Improved method for SNR prediction in machine-learning-based test

Xiaoqin Sheng; Hans G. Kerkhoff

doi:10.1109/IMS3TW.2010.5503007

Improved method for SNR prediction in machine-learning-based test

Xiaoqin Sheng, Hans G. Kerkhoff

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

176 Downloads (Pure)

Abstract

This paper applies an improved method for testing the signal-to-noise ratio (SNR) of Analogue-to-Digital Converters (ADC). In previous work, a noisy and nonlinear pulse signal is exploited as the input stimulus to obtain the signature results of ADC. By applying a machine-learning-based approach, the dynamic parameters can be predicted by using the signature results. However, it can only estimate the SNR accurately within a certain range. In order to overcome this limitation, an improved method based on work is applied in this work. It is validated on the Labview model of a 12-bit 80 Ms/s pipelined ADC with a pulse- wave input signal of 3 LSB noise and 7-bit nonlinear rising and falling edges.

Original language	Undefined
Title of host publication	16th International Mixed-Signals, Sensors and Systems Test Workshop, IMS3TW 2010
Place of Publication	Scottsdale, AZ, USA
Publisher	IEEE
Pages	1-4
Number of pages	4
ISBN (Print)	978-1-4244-7792-0
DOIs	https://doi.org/10.1109/IMS3TW.2010.5503007
Publication status	Published - 7 Jun 2010
Event	16th IEEE International Mixed-Signals, Sensors and Systems Test Workshop, IMS3TW 2010 - La Grande Motte, France Duration: 7 Jun 2010 → 9 Jun 2010 Conference number: 16

Workshop

Workshop	16th IEEE International Mixed-Signals, Sensors and Systems Test Workshop, IMS3TW 2010
Abbreviated title	IMS3TW
Country/Territory	France
City	La Grande Motte
Period	7/06/10 → 9/06/10

Keywords

METIS-277473
ADC
IR-75545
pulse wave
EWI-19177
machine-learning-based
Test
SNR
double-ADC

Access to Document

10.1109/IMS3TW.2010.5503007

Cite this

@inproceedings{c6ecb25b97e24926bd0984e3374488ad,

title = "Improved method for SNR prediction in machine-learning-based test",

abstract = "This paper applies an improved method for testing the signal-to-noise ratio (SNR) of Analogue-to-Digital Converters (ADC). In previous work, a noisy and nonlinear pulse signal is exploited as the input stimulus to obtain the signature results of ADC. By applying a machine-learning-based approach, the dynamic parameters can be predicted by using the signature results. However, it can only estimate the SNR accurately within a certain range. In order to overcome this limitation, an improved method based on work is applied in this work. It is validated on the Labview model of a 12-bit 80 Ms/s pipelined ADC with a pulse- wave input signal of 3 LSB noise and 7-bit nonlinear rising and falling edges.",

keywords = "METIS-277473, ADC, IR-75545, pulse wave, EWI-19177, machine-learning-based, Test, SNR, double-ADC",

author = "Xiaoqin Sheng and Kerkhoff, {Hans G.}",

note = "10.1109/IMS3TW.2010.5503007 ; 16th IEEE International Mixed-Signals, Sensors and Systems Test Workshop, IMS3TW 2010 ; Conference date: 07-06-2010 Through 09-06-2010",

year = "2010",

month = jun,

day = "7",

doi = "10.1109/IMS3TW.2010.5503007",

language = "Undefined",

isbn = "978-1-4244-7792-0",

pages = "1--4",

booktitle = "16th International Mixed-Signals, Sensors and Systems Test Workshop, IMS3TW 2010",

publisher = "IEEE",

address = "United States",

}

Sheng, X & Kerkhoff, HG 2010, Improved method for SNR prediction in machine-learning-based test. in 16th International Mixed-Signals, Sensors and Systems Test Workshop, IMS3TW 2010. IEEE, Scottsdale, AZ, USA, pp. 1-4, 16th IEEE International Mixed-Signals, Sensors and Systems Test Workshop, IMS3TW 2010, La Grande Motte, France, 7/06/10. https://doi.org/10.1109/IMS3TW.2010.5503007

TY - GEN

T1 - Improved method for SNR prediction in machine-learning-based test

AU - Sheng, Xiaoqin

AU - Kerkhoff, Hans G.

N1 - Conference code: 16

PY - 2010/6/7

Y1 - 2010/6/7

N2 - This paper applies an improved method for testing the signal-to-noise ratio (SNR) of Analogue-to-Digital Converters (ADC). In previous work, a noisy and nonlinear pulse signal is exploited as the input stimulus to obtain the signature results of ADC. By applying a machine-learning-based approach, the dynamic parameters can be predicted by using the signature results. However, it can only estimate the SNR accurately within a certain range. In order to overcome this limitation, an improved method based on work is applied in this work. It is validated on the Labview model of a 12-bit 80 Ms/s pipelined ADC with a pulse- wave input signal of 3 LSB noise and 7-bit nonlinear rising and falling edges.

AB - This paper applies an improved method for testing the signal-to-noise ratio (SNR) of Analogue-to-Digital Converters (ADC). In previous work, a noisy and nonlinear pulse signal is exploited as the input stimulus to obtain the signature results of ADC. By applying a machine-learning-based approach, the dynamic parameters can be predicted by using the signature results. However, it can only estimate the SNR accurately within a certain range. In order to overcome this limitation, an improved method based on work is applied in this work. It is validated on the Labview model of a 12-bit 80 Ms/s pipelined ADC with a pulse- wave input signal of 3 LSB noise and 7-bit nonlinear rising and falling edges.

KW - METIS-277473

KW - ADC

KW - IR-75545

KW - pulse wave

KW - EWI-19177

KW - machine-learning-based

KW - Test

KW - SNR

KW - double-ADC

U2 - 10.1109/IMS3TW.2010.5503007

DO - 10.1109/IMS3TW.2010.5503007

M3 - Conference contribution

SN - 978-1-4244-7792-0

SP - 1

EP - 4

BT - 16th International Mixed-Signals, Sensors and Systems Test Workshop, IMS3TW 2010

PB - IEEE

CY - Scottsdale, AZ, USA

T2 - 16th IEEE International Mixed-Signals, Sensors and Systems Test Workshop, IMS3TW 2010

Y2 - 7 June 2010 through 9 June 2010

ER -