Real-time Edge Neuromorphic Tasting from Chemical Microsensor Arrays

Liquid analysis is key to track conformity with the strict process quality standards of sectors like food, beverage, and chemical manufacturing. In order to analyse product qualities online and at the very point of interest, automated monitoring systems must satisfy strong requirements in terms of m...

Descripción completa

Detalles Bibliográficos
Autores: LeBow, Nicholas, Rueckauer, Bodo, Sun, Pengfei, Rovira, Meritxell, Jiménez-Jorquera, Cecilia, Liu, Shih-Chii, Margarit-Taulé, Josep Maria
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/251740
Acceso en línea:http://hdl.handle.net/10261/251740
Access Level:acceso abierto
Palabra clave:Deep convolutional neural networks
Spiking neural networks (SNNs)
Electrochemical sensors
Electronic tongue
Sensor fusion
Neuromorphic engineering
id ES_dec8bb7079d08e3891aef5dff6a9b832
oai_identifier_str oai:digital.csic.es:10261/251740
network_acronym_str ES
network_name_str España
repository_id_str
spelling Real-time Edge Neuromorphic Tasting from Chemical Microsensor ArraysLeBow, NicholasRueckauer, BodoSun, PengfeiRovira, MeritxellJiménez-Jorquera, CeciliaLiu, Shih-ChiiMargarit-Taulé, Josep MariaDeep convolutional neural networksSpiking neural networks (SNNs)Electrochemical sensorsElectronic tongueSensor fusionNeuromorphic engineeringLiquid analysis is key to track conformity with the strict process quality standards of sectors like food, beverage, and chemical manufacturing. In order to analyse product qualities online and at the very point of interest, automated monitoring systems must satisfy strong requirements in terms of miniaturization, energy autonomy, and real time operation. Towards this goal, we present the first implementation of artificial taste running on neuromorphic hardware for continuous edge monitoring applications. We used a solid-state electrochemical microsensor array to acquire multivariate, time-varying chemical measurements, employed temporal filtering to enhance sensor readout dynamics, and deployed a rate-based, deep convolutional spiking neural network to efficiently fuse the electrochemical sensor data. To evaluate performance we created MicroBeTa (Microsensor Beverage Tasting), a new dataset for beverage classification incorporating seven hours of temporal recordings performed over three days, including sensor drifts and sensor replacements. Our implementation of artificial taste is 15× more energy efficient on inference tasks than similar convolutional architectures running on other commercial, low power edge-AI inference devices, achieving over 178× lower latencies than the sampling period of the sensor readout, and high accuracy (97%) on a single Intel Loihi neuromorphic research processor included in a USB stick form factor.This work was supported by the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement no. 747848 and the SNSF-Sinergia WeCare project (N°CRSII5_177255).Peer reviewedFrontiers MediaMarie Curie Fellows AssociationSwiss National Science FoundationConsejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]202120212021info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501http://hdl.handle.net/10261/251740reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#info:eu-repo/grantAgreement/EC/H2020/747848http://doi.org/10.3389/fnins.2021.771480Síinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/2517402026-05-22T06:33:51Z
dc.title.none.fl_str_mv Real-time Edge Neuromorphic Tasting from Chemical Microsensor Arrays
title Real-time Edge Neuromorphic Tasting from Chemical Microsensor Arrays
spellingShingle Real-time Edge Neuromorphic Tasting from Chemical Microsensor Arrays
LeBow, Nicholas
Deep convolutional neural networks
Spiking neural networks (SNNs)
Electrochemical sensors
Electronic tongue
Sensor fusion
Neuromorphic engineering
title_short Real-time Edge Neuromorphic Tasting from Chemical Microsensor Arrays
title_full Real-time Edge Neuromorphic Tasting from Chemical Microsensor Arrays
title_fullStr Real-time Edge Neuromorphic Tasting from Chemical Microsensor Arrays
title_full_unstemmed Real-time Edge Neuromorphic Tasting from Chemical Microsensor Arrays
title_sort Real-time Edge Neuromorphic Tasting from Chemical Microsensor Arrays
dc.creator.none.fl_str_mv LeBow, Nicholas
Rueckauer, Bodo
Sun, Pengfei
Rovira, Meritxell
Jiménez-Jorquera, Cecilia
Liu, Shih-Chii
Margarit-Taulé, Josep Maria
author LeBow, Nicholas
author_facet LeBow, Nicholas
Rueckauer, Bodo
Sun, Pengfei
Rovira, Meritxell
Jiménez-Jorquera, Cecilia
Liu, Shih-Chii
Margarit-Taulé, Josep Maria
author_role author
author2 Rueckauer, Bodo
Sun, Pengfei
Rovira, Meritxell
Jiménez-Jorquera, Cecilia
Liu, Shih-Chii
Margarit-Taulé, Josep Maria
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Marie Curie Fellows Association
Swiss National Science Foundation
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Deep convolutional neural networks
Spiking neural networks (SNNs)
Electrochemical sensors
Electronic tongue
Sensor fusion
Neuromorphic engineering
topic Deep convolutional neural networks
Spiking neural networks (SNNs)
Electrochemical sensors
Electronic tongue
Sensor fusion
Neuromorphic engineering
description Liquid analysis is key to track conformity with the strict process quality standards of sectors like food, beverage, and chemical manufacturing. In order to analyse product qualities online and at the very point of interest, automated monitoring systems must satisfy strong requirements in terms of miniaturization, energy autonomy, and real time operation. Towards this goal, we present the first implementation of artificial taste running on neuromorphic hardware for continuous edge monitoring applications. We used a solid-state electrochemical microsensor array to acquire multivariate, time-varying chemical measurements, employed temporal filtering to enhance sensor readout dynamics, and deployed a rate-based, deep convolutional spiking neural network to efficiently fuse the electrochemical sensor data. To evaluate performance we created MicroBeTa (Microsensor Beverage Tasting), a new dataset for beverage classification incorporating seven hours of temporal recordings performed over three days, including sensor drifts and sensor replacements. Our implementation of artificial taste is 15× more energy efficient on inference tasks than similar convolutional architectures running on other commercial, low power edge-AI inference devices, achieving over 178× lower latencies than the sampling period of the sensor readout, and high accuracy (97%) on a single Intel Loihi neuromorphic research processor included in a USB stick form factor.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021
2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/251740
url http://hdl.handle.net/10261/251740
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv #PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
info:eu-repo/grantAgreement/EC/H2020/747848
http://doi.org/10.3389/fnins.2021.771480
Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Frontiers Media
publisher.none.fl_str_mv Frontiers Media
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422005934096384
score 15.811543

Similares en LA Referencia