Support Vector Regression

By Fan Zhang, Lauren J. O'Donnell. Wiley StatsRef: Statistics Reference Online, 2020

2,472 citations recorded by the source corpus.

Abstract This chapter provides an overview of the support vector regression (SVR), an analytical technique to investigate the relationship between one or more predictor variables and a real-valued (continuous) dependent variable. In the first part of the chapter, we provide a description of the SVR algorithm. Unlike traditional regression methods that depend on assumptions of the model that might not be accurate (e.g., linear data distribution), SVR is a machine learning technique in which a model learns a variable's importance for characterizing the relationship between input and output. In the second part of the chapter, we review a number of studies that have applied SVR to magnetic resonance imaging data to performance multivariate pattern regression analysis of brain disorders. These studies have been successful in revealing spatially distributed patterns across multiple brain regions in several brain disorders including schizophrenia, autism, and attention-deficit/hyperactivity disorder.

Subfields: Cognitive Neuroscience, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/116f4d529b31a4fa695df8aadff8fac65eb3d254

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Learning Equations for Extrapolation and Control (2018, positive): “A second baseline is given by epsilon support vector regression (SVR) (Basak et al., 2007) with two hyperparameters C ∈ 10 {− 3 , − 2 , − 1 , 0 , 1 , 2 , 3 , 3 .”
A novel nonlinear regression model of SVR as a substitute for ANN to predict conductivity of MWCNT-CuO/water hybrid nanofluid based on empirical data (2019, methodology): “A linear regression approach is presented as [30]:”
Big Data Creates New Opportunities for Materials Research: A Review on Methods and Applications of Machine Learning for Materials Design (2019, neutral): “Typical regression algorithms are Kriging or Gaussian process regression [42], artiﬁcial neural networks (ANNs) [43], and support vector machines (SVMs) [44].”
Support vector regression optimized by meta-heuristic algorithms for daily streamflow prediction (2020, methodology): “Over the last two decades, on the global scale, the AI techniques integrated with numerous meta-heuristics algorithms received the extensive application in streamflow modelling and forecasting (Granata et al. 2016; Ghorbani et al. 2018; Hadi and Tombul 2018; Yaseen et al. 2018, 2019b; Rauf et al. 20”
Support vector regression approach with different kernel functions for predicting blast-induced ground vibration: a case study in an open-pit coal mine of Vietnam (2019, background): “SVR relies on a subset of training datasets to build the forecasting model [62].”
Comparing support vector regression and random forests for predicting malaria incidence in Mozambique (2013, methodology): “The most used function is the so called −insensitive loss function [11], and is employed in this study.”
Building Naturalistic Emotionally Balanced Speech Corpus by Retrieving Emotional Speech from Existing Podcast Recordings (2019, background): “where zi and z i are (non-negative) slack variables that allow the model to converge to a feasible solution [61].”
Application of Support Vector Regression for Modeling Low Flow Time Series (2018, background): “The SVM model was chosen because of its high ability in pattern recognition (Azamathulla et al., 2016).”
A review of the-state-of-the-art in data-driven approaches for building energy prediction (2020, background): “For SVR, the goal is to find a linear regression function that could predict the result with acceptable deviation from the actual target [74].”