A Novel Hybrid Feature Importance and Feature Interaction Detection Framework for Predictive Optimization in Industry 4.0 Applications

Zhipeng Ma*, Bo Nørregaard Jørgensen, Zheng Grace Ma

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

25 Downloads (Pure)

Abstract

Advanced machine learning algorithms are increasingly utilized to provide data-based prediction and decision-making support in Industry 4.0. However, the prediction accuracy achieved by the existing models is insufficient to warrant practical implementation in real-world applications. This is because not all features present in real-world datasets possess a direct relevance to the predictive analysis being conducted. Consequently, the careful incorporation of select features has the potential to yield a substantial positive impact on the outcome. To address the research gap, this paper proposes a novel hybrid framework that combines the feature importance detector - local interpretable model-agnostic explanations (LIME) and the feature interaction detector - neural interaction detection (NID), to improve prediction accuracy. By applying the proposed framework, unnecessary features can be eliminated, and interactions are encoded to generate a more conducive dataset for predictive purposes. Subsequently, the proposed model is deployed to refine the prediction of electricity consumption in foundry processing. The experimental outcomes reveal an augmentation of up to 9.56% in the R2 score, and a diminution of up to 24.05% in the root mean square error.

Original languageEnglish
Title of host publicationIECON 2023–49th Annual Conference of the IEEE Industrial Electronics Society
Number of pages6
PublisherIEEE
Publication date16. Nov 2023
ISBN (Electronic)979-8-3503-3182-0
DOIs
Publication statusPublished - 16. Nov 2023
EventIECON 2023–49th Annual Conference of the IEEE Industrial Electronics Society - Marina Bay Sands Expo and Convention Centre, Singapore, Singapore
Duration: 16. Oct 202319. Oct 2023
https://www.iecon2023.org/

Conference

ConferenceIECON 2023–49th Annual Conference of the IEEE Industrial Electronics Society
LocationMarina Bay Sands Expo and Convention Centre
Country/TerritorySingapore
CitySingapore
Period16/10/202319/10/2023
Internet address
SeriesProceedings of the Annual Conference of the IEEE Industrial Electronics Society
ISSN1553-572X

Keywords

  • Feature importance
  • Feature interaction
  • Prediction
  • Optimization
  • Industry 4.0
  • feature importance
  • optimization
  • industry 4.0
  • prediction
  • feature interaction

Fingerprint

Dive into the research topics of 'A Novel Hybrid Feature Importance and Feature Interaction Detection Framework for Predictive Optimization in Industry 4.0 Applications'. Together they form a unique fingerprint.

Cite this