6533b834fe1ef96bd129dd2d
RESEARCH PRODUCT
Automatic defect localization in VLSI circuits: A fusion approach based on the Dempster-Shafer theory
Anthony BoscaroSabir JacquirKevin SanchezPhilippe PerduStéphane Binczaksubject
VLSI analysisMulti-sensor data fusionFault detection and identification[INFO.INFO-MO] Computer Science [cs]/Modeling and SimulationEvidence theorydescription
Defect localization in Very Large Integration Cir-cuits (VLSI) requires to use multi-sensor information such aselectrical waveforms, emission microscopy images and frequencymapping in order to detect, localize and identify the failure. Eachsensor provides a specific kind of feature modeling the evidence.Thus, the defect localization in VLSI can be summarized asa problem of data fusion with heterogeneous and impreciseinformation. This study illustrates how to reproduce the humandecision for modeling and fusing the different multi-sensorfeatures by using the Demspter-Shafer theory. We propose notonly an automatic decision rule for mass functions computingbut also confidence intervals to quantify the final decision and tobring a decision help for the analysts expertise. Finally, a caseof study is reported to attest the expert decision reproducibility
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2017-01-01 |