General Methodology for the Design of Bell-Shaped Analog-Hardware Classifiers

This study introduces a general methodology for the design of analog integrated bell-shaped classifiers. Each high-level architecture is composed of several Gaussian function circuits in conjunction with a Winner-Take-All circuit. Notably, each implementation is designed with modularity and scalabil...

Full description

Bibliographic Details
Main Authors: Vassilis Alimisis, Nikolaos P. Eleftheriou, Argyro Kamperi, Georgios Gennis, Christos Dimas, Paul P. Sotiriadis
Format: Article
Language:English
Published: MDPI AG 2023-10-01
Series:Electronics
Subjects:
Online Access:https://www.mdpi.com/2079-9292/12/20/4211
_version_ 1797574101735309312
author Vassilis Alimisis
Nikolaos P. Eleftheriou
Argyro Kamperi
Georgios Gennis
Christos Dimas
Paul P. Sotiriadis
author_facet Vassilis Alimisis
Nikolaos P. Eleftheriou
Argyro Kamperi
Georgios Gennis
Christos Dimas
Paul P. Sotiriadis
author_sort Vassilis Alimisis
collection DOAJ
description This study introduces a general methodology for the design of analog integrated bell-shaped classifiers. Each high-level architecture is composed of several Gaussian function circuits in conjunction with a Winner-Take-All circuit. Notably, each implementation is designed with modularity and scalability in mind, effectively accommodating variations in classification parameters. The operating principles of each classifier are illustrated in detail and are used in low-power, low-voltage, and fully tunable implementations targeting biomedical applications. The realization of this design methodology occurred within a 90 nm CMOS process, leveraging the Cadence IC suite for both electrical and layout design aspects. In the verification phase, post-layout simulation outcomes were meticulously compared against software-based implementations of each classifier. Through the simulation results and comparison study, the design methodology is confirmed in terms of accuracy and sensitivity.
first_indexed 2024-03-10T21:18:10Z
format Article
id doaj.art-fa9f38edb909416285cccda4b5273ab6
institution Directory Open Access Journal
issn 2079-9292
language English
last_indexed 2024-03-10T21:18:10Z
publishDate 2023-10-01
publisher MDPI AG
record_format Article
series Electronics
spelling doaj.art-fa9f38edb909416285cccda4b5273ab62023-11-19T16:18:24ZengMDPI AGElectronics2079-92922023-10-011220421110.3390/electronics12204211General Methodology for the Design of Bell-Shaped Analog-Hardware ClassifiersVassilis Alimisis0Nikolaos P. Eleftheriou1Argyro Kamperi2Georgios Gennis3Christos Dimas4Paul P. Sotiriadis5Department of Electrical and Computer Engineering, National Technical University of Athens, 15773 Athens, GreeceDepartment of Electrical and Computer Engineering, National Technical University of Athens, 15773 Athens, GreeceDepartment of Electrical and Computer Engineering, National Technical University of Athens, 15773 Athens, GreeceDepartment of Electrical and Computer Engineering, National Technical University of Athens, 15773 Athens, GreeceDepartment of Electrical and Computer Engineering, National Technical University of Athens, 15773 Athens, GreeceDepartment of Electrical and Computer Engineering, National Technical University of Athens, 15773 Athens, GreeceThis study introduces a general methodology for the design of analog integrated bell-shaped classifiers. Each high-level architecture is composed of several Gaussian function circuits in conjunction with a Winner-Take-All circuit. Notably, each implementation is designed with modularity and scalability in mind, effectively accommodating variations in classification parameters. The operating principles of each classifier are illustrated in detail and are used in low-power, low-voltage, and fully tunable implementations targeting biomedical applications. The realization of this design methodology occurred within a 90 nm CMOS process, leveraging the Cadence IC suite for both electrical and layout design aspects. In the verification phase, post-layout simulation outcomes were meticulously compared against software-based implementations of each classifier. Through the simulation results and comparison study, the design methodology is confirmed in terms of accuracy and sensitivity.https://www.mdpi.com/2079-9292/12/20/4211analog VLSIgeneral design methodologybiomedical applicationswake-up circuitanalog classifiers
spellingShingle Vassilis Alimisis
Nikolaos P. Eleftheriou
Argyro Kamperi
Georgios Gennis
Christos Dimas
Paul P. Sotiriadis
General Methodology for the Design of Bell-Shaped Analog-Hardware Classifiers
Electronics
analog VLSI
general design methodology
biomedical applications
wake-up circuit
analog classifiers
title General Methodology for the Design of Bell-Shaped Analog-Hardware Classifiers
title_full General Methodology for the Design of Bell-Shaped Analog-Hardware Classifiers
title_fullStr General Methodology for the Design of Bell-Shaped Analog-Hardware Classifiers
title_full_unstemmed General Methodology for the Design of Bell-Shaped Analog-Hardware Classifiers
title_short General Methodology for the Design of Bell-Shaped Analog-Hardware Classifiers
title_sort general methodology for the design of bell shaped analog hardware classifiers
topic analog VLSI
general design methodology
biomedical applications
wake-up circuit
analog classifiers
url https://www.mdpi.com/2079-9292/12/20/4211
work_keys_str_mv AT vassilisalimisis generalmethodologyforthedesignofbellshapedanaloghardwareclassifiers
AT nikolaospeleftheriou generalmethodologyforthedesignofbellshapedanaloghardwareclassifiers
AT argyrokamperi generalmethodologyforthedesignofbellshapedanaloghardwareclassifiers
AT georgiosgennis generalmethodologyforthedesignofbellshapedanaloghardwareclassifiers
AT christosdimas generalmethodologyforthedesignofbellshapedanaloghardwareclassifiers
AT paulpsotiriadis generalmethodologyforthedesignofbellshapedanaloghardwareclassifiers