Salvato in:
Dettagli Bibliografici
Autori principali: Armeniakos, Giorgos, Duarte, Paula L., Pal, Priyanjana, Zervakis, Georgios, Tahoori, Mehdi B., Soudris, Dimitrios
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2312.01172
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917835598462976
author Armeniakos, Giorgos
Duarte, Paula L.
Pal, Priyanjana
Zervakis, Georgios
Tahoori, Mehdi B.
Soudris, Dimitrios
author_facet Armeniakos, Giorgos
Duarte, Paula L.
Pal, Priyanjana
Zervakis, Georgios
Tahoori, Mehdi B.
Soudris, Dimitrios
contents Printed electronics (PE) technology provides cost-effective hardware with unmet customization, due to their low non-recurring engineering and fabrication costs. PE exhibit features such as flexibility, stretchability, porosity, and conformality, which make them a prominent candidate for enabling ubiquitous computing. Still, the large feature sizes in PE limit the realization of complex printed circuits, such as machine learning classifiers, especially when processing sensor inputs is necessary, mainly due to the costly analog-to-digital converters (ADCs). To this end, we propose the design of fully customized ADCs and present, for the first time, a co-design framework for generating bespoke Decision Tree classifiers. Our comprehensive evaluation shows that our co-design enables self-powered operation of on-sensor printed classifiers in all benchmark cases.
format Preprint
id arxiv_https___arxiv_org_abs_2312_01172
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On-sensor Printed Machine Learning Classification via Bespoke ADC and Decision Tree Co-Design
Armeniakos, Giorgos
Duarte, Paula L.
Pal, Priyanjana
Zervakis, Georgios
Tahoori, Mehdi B.
Soudris, Dimitrios
Machine Learning
Printed electronics (PE) technology provides cost-effective hardware with unmet customization, due to their low non-recurring engineering and fabrication costs. PE exhibit features such as flexibility, stretchability, porosity, and conformality, which make them a prominent candidate for enabling ubiquitous computing. Still, the large feature sizes in PE limit the realization of complex printed circuits, such as machine learning classifiers, especially when processing sensor inputs is necessary, mainly due to the costly analog-to-digital converters (ADCs). To this end, we propose the design of fully customized ADCs and present, for the first time, a co-design framework for generating bespoke Decision Tree classifiers. Our comprehensive evaluation shows that our co-design enables self-powered operation of on-sensor printed classifiers in all benchmark cases.
title On-sensor Printed Machine Learning Classification via Bespoke ADC and Decision Tree Co-Design
topic Machine Learning
url https://arxiv.org/abs/2312.01172