Multi-output least-squares support vector regression machines

Xu, Shuo; An, Xueli; Qiao, Xi; Zhu, Liehuang; Lin, Li

doi:10.1016/j.patrec.2013.01.015

Cited by 221 publications

(164 citation statements)

References 12 publications

Supporting

Mentioning

149

Contrasting

Order By: Relevance

“…To verify the effectiveness of the proposed MLS-TSVR, in this section, a series of comparative experiments with MLS-SVR are performed on Corn (m5, mp5, and mp6) [10], synthetic [10] The detailed characters of these data sets are listed in Table 1, where l, d, and m denote the number of data, the dimension of the input samples, and the dimension of the outputs, respectively.…”

Section: Methodsmentioning

confidence: 99%

“…This section briefly recalls TSVR, TSVR -ε and MLS-SVR, for details, see [10][11][12]. Given a single-output data set…”

Section: Preliminariesmentioning

confidence: 99%

“…This work is supported by the Natural Science Foundation of Shandong Province (Grant No: ZR2016AM24) and the Natural Science Min Hou and Liya Fan / IJAMML 6:1 (2017) [1][2][3][4][5][6][7][8][9][10][11][12][13][14] …”

Section: Acknowledgementsmentioning

confidence: 99%

“…Unfortunately, M-SVR and multiple S-SVR are all to ignore the cross relations among output variables and then decrease the accuracy of regression. In 2013, Xu et al [10] proposed multi-output least squares SVR (MLS-SVR).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Output Least Squares TSVR

Hu¹,

Fan²

2017

Int. J. Appl. Math. Mach. Learning

View full text Add to dashboard Cite

In order to improve the regression accuracy of MLS-SVR presented by Xu et al.[10] with a fast training algorithm, this paper proposes a new regression method named as multioutput least squares twin SVR (MLS-TSVR) for multi-output problems. The main advantage of the proposed method is that the relations among output weight vectors are considered as a whole rather than decomposed in MLS-SVR. Experimental results show that MLS-TSVR has a good property on regression accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

“…This section briefly recalls TSVR, TSVR -ε and MLS-SVR, for details, see [10][11][12]. Given a single-output data set…”

Section: Preliminariesmentioning

confidence: 99%

Section: Acknowledgementsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Output Least Squares TSVR

Hu¹,

Fan²

2017

Int. J. Appl. Math. Mach. Learning

View full text Add to dashboard Cite

show abstract

“…Based on the given error bound, they presented a new algorithm for transductive regression that performs well and can scale to large data sets. Xu et al (2011) proposed a semi-supervised least squares support vector regression and showed their feasibility and efficiency by experiment on a corn data set.…”

Section: Introductionmentioning

confidence: 99%

Study on semi-supervised local constant regression estimation

Seok¹

2012

Journal of the Korean Data and Information Science Society

View full text Add to dashboard Cite

Many different semi-supervised learning algorithms have been proposed for use with unlabeled data. However, most of them focus on classification problems. In this paper, we propose a semi-supervised regression algorithm called the semi-supervised local constant estimator (SSLCE), based on the local constant estimator (LCE), and reveal the asymptotic properties of SSLCE. We also show that the SSLCE has a faster convergence rate than that of the LCE when a well chosen weighting factor is employed. Our experiment with synthetic data shows that the SSLCE can improve performance with unlabeled data, and we recommend its use with the proper size of unlabeled data.

show abstract

An Electromyographic‐Based Control Using Gaussian Mixture Model on an Upper‐Limb Cable‐Driven Rehabilitation Robot

Zheng,

Li,

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

Electromyographic (EMG)‐based admittance control by arm force can provide continuous motion control in robot‐assisted rehabilitation. Natural and complex physical human–robot interactions utilizing intelligent EMG‐based interfaces require a computational estimation model for 3D voluntary forces. Existing computational models infrequently directly encode the interconnections among the spatial‐dimensional components of 3D arm forces and experience performance degradation caused by confounding variables like muscle fatigue in EMG‐based control. Motivated by this challenge, a computational model is proposed using the Gaussian mixture model (GMM), which only requires a user‐friendly calibration by an incremental GMM approach to reduce the effect of muscle fatigue. GMM aims to encode the multivariable connection between EMG and voluntary force by joint probability density distribution. The EMG‐based control system retrieves the estimated voluntary forces given EMG from GMM by utilizing the Gaussian mixture regression. Herein, the performance of the proposed EMG‐based admittance control is tested using GMM by trajectory‐tracking experiments before and after the fatigue‐inducing experiment. The experiments include eight healthy participants. The experimental outcomes prove that the EMG‐based control using calibrated GMM shows an increase of 23.66% and 8.17% in tracking precision and motion compliance, showing potential application across diverse domains involving physical human–robot interactions.

show abstract

Multi-output least-squares support vector regression machines

Cited by 221 publications

References 12 publications

Multi-Output Least Squares TSVR

Multi-Output Least Squares TSVR

Study on semi-supervised local constant regression estimation

An Electromyographic‐Based Control Using Gaussian Mixture Model on an Upper‐Limb Cable‐Driven Rehabilitation Robot

Contact Info

Product

Resources

About