Adaptive Network-Based Fuzzy Inference System (ANFIS) and Least Square Support Vector Machine (LSSVM) are developed for calculating relative humidity in terms of wet bulb depression and dry bulb temperature. To evaluate the aforementioned models, some statistical analyses have been done between the actual and estimated data points. Results obtained from the present models showed their capabilities to calculate relative humidity for divers values of dry bulb temperatures and also wet-bulb depression. The obtained values of MSE and MRE were 0.132 and 0.931, 0.193 and 1.291 for the LSSVM and ANFIS approaches respectively. These developed tools are user-friend and can be of massive value for scientists especially, those dealing with air conditioning and wet cooling towers systems to have a noble check of the relative humidity in terms of wet bulb depression and dry bulb temperatures.

scholarly journals An Application Of A Hybrid Wavelet-SVM Based Approach For Induction Motor Fault Detection

2021 ◽  
Author(s):  
Shermineh Ghasemi
Keyword(s):  
Statistical Learning ◽  
Induction Motors ◽  
Early Stage ◽  
Support Vector ◽  
Decision Threshold ◽  
Electrical Machinery ◽  
Broken Rotor Bars ◽  
Nonlinear Feature Extraction ◽  
Intelligent Methods ◽  
Nonlinear Feature

Induction motors have been widely used in the industries due to their simple and rugged construction. Failures of this electrical machinery may cause considerable losses. Therefore adapting an efficient method to diagnose a fault at a very early stage would prevent any further consequences of this deficiency. The major concern is related to the mechanical failures, normally caused by the inner component deficiencies. Application of intelligent methods have attracted interest in recent years. Support Vector Machine is a supervised learning method, based on statistical learning theory. This thesis presents three different SVM algorithms: SVM, KPCA-SVM and ROC-SVM, applicable for broken rotor bars detection. SVM proved to be reliable method for classification. While application of KPCA-SVM, shows nonlinear feature extraction can improve the performance of classifier with respect to reduce the number of overlapping samples. Furthermore, ROC-SVM has improved the accuracy by selecting a decision threshold for the classifier.

Sign in / Sign up

Export Citation Format

Share Document