Multi-output Kernel Regression for Correlated Multiple Outputs

@article{ART002781607},
author={ 심주용 and 박혜정 and 석경하 },
title={Multi-output Kernel Regression for Correlated Multiple Outputs},
journal={Quantitative Bio-Science},
issn={2288-1344},
year={2021},
volume={40},
number={2},
pages={83-88},
doi={10.22283/qbs.2021.40.2.83},
url={http://dx.doi.org/10.22283/qbs.2021.40.2.83}

TY - JOUR
AU - 심주용
AU - 박혜정
AU - 석경하
TI - Multi-output Kernel Regression for Correlated Multiple Outputs
T2 - Quantitative Bio-Science
PY - 2021
VL - 40
IS - 2
PB - 계명대학교 자연과학연구소
SP - 83-88
SN - 2288-1344
AB - The goal of multi-output regression is to predict multiple realvalued output variables. Research in this area is lacking compared to multi-output classification . In this approach multi-output kernel regression based on kernel regression in which different outputs are assumed to be correlated. We also introduce a modelselection method employs generalized crossvalidation function for choosing optimal values of hyperparameters. Numerical results from synthetic and real datasets are then obtained to illustrate that the proposed outperforms the other methods on multi-output regression problems.
KW - Generalized crossvalidation function, Hyperparameter, Kernel regression, Multi-output regression
DO - 10.22283/qbs.2021.40.2.83
UR - http://dx.doi.org/10.22283/qbs.2021.40.2.83
ER -

심주용 , 박혜정 and 석경하 (2021). Multi-output Kernel Regression for Correlated Multiple Outputs. Quantitative Bio-Science, 40( 2), 83- 88.

심주용 , 박혜정 and 석경하 . 2021, “Multi-output Kernel Regression for Correlated Multiple Outputs”, Quantitative Bio-Science, vol. 40, no. 2, pp. 83-88. Available from: doi:10.22283/qbs.2021.40.2.83

심주용 박혜정 et al. 석경하 “Multi-output Kernel Regression for Correlated Multiple Outputs” Quantitative Bio-Science 40.2 pp. 83-88 (2021): 83.

심주용 , 박혜정 , 석경하 . Multi-output Kernel Regression for Correlated Multiple Outputs Quantitative Bio-Science [Internet]. 2021; 40( 2), : 83-88. Available from: doi:10.22283/qbs.2021.40.2.83

심주용 , 박혜정 and 석경하 . “Multi-output Kernel Regression for Correlated Multiple Outputs” Quantitative Bio-Science 40, no.2 (2021): 83-88. doi: 10.22283/qbs.2021.40.2.83

홈 권호 목록 논문 목록 논문 상세

Multi-output Kernel Regression for Correlated Multiple Outputs

Quantitative Bio-Science

약어 : QBS

2021, vol.40, no.2, pp.83 - 88

DOI : 10.22283/qbs.2021.40.2.83

발행기관 : 계명대학교 자연과학연구소

연구분야 : 통계학

심주용¹ , 박혜정² , 석경하³

¹인제대학교

²P&S 빅데이터 과학 연구소

³인제대학교

인용한 논문 수 : - 서지 간략 보기

초록

The goal of multi-output regression is to predict multiple realvalued output variables. Research in this area is lacking compared to multi-output classification . In this approach multi-output kernel regression based on kernel regression in which different outputs are assumed to be correlated. We also introduce a modelselection method employs generalized crossvalidation function for choosing optimal values of hyperparameters. Numerical results from synthetic and real datasets are then obtained to illustrate that the proposed outperforms the other methods on multi-output regression problems.

키워드

Generalized crossvalidation function, Hyperparameter, Kernel regression, Multi-output regression

참고문헌(16)

[학술지] Tsoumakas G / 2007 / Multi-label classification: an overview / IJDWM 3 : 1 ~ 13
[학술지] Suykens JAK / 1999 / Least square support vector machine classifier / Neural Process Lett 9 : 293 ~ 300
[학술지] Suykens JAK / 2001 / Optimal control by least squares support vector machines / Neural Netw 14 : 23 ~ 35
[단행본] Vapnik VN / 1995 / The nature of statistical learning theory / Springer
[기타] Abdi H / 2013 / Encyclopedia for research methods for the social sciences / Sage. chapter Partial least squares (PLS) regression : 792 ~ 795
[학술지] Rosipal R / 2001 / Kernel partial least squares regression in reproducing kernel Hilbert space / J Mach Learn Res 2 : 97 ~ 123
[학술지] Tuia D / 2011 / Multioutput support vector regression for remote sensing bio"physical parameter estimation / IEEE Geosci Remote S 8 : 804 ~ 808
[학술지] Liu G / 2009 / Multi-output regression on the output manifold / Pattern Recogn 42 : 2737 ~ 2743
[학술지] Xu S / 2013 / Multi-output least-squares support vector regression machines / Pattern Recogn 34 : 1078 ~ 1084
[학술지] Bakker B / 2003 / Task clustering and gating for bayesian multitask learning / J Machine Learn Res 4 : 83 ~ 99
[학술지] Borchani H / 2015 / A survey on multi-output regression / Wires Data Min Knowl 5 : 216 ~ 233
[기타] Xu D / 2019 / A Survey on Multi-output Learning / arXiv 2019;1901.00248
[학술지] Mercer J / 1909 / Functions of positive and negative type and their connection with theory of integral equations / Philos T R Soc A 209 : 415 ~ 446
[학술지] Kimeldorf G / 1971 / Some results on Tchebychean spline functions / J Math Anal Appl 33 : 82 ~ 95
[학술대회] Wahba G / 1990 / Spline models for observational data / CMMS-NSF Regional Conference Series in Applied Mathematics 59.
[학술지] 양준혁 / 2020 / Forecasting the KOSPI 200 Stock Index Based on LSTM Autoencoder / Quantitative Bio-Science 39 (2) : 101 ~ 109