Detection of empty hazelnuts from fully developed nuts by impact acoustics
buir.contributor.author | Çetin, A. Enis | |
buir.contributor.orcid | Çetin, A. Enis|0000-0002-3449-1958 | |
dc.contributor.author | Onaran, İbrahim | en_US |
dc.contributor.author | Dülek, Berkan | en_US |
dc.contributor.author | Pearson, T. C. | en_US |
dc.contributor.author | Yardımcı, Y. | en_US |
dc.contributor.author | Çetin, A. Enis | en_US |
dc.coverage.spatial | Antalya, Turkey | en_US |
dc.date.accessioned | 2016-02-08T11:50:50Z | en_US |
dc.date.available | 2016-02-08T11:50:50Z | |
dc.date.issued | 2005 | en_US |
dc.department | Department of Electrical and Electronics Engineering | en_US |
dc.description | Date of Conference: 4-8 September 2005 | en_US |
dc.description | Conference Name: 13th European Signal Processing Conference, EUSIPCO 2005 | en_US |
dc.description.abstract | Shell-kernel weight ratio is the main determinate of quality and price of hazelnuts. Empty hazelnuts and nuts containing undeveloped kernels may also contain mycotoxin producing molds, which can cause cancer. A prototype system was set up to detect empty hazelnuts by dropping them onto a steel plate and processing the acoustic signal generated when kernels impact the plate. The acoustic signal was processed by five different methods: 1) modeling of the signal in the time domain, 2) computing time domain signal variances in short time windows, 3) analysis of the frequency spectra magnitudes, 4) maximum amplitude values in short time windows, and 5) line spectral frequencies (LSFs). Support Vector Machines (SVMs) were used to select a subset of features and perform classification. 98% of fully developed kernels and 97% of empty kernels were correctly classified. | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/27334 | |
dc.language.iso | English | en_US |
dc.publisher | IEEE | en_US |
dc.source.title | Proceedings of the 13th European Signal Processing Conference, EUSIPCO 2005 | en_US |
dc.subject | Acoustic signals | en_US |
dc.subject | Computing time | en_US |
dc.subject | Frequency spectra | en_US |
dc.subject | Impact acoustics | en_US |
dc.subject | Line spectral frequencies | en_US |
dc.subject | Maximum amplitude | en_US |
dc.subject | Prototype system | en_US |
dc.subject | Steel plates | en_US |
dc.subject | Time domain | en_US |
dc.subject | Time windows | en_US |
dc.subject | Acoustic waves | en_US |
dc.subject | Signal detection | en_US |
dc.subject | Support vector machines | en_US |
dc.title | Detection of empty hazelnuts from fully developed nuts by impact acoustics | en_US |
dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Detection of empty hazelnuts from fully developed nuts by impact acoustics.pdf
- Size:
- 206.11 KB
- Format:
- Adobe Portable Document Format
- Description:
- Full printable version