A bootstrap based virtual sample generation method for improving the accuracy of modeling complex chemical processes using small datasets

Qun Xiong Zhu, Hong Fei Gong, Yuan Xu, Yan Lin He

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

12 Citations (Scopus)

Abstract

Though in the era of big data, it remains a challenge to be tackled that the forecasting model with high accuracy and robustness needs to be built using small size samples. One effective tool of addressing this problem is the virtual sample generation (VSG), which can generate a mass of new virtual samples on the basis of small sample sets. The bootstrap method is adopted to feasibly resample the virtual samples in this paper. The effectiveness of the proposed bootstrap virtual sample generation (BVSG) is evaluated over one real case. The experimental results show that the proposed approach achieves better performance with the aid of virtual samples.

Original languageEnglish
Title of host publicationProceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017
EditorsMingxuan Sun, Huijun Gao
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages84-88
Number of pages5
ISBN (Electronic)9781509054619
DOIs
Publication statusPublished - 13 Oct 2017
Externally publishedYes
Event6th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2017 - Chongqing, China
Duration: 26 May 201727 May 2017

Publication series

NameProceedings of 2017 IEEE 6th Data Driven Control and Learning Systems Conference, DDCLS 2017

Conference

Conference6th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2017
Country/TerritoryChina
CityChongqing
Period26/05/1727/05/17

Keywords

  • Extreme Learning Machine
  • Prediction Model
  • Small Dataset
  • Virtual Sample Generation

Fingerprint

Dive into the research topics of 'A bootstrap based virtual sample generation method for improving the accuracy of modeling complex chemical processes using small datasets'. Together they form a unique fingerprint.

Cite this