Show simple item record

dc.contributor.authorSiegel, Joshua E
dc.contributor.authorPratt, Shane Richard
dc.contributor.authorSun, Yongbin
dc.contributor.authorSarma, Sanjay E
dc.date.accessioned2019-06-20T16:05:43Z
dc.date.available2019-06-20T16:05:43Z
dc.date.issued2018-06
dc.date.submitted2018-05
dc.identifier.issn0952-1976
dc.identifier.urihttps://hdl.handle.net/1721.1/121372
dc.description.abstractWe examine methods for detecting and disrupting electronic arc faults, proposing an approach leveraging Internet of Things connectivity, artificial intelligence, and adaptive learning. We develop Deep Neural Networks (DNNs) taking Fourier coefficients, Mel-Frequency Cepstrum data, and Wavelet features as input for differentiating normal from malignant current measurements. We further discuss how hardware-accelerated signal capture facilitates real-time classification, enabling our classifier to reach 99.95% accuracy for binary classification and 95.61% for multi-device classification, with trigger-to-trip latency under 200 ms. Finally, we discuss how IoT supports aggregate and user-specific risk models and suggest how future versions of this system might effectively supervise multiple circuits. Keywords: Emerging applications and technology; Intelligent infrastructure; Ambient intelligence; Embedded intelligence; Distributed sensing; Arc fault detection; Real-timeen_US
dc.language.isoen_US
dc.publisherElsevieren_US
dc.relation.isversionofhttps://doi.org/10.1016/j.engappai.2018.05.009en_US
dc.rightsCreative Commons Attribution-NonCommercial-NoDerivs Licenseen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/en_US
dc.sourceSubirana, Brianen_US
dc.titleReal-time Deep Neural Networks for internet-enabled arc-fault detectionen_US
dc.typeArticleen_US
dc.identifier.citationSiegel, Joshua E. et al. "Real-time Deep Neural Networks for internet-enabled arc-fault detection." Engineering Applications of Artificial Intelligence 74 (September 2018): 35-42 © 2018 Elsevieren_US
dc.contributor.departmentMassachusetts Institute of Technology. Office of Digital Learningen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mechanical Engineeringen_US
dc.contributor.approverSubirana, Brianen_US
dc.relation.journalEngineering Applications of Artificial Intelligenceen_US
dc.eprint.versionOriginal manuscripten_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.embargo.termsNen_US
dspace.date.submission2019-04-04T11:12:44Z
mit.journal.volume74en_US
mit.licensePUBLISHER_CCen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record