Wheat and hazelnut inspection with impact acoustics time-frequency patterns

buir.contributor.authorÇetin, A. Enis
buir.contributor.orcidÇetin, A. Enis|0000-0002-3449-1958
dc.citation.epage9en_US
dc.citation.spage1en_US
dc.contributor.authorİnce, N. F.en_US
dc.contributor.authorOnaran, İbrahimen_US
dc.contributor.authorTewfik, A. H.en_US
dc.contributor.authorKalkan, H.en_US
dc.contributor.authorPearson, T.en_US
dc.contributor.authorÇetin, A. Enisen_US
dc.contributor.authorYardimci, Y.en_US
dc.coverage.spatialMinneapolis, Minnesota
dc.date.accessioned2016-02-08T11:43:54Z
dc.date.available2016-02-08T11:43:54Z
dc.date.issued2007-06en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 17-20 June, 2007
dc.descriptionConference name: 2007 ASABE Annual International Meeting
dc.description.abstractKernel damage caused by insects and fungi is one of the most common reason for poor flour quality. Cracked hazelnut shells are prone to infection by cancer producing mold. We propose a new adaptive time-frequency classification procedure for detecting cracked hazelnut shells and damaged wheat kernels using impact acoustic emissions recorded by dropping wheat kernels or hazelnut shells on a steel plate. The proposed algorithm is based on a flexible local discriminant bases (F-LDB) procedure. The F-LDB method combines local cosine packet analysis and a frequency axis clustering approach which supports individual time and frequency band adaptation. Discriminant features are extracted from the adaptively segmented acoustic signal, sorted according to a Fisher class separability criterion, post processed by principal component analysis and fed to linear discriminant. We describe experimental results that establish the superior performance of the proposed approach when compared with prior techniques reported in the literature or used in the field. Our approach achieved classification accuracy in paired separation of undamaged wheat kernels from IDK, Pupae and Scab damaged kernels with 96%, 82% and 94%. For hazelnuts the accuracy was 97.1%.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T11:43:54Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2007en
dc.identifier.doi10.13031/2013.23455
dc.identifier.urihttp://hdl.handle.net/11693/27084
dc.language.isoEnglishen_US
dc.publisherASABE
dc.relation.isversionofhttps://doi.org/10.13031/2013.23455
dc.source.title2007 ASABE Annual International Meeting, Technical Papersen_US
dc.subjectAcoustic measurementen_US
dc.subjectAdaptive signal processingen_US
dc.subjectPattern classificationen_US
dc.subjectTime-frequency analysisen_US
dc.subjectAcoustic emissionsen_US
dc.subjectAlgorithmsen_US
dc.subjectPattern recognitionen_US
dc.subjectPrincipal component analysisen_US
dc.subjectSignal processingen_US
dc.subjectCracked hazelnuten_US
dc.subjectKernel damageen_US
dc.subjectCropsen_US
dc.titleWheat and hazelnut inspection with impact acoustics time-frequency patternsen_US
dc.typeConference Paperen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Wheat and hazelnut inspection with impact acoustics time-frequency patterns.pdf
Size:
296.14 KB
Format:
Adobe Portable Document Format
Description:
Full printable version