Show simple item record

dc.contributor.authorGupta, Otkrist
dc.contributor.authorDas, Anshuman Jyothi
dc.contributor.authorHellerstein, Joshua K.
dc.contributor.authorRaskar, Ramesh
dc.date.accessioned2020-12-17T15:34:11Z
dc.date.available2020-12-17T15:34:11Z
dc.date.issued2018-03
dc.date.submitted2017-07
dc.identifier.issn2045-2322
dc.identifier.urihttps://hdl.handle.net/1721.1/128847
dc.description.abstractThe analysis and identification of different attributes of produce such as taxonomy, vendor, and organic nature is vital to verifying product authenticity in a distribution network. Though a variety of analysis techniques have been studied in the past, we present a novel data-centric approach to classifying produce attributes. We employed visible and near infrared (NIR) spectroscopy on over 75,000 samples across several fruit and vegetable varieties. This yielded 0.90-0.98 and 0.98-0.99 classification accuracies for taxonomy and farmer classes, respectively. The most significant factors in the visible spectrum were variations in the produce color due to chlorophyll and anthocyanins. In the infrared spectrum, we observed that the varying water and sugar content levels were critical to obtaining high classification accuracies. High quality spectral data along with an optimal tuning of hyperparameters in the support vector machine (SVM) was also key to achieving high classification accuracies. In addition to demonstrating exceptional accuracies on test data, we explored insights behind the classifications, and identified the highest performing approaches using cross validation. We presented data collection guidelines, experimental design parameters, and machine learning optimization parameters for the replication of studies involving large sample sizes. ©2018 The Author(s).en_US
dc.language.isoen
dc.publisherSpringer Natureen_US
dc.relation.isversionofhttps://dx.doi.org/10.1038/S41598-018-23394-3en_US
dc.rightsCreative Commons Attribution 4.0 International licenseen_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_US
dc.sourceScientific Reportsen_US
dc.titleMachine learning approaches for large scale classification of produceen_US
dc.typeArticleen_US
dc.identifier.citationGupta, Otkrist et al., "Machine learning approaches for large scale classification of produce." Scientific Reports 8, 1 (March 2018): 5226 doi. 10.1038/s41598-018-23394-3 ©2018 Author(s)en_US
dc.contributor.departmentMassachusetts Institute of Technology. Media Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.relation.journalScientific Reportsen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dc.date.updated2019-08-02T14:39:06Z
dspace.date.submission2019-08-02T14:39:08Z
mit.journal.volume8en_US
mit.journal.issue1en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record