Lightweighted AI-based Inference using Deterministic Randomness Compensation for Microcontroller ADC Resolution Enhancement

Jisu Kwon, Daejin Park

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Typically, circuits had to be designed at high cost to prevent irregular and random noise. This paper combines a lowcost designed part with a lightweight compensation technique, instead of designing a noise-tolerant circuit at a high cost. Technique that using compensate program in embedded system has been applied to ADC case study for compensate ADC output like as ideal. The proposed technique implemented in embedded systems can compensate for deterministic noise operating on static hardware (i.e., ADC) as a very small resource. The proposed technique improves the 10-bit ADC ENOB by 0.27, and it can be used in only 3.3% additional power consumption from ADC. The embedded system compensation technique can be applied not only to ADCs, but also to various hardware that include human uninterpretable deterministic noise.

Original languageEnglish
Title of host publicationProceedings - International SoC Design Conference 2022, ISOCC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages368-369
Number of pages2
ISBN (Electronic)9781665459716
DOIs
StatePublished - 2022
Event19th International System-on-Chip Design Conference, ISOCC 2022 - Gangneung-si, Korea, Republic of
Duration: 19 Oct 202222 Oct 2022

Publication series

NameProceedings - International SoC Design Conference 2022, ISOCC 2022

Conference

Conference19th International System-on-Chip Design Conference, ISOCC 2022
Country/TerritoryKorea, Republic of
CityGangneung-si
Period19/10/2222/10/22

Keywords

  • analog-to-digital converter (ADC)
  • effective number of bit (ENOB)
  • microcontroller unit (MCU)
  • neural network
  • noise

Fingerprint

Dive into the research topics of 'Lightweighted AI-based Inference using Deterministic Randomness Compensation for Microcontroller ADC Resolution Enhancement'. Together they form a unique fingerprint.

Cite this