A signal representation approach for discrimination between full and empty hazelnuts

buir.contributor.authorÇetin, A. Enis
buir.contributor.orcidÇetin, A. Enis|0000-0002-3449-1958
dc.citation.epage2468en_US
dc.citation.spage2464en_US
dc.contributor.authorOnaran, İbrahimen_US
dc.contributor.authorİnce, N. F.en_US
dc.contributor.authorTevfik, A. H.en_US
dc.contributor.authorÇetin, A. Enisen_US
dc.coverage.spatialPoznan, Polanden_US
dc.date.accessioned2016-02-08T11:42:39Z
dc.date.available2016-02-08T11:42:39Z
dc.date.issued2007en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 3-7 September 2007en_US
dc.descriptionConference Name: 15th European Signal Processing Conference, EURASIP 2007en_US
dc.description.abstractWe apply a sparse signal representation approach to impact acoustic signals to discriminate between empty and full hazelnuts. The impact acoustic signals are recorded by dropping the hazelnut shells on a metal plate. The impact signal is then approximated within a given error limit by choosing codevectors from a special dictionary. This dictionary was generated from sub-dictionaries that are individually generated for the impact signals corresponding to empty and full hazelnut. The number of codevectors selected from each sub-dictionary and the approximation error within initial codevectors are used as classification features and fed to a Linear Discriminant Analysis (LDA). We also compare this algorithm with a baseline approach. This baseline approach uses features which describe the time and frequency characteristics of the given signal that were previously used for empty and full hazelnut separation. Classification accuracies of 98.3% and 96.8% were achieved by the proposed approach and base algorithm respectively. The results we obtained show that sparse signal representation strategy can be used as an alternative classification method for undeveloped hazelnut separation with higher accuracies.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T11:42:39Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2007en
dc.identifier.issn2219-5491en_US
dc.identifier.urihttp://hdl.handle.net/11693/27037
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.source.titleProceedings of the 15th European Signal Processing Conference, EURASIP 2007en_US
dc.subjectApproximation errorsen_US
dc.subjectClassification accuracyen_US
dc.subjectClassification featuresen_US
dc.subjectClassification methodsen_US
dc.subjectCode vectorsen_US
dc.subjectError limitsen_US
dc.subjectFrequency characteristicen_US
dc.subjectHazelnut shellsen_US
dc.subjectImpact acousticsen_US
dc.subjectImpact signalsen_US
dc.subjectLinear discriminant analysisen_US
dc.subjectMetal platesen_US
dc.subjectSignal representationsen_US
dc.subjectSparse signal representationen_US
dc.subjectAcoustic wavesen_US
dc.subjectAlgorithmsen_US
dc.subjectSignal processingen_US
dc.subjectSeparationen_US
dc.titleA signal representation approach for discrimination between full and empty hazelnutsen_US
dc.typeConference Paperen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
A signal representation approach for discrimination between full and empty hazelnuts.pdf
Size:
524.58 KB
Format:
Adobe Portable Document Format
Description:
Full printable version