Efficient Discharge Waveform Distribution Measurement Using Active Machine Learning
- Resource Type
- Conference
- Authors
- Xie, Yuting; Zhang, Ling; Chen, Junhui; Li, Da; Yang, Zhenzhong; Ren, Dan; Li, Er-Ping
- Source
- 2022 IEEE Electrical Design of Advanced Packaging and Systems (EDAPS) Advanced Packaging and Systems (EDAPS), 2022 IEEE Electrical Design of. :1-3 Dec, 2022
- Subject
- Components, Circuits, Devices and Systems
Fields, Waves and Electromagnetics
Signal Processing and Analysis
Learning systems
Uncertainty
Current measurement
Machine learning
Packaging
Discharges (electric)
Real-time systems
Near-field scanning (NFS)
active learning
query-by-committee (QBC)
- Language
- ISSN
- 2151-1233
Near-field scanning (NFS) is a promising method to capture the current propagation in an electronic system through an automated scanning system. This article presents a novel and efficient measurement method for discharge waveform distribution based on active machine learning using NFS. Implicitly, the query-by-committee (QBC) active learning method is adopted to select scanning points with high uncertainty. The proposed approach is computationally efficient in real-time NFS, demonstrates higher reconstruction accuracy than random sampling using the same amount of sparse samples, and is much more efficient than full scanning.