An agent-based fuzzy collaborative intelligence approach for precise and accurate semiconductor yield forecasting

Tin-Chih Chen, Yi Chi Wang

Research output: Contribution to journalArticlepeer-review

31 Scopus citations

Abstract

Yield forecasting is an important task for the manufacturer of semiconductors. Owing to the uncertainty in yield learning, it is, however, often difficult to make precise and accurate yield forecasts. To solve this problem, we propose an agent-based fuzzy collaborative intelligence approach that is modified from the fuzzy linear regression and back propagation network approach. In the proposed methodology, software agents rather than domain experts are used to improve the efficiency of collaboration. In addition, an agent decides the adjustable parameters by referencing to others so that the overall prediction performance can be improved in an effective way. In addition, we proposed a simple and effective way to aggregate the fuzzy forecasts by agents. Compared with the fuzzy linear regression and back propagation network approach, the proposed methodology reduced the average range and mean absolute percentage error by 18% and 99%, respectively.

Original languageEnglish
Article number6472058
Pages (from-to)201-211
Number of pages11
JournalIEEE Transactions on Fuzzy Systems
Volume22
Issue number1
DOIs
StatePublished - 1 Feb 2014

Keywords

  • Agent
  • fuzzy collaborative intelligence
  • semiconductor
  • yield forecasting

Fingerprint Dive into the research topics of 'An agent-based fuzzy collaborative intelligence approach for precise and accurate semiconductor yield forecasting'. Together they form a unique fingerprint.

Cite this