专利检索 ap:("MEDIATEK INC.") AND inv:"Chia-Jung Ni" 第 1 页

1.

发明公开
Outlier Integrated Circuit Detection Method and Outlier Integrated Circuit Detection System by Using Machine Learning Frameworks 审中-公开

公开(公告)号：US20240230755A9

公开(公告)日：2024-07-11

申请号：US18376447

申请日：2023-10-04

申请人： MEDIATEK INC.

发明人： Yu-Lin Yang , Chin-Wei Lin , Po-Chao Tsao , Tung-Hsing Lee , Chia-Jung Ni , Chi-Ming Lee , Yi-Ju Ting

IPC分类号： G01R31/28 , G06N20/00

CPC分类号： G01R31/2894 , G06N20/00

摘要： An outlier IC detection method includes acquiring first measured data of a first IC set, training the first measured data for establishing a training model, acquiring second measured data of a second IC set, generating predicted data of the second IC set by using the training model according to the second measured data, generating a bivariate dataset distribution of the second IC set according to the predicted data and the second measured data, acquiring a predetermined Mahalanobis distance on the bivariate dataset distribution of the second IC set, and identifying at least one outlier IC from the second IC set when at least one position of the at least one outlier IC on the bivariate dataset distribution is outside a range of the predetermined Mahalanobis distance.

2.

发明公开
Outlier Integrated Circuit Detection Method and Outlier Integrated Circuit Detection System by Using Machine Learning Frameworks 审中-公开

公开(公告)号：US20240133949A1

公开(公告)日：2024-04-25

申请号：US18376447

申请日：2023-10-03

申请人： MEDIATEK INC.

发明人： Yu-Lin Yang , Chin-Wei Lin , Po-Chao Tsao , Tung-Hsing Lee , Chia-Jung Ni , Chi-Ming Lee , Yi-Ju Ting

IPC分类号： G01R31/28 , G06N20/00

CPC分类号： G01R31/2894 , G06N20/00

摘要： An outlier IC detection method includes acquiring first measured data of a first IC set, training the first measured data for establishing a training model, acquiring second measured data of a second IC set, generating predicted data of the second IC set by using the training model according to the second measured data, generating a bivariate dataset distribution of the second IC set according to the predicted data and the second measured data, acquiring a predetermined Mahalanobis distance on the bivariate dataset distribution of the second IC set, and identifying at least one outlier IC from the second IC set when at least one position of the at least one outlier IC on the bivariate dataset distribution is outside a range of the predetermined Mahalanobis distance.