Ghent University Academic Bibliography

Advanced

Machine learning based error detection in transient susceptibility tests

Roberto Medico UGent, Niels Lambrecht UGent, Hugo Pues, Dries Vande Ginste UGent, Dirk Deschrijver UGent, Tom Dhaene UGent and Domenico Spina UGent (2018) IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY .
abstract
Compliance to electromagnetic compatibility (EMC) standards is a fundamental requirement for modern integrated circuits (ICs). In this framework, error detection in transient susceptibility tests is of crucial importance to assess the circuit robustness. However, performing such tests is expensive and requires an ad hoc hardware, whose configuration must be adapted for the different test setups, i.e., the transient waveforms, defined in the EMC standards. This paper describes a novel machine learning based approach for error detection, which only requires the raw output data from a susceptibility test: neither additional information about the architecture of the device under test nor the test configuration is needed. We applied and evaluated anomaly detection techniques (a branch of machine learning methods focused on error detection) for transient susceptibility tests with two pertinent examples (one simulation- and one measurementbased). The proposed techniques detected errors successfully in both unsupervised and supervised scenarios. Moreover, these can give insight on the output behaviors that are more likely to cause errors during the test. As shown by our results, an anomaly detection-based approach is an applicable and viable solution for automatic error detection in transient susceptibility tests.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
in press
subject
journal title
IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY
publisher
Institute of Electrical and Electronics Engineers (IEEE)
ISSN
0018-9375
1558-187X
DOI
10.1109/temc.2018.2821712
language
English
UGent publication?
yes
classification
A1
id
8563497
handle
http://hdl.handle.net/1854/LU-8563497
date created
2018-05-30 07:45:53
date last changed
2018-07-09 12:57:45
@article{8563497,
  abstract     = {Compliance to electromagnetic compatibility (EMC)
standards is a fundamental requirement for modern integrated
circuits (ICs). In this framework, error detection in transient
susceptibility tests is of crucial importance to assess the circuit
robustness. However, performing such tests is expensive and requires
an ad hoc hardware, whose configuration must be adapted
for the different test setups, i.e., the transient waveforms, defined
in the EMC standards. This paper describes a novel machine
learning based approach for error detection, which only requires
the raw output data from a susceptibility test: neither additional
information about the architecture of the device under test nor the
test configuration is needed. We applied and evaluated anomaly
detection techniques (a branch of machine learning methods
focused on error detection) for transient susceptibility tests with
two pertinent examples (one simulation- and one measurementbased).
The proposed techniques detected errors successfully in
both unsupervised and supervised scenarios. Moreover, these
can give insight on the output behaviors that are more likely to
cause errors during the test. As shown by our results, an anomaly
detection-based approach is an applicable and viable solution for
automatic error detection in transient susceptibility tests.},
  author       = {Medico, Roberto and Lambrecht, Niels and Pues, Hugo and Vande Ginste, Dries and Deschrijver, Dirk and Dhaene, Tom and Spina, Domenico},
  issn         = {0018-9375},
  journal      = {IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY },
  language     = {eng},
  publisher    = {Institute of Electrical and Electronics Engineers (IEEE)},
  title        = {Machine learning based error detection in transient susceptibility tests},
  url          = {http://dx.doi.org/10.1109/temc.2018.2821712},
  year         = {2018},
}

Chicago
Medico, Roberto, Niels Lambrecht, Hugo Pues, Dries Vande Ginste, Dirk Deschrijver, Tom Dhaene, and Domenico Spina. 2018. “Machine Learning Based Error Detection in Transient Susceptibility Tests.” Ieee Transactions on Electromagnetic Compatibility .
APA
Medico, R., Lambrecht, N., Pues, H., Vande Ginste, D., Deschrijver, D., Dhaene, T., & Spina, D. (2018). Machine learning based error detection in transient susceptibility tests. IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY .
Vancouver
1.
Medico R, Lambrecht N, Pues H, Vande Ginste D, Deschrijver D, Dhaene T, et al. Machine learning based error detection in transient susceptibility tests. IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY . Institute of Electrical and Electronics Engineers (IEEE); 2018;
MLA
Medico, Roberto, Niels Lambrecht, Hugo Pues, et al. “Machine Learning Based Error Detection in Transient Susceptibility Tests.” IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY (2018): n. pag. Print.