Multi layer kernel learning for time series forecasting

Agus Widodo, Indra Budi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

Multiple Kernel Learning (MKL) is one of recent approaches to choose suitable kernels from a given pool of kernels by exploring the combinations of multiple kernels. For linear kernel, the target kernel is a linear combination some base kernels. However, some literatures suggest that a linear combination of kernels cannot consistently outperform either the uniform combination of base kernels or simply the best single kernel. Hence, some researchers attempt to study the non-linear combination of kernels, such as polynomial combination of kernels or two-layer MKL. This paper extends the previous work on two-layer MKL into three-layer MKL especially in the field of regression to forecast future values of time series. Our experiment on several time series dataset demonstrates that our proposed method generally outperforms the linear combination of kernels.

Original languageEnglish
Title of host publication2012 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2012 - Proceedings
Pages313-318
Number of pages6
Publication statusPublished - 1 Dec 2012
Event2012 4th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2012 - Depok, Indonesia
Duration: 1 Dec 20122 Dec 2012

Publication series

Name2012 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2012 - Proceedings

Conference

Conference2012 4th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2012
Country/TerritoryIndonesia
CityDepok
Period1/12/122/12/12

Keywords

  • color moments
  • Indonesian medicinal plant identification
  • local binary pattern variance
  • morphological
  • probabilistic neural network

Fingerprint

Dive into the research topics of 'Multi layer kernel learning for time series forecasting'. Together they form a unique fingerprint.

Cite this